Plant phenotyping methods.

High-throughput phenotyping platform for facility crops based on optical sensing technology: A review →

High-throughput acquisition of crop phenotypic information is one of the key technologies for achieving intelligent facility agriculture and precision breeding. Traditional phenotypic data collection methods suffer from low efficiency and strong subjectivity, making it difficult to achieve multi-scale continuous monitoring and meet the demands of modern research and production. This paper systematically reviews the technological framework and development trajectory of optical sensing technology-driven phenotypic platforms for facility crops. First, starting from optical sensing technologies, a comparative analysis highlights the advantages and limitations of RGB, multi-/hyperspectral, thermal infrared, and LiDAR sensors in phenotypic perception. Second, the characteristics and applicable scenarios of stationary, rail-mounted, mobile robot, and unmanned aerial vehicle (UAV) platform architectures are summarized. Furthermore, the evolution of phenotypic data processing methods is examined, focusing on the shift from traditional feature engineering to deep learning-driven approaches. Finally, key challenges such as multimodal data fusion, system cost, and real-time performance are discussed, along with the future direction of phenotypic platforms toward intelligent closed-loop decision-making systems. This article systematically reviews the facility agriculture phenotyping platforms driven by optical sensing technology, and also incorporates representative research progress in field phenotyping studies. These advances provide transferable sensing technologies, methodological frameworks, and platform design concepts that can facilitate the development of phenotyping platforms for controlled-environment agriculture.

Why it matches plant phenotyping methods施設作物の光学センシング型ハイスループット表現型解析プラットフォームを体系的にレビューしており、センサー、プラットフォーム構成、データ処理を中心に扱うため、方法論レビューとして明確に適格です。

abstractThis paper systematically reviews the technological framework and development trajectory of optical sensing technology-driven phenotypic platforms for facility crops.

Visual-SLAM for the detection of hidden tomatoes in greenhouses by Hierarchical Localization and GLOMAP for robotized harvesting →

Advanced crop monitoring inside greenhouses is becoming one of the primary objectives of research centers. High-performance sensors, such as LiDAR or stereo cameras, have traditionally been employed for this purpose, though these often have a high cost. This work proposes a Visual-SLAM system using a monocular camera, which is significantly more cost-effective and specifically tailored for agricultural applications, such as mapping tomato crops in a greenhouse. Tests were carried out on a real tomato bunch, located in the Agroconnect experimental greenhouse. A ROS 2 Humble node was developed to run on the robot in order to capture images of these crops, which were then stored for offline processing. To generate a 3D mapped model for the crop in the greenhouse, the GLOMAP mapper, based on Structure-From-Motion, was integrated with the Hierarchical Localization toolbox. This initial mapping is a foundation for future, more advanced algorithms to analyze growth patterns, and optimize agricultural management. The system leverages a hierarchical localization paradigm based on a coarse-to-fine strategy: it first performs global retrieval to generate location hypotheses, then combines local features within the identified candidate regions. The results show a correct identification of the tomato cluster, correctly characterising the tomato that is occluded and inaccessible by classical vision technologies. The reconstructed 3D model was further validated against manual ground-truth measurements of fruit size, centroid position, and orientation, confirming the geometric accuracy of the proposed low-cost monocular pipeline.

Why it matches plant phenotyping methods単なる収穫対象の位置検出ではなく、単眼Visual-SLAMと3D再構成を開発し、果実サイズ・重心位置・向きを実測値で検証しているため、植物器官形質の取得手法が中心である。

abstractThis work proposes a Visual-SLAM system using a monocular camera, which is significantly more cost-effective and specifically tailored for agricultural applications, such as mapping tomato crops in a greenhouse.

UGV-based multimodal RGBD–multispectral fusion framework enables high-quality 3D phenotyping of greenhouse lettuce seedlings →

High-throughput phenotyping of lettuce seedlings is highly prone to background confusion because the seedlings are small, have weak textural features, and exhibit spectral reflectance similar to that of the substrate. Traditional single-visual-modality approaches struggle to achieve reliable structural and physiological characterization simultaneously under the repetitive backgrounds and dense arrangements typical of greenhouse tray cultivation. To address these challenges, we establish a multimodal 3D phenotyping framework tailored for controlled agriculture environments, enabling the quantification of structural and physiological characteristics of lettuce seedlings. This framework is based on an unmanned ground vehicle (UGV) platform integrating a RGBD camera and a quad-band multispectral sensor which are rigidly coupled and synchronously triggered. An alignment module based on established feature matching algorithm is introduced to register the misalignment between source multispectral and RGBD images. Subsequently, we design a novel dual-backbone instance segmentation network, MS-SegNet, to enhance segmentation accuracy by hierarchically fusing geometric information with multispectral features. A robust 3D metric pose estimation pipeline, incorporating standard SfM initialization, scale recovery, and generalized ICP refinement, is constructed to generate 3D point clouds with spectral attributes and semantic labels. Finally, key structural and physiological phenotype parameters of each seedling are calculated based on the 3D semantic multispectral point clouds. Experiments demonstrate that MS-SegNet achieves significant advantages in instance segmentation of lettuce seedlings with mAP@50:95 = 0.854. The metric 3D pose estimation pipeline exhibits reliable performance under complex controlled conditions. The quality of the 3D reconstructions is indirectly validated through downstream structural trait extraction. The estimated seedling height and crown width show high correlation with manual measurements, achieving R 2 values of 0.8379 and 0.918, and RMSE values of 10.94 mm and 11.56 mm, respectively. Overall, by systematically integrating these adapted components with the novel segmentation architecture, this framework achieves stable performance improvements in 3D reconstruction, instance segmentation, and phenotypic analysis under greenhouse conditions. It provides a scalable, integrated technical solution for non-destructive, high-throughput phenotyping of crop seedlings in controlled environments.

Why it matches plant phenotyping methodsRGBD・マルチスペクトル・UGVを統合した3Dフェノタイピング基盤を開発し、分割・再構成・構造／生理形質抽出を検証しており、フェノタイピング手法が研究の中心である。

abstractwe establish a multimodal 3D phenotyping framework tailored for controlled agriculture environments, enabling the quantification of structural and physiological characteristics of lettuce seedlings.

A UAV-based sparse-view 3DGS framework for greenhouse strawberry reconstruction →

UAV-based multi-view reconstruction is an important approach for high-precision, non-destructive 3D crop phenotyping. However, in greenhouse environments, UAV image acquisition is often restricted to sparse viewpoints because of UAV-induced airflow disturbances and the structural complexity of the greenhouse, which severely hinders accurate 3D phenotyping. To address this challenge, this study develops a task-driven phenotyping framework for constrained UAV viewpoints in greenhouse environments, integrating a vision-triggered flight planning strategy with an improved sparse-view 3DGS pipeline, termed SparseBerry-3DGS, for multi-view image acquisition and 3D phenotyping of greenhouse strawberries in GNSS-denied environments. Specifically, 3D Gaussian Splatting (3DGS) is improved by incorporating flow-guided initialization, depth supervision, and an adaptive pruning strategy, which effectively alleviate geometric collapse and floating artifacts under sparse-view conditions. Furthermore, sequential semantic masks generated by SAM2 are utilized to guide the segmentation of strawberry point clouds, thereby reducing background interference and segmentation errors. Experimental results show that the vision-triggered flight strategy enables stable capture of 16 surrounding images for each target fruit. Under sparse-view conditions, SparseBerry-3DGS improves reconstruction stability, with the average peak signal-to-noise ratio (PSNR) reaching 18.25 dB, corresponding to an 18% improvement. The SAM2-based segmentation module achieves high accuracy, with the mean intersection over union (mIoU) above 0.95. Geometric evaluation based on strawberry longitudinal diameter yielded an of 0.88, supporting the accuracy of fruit-scale geometric reconstruction. For weight estimation, five-fold cross-validation yielded an of 0.90 and an RMSE of 3.62 g, showing better predictive performance than models based on 2D projected area and standard 3DGS point clouds. This study provides a new approach for high-throughput, non-invasive digital crop phenotyping in greenhouse horticulture.

Why it matches plant phenotyping methods温室イチゴの3D形状再構成と重量推定を目的に、制約視点UAV撮影、SparseBerry-3DGS再構成、点群セグメンテーションを統合した表現型取得手法を開発・検証しており、方法が研究の中心である。

abstractthis study develops a task-driven phenotyping framework for constrained UAV viewpoints in greenhouse environments

Image-Based Phenotyping for Early Assessment of Radiosensitivity of Cowpea (Vigna unguiculata L. Walp.) Seedlings Irradiated with Gamma Rays →

Calibrating the mutagenic dose is the first practical step of any radiation mutation-breeding programme, and it is usually summarised by the median lethal dose (LD50) or the median growth-reduction dose (GR50). We asked whether an accessible, image-based phenotyping pipeline can quantify the early radiation response of cowpea (Vigna unguiculata L. Walp.) seedlings finely enough to estimate GR50 and to rank organ- and pigment-level sensitivities. Seeds of the traditional Paraguayan landrace kumandá pyta’i were exposed to Cobalt-60 gamma rays at 0, 100, 200, 300, 400, 500, 600, and 700 Gy, grown in a greenhouse, and photographed at the early seedling stage. A single calibrated photograph (5.1 px mm−1) of 83 seedlings was segmented in Fiji/ImageJ 1.54p and analysed with Python to extract morphometric traits (total, root, and shoot length, root:shoot ratio, tortuosity, and a two-dimensional biomass proxy) and colorimetric traits (CIE L*a*b*, a normalised greenness index, and colour-class pixel fractions). Because the data departed from normality, dose effects were tested with Kruskal–Wallis, Spearman rank correlation, and Dunn post hoc tests, and GR50 was estimated by regression of each trait expressed as a percentage of the control. Total length, shoot length, and the biomass proxy declined significantly with dose (Spearman ρ = −0.40, −0.51, and −0.47; all p < 0.001), preceded by a low-dose stimulation at 100 Gy. Estimated GR50 values were ≈390 Gy for shoot length, ≈510 Gy for total length, and ≈550 Gy for the biomass proxy, within the range reported for other cowpea genotypes. Shoot elongation was more radiosensitive than root elongation, so the root:shoot ratio did not decline; tortuosity showed no dose response. Among pigment traits, the loss of greenness was the most robust signal (a* increased, ρ = +0.62, p = 5 × 10−10; green pixel fraction fell from 0.32 to near zero by 500 Gy). These results show that single-photograph phenotyping resolves a coherent, statistically supported dose response and yields a GR50 estimate usable for dose calibration. For kumandá pyta’i, doses of roughly 300–400 Gy (below GR50) are the most defensible starting window for mutation induction. The framework is reproducible and low-cost, but it is based on one greenhouse experiment and a single genotype, and should be validated across independent trials and cultivars.

Why it matches plant phenotyping methods画像取得・セグメンテーション・解析による形態および色彩形質の抽出を中心に、放射線応答とGR50を推定する低コスト画像ベース表現型解析法を提示しているため。

abstractA single calibrated photograph (5.1 px mm−1) of 83 seedlings was segmented in Fiji/ImageJ 1.54p and analysed with Python to extract morphometric traits

Efficient Ripeness Monitoring in Open-Facility Environments Using a Quadruped Robot and Panoramic AI Recognition →

Efficient facility-scale tomato ripeness monitoring remains difficult in greenhouses where uneven terrain limits conventional wheeled and rail-guided platforms and planar cameras provide restricted coverage. This study developed a wheel-legged quadruped monitoring system integrating LiDAR, a depth camera, and a panoramic camera. An adaptive gait-switching strategy supported navigation across heterogeneous terrain. Panoramic images were projected into six perspective views, and the left and right views were processed using a YOLOv8-based ripeness recognition model. Time-synchronized detections and robot poses were fused to map ripeness observations into three-dimensional greenhouse coordinates. Five field experiments in a commercial tomato facility demonstrated autonomous row traversal, inter-row transition, and avoidance of pedestrians, obstacles, and cultivation boundaries. The recognition pipeline continuously identified multiple ripeness stages under variable illumination, foliage occlusion, and robot motion, while the spatial fusion procedure produced a facility-scale three-dimensional ripeness distribution. The integration of terrain-adaptive quadruped mobility, panoramic perception, and spatial mapping provides a practical framework for continuous ripeness monitoring and can support targeted harvesting, yield forecasting, and crop management.

Why it matches plant phenotyping methodsトマト果実の成熟度を画像認識で取得するロボット型フェノタイピングシステムを開発し、実環境で評価しており、表現型取得法が研究の中心である。

abstractThis study developed a wheel-legged quadruped monitoring system integrating LiDAR, a depth camera, and a panoramic camera.

Precision Greenhouse Rose Phenotyping from UAV Imagery Using a Multi-Source Dataset and Lightweight BloomRoseNet →

Accurate detection of blooming roses and flower buds is essential for greenhouse phenotyping, cultivation scheduling, harvest planning, and yield management. However, UAV-derived greenhouse imagery presents major challenges because rose targets are often small, densely distributed, partially occluded, and visually similar to complex backgrounds. This study proposes a lightweight rose detection framework that combines multi-source dataset construction with an improved YOLOv12n-based detector, termed BloomRoseNet. A GreenHouse Rose dataset was constructed by integrating self-collected UAV overhead images, screened RoseTracker images, and supplementary multi-view rose images to increase diversity in scale, growth stage, viewpoint, and background complexity. BloomRoseNet introduces task-oriented improvements for fine-grained feature extraction, adaptive feature fusion, and attention-enhanced detection. The supplementary multi-view data improved precision, recall, and mAP@50 from 85.2%, 82.8%, and 89.2% to 86.1%, 85.3%, and 90.5%, respectively. Compared with the baseline YOLOv12n, BloomRoseNet increased precision, recall, mAP@50, and mAP@50:95 by 3.2, 3.3, 3.6, and 1.6 percentage points, respectively, while reducing parameters from 2.55 M to 2.08 M and model size from 5.5 MB to 4.5 MB. The model also maintained real-time inference capability and stronger robustness under blur, occlusion, and illumination disturbances. The proposed framework provides an effective and practical solution for UAV-based greenhouse rose monitoring and supports precision cultivation management.

Why it matches plant phenotyping methodsバラの開花・蕾を対象としたUAV画像フェノタイピング手法を開発し、データセット構築、検出モデル改良、性能評価を中心に扱っているため。

abstractThis study proposes a lightweight rose detection framework that combines multi-source dataset construction with an improved YOLOv12n-based detector, termed BloomRoseNet.

Analytically derived sphere correction enables transferable RGB-D fruit sizing across fruit shapes and depth-sensing principles. →

Abstract Depth cameras measure the distance to a fruit's surface, whereas converting its silhouette into physical dimensions requires the depth of its center; corrections for this offset have so far been empirical, and therefore bound to the crop, sensor, and dataset they were fitted on. This paper derives the correction analytically. For a spherical fruit, integrating the surface-depth distribution over the visible hemisphere yields a closed-form sphere correction whose coefficient follows from sampling geometry, together with a theoretical justification of the median mask depth as the representative statistic. Combined with deep instance segmentation on RGB-D imagery of hydroponic melons, the empirically optimal coefficient coincided with the derived value, and the pipeline reached R 2 of 0.966 for fruit length (MAE 1.43 mm), 0.959 for width (1.84 mm), and 0.861 for end-to-end fresh weight (MAPE 4.6%). The analytical form made the measurement transferable. Applied unchanged to cylindrical mini-cucumbers, the pipeline held mm-level accuracy (width MAE 0.52 mm; fresh weight R 2 0.955 after coe cient refitting), with the correction's negligibility predicted in advance by an R / Z corollary; across active-stereo and time-of-flight cameras, the optimal coefficients proved non-interchangeable, identifying the coefficient as a physical parameter that absorbs geometry, sensor physics, and fruit shape. A field system that fuses and cross-verifies the two sensors, with an error-propagation confidence gate and parameterized grading logic, reproduced 2-3% fresh-weight error and 90.9% confirmed-judgment grading accuracy over four validation sessions in a commercial greenhouse unseen during development. Throughout, geometric components transferred unchanged while learned and regression components required recalibration - a boundary the model predicts and the system itself monitors.

Why it matches plant phenotyping methodsRGB-D画像と深度補正を用いて果実の寸法・重量を推定する手法を開発し、異なる果形・センサー・圃場で精度検証しており、植物表現型取得が中心である。

abstractThis paper derives the correction analytically.

Automated Video Tracking to Phenotype Plant Resistance to Aphid-Transmitted Yellow Dwarf Viruses in Grass Seed Crops →

Grass seed crops are susceptible to yellow dwarf viruses transmitted by aphids. The Willamette Valley in Oregon, United States, is the leading producer of cool-season grass seed crops globally, and industry reports have attributed seed yield loss and shortened stand longevity to aphid-transmitted yellow dwarf viruses. Genetic resources are needed for effective and sustainable management of this pest, specifically the Rhopalosiphum padi–PAV pathosystem, in grass seed production to reduce foliar insecticide applications and maintain optimum seed yield potential. High-throughput phenotyping methods are needed to screen grass seed cultivars to identify resistant traits for traditional breeding programs. An automated video tracking procedure was optimized to evaluate host plant resistance in cool-season grass seed crops to R. padi–PAV with live plants and viruliferous and nonviruliferous aphid populations. Feeding behavior recorded with automated video tracking was strongly correlated with “ground-truthed” observations by human observers. Partial resistance (antixenosis and antibiosis) and tolerance traits were detected in select perennial ryegrass and tall fescue cultivars evaluated with traditional phenotyping methods in a greenhouse setting and with high-throughput phenotyping using automated video tracking in the laboratory. Across grass cultivars, nonviruliferous aphids had greater fitness and preference for noninfected grass plants compared with viruliferous aphids. Automated video tracking can be used as a high-throughput phenotyping method for continued evaluation of host plant resistance in grasses grown for seed production, as well as to identify resistant genotypes in other grass crops susceptible to aphid–yellow dwarf virus virus–vector systems.

Why it matches plant phenotyping methods自動動画追跡を用いてアブラムシ媒介ウイルスに対する植物抵抗性を高スループットに評価する手法を最適化・検証し、従来観察との相関および抵抗性形質の検出を示しており、表現型取得法が研究の中心である。

abstractHigh-throughput phenotyping methods are needed to screen grass seed cultivars to identify resistant traits for traditional breeding programs.

Cucumber3DGaussians: Plant architecture analysis using semantic-aware Gaussian splatting →

Monitoring continuous agricultural canopies is fundamentally limited by the geometric constraints and computational bottlenecks of traditional 3D reconstruction. This study presents a 3D volumetric phenotyping pipeline integrating semantic mask generation with 3D Gaussian Splatting (3DGS) to quantify greenhouse cucumber canopy architecture. To drive component-specific optimization, we evaluated custom-trained convolutional networks (YOLO11) against a zero-shot foundation model (SAM3), determining that SAM3 provided the necessary boundary precision for accurate spatial isolation. The optimized 3DGS model outperformed implicit NeRF baselines, preserving fine-scale morphological details at real-time rendering speeds ( ≈ 48 FPS). To enable actionable measurement, a uniform voxelization protocol was applied to the point cloud, successfully neutralizing algorithmic densification bias. This technical framework yielded highly accurate physical geometry, achieving a Root Mean Square Error (RMSE) of ≤ 0.59 cm against in situ leaf measurements. Transitioning to agronomic interpretation, the pipeline was deployed to quantify complex canopy architecture. It mathematically mapped structural congestion zones and provided a temporal validation of a standard pruning intervention, explicitly capturing the geometric increase in lower-canopy porosity and the upward translation of biomass. This framework provides a robust, scale-accurate tool for monitoring plant architecture and guiding dynamic canopy management.

Why it matches plant phenotyping methods植物キャノピーの3D形状を取得・定量化する画像ベースの表現型解析パイプラインを開発し、実測葉寸法で精度検証しているため、方法が研究の中心である。

abstractThis study presents a 3D volumetric phenotyping pipeline integrating semantic mask generation with 3D Gaussian Splatting (3DGS) to quantify greenhouse cucumber canopy architecture.

Machine learning-based estimation of leaf chlorophyll content in greenhouse-grown muskmelon using portable hyperspectral reflectance measurements →

Abstract has not been obtained from indexed metadata or an accessible article page.

Why it matches plant phenotyping methods携帯型ハイパースペクトル測定と機械学習により、葉のクロロフィル含量という植物形質を推定する手法が題名上の中心であるため。

titleMachine learning-based estimation of leaf chlorophyll content in greenhouse-grown muskmelon using portable hyperspectral reflectance measurements

RT-ZSDR: A real-time zero-shot segmentation and dense reconstruction framework for plant phenotyping robot →

Annotation scarcity, poor model generalization and lagged data processing remain key bottlenecks hindering the practical deployment of phenotyping robots. To address these issues, we developed a novel phenotyping robot capable of online 3D reconstruction and zero-shot segmentation directly on the edge. Diverging from conventional semantic SLAM, our core contribution is RT-ZSDR, a framework featuring two key methodological novelties. First, we introduce the ForeCut pipeline for target extraction, which innovatively fuses DINO features with 3D geometric spatial information, leveraging multi-view semantic-spatial consistency to achieve annotation-free, zero-shot dense segmentation and reconstruction. Second, we designed a hardware-coupled loop closure strategy utilizing the robotic arm's kinematic feedback as prior constraints to significantly improve loop closure recall. Supported by edge computing Jetson Orin NX, the tracking and segmentation process takes approximately 0.24 s per frame after an initialization period of 1.82 s. RT-ZSDR's phenotypic measurements demonstrated strong correlations with reference baseline in both laboratory settings (n=90, PlantEye measurements as reference baseline; R 2 =0.990, 0.939, 0.725, and 0.861 for plant height, projected leaf area, surface area, and volume) and practical greenhouse environments (n=48, manual measurements as reference baseline; R 2 =0.965, 0.862 for plant height and stem diameter). Additionally, evaluated against COLMAP benchmarks (n=24), the system achieved a mean 3D reconstruction F1-score of 0.816.

Why it matches plant phenotyping methods植物フェノタイピングロボット向けに、ゼロショット分割・3D再構成・エッジ処理を開発し、植物形質を基準測定およびベンチマークと比較検証しており、取得・抽出手法が研究の中心である。

abstractwe developed a novel phenotyping robot capable of online 3D reconstruction and zero-shot segmentation directly on the edge.

A deep learning-based VMSNet for high-precision point cloud segmentation and ripe tomato diameter phenotyping in greenhouses →

Ripe tomato fruit display diverse 3D morphologies driven by genetics, environment, and management, yet these differences remain hard to quantify in the absence of precise point-cloud segmentation tools. This paper proposes the VMSNet to accurately segment tomato fruits and extract phenotypic traits based on the segmentation results, including horizontal and vertical diameters. Point clouds are obtained through depth cameras. After preprocessing and labeling the fruits, a dataset is established using global enhancement and local enhancement. On the base framework of PointNet++, the downsampling method was replaced, a multi-scale attention module (MS_A) was integrated, the combination scheduling strategy was optimized, and VMSNet was constructed. Following segmentation, the fruit growth direction is estimated by density-weighted method, and principal component analysis (PCA) is used to establish a rotation plane. By rotating according to the slicing angle, the fruit point cloud is completed and fitted into an ellipsoid. Random Sample Consensus (RANSAC) is used to smooth the outliers. The OBB is applied to extract the horizontal and vertical diameters, which are compared with measurement to verify the algorithm’s accuracy. The results indicate that the accuracy of VMSNet in segmenting ripe tomato fruits is 97.96%. The correlation coefficients R 2 between the calculated and measured values of the horizontal and vertical diameters reached 0.89 and 0.86, respectively. This proposed proposal provides robust point cloud segmentation and completion for phenotypic analysis for other same species greenhouse crop.

Why it matches plant phenotyping methods深度学習による点群分割とトマト果実径の抽出手法を開発し、実測値との比較で精度検証しており、植物表現型取得が研究の中心である。

abstractThis paper proposes the VMSNet to accurately segment tomato fruits and extract phenotypic traits based on the segmentation results, including horizontal and vertical diameters.

Development and validation of a low-cost imaging system for seedling germination kinetics through time-cumulative analysis →

The ready-to-eat lettuce industry is rapidly expanding, increasing the need for reliable, scalable methods to assess seed germination and early growth under realistic soil conditions. This study presents an automated imaging-based approach for quantifying germination dynamics and seedling vigor using a low-cost multi-camera system under greenhouse conditions. Lettuce seeds were grown in soil either inoculated or non-inoculated with the soil-borne pathogen Rhizoctonia solani. Top-view images were acquired using commercial surveillance cameras and processed through a calibrated pipeline including geometric correction, color normalization, vegetation segmentation, clustering, and temporal tracking of emergence events. Seedling vigor was quantified through projected leaf area estimation. The proposed method enables accurate estimation of germination kinetics and growth dynamics under field-like conditions. Automated counts were validated against manual measurements at both intermediate and final time points, achieving high agreement in both cases. At the final assessment, the method reached R² = 0.98 and RMSE = 1.12, while at the midterm evaluation it achieved improved performance with R² = 0.998 and RMSE = 0.5, reflecting the lower complexity of plant structure at earlier growth stages. Results showed that pathogen inoculation significantly reduced both germination rate and seedling vigor, with up to 70% reduction in biomass accumulation. The proposed framework provides a robust, low-cost solution for high-throughput phenotyping of early plant development in soil-based systems, supporting scalable agricultural experimentation.

Why it matches plant phenotyping methods低コスト多カメラ画像システムと画像解析パイプラインを開発・検証し、発芽動態と幼植物活力を定量化しているため、植物フェノタイピング手法が中心です。

abstractThis study presents an automated imaging-based approach for quantifying germination dynamics and seedling vigor using a low-cost multi-camera system under greenhouse conditions.

Screening of Florida Sugarcane Varieties Against Thielaviopsis spp., the Causal Agent of Pineapple Sett Rot. →

The Florida sugarcane industry is transitioning from manual to mechanical planting systems that use comparatively smaller seedcane pieces (billets) as planting material. A major limitation of mechanical planting is the increased seedcane requirement owing to mechanical damage and the increased vulnerability of seedcane pieces to soilborne pathogens that cause sett rots, particularly pineapple sett rot caused by Thielaviopsis spp. Current sugarcane breeding programs in Florida screen for major diseases, such as rusts, smut, ratoon stunting, and viruses, early in the breeding process but not for pineapple sett rot. This study aimed to isolate and identify Thielaviopsis spp. in the Everglades Agricultural Area (EAA), develop a single-bud inoculation protocol for greenhouse-based disease screening, and phenotype the current widely grown sugarcane varieties in Florida against Thielaviopsis spp. The pathogen was confirmed as T. ethacetica , consistent with previous reports from the EAA. A reproducible inoculation method was established and validated through symptom assessment, pathogen reisolation, and molecular confirmation. Using this protocol, six widely grown Florida sugarcane varieties showed significantly reduced germination (by more than 50%) and reduced above- and belowground morphological characteristics under infection, indicating susceptibility. Varietal differences were observed, with CP 03-1912 showing the highest mortality percentage and reduced growth under T. ethacetica infection. These findings highlight the vulnerability of current varieties to pineapple sett rot, especially under mechanical planting systems where smaller seedcane pieces are used. Furthermore, the developed inoculation protocol provides a scalable tool for early stage evaluation of resistance in breeding programs, offering potential to accelerate the development of varieties better adapted to mechanical planting.

Why it matches plant phenotyping methodsサトウキビの病害抵抗性を評価するための単芽接種・症状評価プロトコルを開発し、再現性を検証した研究であり、植物病害表現型の取得法が中心である。

abstractdevelop a single-bud inoculation protocol for greenhouse-based disease screening

Chlorophyll fluorescence-based control of greenhouse supplemental lighting improves energy use efficiency in lettuce. →

Plant-driven lighting control has been proposed as a strategy to regulate supplemental light-emitting diode (LED) intensity according to real-time plant physiological status. This study developed a multiple linear regression (MLR) model to predict quantum yield of photosystem II (Φ PSII ) from environmental variables and evaluated its integration into a chlorophyll fluorescence-based biofeedback light control. The model incorporated light intensity, CO 2 concentration, air temperature, vapor pressure deficit, short-term light history, and diurnal effects. In a greenhouse validation experiment, supplemental lighting was regulated using either direct chlorophyll fluorometer measurements of Φ PSII (sensor-based control) or Φ PSII values predicted by the machine learning model (ML-based control), and compared with a constant photosynthetic photon flux density (PPFD) treatment. Both sensor- and ML-based control stabilized photochemical activity across the photoperiod relative to constant PPFD. Although plant growth did not differ among treatments, sensor-based ETR control achieved the highest energy use efficiency for LED lighting in this study. These findings demonstrate the feasibility of integrating predictive ML models into plant-based lighting control systems and indicate that sensor-based biofeedback control improved the energy-use efficiency of greenhouse supplemental lighting without compromising crop growth.

Why it matches plant phenotyping methods植物の光合成生理状態（ΦPSII）を予測・計測するモデルを開発し、蛍光センサーによるフィードバック照明制御へ統合して検証しており、植物フェノタイピング手法が中心です。

abstractThis study developed a multiple linear regression (MLR) model to predict quantum yield of photosystem II (Φ PSII ) from environmental variables and evaluated its integration into a chlorophyll fluorescence-based biofeedback light control.

F2DMAS: a smartphone video-based 3D phenotyping workflow for potted plants in complex backgrounds →

Introduction: Plant phenotyping requires accurate and repeatable three-dimensional structural information, but practical acquisition conditions in greenhouses, seedling rooms, and indoor pot experiments often include complex backgrounds, handheld motion blur, and thin leaf structures. These factors reduce the robustness of conventional three-dimensional reconstruction methods and limit their use in low-cost and automated phenotyping. Methods: To address this problem, this paper proposes F2DMAS, an automated three-dimensional plant phenotyping workflow using consumer-grade smartphone videos. The workflow first converts multiview RGB videos into image sequences and removes motion-blurred frames through frequency-domain quality filtering. A frequency-spatial plant segmentation module, termed FSAM3, is then introduced to separate plant structures from complex backgrounds without task-specific annotated training data. The segmented image sequences are further reconstructed using 2D Gaussian Splatting, followed by TSDF-based meshing, scale recovery, and virtual measurement for extracting plant height, canopy width, leaf length, and leaf width. Results: Experiments were conducted on 15 plant species under two acquisition scenarios. The proposed workflow achieved stable plant reconstruction under non-ideal background conditions, with PSNR, SSIM, and LPIPS values of 31.09, 0.9711, and 0.0365, respectively. Compared with the baseline reconstruction workflow, F2DMAS substantially reduced the processing time for mesh extraction while improving reconstruction quality. The extracted phenotypic traits showed strong agreement with manual measurements, with R² values ranging from 0.90 to 0.99, RMSE values ranging from 0.64 to 1.21 cm, and MAPE values ranging from 4.50% to 9.73%. Discussion: These results indicate that F2DMAS can provide an end-to-end workflow from smartphone video acquisition and plant segmentation to three-dimensional reconstruction and phenotypic trait extraction. The proposed method offers a practical and deployable solution for greenhouse seedling cultivation, potted plant experiments, and low-cost three-dimensional plant phenotyping.

Why it matches plant phenotyping methodsスマートフォン動画から植物の3D構造を再構成し、複数の形態形質を抽出・検証するワークフロー自体が中心的な方法論的貢献である。

abstractThe extracted phenotypic traits showed strong agreement with manual measurements, with R² values ranging from 0.90 to 0.99

GCP-YOLO: high-precision detection of tiny chili flowers in complex greenhouse scenes. →

Precise identification of chili flowers and buds is essential for enabling intelligent robotic pollination, continuous crop monitoring, and early yield prediction in protected horticulture. Reliable visual sensing remains challenging because chili targets are extremely small, densely distributed, and frequently occluded by foliage, while greenhouse environments introduce strong illumination variations and background reflections. These factors often lead to insufficient feature extraction and unstable detection accuracy in existing models, limiting their practical deployment in automated monitoring systems. To address these challenges, this study proposes GCP-YOLO, a lightweight yet high-performance detection framework built upon the YOLOv11n architecture. The model enhances small-target perception through three key improvements. First, a redesigned Generalized Feature Pyramid Network (GFPN) strengthens cross-scale feature interaction, improving the fusion of fine-grained texture cues and deep semantic information. Second, a C2CGA context-guided attention module is introduced to emphasize floral structural features while suppressing background noise caused by reflections and canopy clutter. Third, extended multi-scale detection heads (P2-P6) incorporate broader contextual information to reduce missed detections and false positives in dense planting scenarios. Experimental results on a custom chili flower dataset show that the proposed method achieves 92.8% precision, 83.7% recall, 90.8% mAP50, and 72.7% mAP50-95, improving upon the YOLOv11n baseline by 2.1, 1.3, 3.9, and 6.6 percentage points, respectively. Deployment on an NVIDIA Jetson AGX Orin edge platform demonstrates real-time inference at 97.9 FPS, confirming its suitability for on-device phenotyping. Overall, the proposed approach significantly improves detection robustness under complex greenhouse conditions, providing an effective visual sensing methodology for automated crop monitoring and data-driven yield estimation.

Why it matches plant phenotyping methodsチリの花・蕾という植物器官の画像検出手法を中心に、モデル改良、専用データセットでの性能評価、エッジ実装まで行っており、植物表現型取得の技術的貢献が明確である。

titleGCP-YOLO: high-precision detection of tiny chili flowers in complex greenhouse scenes.

Lightweight Real-Time Strawberry Volume Estimation Based on Instance Segmentation and Principal-Axis Slicing →

Real-time strawberry volume estimation is a pivotal technology for automated harvesting and precision grading. However, conventional contact methods are prone to damaging fruits, while existing vision-based approaches struggle to balance high accuracy with low computational overhead. To address these challenges, this study proposes a two-stage real-time volume estimation framework coupling a red-green-blue-depth (RGB-D) sensor with an “Instance segmentation–Principal-axis slicing” framework. First, to precisely extract target contours in complex backgrounds, we designed Deformable Feature Aware-YOLO (DFA-YOLO) based on the YOLO11-seg architecture. This model enhances the geometric perception of irregular fruit edges and effectively overcomes the challenges of background noise and multi-scale variations, providing high-precision masks for subsequent spatial mapping. Subsequently, a principal-axis-slicing algorithm extracts the mask’s centroid and principal axis, perpendicularly slicing the mask into infinitesimal micro-slices. By computing and accumulating the pixel-space volume of these slices, the system converts them into precise 3D physical volumes based on RGB-D depth mapping. The entire system was deployed on an NVIDIA Jetson Orin edge computing platform and validated in a greenhouse. Experimental results demonstrate that the estimated volume highly agrees with the true volume, achieving a coefficient of determination (R2) of 0.945 and a mean absolute percentage error (MAPE) of 9.0%. Under typical operating conditions (1–5 targets per field of view), the system maintains an overall frame rate of 8–15 FPS, requiring only 55 ms for single-fruit estimation. This method exhibits favorable stability and lightweight efficiency under the tested greenhouse conditions, offering a reliable solution for real-time non-destructive crop phenotypic monitoring in computationally constrained agricultural environments.

Why it matches plant phenotyping methodsイチゴ果実の体積という植物器官形質を、RGB-D画像、インスタンスセグメンテーション、主軸スライシングで推定する方法を開発し、精度とリアルタイム性能を検証しているため、フェノタイピング手法が中心です。

abstractthis study proposes a two-stage real-time volume estimation framework coupling a red-green-blue-depth (RGB-D) sensor with an “Instance segmentation–Principal-axis slicing” framework.

Predicting capsicum leaf water stress using mid-infrared ATR-FTIR spectroscopy. →

Leaf water status is a key indicator for irrigation scheduling and early stress detection, but many spectroscopic prediction studies have mainly relied on near-infrared features. Here, practical prediction models were developed using mid-infrared (MIR) ATR-FTIR spectra of capsicum (Capsicum annuum L.) leaves collected under glasshouse conditions during a 10-day gradual dehydration period, alongside an irrigated control. Spectra (4000-450 cm⁻1) were measured with minimal sample preparation, and leaf water traits were quantified using fuel moisture content (FMC), equivalent water thickness (EWT), and specific leaf weight (SLW). Water-related MIR bands at 3370 and 1641 cm⁻1 showed the most consistent response to dehydration, and simple band ratios generally provided stronger predictions than single bands. The best ratios were A1641/A2159 for FMC (R2 = 0.81; RMSE = 12.80) and A3370/A2849 for EWT (R2 = 0.72; RMSE = 0.0034) and SLW (R2 = 0.62; RMSE = 6.95 × 10⁻4), while predicted-versus-measured performance yielded R2 values of 0.72 for FMC, 0.68 for EWT, and 0.52 for SLW. These results indicate that MIR ATR-FTIR spectroscopy, when coupled with selected band ratios, can provide a rapid, low-preparation laboratory-based approach for estimating capsicum leaf water traits under controlled dehydration, supporting plant-based water stress assessment under controlled conditions and providing a basis for further irrigation-related sensing studies. However, the models are preliminary and require validation with larger independent datasets and tightly standardised measurement conditions before operational use in irrigation management.

Why it matches plant phenotyping methodsMIR ATR-FTIRスペクトルと選択バンド比を用いて、葉の水分形質を推定するセンシング・予測手法の開発と性能評価が中心である。

abstractHere, practical prediction models were developed using mid-infrared (MIR) ATR-FTIR spectra of capsicum (Capsicum annuum L.) leaves

Adaptive spectral-thermal illumination management for protected tomato cultivation: a fused deep learning and pareto-based decision framework. →

This study presents an intelligent greenhouse lighting control framework that integrates a CNN-ELM photosynthesis prediction model with MOEA/D-based multi-objective optimization to improve tomato production while reducing the carbon impact of supplemental LED lighting. The CNN-ELM model was trained using key environmental variables, including photosynthetic photon flux density (PPFD), red-to-blue light ratio, canopy temperature, CO 2 concentration, and relative humidity. Within the experimental conditions, the model achieved high predictive accuracy, with an R² of 0.976 and an RMSE of 0.712 µmol m -2 s -1 . Using these predictions, the MOEA/D algorithm generated Pareto-optimal lighting strategies, which were ranked through entropy-weighted TOPSIS and implemented via cloud-based control connected to a LoRa wireless sensor network and pulse-width-modulated LED drivers. The system was evaluated during a 110-day tomato cultivation trial and compared with single-parameter control and ambient-condition treatments. Results showed a 38.4% reduction in LED-related carbon emissions, a 22.6% increase in net photosynthetic rate, and a 31.7% improvement in harvestable yield relative to ambient conditions. Physiological analyses further indicated enhanced photosynthetic performance, radiation-use efficiency, and light utilization. Overall, the findings demonstrate that data-driven, closed-loop lighting management can simultaneously enhance productivity and reduce greenhouse gas emissions in controlled-environment agriculture when applied within the validated operational domain.

Why it matches plant phenotyping methods光合成という植物生理形質を予測するCNN-ELMモデルを中核に、センサーネットワークと閉ループ制御を統合・評価しており、単なる栽培試験ではなく形質推定手法の応用が主要内容である。

abstractThis study presents an intelligent greenhouse lighting control framework that integrates a CNN-ELM photosynthesis prediction model with MOEA/D-based multi-objective optimization

ClearDepthIAS enables automated high-throughput quantification of roots in soil-grown taproot crops. →

Understanding root system architecture (RSA) is critical for improving crop productivity and resilience, yet phenotyping root traits such as root growth angle and rooting depth remains technically challenging, especially at high throughput. Here, we present ClearDepthIAS, a high-throughput imaging and analysis platform that enables non-destructive, automated quantification of root architecture traits in taproot system crops. By capturing and stitching 360° images of roots growing along the transparent walls of pots and applying deep learning-based segmentation (ClearDepth-WRT), we measured wall root shallowness (WRS)-a proxy for root growth angle-with high precision. We demonstrated for the tap root systems of soybean and canola that the system accurately detects root tips, quantifies their vertical distribution, and extracts biologically meaningful traits such as root area, distribution indices, and growth angles. Validation experiments in canola and soybean demonstrated that WRS can correlate with root crown architecture in mature plants, both in greenhouse and field settings. Furthermore, WRS and root distribution indices derived from ClearDepthIAS are predictors of early root architecture and can be correlated with root biomass distribution across soil depths under field conditions; however, environmental interactions may influence these relationships and weaken or even negate such correlations, as observed when comparing field to field variation in root system architecture. Our system enables efficient phenotyping of genetically diverse populations, with medium to high trait heritability, supporting its utility for genome-wide association studies and breeding. ClearDepthIAS accelerates the development of root ideotypes for improved resource acquisition and carbon sequestration, offering a scalable tool for supporting climate-resilient agriculture.

Why it matches plant phenotyping methods植物根系形態を自動取得・定量化する画像解析プラットフォームを開発し、精度と圃場での妥当性を検証しており、フェノタイピング手法が研究の中心である。

abstractwe present ClearDepthIAS, a high-throughput imaging and analysis platform that enables non-destructive, automated quantification of root architecture traits

Early Detection of Muskmelon Powdery Mildew Using Time-Series 3D Multispectral Point Clouds →

Melon (Cucumis melo L.) is a globally significant horticultural crop, characterized by high nutritional value and substantial commercial status. However, frequent outbreaks of powdery mildew severely threaten its yield and fruit quality. Current early detection methods primarily focus on detached leaf assays, which often lack sufficient model generalization. This study proposes a temporal 3D multispectral point cloud reconstruction method for melon plants by integrating multispectral imaging with 3D reconstruction technology. An Artificial Neural Network (ANN) model for 3D spatial light field distribution was developed based on a hemispherical white reference to achieve precise reflectance calibration of the multispectral point clouds. Post-calibration, the coefficient of variation (CV) for the spectral reflectance of the hemispherical reference in 3D space was reduced to less than 2.4%. On this basis, an early classification model for melon powdery mildew was constructed using Partial Least Squares Discriminant Analysis (PLS-DA) based on the mean reflectance spectra of individual plant point clouds. The results demonstrate that the average recognition accuracy reaches 85.94% from 4 days post-inoculation onwards, enabling disease early warning three days in advance. This research provides critical theoretical support and technical reference for the non-destructive early monitoring and precision smart plant protection of crops in facility agriculture.

Why it matches plant phenotyping methodsメロン個体の病徴状態を対象に、時系列3Dマルチスペクトル点群の再構成・反射率校正と早期病害分類を開発しており、植物表現型取得手法が中心である。

abstractThis study proposes a temporal 3D multispectral point cloud reconstruction method for melon plants by integrating multispectral imaging with 3D reconstruction technology.

Machine learning-assisted non-destructive prediction of root architecture in early-stage tomato rootstocks. →

The architecture of the root system is a primary factor in determining rootstock performance, affecting water and nutrient uptake, biomass accumulation, and overall vigor. However, direct root phenotyping is destructive, labor-intensive, and difficult to do routinely in breeding programs. The present study investigated early root morphological variation among developed interspecific tomato rootstock candidates (Solanum lycopersicum x S. habrochaites). The ability of linear regression and machine learning models to predict root traits from easily measured plant growth parameters was assessed. Nineteen interspecific hybrid rootstock candidates, two commercial rootstocks, and one scion were grown under optimal greenhouse conditions and evaluated at 0, 10, 20, and 30 days after planting. Root length, root surface area, root diameter, and root volume were determined by digital image analysis. In contrast, genotype, plant length, and stem diameter were used as input variables. Significant genotype x sampling date effects were observed for most morphological and biomass traits, indicating dynamic changes in root and shoot development during the first 30 days of growth. The rootstock candidates RSH-17 and RSH-6 generally showed relatively higher root length, surface area, root volume, and biomass accumulation than the commercial rootstocks and scion. XGBoost and OLR were the best predictive models, with R 2 values as high as 0.95 for root length, surface area, and volume. Root diameter was predicted less accurately than root length, surface area, and volume, suggesting that it might be a more independent or less variable root trait during early development. Overall, results suggest that vigor-related traits can serve as useful proxies for estimating major root architectural traits in early-stage tomato rootstock selection. Both XGBoost and OLR performed well, suggesting that root and shoot development were highly coordinated under optimal (non-stress) conditions. Hence, predictive modeling may help prioritize promising rootstock candidates before destructive root analysis. However, more validation under stress conditions and for longer periods of development is needed to determine the greater applicability of these models.

Why it matches plant phenotyping methods根系形態形質をデジタル画像解析で取得し、線形回帰・機械学習による非破壊予測モデルを評価・比較しており、植物フェノタイピング手法が研究の中心である。

abstractThe ability of linear regression and machine learning models to predict root traits from easily measured plant growth parameters was assessed.

From Phenotyping to Supervised Agentic Decision Support: A Review of Sensing and Artificial Intelligence for Greenhouse Strawberry Cultivation →

Strawberry greenhouse cultivation is increasingly supported by sensing technologies, artificial intelligence (AI), and decision-support infrastructure, but their horticultural value depends on whether heterogeneous measurements can be translated into biologically meaningful crop states and practical management decisions. This review synthesizes strawberry phenotyping, multimodal sensing, AI-based crop-state interpretation, and supervised agentic coordination as a phenotyping-to-action framework for greenhouse strawberry cultivation. The reviewed studies show substantial progress in measuring and interpreting vegetative, reproductive, fruit-quality, stress-related, and environmental crop states through imaging, spectral, environmental, root-zone, and modeling approaches. However, much of the literature still emphasizes measurement accuracy, model performance, or infrastructure capability, whereas fewer studies validate whether AI-derived outputs improve crop response, management decisions, workflow, resource use, or production outcomes. The review therefore distinguishes sensing technologies for data acquisition and measurement from AI-based methods for interpretation and prediction, and examines how crop-state information can be connected to practical greenhouse decision making. It also compares established decision technologies, including expert systems, model predictive control, digital twins, and closed-loop coordination, with supervised agentic coordination as bounded decision-support concepts rather than as evidence of unrestricted autonomous control. Future work should emphasize phenotype-to-action validation, domain-aware benchmarking, and supervised deployment studies that connect model outputs with decision rules, crop outcomes, operational constraints, and grower oversight. By grounding sensing technologies and AI-based interpretation methods in crop-response validation, strawberry greenhouse systems can progress toward supervised, crop-state-driven decision support.

Why it matches plant phenotyping methods温室イチゴのフェノタイピング、マルチモーダルセンシング、AIによる作物状態解釈を中心に整理する方法論レビューであり、植物状態の取得・推定手法が主題。

abstractThis review synthesizes strawberry phenotyping, multimodal sensing, AI-based crop-state interpretation, and supervised agentic coordination as a phenotyping-to-action framework for greenhouse strawberry cultivation.

Curvature-aware 3D length estimation of greenhouse cucumbers using RGB-D imaging and cubic spline arc-length integration →

Commercial greenhouse cucumber production is graded by fruit length, which drives harvest scheduling, labour allocation, and logistics. Manual measurement with thread or caliper is accurate but infeasible at commercial scale. This paper presents CucumberVision, a non-contact length estimation framework using an Intel RealSense D435 RGB-D camera. A YOLO26n instance segmentation model locates cucumbers, and SAM (ViT-B backbone) refines each detection to a pixel-precise mask. Five methods are evaluated under matched conditions: (M1) a dominant-axis skeleton scan-line baseline; (M2) PCA on the bounding-box depth point cloud; (M3) SAM mask with medial-axis skeletonisation; (M4) a hybrid keypoint-guided approach using a YOLO26-pose model predicting five anatomical landmarks (KP0--KP4) with piecewise 3D arc-length; and (M5) a novel medial arc spline method fitting a cubic spline through the 3D medial axis of the SAM mask and computing arc length by trapezoidal integration -- the first such application to elongated vegetable measurement. All methods share five-frame burst depth averaging, colour-stream intrinsic alignment, and adaptive method selection with cascading fallbacks ensuring 100% coverage. A benchmark of 48 captures across seven cucumbers in three size categories (small ~8 cm, medium ~13 cm, large ~25 cm) with thread-based ground truth establishes a significant accuracy hierarchy: M1 (MAPE 9.68%) > M2 (5.31%) > M4 (5.51%) > M3 (5.82%) > M5 (4.13%). M5 significantly outperforms all competitors at Bonferroni-corrected alpha=0.0125. A secondary contribution is identifying a 12--18% length underestimation caused by using depth-stream rather than colour-stream intrinsics after rs.align(rs.stream.color) -- an under-reported error source. The complete system is released open source and runs in real time on a single consumer-grade GPU.

Why it matches plant phenotyping methodsRGB-D画像からキュウリ果実長を推定する手法を開発し、複数手法との比較検証、実測値によるベンチマーク、誤差要因分析まで行っており、植物形質取得が研究の中心です。

abstractThis paper presents CucumberVision, a non-contact length estimation framework using an Intel RealSense D435 RGB-D camera.

A Stage-Aware Cascaded Detection-Segmentation Framework for Leaf Phenotyping and Leaf Dry Biomass Estimation of Pepper Seedlings. →

Quantitative phenotyping of pepper seedlings is important for greenhouse plug tray seedling cultivation, but it remains constrained by inefficient manual monitoring, complex greenhouse backgrounds, and growth-stage-dependent discrepancies between two-dimensional image traits and actual leaf biomass. In this study, a cascaded vision framework with stage-specific morphological correction was developed for nondestructive seedling phenotyping. The framework integrated Visual Dynamic Momentum YOLO (VDM-YOLO) for individual seedling localization and growth-stage recognition, Variance Guided Strip Ghost Gated UNet (VSG-UNet) for lightweight, high-resolution leaf segmentation, and a stage-aware correction model for leaf dry biomass estimation. In performance evaluation, VDM-YOLO achieved a mean average precision at an intersection over union threshold of 0.5 (mAP0.5) of 89.27%, improving mAP0.5 by 1.82 percentage points over YOLOv12. VSG-UNet achieved a mean intersection over union (mIoU) of 83.9% and a Dice coefficient of 81.8%, while reducing floating point operations (FLOPs) and parameters by 44.2% and 61.2%, respectively, compared with U-Net. After stage-aware calibration, the coefficient of determination (R2) between segmented area and leaf dry weight increased from 0.764 to 0.813, and the root mean square error (RMSE) decreased from 0.0210 g to 0.0190 g. These results demonstrated that the proposed framework provided a proof of concept approach based on RGB images for the nondestructive assessment of leaf area and leaf dry biomass in pepper seedlings under restricted experimental conditions.

Why it matches plant phenotyping methodsRGB画像による葉の検出・セグメンテーションと、葉面積から葉乾燥バイオマスを推定する手法を開発・評価しており、植物表現型取得が研究の中心である。

abstracta cascaded vision framework with stage-specific morphological correction was developed for nondestructive seedling phenotyping.

Canopy Structure and Water Use Efficiency Variations Between Short- and Long-Day Strawberry Cultivars Revealed by Non-Destructive 3D Phenotyping →

Cultivars of strawberry (Fragaria × ananassa) differ in photoperiodic responses, which influence the balance between vegetative and reproductive growth, shaping canopy development, biomass production, and water use efficiency (WUE). Using 3D point-cloud phenotyping, this study compared the canopy structure and WUE of the short-day cultivar ‘Sonata’ and long-day cultivar ‘Favori’ grown under identical greenhouse conditions. Cultivar-specific growth and water use traits were quantified using daily non-destructive 3D point cloud phenotyping combined with continuous whole-plant gravimetry, supported by manual and destructive measurements. Non-destructive estimates of plant height and digital biomass corresponded moderately to measurements (height: R2 = 0.628; biomass: R2 = 0.579; mean absolute percentage error (MAPE) = 13.86%). Growth analysis indicated similar relative growth rates between the two cultivars, whereas the crop growth rate was higher in ‘Sonata’ than in ‘Favori’. Integration of growth estimates with gravimetric records revealed higher period average WUE in ‘Sonata’ (3.1 mg g−1) than in ‘Favori’ (2.5 mg g−1). These results highlight the distinctive growth strategies of a canopy-driven pattern in ‘Sonata’ and a reproduction-driven pattern in ‘Favori’. The combined 3D phenotyping–gravimetry framework provides a high-resolution, non-destructive approach to quantify cultivar-specific growth and water use traits.

Why it matches plant phenotyping methods3D点群による非破壊フェノタイピングと連続重量計測を組み合わせ、植物形態・バイオマス・水利用形質を定量化し、測定精度も検証しているため、手法が研究の中心である。

abstractUsing 3D point-cloud phenotyping, this study compared the canopy structure and WUE

Editorial: Plant phenotyping for agriculture →

Modern agriculture operates at an unprecedented crossroads, it must simultaneously accelerate crop yields to feed an expanding global population and adapt to the severe, fluctuating pressures of climate change, structural soil degradation, abiotic water deficits, and evolving biological threats. Historically, selecting resilient crop varieties and implementing field-scale management strategies relied extensively on destructive, labor-intensive, and fundamentally subjective visual metrics. This manual processing approach has long been recognized as the primary operational bottleneck in agricultural advancement.To bridge the gap between rapidly expanding genomic data and actual field performance, the systematic, non-destructive quantification of structural and functional plant traits, plant phenotyping, has emerged as a transformative frontier. By integrating high-throughput engineering, multi-scale remote sensing, deep learning, and advanced molecular biology, modern phenotyping transitions crop science away from qualitative estimation toward highly reproducible, multidimensional data frameworks. This Research Topic presents new advances in advanced 3D reconstruction and deep semantic segmentation at the seedling stage; amodal fruit segmentation, morphological extraction, and early water-stress diagnostics; high-throughput in-field seedling counting and dynamic density modeling; multimodal foundation models, network pruning, and intelligent phytoprotection; aerial and spaceborne remote sensing for canopy analysis and weed monitoring; plant physiology, functional spectroscopy, and functional genomics under abiotic stress; and automated diagnostics for real-time orchard scouting and vineyard management.Automating the characterization of complex spatial layouts under controlled or greenhouse environments is essential for early variety selection and early-stage structural evaluation. Several contributions within this volume provide key breakthroughs in navigating overlapping tissues, severe occlusions, and low-contrast edge regions. showcases how substituting standard convolutions with deformable convolutions enables deep neural networks to accurately isolate the main stem of mature, high-density crops like soybeans. This architecture overcomes the traditional challenges of color mimicry and severe occlusion by pods and leaves, achieving an outstanding mIoU of 90.58% and providing reliable indices for lodging resistance and structural yield modeling (R 2 = 0.9746).Accurately extracting fruit morphology under commercial greenhouse conditions remains heavily constrained by overlapping crop structures, foliage cover, and variable shadows. Simple semantic masks typically fail when a target fruit is partially blocked, leading to a loss of key volumetric data.To resolve the challenge of hidden boundaries, Li, Yin, et al. (2025) developed CGA-ASNet, a specialized RGB-D amodal segmentation network driven by a Contextual and Global Attention (CGA) module designed to restore occluded tomato regions. Trained on a high-fidelity synthetic greenhouse dataset (Tomato-sim) generated via NVIDIA Isaac Sim's Replicator Composer and optimized with a mean coordinate fusion algorithm for real-world validation, this architecture expands the network's receptive field to predict the complete, hidden circular forms of occluded tomatoes, achieving an F@0.75 score of 94.2 and an amodal mIoU of 82.4%. This proves that simulation-to-real (Sim2Real) domain pathways can successfully decode full physical volumes under dense commercial canopies.Complementing this structural restoration, Yang, Li, et al. (2025) designed an integrated diagnostic framework to identify early water stress dynamics in greenhouse tomatoes. Built upon an optimized YOLOv11n core, their system integrates adaptive kernel convolutions (AKConv) into the network backbone's C3k2 modules and implements a recalibration feature pyramid detection head based on the specialized P2 small-target layer. This combination achieved a 5.4% increase in mAP50-95 for identifying fine phenotypic parts. By applying automated geometric analysis to the extracted bounding boxes, the system extracts plant heights and petiole count with low relative errors, feeding these phenotypic parameters into a Random Forest classification routine that flags water-stressed plants with 98% accuracy to guide targeted, automated drip irrigation.Accurate plant stands during early vegetative stages represent the foundational metric required to establish true field emergence rates, validate seed vigor across diverse breeding blocks, and perform early yield predictions.To solve the challenges of small targets, extreme spatial density, and adjacent leaf overlap, Zang et al. (2025) designed DM_IOC_fpn, a wheat seedling counting framework that balances local and global contextual features. By structuring a point-annotated dataset and embedding a densityenhanced encoder module, their network balances micro-scale spatial limits with macro-scale canopy structures. Optimized through a combined loss function tracking counting, classification, and regression parameters, this architecture achieved low error scores (RMSE = 2.91; MAE = 2.23), outperforming standard object-detection benchmarks in complex field environments.At the same time, scaling up to real-time aerial monitoring required major reductions in model complexity to support resource-constrained edge computers on autonomous aerial platforms. Feng, Nie, and Li (2025) engineered an ultra-lightweight YOLOv8n variant tailored for real-time maize seedling counting from high-speed UAV RGB overflights. By reparametrizing RepConv with HGNetV2, they constructed a lean Rep_HGNetV2 backbone, integrated a Bidirectional Feature Pyramid Network (BiFPN) for multi-scale feature alignment, and implemented a Task Dynamically Aligned Detection Head (TDADH). This architecture compressed total model parameters by 47% and reduced weight sizes to 3.5 MB while maintaining a 96.5% detection accuracy and an ultra-fast processing speed of 146.3 FPS, paving the way for low-cost, real-time field scouting.Automated phytoprotection requires machine-vision architectures capable of generalizing across highly diverse species, complex field conditions, and varying computational boundaries. A significant subset of the published papers addresses these challenges through foundation model adaptation, multi-modal alignment, and efficient network compression.A major paradigm shift presented in this collection involves moving away from task-specific training and toward foundation model adaptation. Chen, Ruan, et al. (2026) introduce a novel architecture integrating the DinoV3 foundation model with a Unet framework to achieve robust leaf lesion segmentation across diverse species (such as coffee and black gram). By incorporating a Spatial Prior Module (SPM), their approach surpassed standard benchmark networks by over 10.5% in IoU while reducing inference times by approximately 93.6%, demonstrating that highparameter foundation models can be highly optimized for resource-constrained edge devices in real-time scouting.To solve the perennial problem of limited training data for rare or emerging crop diseases, Cooper et al. ( 2026) developed an ingenious synthetic data generation pipeline. Combining 3D procedural leaf modeling in Blender with diffusion-based disease synthesis (Stable Diffusion fine-tuned with LoRA and ControlNet), they synthesized highly accurate plant disease images with perfect groundtruth annotation masks. When deployed in low-resource data settings, combining these synthetic pipelines with restricted real-world datasets consistently drives significant improvements in downstream segmentation tasks. To tackle specific, complex pathologies, Xu, Chang, et al. (2025) developed the TSSC deep learning model, which embeds three-neighbor channel attention paired with a complementary squeeze-and-excitation mechanism. This specific architecture minimizes structural degradation risks while pushing classification accuracy to 99.61% for highly complex pea leaf pathologies. Similarly, Feng, Liu, et al. (2025) tackled overlapping leaf occlusions and small lesion footprints in citrus groves with YOLO-Citrus, an optimized framework integrating C3K2-STA, ADown modules, and a Wise-Inner-MPDIoU loss function to strike a balance between edge computational constraints and field deployment.UAVs and high-resolution satellite imagery have expanded the operational scale of phenotyping from individual pots to vast breeding blocks and commercial fields, allowing researchers to capture macro-dynamic parameters over time.In complex canopy systems that defy standard top-down aerial sensing, such as single-staked white Guinea yams, Iseki et al. (2026) demonstrated the distinct advantage of utilizing multi-angle (combined nadir and oblique) UAV imaging configurations. When coupled with support vector regression, this method captures complementary canopy-structure information to model shoot biomass trajectories (R 2 = 0.79) across multiple years and management zones. These nondestructive, time-series datasets enabled the fitting of genotype-specific Richard's growth curves using Bayesian inference, isolating valuable genetic variations in early growth allocation.To capture full-season vertical physiological changes over large scales, Li, Yue, and Luo (2025) developed a hybrid CNN-LSTM-Attention (CLA) model designed to estimate the full-period Leaf Area Index (LAI) in rice using multi-temporal UAV multispectral imagery. By using the CNN layer to extract instantaneous spatial features, the LSTM block to process seasonal time-series intervals, and a self-attention mechanism to weight critical growth transitions, their platform achieved a high coefficient of determination (R 2 = 0.92) and kept relative root mean square errors (RRMSE) below 9%. This network minimized soil background noise during early vegetative stages (LAI values 1-

Why it matches plant phenotyping methods植物フェノタイピングの技術動向を扱うEditorialであり、画像解析、UAVセンシング、深層学習、形質抽出などの方法が中心的に整理されている。

titleEditorial: Plant phenotyping for agriculture

Continuous monitoring of plant transpiration dynamics with a leaf-mounted sensor across environmental conditions →

O_LITranspiration plays a central role in plant water relations and strongly influences plant growth. Continuous monitoring is essential for understanding responses to environmental conditions and improving water management in both natural and agricultural systems. Gas-exchange techniques such as infrared gas analysers (IRGAs) and porometers are widely used but are challenging for long-term or large-scale monitoring. On the other hand, the FylloClip is a low-cost, leaf-mounted capacitance sensor developed previously to monitor transpiration by detecting condensation of water vapour near the leaf surface. Here, we evaluated the potential of the FylloClip for monitoring transpiration dynamics and assessed environmental conditions that may affect its performance. C_LIO_LIThe FylloClip was tested under growth chamber, greenhouse, and tropical field conditions. We evaluated how its capacitance measurements respond to rainfall, temperature and humidity, and compared FylloClip measurements with transpiration measured with an IRGA. C_LIO_LIThere was a strong correlation (r = 0.85) between FylloClip and IRGA data. Both systems captured similar diurnal transpiration patterns, with transpiration declining simultaneously under water deficit. Rainfall and very high relative humidity produced FylloClip signals that could be misinterpreted as high transpiration, although transpiration is negligible under these conditions. C_LIO_LIOur results revealed that FylloClips capture temporal patterns of transpiration with high accuracy and resolution, providing a reliable tool for long-term, large-scale monitoring of transpiration dynamics in ecophysiological studies and precision agriculture. C_LI

Why it matches plant phenotyping methods葉面センサーによる蒸散動態測定法を開発・評価し、IRGAとの比較検証および環境条件による性能評価を行っており、植物生理形質の取得が中心である。

abstractHere, we evaluated the potential of the FylloClip for monitoring transpiration dynamics and assessed environmental conditions that may affect its performance.

Image-based Phenotyping and Machine Learning Prediction of Rice Genotypes to Combined Drought-Salinity Stresses →

Abstract Simultaneous stresses of salinity and drought often coincide during rice-growing seasons in coastal areas due to insufficient water resources and inadequate irrigation infrastructure. Consequently, combined salinity-drought stress poses a major threat to rice production. To investigate the effects of combined salinity-drought stress, a two-season study was conducted utilizing soil media. The first season involved screening 58 rice genotypes, while the second season focused on validating the consistency of response in 20 selected tolerant and susceptible genotypes. These included established tolerant checks (Pokkali and Salumpikit) and susceptible checks (IR 29 and IR 20). Both drought and salinity treatments were given at an electrical conductivity (EC) of 10 dSm⁻¹ and 75% field capacity at the seedling stage. The experimental design was arranged in a modified lattice design in each season, with six blocks and three replications in the first season and two blocks and five replications in the second season. The data collected are leaf symptoms, biomass weight, and shoot length. A number of 330 images captured by a smartphone camera. Machine learning models were employed to predict drought-salinity tolerance criteria. The study revealed that XGBoost model achieved an accuracy of 90.62%. The study identified two genotypes, IR18A1925-SKI-0 and Inpari 30, that exhibited insignificance to Pokkali, based on assessment of shoot length, biomass, and leaf symptoms. These two genotypes were also consistently clustered with Salumpikit. These findings highlight potential of machine learning techniques in predicting rice tolerance to combined salinity-drought stress, with the XGBoost model demonstrating superior predictive capability in this study.

Why it matches plant phenotyping methodsスマートフォン画像から葉症状・バイオマス・草丈などの表現型を取得し、機械学習で複合ストレス耐性を予測する手法の適用が研究の中心である。

titleImage-based Phenotyping and Machine Learning Prediction of Rice Genotypes to Combined Drought-Salinity Stresses

Integrating hyperspectral reflectance and machine learning for rapid diagnosis of nutrient deficiencies in greenhouse chrysanthemum leaves. →

Under greenhouse production conditions, variability in fertilization management, substrate properties, and microenvironmental factors can disrupt balanced nutrient uptake, often resulting in localized or transient multi-element nutrient imbalances. Hyperspectral sensing provides continuous and high-resolution spectral information for plant nutrient assessment. However, most existing studies focus on single-element deficiencies or simplified scenarios, which limits their applicability to complex nutritional environments encountered in practice. To address this limitation, we designed a series of single- and dual-element deficiency treatments in four cultivars of chrysanthemum (Chrysanthemum morifolium Ramat.), an important cut-flower crop whose ornamental quality is highly influenced by nutrient supply. Sampling was conducted at five key growth stages across three independent experiments, yielding a total of 615 data points. Each treatment included replicates and was confirmed based on characteristic deficiency symptoms. A hyperspectral-based qualitative classification framework was developed to assess nutrient imbalances under controlled greenhouse conditions. Results indicate that although some nutrient deficiencies exhibit similar visual or phenotypic symptoms, their hyperspectral responses are distinguishable, suggesting that hyperspectral data can capture subtle differences associated with distinct nutrient imbalance conditions. To mitigate class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) was applied, and multiple classification models were evaluated using cross-validation. The Gradient Boosting Decision Tree (GBDT) classifier combined with SMOTE showed the most consistent performance across nutrient-recognition tasks, achieving cross-validation accuracies from 0.9191 ± 0.0401 to 0.8556 ± 0.0516, balanced accuracies from 0.9595 to 0.8447, F1 from 0.9591 to 0.8496 and testing accuracies from 0.9200 to 0.8269, balanced accuracies from 0.9167 to 0.8269, F1 from 0.9140 to 0.8244. Overall, this study presents a non-destructive hyperspectral framework for classifying multi-element nutrient imbalances and demonstrates its effectiveness under greenhouse conditions, supporting hyperspectral-based nutritional assessment in ornamental crops. Further validation across diverse genotypes, seasons, and environmental conditions is needed to confirm broader applicability and model generalizability.

Why it matches plant phenotyping methodsキク葉の栄養状態という植物状態を、ハイパースペクトル計測と機械学習で非破壊的に分類する枠組みを開発・検証しており、表現型取得・抽出法が研究の中心である。

abstractA hyperspectral-based qualitative classification framework was developed to assess nutrient imbalances under controlled greenhouse conditions.

Rapid preliminary screening of Tomato brown rugose fruit virus based on surface-enhanced Raman spectroscopy and machine learning. →

Introduction Tomato brown rugose fruit virus (ToBRFV) represents a growing threat to global tomato production, causing severe losses in crop yield and fruit quality. Although the standard RT-qPCR assay is highly accurate, its reliance on laboratory processing, specialized equipment, and trained personnel limits its applicability for rapid on-site diagnostics. To address this limitation, this study evaluated a biosensing method that does not require labels and combines surface-enhanced Raman scattering (SERS) with machine learning to distinguish tomato leaves infected with ToBRFV from healthy leaves. Methods Following health status confirmation via RT-qPCR, leaf extracts were directly deposited onto silver nanorod arrays for SERS spectral acquisition. Three classification models were evaluated: PCA-LDA, PLS-DA, and SVM. Results The results showed that all models were able to discriminate infected samples from healthy samples in the present dataset. Notably, the SVM model exhibited the best performance, achieving an accuracy of 91.67%, a sensitivity of 100.00%, a specificity of 81.48%, and an area under the ROC curve (AUC) of 0.993. Discussion This result suggests that SERS spectra may contain biochemical information associated with ToBRFV infection and that such information can be used for sample classification using machine learning models. In its present form, this approach is intended as a rapid, low-cost, field-deployable preliminary screening tool - not a replacement for RT-qPCR or other confirmatory molecular assays. The reported accuracy was obtained on mechanically inoculated plants of a single cultivar under controlled greenhouse conditions and should therefore be interpreted as a proof-of-concept upper bound; field-scale validation is the focus of ongoing work.

Why it matches plant phenotyping methodsSERSと機械学習を用いて感染トマト葉と健全葉を識別する植物病害状態の取得・分類法が研究の中心であり、複数モデルの性能評価も行っている。

abstractthis study evaluated a biosensing method that does not require labels and combines surface-enhanced Raman scattering (SERS) with machine learning to distinguish tomato leaves infected with ToBRFV from healthy leaves.

Uncertainty-Aware 3D Plant Reconstruction from Sparse Video Frames Using Neural Radiance Fields →

Abstract Automated three-dimensional reconstruction of plant architecture under- pins high-throughput crop phenotyping, yet its deployment in practical field settings is constrained by two fundamental limitations of Neural Radiance Fields (NeRF): degraded geometry under sparse, unstructured image capture, and a complete absence of calibrated uncertainty estimates that would allow practitioners to distinguish reliable geometry from reconstruction artefacts. We present UA-PlantNeRF, a unified framework that resolves both limita- tions through three tightly coupled contributions. First, building on VISAR, our prior intelligent video frame-selection strategy (weights α1 = 0.4, α2 = 0.3, α3 = 0.3), the pipeline identifies maximally informative, non-redundant view- points from raw footage with as few as 15 frames. Second, a dual-head NeRF architecture augmented with Monte Carlo Dropout produces jointly decom- posed aleatoric and epistemic uncertainty alongside each reconstructed voxel, trained under a heteroscedastic negative log-likelihood objective. Third, split conformal prediction—with calibration performed on held-out plants to preserve exchangeability— yields provable, distribution-free per-ray cov- erage guarantees at any user-specified confidence level. Evaluated across three benchmarks (Pheno4D, ROSE-X, and our novel UA-Field greenhouse dataset) at sparsity levels N ∈ {15, 30, 50}, UA-PlantNeRF achieves PSNR 28.7±0.6 dB and SSIM 0.89±0.01 at N = 30, outperforming all sparse-view baselines (p

Why it matches plant phenotyping methods植物の3D構造・アーキテクチャを推定する画像ベースのNeRF手法を開発し、複数ベンチマークで評価しているため、植物表現型計測法が中心です。

abstractEvaluated across three benchmarks (Pheno4D, ROSE-X, and our novel UA-Field greenhouse dataset)

Diagnostic system for tebuthiuron soil ecotoxicity using morphophysiological indicators of Mucuna pruriens validated by Lactuca sativa. →

This study developed an integrated diagnostic system for tebuthiuron-induced soil ecotoxicity based on morphophysiological indicators of Mucuna pruriens, using the germination index (GI) of Lactuca sativa as a sensitive ecotoxicological validation endpoint. The experiment was conducted under greenhouse conditions using a completely randomized design with 12 treatments and 360 individual pots (independent samples evaluated via destructive sampling), which were distributed across five evaluation periods at 14, 28, 42, 56, and 70 days after sowing. Morphophysiological variables, including plant height, root length, shoot and root dry mass, chlorophyll content, nodule number, and visual phytotoxicity, were quantified and integrated with multivariate and probabilistic modeling approaches. Given the multifactorial nature of the germination index, Principal Component Analysis (PCA) was applied to identify ecological and physiological gradients associated with plant vigor, stress, and symbiotic functioning. The PCA outputs were subsequently used as inputs for Probabilistic Neural Networks (PNNs), enabling the classification and prediction of bioindicator-based ecotoxicological levels using mathematically defined low, medium, and high GI classes. Model performance was internally assessed using training and validation datasets, confusion matrices, overall accuracy, sensitivity, specificity, and ROC curves. Because no independent external dataset was available, the predictive performance should be interpreted as evidence of internal consistency rather than definitive generalizability across different soils, climates, herbicide doses, or field conditions. Multivariate analyses revealed that ecotoxicological attenuation trajectories in tebuthiuron-contaminated soils are inherently nonlinear, being structured by coordinated shifts in morphophysiological traits rather than isolated responses of individual variables. The integrated PCA-PNN framework demonstrated that aboveground traits. Particularly plant height, chlorophyll content, and shoot dry mass, were more sensitive indicators of tebuthiuron-induced stress than root traits alone. Higher GI values were associated with PCA regions characterized by increased shoot biomass, greater plant height, reduced phytotoxicity, and improved physiological performance, whereas lower GI classes corresponded to suppressed growth and multidimensional stress signatures. The progressive convergence between plant vigor and GI across evaluation periods suggests a gradual mitigation of ecotoxicological stress signals on the indicator plants, indicating transitions from acute injury to physiological adaptation states. These findings confirm that M. pruriens functions as an effective bioindicator for diagnosing soil ecotoxicological status and monitoring tebuthiuron-induced impacts. However, as tebuthiuron residues were not chemically quantified, these responses should not be interpreted as direct evidence of herbicide degradation, dissipation, or removal. These findings confirm that M. pruriens functions as an effective bioindicator for diagnosing soil ecotoxicological status and monitoring tebuthiuron-induced impacts. However, as tebuthiuron residues were not chemically quantified, the observed improvements should be interpreted as evidence of physiological adaptation and/or ecological attenuation rather than definitive proof of herbicide degradation or removal. Overall, this approach provides a robust framework for early detection of soil contamination and supports its application in monitoring and guiding soil rehabilitation processes, with potential for future validation under field conditions.

Why it matches plant phenotyping methods植物の形態・生理形質を統合し、PCA-PNNで植物ストレスおよび土壌生態毒性レベルを診断する手法の開発・内部検証が中心であり、単なる生物学的測定ではない。

abstractThis study developed an integrated diagnostic system for tebuthiuron-induced soil ecotoxicity based on morphophysiological indicators of Mucuna pruriens

Large language model assisted decision support framework for uncertainty aware detection and management of tomato lateral shoots. →

Accurate identification of tomato lateral shoots is essential for automated pruning and plant monitoring in greenhouse production. However, complex illumination, leaf occlusion, and morphological variability often reduce detection reliability in optical vision systems. This study proposes an optical vision-based framework that integrates deep learning perception with large language model assisted pruning decision support. A tomato lateral Shoot image dataset was constructed using RGB imaging in greenhouse environments. A lightweight YOLOv8n instance segmentation model with the Convolutional Block Attention Module (CBAM) was developed to enhance feature representation. Data augmentation strategies were applied to simulate illumination variations and improve model robustness. Model interpretability was analyzed using Principal Component Analysis (PCA) and Gradient weighted Class Activation Mapping (Grad CAM). Experimental results show that the proposed YOLOv8n-seg+CBAM model achieves a mAP 0.5 of 98.1% with only 3.28M parameters and an average inference time of 8.0 ms per image. Monte Carlo Dropout was further introduced to estimate the spatial uncertainty of cutting points. These structured perception features were provided to a large language model (LLM), enabling context aware pruning decision assistance. The proposed framework integrates vision-based shoot detection, uncertainty estimation, and LLM-assisted reasoning into a unified pipeline, enabling more reliable pruning decisions and improving safety and robustness compared with vision-only approaches in greenhouse environments.

Why it matches plant phenotyping methodsトマト側枝をRGB画像から検出・セグメンテーションし、不確実性推定まで行う画像ベースの植物形態計測手法を開発しており、方法論が中心である。

abstractThis study proposes an optical vision-based framework that integrates deep learning perception with large language model assisted pruning decision support.

A Measurement-Driven Digital Twin Architecture for Plant-Level Biomass Estimation and Growth Forecasting in Hydroponic Systems →

Alternatives to soil-based horticulture, such as hydroponics, have been developed to respond to food distribution concerns for dense urban centers. A new system was developed to track an individual lettuce plant's growth in a hydroponic environment, utilizing streams of measured information and available models to continuously update the growth trajectory estimates for a plant. These "digital twin" models were integrated into an operating hydroponic greenhouse, with custom horticultural and sensor hardware to grow and measure relevant information. To aid in updating model parameters, plant yield was continuously measured with a custom neural network, using RGB-D images of the plants as an input. The network, trained on a collected dataset of 1300 images, was able to estimate mass within 1.5 g of the ground-truth value. After integration into the custom system, digital twin growth projections could approximate future yield between one and four days in the future, maintaining around a 2 g forecasting error.

Why it matches plant phenotyping methodsRGB-D画像から個体レタスの収量・質量を推定するニューラルネットワークと、センサー統合型の成長追跡基盤が研究の中心であり、植物形質の取得・予測手法を実質的に開発・検証している。

abstractA new system was developed to track an individual lettuce plant's growth in a hydroponic environment, utilizing streams of measured information and available models to continuously update the growth trajectory estimates for a plant.

A Lightweight Real-Time Tomato Leaf Disease Detection System for Edge-Based Smart Agriculture. →

Tomato leaf diseases substantially reduce tomato yields and quality and remain a persistent challenge for efficient crop management. Although deep learning-based detectors have achieved strong accuracy in controlled benchmarks, many existing solutions are still difficult to transfer to resource-constrained agricultural systems because they rely on high-end GPUs, consume considerable power, and often lose performance after deployment on embedded devices. To address this practical gap, this study proposes HGS-YOLO, a system-oriented deployable lightweight adaptation of YOLOv11 for leaf-level tomato disease detection, together with an end-to-end edge sensing pipeline for low-power agricultural deployment. The main contribution lies in the coordinated system-level co-design of model structure, optimization, and deployment rather than in a novel detector architecture. Specifically, YOLOv11 is adapted through three coordinated modifications: an HGNetV2 backbone for efficient feature extraction, an HS-FPN neck with channel attention for lightweight multi-scale fusion, and an MPDIoU loss function for more stable localization optimization. Beyond the model architecture, the study establishes a complete engineering pipeline that includes training, optimization, post-training quantization, and hardware deployment with BPU acceleration on a D-Robotics RDK X5 handheld platform. Comprehensive benchmark experiments indicate that HGS-YOLO achieves 93.6% mAP50 and 72.1% mAP@[0.5:0.95] with 86.5% recall, only 1.3 M parameters, and a 3.1 MB model size, substantially reducing the model complexity and storage cost relative to the YOLOv11 baseline. A three-seed retraining comparison shows that HGS-YOLO trades roughly 0.5 mAP50 points for this compactness (a statistically significant but small concession) and recovers the cost on the deployment side: on the RDK X5 chip, HGS-YOLO is the fastest, most memory-efficient, and lowest-power model among all compared detectors. Indoor deployment tests using separately collected tomato leaf samples further achieve 90.3% mAP50, 82.3% recall, 89.0% precision, 25.0 ± 0.4 ms end-to-end latency, 40.0 ± 0.6 FPS, and 9.8 ± 0.4 W average system power. After PTQ, the mAP50 drops from 93.6% to 93.0% on the same benchmark; because this figure was measured under controlled imaging conditions, it is presented as an in-distribution reference point rather than as evidence of robustness in the open field. We also took the handheld system into a working tomato greenhouse for a small outdoor field round, where it ran end-to-end and produced on-device disease detections under natural sunlight, specular highlights, partial occlusion, background clutter, and handheld motion blur. These results show that HGS-YOLO reaches a good balance of accuracy, efficiency, and deployability and that it works in the field on an independent small-scale test; validating it more widely across sites, seasons, and weather is left to future work.

Why it matches plant phenotyping methodsトマト葉の病害状態を画像から推定する軽量検出モデルとエッジセンシング・展開パイプラインを開発し、ベンチマーク、量子化、ハードウェア性能、屋内外試験で検証しており、植物表現型取得が中心である。

abstractthis study proposes HGS-YOLO, a system-oriented deployable lightweight adaptation of YOLOv11 for leaf-level tomato disease detection, together with an end-to-end edge sensing pipeline for low-power agricultural deployment.

A real-time ripeness detection model for tomatoes in complex greenhouse environments. →

Timely harvesting of fresh tomatoes is urgently needed. To address this issue, this study proposes DDC-YOLOv11n, a model suitable for real-time detection of tomato ripeness in complex greenhouse environments. A Zero-DCE adaptive enhancement module is first deployed at the input stage to restore and enhance the true color and texture details of the images. An improved Deep Residual Shrinkage Network (DRSN) is then added to YOLOv11n to perform adaptive soft-threshold filtering on feature maps, reducing the interference of image noise on the detection targets. Finally, the CBAM spatial attention is enhanced through dilated convolution and channel grouping to form the LKCBAM module, which expands the equivalent receptive field while controlling the increase in parameters, thereby improving tomato detection accuracy in occluded and dense scenes. Experimental results show that the DDC-YOLOv11n model achieves the best recognition performance: compared with the original YOLOv11n, its mAP@0.5, precision, recall, and F1 score are increased by 16.8%, 24.6%, 8.3%, and 18.1%, respectively. These findings facilitate real-time tomato ripeness detection in complex greenhouse environments and provide perceptual information for subsequent management tasks such as harvesting.

Why it matches plant phenotyping methodsトマト果実の成熟度という植物器官の状態を画像から推定するモデルを開発・評価しており、フェノタイピング手法が研究の中心である。

titleA real-time ripeness detection model for tomatoes in complex greenhouse environments.

Explainable Deep Learning for Greenhouse Horticulture: Feature and Temporal Interpretability in Crop Yield and Energy Optimization →

Optimizing crop yield while minimizing energy consumption remains a central challenge in greenhouse horticulture. This study introduces an integrated deep learning framework that couples multi-horizon time-series forecasting with dual-layered explainability to address the critical need for spatiotemporal transparency in optimizing greenhouse crop yield and energy efficiency. Four deep learning architectures, including the One-Dimensional Convolutional Neural Network (1D-CNN), Long Short-Term Memory Network (LSTM), Bidirectional Long Short-Term Memory Network (BiLSTM), and TinyTimeMixer (TTM), were evaluated across two varieties of capsicum. LSTM and BiLSTM achieved the highest accuracy for incremental yield prediction, whereas TTM outperformed other models in forecasting daily energy usage, reflecting the distinct temporal characteristics of biological growth and environment-driven energy demand. To uncover the factors driving these predictions, two complementary explainability methods were applied: Gradient SHapley Additive exPlanations (SHAP) for feature-level attribution and a Temporal Convolutional Network with Convolutional Block Attention Module (TCN–CBAM) attention mechanism for joint temporal-feature interpretation. Radiation and drainage-related variables consistently emerged as the dominant contributors to yield, whereas external temperature, and humidity were the primary determinants of energy usage. Temporal attention further showed that yield is influenced by both recent irrigation responses and longer-term developmental dynamics, while energy consumption is driven mainly by short-term climatic fluctuations. These findings provide actionable insights for irrigation scheduling, climate-control strategies, and energy optimization, supporting more transparent and sustainable greenhouse management.

Why it matches plant phenotyping methods温室作物の収量という植物形質を深層学習で予測し、複数モデル比較と説明可能性解析を行う計算的形質推定手法が研究の中心である。

abstractThis study introduces an integrated deep learning framework that couples multi-horizon time-series forecasting with dual-layered explainability

Near-Infrared Interaction Spectroscopy Under Daylight Conditions to Assess Total Soluble Solids in On-the-Plant Strawberries →

Robust in-field sensing technologies are essential for advancing precision agriculture and autonomous field robotics toward analysing internal quality attributes of fruits and vegetables. This study demonstrated in-the-field, non-contact near-infrared (NIR) spectroscopy for determining total soluble solids (TSS), a measure of sugar content, in on-the-plant strawberries under daytime conditions. A compact NIR interaction instrument (750–1020 nm), designed for robotic operation, was built and tested in a polytunnel environment under varying day- and night-time conditions. The instrument was calibrated using a partial least squares regression (PLSR) model built on laboratory data collected in 2025 from 200 strawberries of a single variety. It was tested on 100 strawberries of two varieties that were measured in 2024, while still attached to the plant. During night-time operation, TSS was predicted with a standard error of prediction ( SEP ) of 0.73 % TSS and a bias of 0.65 % TSS. Under challenging daytime conditions with strong and fluctuating ambient light, measurements were more affected by additional shot noise from the ambient light, resulting in SEP s up to 1.35 % TSS and biases up to 1.45 % TSS, both of which are acceptable for most applications. The measurement time was 12 s. Robust performance was achieved by implementing rapid and continuous ambient light sampling and correction, combined with outlier rejection of spectra of insufficient quality. These findings confirm the feasibility of in-field, on-the-plant NIR spectroscopy for assessing internal fruit quality and provide practical design guidelines to support further in-field implementations of NIR spectroscopy.

Why it matches plant phenotyping methodsイチゴ果実の糖度という植物器官形質を、ロボット搭載可能なNIRセンサーで非接触測定する手法を開発・検証しており、環境光補正や性能評価も中心的に扱っている。

abstractThis study demonstrated in-the-field, non-contact near-infrared (NIR) spectroscopy for determining total soluble solids (TSS), a measure of sugar content, in on-the-plant strawberries under daytime conditions.

Plant and substrate-based indices for salinity monitoring in Cestrum nocturnum →

This study proposes salinity indices based on plant and substrate measurements to define reference thresholds for salinity management in potted crops, using Cestrum nocturnum as a model species. A greenhouse experiment was conducted with plants grown in containers and irrigated with nutrient solutions at three electrical conductivity (EC) levels (2.0, 4.5, and 7.0 dS m - ¹). Plant responses were assessed through vegetative growth, visual quality, flowering intensity, continuous stem diameter variation (maximum daily stem shrinkage, MDS), cumulative evapotranspiration (ETa), and substrate bulk EC monitored with sensors. Increasing salinity reduced vegetative growth, particularly shoot biomass, while enhancing flowering intensity at 4.5 dS m - ¹, indicating a shift from vegetative to reproductive development. The moving average of MDS (avgMDS) responded to salinity, showing both increases and decreases depending on stress intensity, and, when expressed as signal intensity (SI: control/salinity), discriminated between stress levels, establishing alert (1.10) and critical (1.38) thresholds. Salinity decreased ETa by 35% and 65% at 4.5 and 7.0 dS m - ¹, respectively, and ETa-based SI defined alert (1.20) and critical (1.55) thresholds. The hourly moving average of bulk EC (avgECb) enabled continuous assessment of salinity dynamics, minimizing the influence of substrate moisture variability. The use of avgMDS, ETa, and avgECb enables the detection and interpretation of salinity stress by integrating plant physiological responses with substrate conditions, while the combined use of two or more indices improves the robustness of the assessment, providing a quantitative framework for salinity management in potted crops.

Why it matches plant phenotyping methods植物の生理応答とセンサー計測から塩ストレスを定量検出する指標を開発し、警戒・臨界閾値を設定して技術的に評価しているため、単なる生育測定ではない。

abstractThis study proposes salinity indices based on plant and substrate measurements to define reference thresholds for salinity management in potted crops

A Public-Data-Based Multimodal Framework for Plant Growth State Analysis Toward Future Filter-Free Aquaponic Validation →

This study proposes the Hydroponic Plant Growth Analysis System (HPGAS), a public-data-based preliminary framework for multimodal plant growth state analysis toward future filter-free aquaponic validation. The HPGAS integrates plant images, water quality signals, and environmental signals to estimate an image-centered growth index, growth stage, and proxy abnormal state probability. Because no public dataset jointly provides plant images, direct growth labels, fish metabolic variables, suspended solids, and nitrification-related measurements from a real filter-free aquaponic system, this study is not a direct operational validation. A two-stage evaluation was conducted using the Autonomous Greenhouse Challenge (AGC), HydroGrowNet, and two aquaponic Internet of Things (IoT) water quality datasets. Stage 1 implemented dataset loaders, image–sensor alignment, proxy label generation, and unimodal and fusion baselines. Stage 2 expanded handcrafted image and sensor-context features and adopted month-wise hold-out evaluation. The image-only model achieved the best growth index regression performance, with a root mean square error (RMSE) of 0.0492 ± 0.0187, whereas the fusion model showed a RMSE of 0.0837 ± 0.0196. Conversely, the fusion model achieved the best proxy abnormal state classification performance, with a F1 score of 0.9695 ± 0.0057 under the clean condition, decreasing to 0.9232 ± 0.0263 under sensor dropout and 0.9132 ± 0.0169 under image noise. Under sensor dropout, the fusion model was more stable than the sensor-only model, whereas under image noise it degraded more than the image-only model. These results indicate that multimodal fusion is most useful for proxy abnormal state classification and robust state interpretation, rather than universally superior scalar growth regression. The HPGAS provides a reproducible baseline for future real filter-free aquaponic experiments, while its operational validity remains to be tested using real filter-free aquaponic data.

Why it matches plant phenotyping methods植物画像とセンサーデータを統合し、成長指数・成長段階・異常状態確率を推定する再現可能な解析フレームワークを開発・評価しており、植物表現型の取得・推定手法が中心である。

abstractThis study proposes the Hydroponic Plant Growth Analysis System (HPGAS), a public-data-based preliminary framework for multimodal plant growth state analysis

Macronutrient deficiency reduces growth and influences vegetation indices of greenhouse grown ornamental and vegetable plants as measured by the TraitFinder digital phenotyping system. →

Introduction: Recent technological advances in high resolution image capture and analysis have led to increased adoption of high-throughput digital phenotyping in plant science research. High-throughput digital phenotyping provides a nondestructive method to quantify changes in plant growth and health in response to environmental factors or developmental cues. Moreover, it allows researchers to conduct large experiments in a time- and cost-efficient manner. The TraitFinder is a digital phenotyping system developed by Phenospex (Heerlen, Netherlands) that measures plant morphological (e.g., digital biomass) and spectral (leaf light reflectance) information. Leaf reflectance is presented as five vegetation indices (e.g., normalized difference vegetation index). Methods: This project evaluated nitrogen (N), phosphorus (P), and potassium (K) deficiency in greenhouse grown ornamental and vegetable plants using the TraitFinder. Plant species included celosia, coleus, marigold, petunia, and tomato. Plants were fertilized with a complete Hoagland's solution (control), and three modified solutions: Hoagland's solution without nitrogen (-N), phosphorus (-P), or potassium (-K). Each plant species was evaluated separately with eight replicate plants per treatment, organized as a randomized complete block design. Results: Treatment with -N, -P, and -K solutions resulted in reduced vegetative growth and decreased concentration of the corresponding macronutrient in leaf tissue for all species evaluated. We observed that the presence of flowers would negatively affect calculations of the vegetation indices due to their distinct spectral properties; therefore, flowers must be excluded to accurately quantify plant health parameters. In general, we observed a common trend where GLI (green leaf index) and NDVI (normalized difference vegetation index) decreased, and NPCI (normalized pigment chlorophyll index) and PSRI (plant senescence reflectance index) increased in response to macronutrient deficiency. The measure of GLI, NDVI, NPCI, and PSRI were different from the control plants, but these observations were dependent on the nutrient deficiency and species tested. Discussion: Our results underscore the importance of accounting for species-specific spectral signatures when assessing plant responses to nutrient deficiencies. This project also provides reference values for interpreting vegetation indices, offering valuable guidance for scientists implementing digital phenotyping in their experimental protocols. Digital phenotyping can significantly improve experimental throughput and provide quantitative insights into plant health.

Why it matches plant phenotyping methodsTraitFinderによる形態・スペクトル形質の取得と、花の除外や種特異的スペクトルへの対応を含むデジタルフェノタイピングの実質的な適用・評価が中心である。

abstractThe TraitFinder is a digital phenotyping system developed by Phenospex (Heerlen, Netherlands) that measures plant morphological (e.g., digital biomass) and spectral (leaf light reflectance) information.

Proactive Irrigation Timing Decision-Making for Greenhouse Tomatoes via STL-LSTM Deep Learning and Plant–Soil Dual-Threshold Sensing →

Traditional irrigation management for tomatoes in solar greenhouses relies heavily on empirical manual experience and single soil moisture indicators, often leading to irrigation scheduling that lacks crop-specific physiological evidence and results in suboptimal water-use efficiency. To address these challenges, this study developed an intelligent, plant-centric irrigation decision-making framework for greenhouse tomatoes in the arid region of Xinjiang. Central to this framework is the precise identification of irrigation timing—the most critical first step and a fundamental prerequisite for achieving true on-demand irrigation. By monitoring the high-frequency dynamics of stem diameter (SD) and integrating soil moisture data, the physiological responsiveness of tomatoes to water stress was systematically analyzed. A hybrid predictive model, STL-LSTM, was constructed by coupling Seasonal-Trend decomposition using Loess (STL) with Long Short-Term Memory (LSTM) networks to forecast 24-h SD trends. Furthermore, an innovative dual-threshold irrigation mechanism was established, utilizing a physiological trigger (Maximum Daily Shrinkage, MDS > 70 μm) and a soil moisture constraint (Volumetric Water Content, VWC ≤ 17%). Results demonstrated that tomato SD exhibited distinct diurnal rhythms, with MDS and Daily Increment (DI) identified as highly sensitive indicators of plant water status. The proposed STL-LSTM model achieved superior predictive performance during the peak fruiting stage, with a coefficient of determination (R2) of 0.9184, representing an improvement of 14.8% and 27.56% over standalone LSTM and ARIMA models, respectively. The validation of the dual-threshold mechanism confirms its ability to balance real-time crop water demand with conservation requirements, effectively mitigating the risks of premature or delayed irrigation inherent in traditional methods. This research provides scientific rationale and technical support for the transition of greenhouse agriculture in arid regions towards precision irrigation and optimised water resource management.

Why it matches plant phenotyping methodsトマト茎径を植物の水分状態指標として高頻度センシングし、STL-LSTMによる予測と二重閾値の検証を行うことが中心であり、単なる灌漑実験ではない。

abstractCentral to this framework is the precise identification of irrigation timing—the most critical first step and a fundamental prerequisite for achieving true on-demand irrigation.

CF-DETR: a robust transformer-based framework for small-scale chili flower detection in industrial chili production systems. →

Chili pepper (Capsicum spp.) is a high-value industrial horticultural crop widely utilized in food processing, pharmaceuticals, and natural pigment production. Accurate monitoring of flowering is critical for yield formation, pollination management, and early-stage production forecasting in industrial chili production systems. However, in greenhouse environments, chili flowers typically exhibit small object scale and are affected by issues such as lighting variations and occlusion, which pose significant challenges for reliable visual detection. These factors often result in missed detections and unstable performance in practical phenological monitoring tasks. To address these challenges, this study proposes CF-DETR, a robust transformer-based framework for small-scale chili flower detection. Built upon the RT-DETR architecture, the proposed method introduces an efficiency-optimized FasterNet backbone to enhance fine-grained feature extraction for small targets while maintaining computational efficiency. In addition, a dynamic upsampling mechanism is incorporated to preserve structural details during feature reconstruction, and a Bidirectional Multi-scale Attention Feature Pyramid Network (BiMAFPN) is designed to strengthen cross-scale feature interaction under complex greenhouse backgrounds and occlusion conditions. Experiments conducted on a self-constructed greenhouse dataset demonstrate that CF-DETR achieves a Precision of 94.1%, mAP50 of 83.5%, and mAP50-95 of 64.5%, outperforming the baseline RT-DETR-r18 model. Furthermore, deployment on an NVIDIA Jetson AGX Orin platform achieves real-time inference at 30.65 FPS, validating its practical applicability in edge-enabled agricultural systems. The proposed framework provides a reliable visual sensing solution for small-scale phenology monitoring, enabling intelligent pollination management, early yield prediction, and data-driven decision-making in industrial chili production. This work contributes to the advancement of precision horticulture and the digital transformation of industrial crop production systems.

Why it matches plant phenotyping methodsチリ花の検出を目的とする画像ベースの手法を開発し、データセット上で性能評価とエッジ実装検証を行っており、植物の開花状態を取得する方法が中心である。

abstractthis study proposes CF-DETR, a robust transformer-based framework for small-scale chili flower detection.

Fungal infections: Classification performance and detectability with machine learning models. →

This study explores the use of AI-driven machine learning algorithms for the early detection of fungal diseases in tomato plants, a method that enhances diagnostic accuracy and enables more effective crop protection. The research was conducted in 2023 in Shandong Province, China, using two tomato cultivars - Dongfeng-1 and Gypsy. Ten greenhouse plots (2,000 m² each) and ten open-field plots (5,000 m² each) were studied, with image data collected via high-resolution cameras, multispectral sensors, and microclimate sensors, yielding approximately 20,000 annotated images. Five machine learning models were tested: convolutional neural networks (CNNs), random forests, gradient boosting, support vector machines (SVMs), and k-nearest neighbors (KNN). CNNs demonstrated superior accuracy in both greenhouse (95.2% ± 0.3) and open-field plots (92.5% ± 0.5), with corresponding AUC-ROC values of 0.96 and 0.93 (p = 0.001). The false positive rate for CNNs was 4.1% in greenhouses and 5.3% in open-field plots, while diagnostic time was shorter in greenhouses (8.3 s vs. 10.5 s). Compared to visual inspection, CNNs significantly improved diagnostic accuracy and reduced fungicide use. To ensure robustness, the models were evaluated under varying lighting and microclimate conditions. Assessments on both GPU and CPU platforms demonstrated the model's feasibility for deployment on edge devices and cloud-based systems.

Why it matches plant phenotyping methodsトマト植物の真菌病を画像・センサー観測から推定する機械学習手法を開発・比較し、精度、頑健性、計算環境で評価しており、病害状態の表現型取得が中心である。

abstractThis study explores the use of AI-driven machine learning algorithms for the early detection of fungal diseases in tomato plants

Boundary-Refined DeepLabV3+ for Crop Disease Detection in Greenhouse Vegetable Images →

Accurate pixel-level delineation of crop disease in greenhouse images is challenging due to weak lesion margins, scale variations, leaf-vein interference, specular highlights and partial occlusion. This paper introduces a boundary-refined DeepLabV3+ model that keeps the encoder-decoder efficiency of the original framework and adds a boundary supervision branch, uncertainty-aware cross-scale fusion, and an adaptive refinement gate. The network is tested on a set of 6,840 curated greenhouse images that include leaves of tomatoes, cucumbers, peppers and eggplants, as well as 8 disease categories and healthy tissue. Under a fixed split by greenhouse compartment, the proposed model has achieved a mean intersection over union of 89.7%, a mean F1 score of 94.8%, and a boundary F1 of 86.9% at a two-pixel tolerance. The corresponding values are 3.8, 2.4 and 7.6 percentage points higher than those of the standard DeepLabV3+. The mean Intersection over Union (IoU) under low-illumination and condensation-blur conditions are 3.1 and 2.7, respectively. Ablation studies show that boundary supervision is responsible for most of the contour improvement, and uncertainty-aware fusion reduces false lesion expansion along veins. The model has 31.6 million parameters and, after mixed-precision optimisation, runs at 18.7 frames per second on an embedded graphics chip. Based on the above results, explicit boundary reasoning can improve the precision of disease-area estimation without sacrificing the efficiency required in practice; it is thus suitable for greenhouse scouting, targeted spraying and longitudinal severity assessment.

Why it matches plant phenotyping methods温室画像から作物病斑の画素レベル境界と病害面積を推定する画像解析手法を開発・検証しており、植物病害状態の表現型取得が中心である。

abstractThis paper introduces a boundary-refined DeepLabV3+ model that keeps the encoder-decoder efficiency of the original framework and adds a boundary supervision branch, uncertainty-aware cross-scale fusion, and an adaptive refinement gate.

Embedding of ripening topology into one-stage detection for tomato cluster phenotyping. →

The automated assessment of tomato ripeness is vital for modern greenhouse operations, yet challenges remain due to variable environmental conditions. To provide a solution, we propose rank-aware You Only Look Once (YOLO), a novel detection framework that incorporates the biological prior of top-to-bottom ripening within fruit clusters. This is achieved through two key innovations: an efficient position-aware head for regressing relative height for fruits and a dynamic margin-aware ranking loss (DM-RankLoss) that enforces the correct spatial sequence. Evaluated on a 3500-image dataset from a solar greenhouse, our plug-and-play module could boost the mean average precision (mAP) at intersection over union (IoU) threshold of 0.50 (mAP 50 ) of multiple YOLO architectures by up to 5.66 pecentage points. The model effectively learns the cluster topology, achieving a height-mean absolute error (H-MAE) of 0.107 (normalized) and a pairwise ranking accuracy (PRA) of 84.59%, while it reduces the parameter count by over 10% compared to the baseline for efficient deployment. Visualizations confirm that the model leverages spatial context to resolve color ambiguities. Our work offers a sensor-free, accurate, and efficient solution for in situ phenotyping in agricultural robotics.

Why it matches plant phenotyping methodsトマト果実の熟度・クラスター内位置関係を推定するYOLOベースの画像解析法を開発し、データセットで性能評価しており、フェノタイピング手法が中心である。

abstractwe propose rank-aware You Only Look Once (YOLO), a novel detection framework that incorporates the biological prior of top-to-bottom ripening within fruit clusters.

YieldNet: A Near-Zero-Cost YOLOv8n Enhancement for UAV-Based Real-Time Green Tomato Detection to Support Pre-Harvest Yield Forecasting →

Abstract Accurate pre-harvest yield forecasting of greenhouse tomatoes is essential for reducing post-harvest losses, with reliable detection of immature green tomatoes being the core challenge. However, these fruits are small, heavily occluded, and chromatically highly similar to foliage, making real-time detection from low-altitude UAV imagery extremely difficult, while onboard edge processors impose stringent power and weight constraints. To address this, we propose YieldNet, an ultra-lightweight framework that introduces near-zero-overhead enhancements to vanilla YOLOv8n: the backbone is replaced with ShuffleNetV2 to strengthen small-object representation; Efficient Channel Attention (ECA) modules are embedded after the P3–P5 layers in the neck to suppress leaf-background interference; and PIoU v2 loss is adopted to refine bounding-box regression for densely overlapped fruits via size-adaptive and non-monotonic focusing mechanisms. The model is rigorously validated on both a self-collected real-world UAV dataset comprising 600 low-altitude green-tomato images and a public multi-ripeness benchmark. Compared with the YOLOv8n baseline, YieldNet achieves relative improvements in mAP@50-95, Recall, and F1-score by 18.9%, 6.1%, and 5.8%, respectively, on the large dataset, and enhances Recall, F1-score, and Precision by relative gains of 4.3%, 4.0%, and 3.8%, respectively, on the small dataset, while increasing parameters only from 3.0\,M to 3.3\,M and reducing FLOPs from 8.1\,G to 8.0\,G. This work provides an efficient, readily deployable solution for high-precision real-time detection of immature green tomatoes on UAV platforms, enabling reliable pre-harvest yield estimation.

Why it matches plant phenotyping methodsUAV画像から未成熟トマト果実を検出し、収量予測に用いるYOLOベースの画像解析手法を開発・複数データセットで検証しており、植物器官の表現型取得が中心です。

abstractwe propose YieldNet, an ultra-lightweight framework that introduces near-zero-overhead enhancements to vanilla YOLOv8n

GrowScreen-Rhizo 3 - automated large-scale high throughput greenhouse phenotyping of plant root and shoot development. →

Roots play a pivotal role for plant performance, but they are difficult to access, which hampers quantitative measurements. Repeated imaging of rhizotrons, flat growth containers with a transparent side, has proven suitable to assess dynamics of root traits in indoor experiments. However, measuring hundreds of soil-grown plants with high temporal resolution remains a laborious challenge. We introduce a novel whole-plant phenotyping platform with a capacity of almost 900 rhizotrons, which we named GrowScreen-Rhizo 3. This platform was designed to image shoots and roots of individual plants simultaneously and derive digital proxy traits for biomass and growth. In addition, built-in weighing and watering stations deliver water use data for each rhizotron. To achieve the desired throughput (image all 896 plants once a day) a high degree of automatization and standardization was required. We realized a modular plant-to-sensor solution, using a fleet of automated guided vehicles (AGVs) to transport large rhizotrons (80x40x5 cm) to four measurement chambers for daily imaging, weighing, and watering. Simultaneous imaging of the root system with a high-resolution camera (116 μm per px) and the shoot from six different viewing angles allows to monitor plant growth with high spatial and temporal accuracy. First, we verified that moving plants to the measurement chambers did not significantly affect above- or belowground plant growth. Next, we measured phenotypic variation in root and shoot traits of 24 barley genotypes, parents of a nested association mapping population. Our analysis revealed that heritability of root traits such as root system depth and seminal root length was moderate to high (r 2 =0.52 and r 2 =0.93, respectively), enabling further assessment of increasing numbers of recombinant genotypes. The results demonstrate the suitability of GrowScreen-Rhizo 3 to phenotype a range of plant species characterized by various growth habits, including crop, niche, and wild plant species. We conclude that GrowScreen-Rhizo 3 will contribute significantly to the development of phenotyping pipelines for the identification of candidate genotypes with improved resource use efficiency and to pre-breeding processes of climate-resilient crops.

Why it matches plant phenotyping methods根とシュートを自動撮像し、バイオマス・成長などの形質を抽出する大規模フェノタイピング platform の開発・検証が中心である。

abstractWe introduce a novel whole-plant phenotyping platform with a capacity of almost 900 rhizotrons, which we named GrowScreen-Rhizo 3.

VGDS-PointNet++ for organ segmentation and phenotypic trait estimation in greenhouse tomato seedlings. →

Introduction To accurately segment point clouds and quickly calculate leaf length and stem diameter, thereby enabling phenotypic analysis and variety selection of greenhouse tomato plants, this paper proposes a voxel grid downsampling (VGDS)-PointNet++-based model for point cloud segmentation and trait calculation. Methods The point clouds of the tomato canopy were acquired using a depth camera. After labeling, point cloud augmentation was performed, and the tomato point cloud dataset (TPCD) containing 1,552 sets of data was rebuilt. Voxel grid downsampling was applied to replace the original sampling strategy of PointNet++. Models of PointNet, PointNet++, VGDS-PointNet++, and Point Transformer were trained with the TPCD and compared on segmentation quality with accuracy and mean Intersection over Union (mIoU). After segmentation, skeletal morphology was fitted for non-occluded leaves by applying a series of surface fitting techniques. The leaf lengths and stem diameters were automatically calculated and compared with the manually measured values. Results The validation results showed that the average runtime of voxel grid downsampling was 0.132 s, which was lower than under the same number of sampled points. Compared to the other three models, the proposed model had higher accuracy and mIoU, reaching up to 96.80% and 88.95%, respectively. The proposal's accuracy and mIoU increased by 3.9% and 4.45% over PointNet++, respectively. The determination coefficient R 2 between the automatic calculation and manual measurement values of leaf length and stem diameter was 0.93 and 0.87, respectively. Discussion This can help extract phenotypic traits of tomatoes using depth cameras.

Why it matches plant phenotyping methods深度カメラ点群のセグメンテーションと葉長・茎径の自動推定手法を開発し、手測定および複数モデルと比較検証しており、表現型取得が研究の中心である。

abstractthis paper proposes a voxel grid downsampling (VGDS)-PointNet++-based model for point cloud segmentation and trait calculation

Detection and Quantification of Dysprosium in Plant Tissues. →

The growing demand for rare-earth elements (REEs), particularly dysprosium (Dy), underscores the need for sustainable extraction methods. Recovery of Dy, particularly from geographically distributed waste sources, is challenging. This gap positions phytomining, a technique using plants to accumulate metals, as a promising alternative. However, plant species differ in their ability to accumulate metals in high concentrations, necessitating efficient screening methods. In this study, we developed a high-throughput fluorescence-based assay to detect and quantify Dy uptake in plant tissues. The Dy detection method described in the present work exploits Dy's unique spectroscopic properties for sensitive and efficient analysis, enabling the detection of concentrations as low as 0.07 μM, with a detection limit of 0.2 μM in a plant matrix. By incorporating sodium tungstate (Na 2 WO 4 ) as a fluorescence enhancer, we achieved robust emission intensities at 480 and 580 nm, facilitating Dy quantification in complex plant matrices. Additionally, the use of time-resolved fluorescence techniques reduces background autofluorescence from plant tissues, enhancing signal specificity. Validation of the fluorescence method with inductively coupled plasma mass spectrometry (ICP-MS) demonstrated a strong correlation in Dy levels. Greenhouse trials confirmed the method's utility for screening Dy accumulation in living plants and highlighted the potential for rapid stand-off detection. This fluorescence-based approach offers a scalable, efficient tool for identifying Dy-accumulating plants and advances phytomining as a sustainable strategy for REE recovery.

Why it matches plant phenotyping methods植物組織中のDy蓄積という植物状態を蛍光センサーで定量する高スループット手法を開発し、ICP-MSで検証しており、表現型取得法が中心である。

abstractIn this study, we developed a high-throughput fluorescence-based assay to detect and quantify Dy uptake in plant tissues.

CNN-Assisted Growth Monitoring and Stress Management of Cucumber in Semi-Transparent PV Greenhouses for Agrivoltaics →

Currently operating commercial photovoltaics (PV) systems integrated with agricultural production (Agrivoltaics) offer immense potential for the dual harvest of renewable energy and agro-products. Within controlled-environment agriculture (CEA), the use of semi-transparent photovoltaics (ST-PV) and the ability to control the microclimate and shading are beneficial for the production of high-value crops such as cucumbers. The objective of this research was to commence the cultivation of cucumbers under evolving CEA-PV systems by combining greenhouse experiments with computer vision (CV) based driven phenotyping to create an analytical framework and system control framework for the cultivation of cucumbers in an evolving CEA-PV system. The method involved using the monitored plant vigor to control in real time the irrigation and shading of the cucumber plants. The control of irrigation and shading was based on the monitored plant vigor as determined by a U-Net++ implementation for canopy segmentation, an EfficientNet-B3 implementation for stress detection, and a CNN regressor for growth trait estimation. Within the greenhouse, uniform environmental and fertigation conditions were established to evaluate the effect of four shading regimes (0%, 20%, 40%, 60%) on the cucumbers. Simulated, yet representative results predicted cucumber yields to be stable (within ±4% of full yield) with a 20% shading and a 15-20% reduction in water use compared to full sun. Yield was also observed to drop by 10-14% under higher shading of 40 to 60% due to insufficient photosynthetic activity for fruiting. The CNN based models were robust, (segmentation IoU 0.91, stress-class F1 0.92, LAI regression R²≈0.93), allowing for precise and comprehensive monitoring in an annual non-invasive fashion. The greenhouse's annual photovoltaic (PV) output was estimated to be 1,550 to 1,750 kWh/kWp which is able to exceed the energy demand resulting to a net energy surplus. The outcome demonstrates that the cucumber crop can be successfully combined with controlled environment agrovoltaic systems with moderate shading for optimum cucumber yield. Moreover, informed supervision through Artificial Intelligence (AI) helps to navigate closed-loop systems and enhance the water-use efficiency and yield stability.

Why it matches plant phenotyping methodsCNNによるキャノピー分割、ストレス検出、成長形質推定を中核とする植物フェノタイピングおよび閉ループ制御フレームワークであり、性能指標も報告されているため。

abstractcombining greenhouse experiments with computer vision (CV) based driven phenotyping to create an analytical framework and system control framework for the cultivation of cucumbers

Phenotyping Root and Shoot Traits for Drought Response in Bambara Groundnut ( Vigna subterranea (L.) Verdc.). →

Drought stress poses a significant challenge to food security in sub-Saharan Africa, particularly for smallholder farmers in dryland systems. Bambara groundnut ( Vigna subterranea (L.) Verdc.), an underutilised legume with inherent drought tolerance, remains underexplored in terms of its root system traits. This greenhouse study investigated the early root and shoot responses of six Bambara groundnut genotypes under well-watered (100% field capacity) and water-stressed (50% field capacity) conditions using rhizotron-based phenotyping. Significant genotypic differences ( p < 0.01) were observed in root traits such as root system depth (RSD: 11.0-19.9 cm), root system width (RSW: 6.96-12.2 cm), and root dry mass (RDM: 0.42-1.27 g). The ARC genotype exhibited a strong drought-avoidance strategy, increasing RSD from 12.2 to 19.9 cm and RDM from 0.42 to 1.16 g under stress. The Tiga Nicuru DIP-C-F7471 genotype showed adaptive plasticity, maintaining deeper roots (11.0-14.5 cm), high convex hull area (CHA), and root-shoot ratio (RSR) values, despite a reduction in RDM, suggesting a resource-conserving strategy. Principal Component Analysis (PCA) captured 93.6% of the total variability among genotypes. Root traits, particularly total root length (TRL), convex hull area (CHA), root system width (RSW), and root dry mass (RDM), were the main contributors to genotype differentiation. Strong positive correlations (r = 0.88-0.97) between root and shoot traits suggest that genotypes with more developed root systems also supported greater shoot growth, highlighting the coordinated response of above- and below-ground traits under drought stress. These findings provide valuable targets for breeding and highlight the value of rhizotron-based screening for root trait selection. Future field validation and full-season studies are recommended to confirm their relevance for improving yield stability in dryland agriculture.

Why it matches plant phenotyping methods根系・地上部形質を取得するrhizotron-based phenotypingを用い、そのスクリーニング価値を主要な貢献として扱っているため、植物フェノタイピング手法の実質的応用に該当する。

abstractusing rhizotron-based phenotyping

An environment-guided visual-temporal deep learning framework for early disease detection in greenhouse horticultural crops. →

Introduction In protected horticultural production, early disease identification and precise intervention are critical for safeguarding crop yield and quality while reducing chemical pesticide inputs. However, early-stage greenhouse diseases often exhibit extremely subtle visual symptoms, and their occurrence and progression are highly dependent on environmental condition variations, making stable and reliable early warning difficult to achieve using conventional methods based on single visual information or simple multimodal fusion. Methods To address this challenge, a visual-environment joint early disease perception framework for greenhouse horticultural crops is proposed. Through an environment-guided visual attention mechanism and a spatial-temporal joint modeling strategy, environmental variables such as temperature, humidity, vapor pressure deficit, and CO 2 concentration are transformed from passive features into active priors, thereby guiding visual feature learning and enhancing sensitivity to weak disease signals. The proposed method is systematically validated on a real-world greenhouse multimodal temporal dataset. Results Experimental results demonstrate that the proposed approach achieves an accuracy of 91.3%, a recall of 88.9%, and an F1-score of 89.8% in overall disease detection tasks, significantly outperforming multiple baseline models based on convolutional neural networks (CNNs), Transformers, and existing multimodal fusion strategies. In early-stage disease detection scenarios, early precision and early recall reach 88.5% and 86.1%, respectively, with the lead time extended to 2.7 days, indicating a clear advantage in early warning capability. Ablation studies further verify the critical roles of environment-guided attention, spatial-temporal joint modeling, and the joint loss function in improving early detection performance and stability. Discussion This study provides a practically valuable technical pathway for early intelligent warning and precise regulation of greenhouse crop diseases. By integrating environmental dynamics with visual perception, the proposed framework improves the sensitivity and robustness of early disease detection in complex greenhouse conditions, showing strong potential for practical deployment in protected horticulture.

Why it matches plant phenotyping methods環境情報と画像・時系列情報を統合して、植物病徴を早期検出する深層学習フレームワークの開発と実データでの系統的検証が中心であり、植物の病害状態を直接推定するため。

abstracta visual-environment joint early disease perception framework for greenhouse horticultural crops is proposed.

Predicting Rice Quality in Indica Rice Using Multidimensional Data and Machine Learning Strategies →

Integrating agricultural remote sensing and phenomics for full-growth-period rice quality prediction is vital for early non-destructive screening and breeding; however, studies integrating genomic and multi-source phenotypic data across multiple environments remain limited. This study addressed this gap by integrating genomic SNP data, UAV-based spectral data, and individual multidimensional phenotypic data of 61 indica rice varieties (field and greenhouse environments). As a proof-of-concept study, feature selection methods (LASSO, MI, RFE, SPA) were used to mitigate overfitting and the “p >> n” problem, with further validation needed in larger populations. The results showed that amylose content is genetically dominated, protein content is genetically determined and influenced by gene-environment interactions, and chalkiness traits are determined by three combined factors. For amylose content, SNP data under the Random Forest model at the population level (phenomics data from field UAV remote sensing of variety populations) achieved optimal performance (R2 = 0.92; MAE = 1.1; RMSE = 1.5), while the Stacking Ensemble method enhanced accuracy at the individual level (phenomics data from greenhouse single-plant phenotyping per variety). Chalky grain rate and chalkiness degree showed SNP-comparable prediction accuracy, with Stacking significantly improving performance at the population level (R2 = 0.89 and 0.85, respectively). Protein content prediction remained relatively low (optimal R2 = 0.56) due to strong environmental sensitivity and complex interactions. This framework extends traditional single-environment/single-data-source approaches, providing an effective strategy for early, high-throughput, non-destructive rice quality screening. Further validation with larger datasets, more growing seasons, or independent populations is required for reliable application in breeding-related practices.

Why it matches plant phenotyping methodsUAVスペクトル計測と個体フェノタイピングを統合し、機械学習でイネの品質形質を非破壊・高 throughput に予測する枠組みが研究の中心である。

abstractIntegrating agricultural remote sensing and phenomics for full-growth-period rice quality prediction is vital for early non-destructive screening and breeding

SCEA-YOLO: A General-Purpose Maturity Grading Model of Multi-Crop Greenhouse Robots. →

Accurate classification of fruit maturity is essential for automated grading and robotic manipulation in modern greenhouse cultivation. Most existing methods rely on crop-specific models, severely restricting their scalability in multi-crop scenarios. To overcome this limitation, this study presents SCEA-YOLO, a unified and efficient instance segmentation framework built on YOLOv11s-seg, for simultaneous maturity classification of tomatoes and sweet peppers. To boost feature discrimination, reduce computational redundancy, and alleviate class imbalance, SCEA-YOLO integrates spatial-channel reconstruction convolution and an efficient multi-scale attention mechanism, while replacing the original detection head with the proposed EA-Head. The model is evaluated on a hybrid dataset captured under diverse greenhouse conditions, including varying illumination, fruit occlusion, and overlapping canopies. Its robustness to different viewing angles and camera distances is further validated via deployment on an automated grading robot. Compared with the baseline, SCEA-YOLO enhances classification precision and mAP50–95 by 5.3% and 2.3% for tomatoes, and 1.2% and 1.4% for sweet peppers, respectively. With only 33.2 GFLOPs, the model satisfies real-time inference demands. Benefiting from its lightweight structure and real-time performance, SCEA-YOLO can be readily deployed on embedded systems and robotic platforms. It offers a practical, unified, and scalable solution for intelligent fruit maturity evaluation in multi-crop greenhouse production.

Why it matches plant phenotyping methodsトマトとピーマン果実の成熟度を画像から分類・評価するモデルを開発し、データセットおよびロボット上で性能検証しており、植物表現型取得手法が中心である。

abstractthis study presents SCEA-YOLO, a unified and efficient instance segmentation framework built on YOLOv11s-seg, for simultaneous maturity classification of tomatoes and sweet peppers.

Early Detection and Differentiation of Dragon Fruit Plant Diseases Using Optical Spectral Reflectance →

Dragon fruit (Hylocereus spp.) is an emerging crop in the tropics and subtropics, but its production is increasingly threatened by diseases that reduce yield and profitability. Early diagnosis of these diseases is crucial for timely intervention, yet visual symptoms often appear only after significant infection has occurred. The study aims to evaluate how optical spectral reflectance can detect dragon fruit diseases and identify the most responsive spectral regions. In this study, six major dragon fruit stem diseases: Neoscytalidium stem canker, stem sunburn, anthracnose, Botryosphaeria stem canker, Bipolaris stem rot, and bacterial soft rot were characterized by the goal of identifying unique spectral signatures for early detection and differentiation of each disease. Seventy-two potted dragon fruit plants of three distinct species were grown under four organic vermicompost treatments (0, 5, 10, 20 tons/acre) in both open-field and high-tunnel conditions together, in a randomized complete block design. A handheld spectroradiometer (350–2500 nm) was used to collect reflectance from the diseased and healthy cladodes (stem segment). Various spectral vegetative indices were computed to identify disease-specific features. The results revealed distinct spectral features for each disease. Infected cladodes consistently exhibited higher reflectance especially in the visible region (400–700 nm) and the near-infrared region (900–2500 nm) of the spectrum than healthy cladodes. The Normalized Difference Vegetative Index (NDVI), Green Normalized Difference Vegetative Index (GNDVI), and Spectral Ratio (SR) spectral indices were significantly higher in healthy plants than in diseased ones, reflecting higher chlorophyll concentration and plant biomass. Conversely, the 1110/810 ratio was lower in healthy plants than in diseased plants, suggesting a more compact internal plant structure. Statistical analysis revealed highly significant differences (p

Why it matches plant phenotyping methods光学スペクトル反射とスペクトル指数を用いて、ドラゴンフルーツの病徴を早期検出・識別する方法が研究の中心であり、感染植物の状態を直接推定している。

abstractThe study aims to evaluate how optical spectral reflectance can detect dragon fruit diseases and identify the most responsive spectral regions.

Computer vision and IoT based plant phenotyping and growth monitoring with 3D point clouds →

Computer vision and Internet of Things (IoT) technologies offer robust solutions for plant phenotyping, but traditional mainstream segmentation methods often fail in high-density plantings with overlapping foliage. This study introduces an integrated phenotyping system combining automated data capture and high-temporal RGB-D imaging using off-the-shelf hardware (Intel RealSense D435 and Raspberry Pi) to generate 3D point clouds of lettuce under controlled greenhouse conditions. While recent agricultural applications have shown limited success and required domain-specific adaptations, Segment Anything Model (SAM) and FastSAM were demonstrated to achieve exceptional zero-shot segmentation performance for individual lettuce plants in high-density arrangements without additional training. This capability effectively addresses the traditional challenges of species-specific parameter tuning and extensive training data requirements and fine-tuning. By mapping 2D segmentation masks to corresponding 3D point clouds, the system accurately extracted key phenotypic traits, namely plant height, length, and width, from which area and volume were subsequently estimated, showing strong correlations with manual measurements for Rex and Rouxai lettuce cultivars. This high-temporal, non-destructive monitoring provided unique insights into plant growth dynamics. The study highlights distinct growth patterns among these cultivars, underscoring the importance of tailored phenotyping approaches to optimise crop management strategies. By addressing the limitations of existing phenotyping methods, this work advances precision agriculture technologies, offering a cost-effective and efficient solution for monitoring dynamic crop growth with potential applications across various crops and growing conditions.

Why it matches plant phenotyping methodsRGB-D撮像、3D点群、セグメンテーションを統合した植物表現型取得システムを開発し、草丈・長さ・幅などを抽出して手測定と検証しているため、方法が中心的である。

abstractThis study introduces an integrated phenotyping system combining automated data capture and high-temporal RGB-D imaging using off-the-shelf hardware (Intel RealSense D435 and Raspberry Pi) to generate 3D point clouds of lettuce under controlled greenhouse conditions.

Computer vision and IoT based plant phenotyping and growth monitoring with 3D point clouds →

Computer vision and Internet of Things (IoT) technologies offer robust solutions for plant phenotyping, but traditional mainstream segmentation methods often fail in high-density plantings with overlapping foliage. This study introduces an integrated phenotyping system combining automated data capture and high-temporal RGB-D imaging using off-the-shelf hardware (Intel RealSense D435 and Raspberry Pi) to generate 3D point clouds of lettuce under controlled greenhouse conditions. While recent agricultural applications have shown limited success and required domain-specific adaptations, Segment Anything Model (SAM) and FastSAM were demonstrated to achieve exceptional zero-shot segmentation performance for individual lettuce plants in high-density arrangements without additional training. This capability effectively addresses the traditional challenges of species-specific parameter tuning and extensive training data requirements and fine-tuning. By mapping 2D segmentation masks to corresponding 3D point clouds, the system accurately extracted key phenotypic traits, namely plant height, length, and width, from which area and volume were subsequently estimated, showing strong correlations with manual measurements for Rex and Rouxai lettuce cultivars. This high-temporal, non-destructive monitoring provided unique insights into plant growth dynamics. The study highlights distinct growth patterns among these cultivars, underscoring the importance of tailored phenotyping approaches to optimise crop management strategies. By addressing the limitations of existing phenotyping methods, this work advances precision agriculture technologies, offering a cost-effective and efficient solution for monitoring dynamic crop growth with potential applications across various crops and growing conditions.

Why it matches plant phenotyping methodsRGB-D画像、3D点群、セグメンテーションを統合して植物形質を抽出するフェノタイピングシステムの開発・評価が中心であり、手動測定との相関検証も行っているため。

abstractThis study introduces an integrated phenotyping system combining automated data capture and high-temporal RGB-D imaging using off-the-shelf hardware (Intel RealSense D435 and Raspberry Pi) to generate 3D point clouds of lettuce under controlled greenhouse conditions.

Detection of Foliar Phosphorus in Potato Crops Using Multispectral Imagery →

Phosphorus is essential for potato cultivation; however, its low natural availability and high fixation in the soil require efficient management strategies. In this context, rapid and non-destructive methods for estimating foliar phosphorus content are important to reduce waste and improve production efficiency. This study evaluated the use of multispectral images acquired by a Survey 3 (MAPIR) camera to estimate foliar phosphorus content in potato crops at the tuberization stage, when topdressing fertilization is typically applied. To generate variability in foliar phosphorus levels, an experiment was conducted under greenhouse conditions using a randomized complete block design with eight P₂O₅ rates (0, 50, 100, 200, 400, 800, 1,600, and 3,200 kg ha⁻¹) and 40 replications. Spectral indices (NDVI, GNDVI, and GRVI) were analyzed, and regression models and machine learning algorithms (Random Forest, Multilayer Perceptron, and SMOreg) were applied to predict foliar phosphorus content. NDVI showed a significant inverse correlation with phosphorus content, attributed to the nutritional dilution effect. Among the evaluated methods, Random Forest showed the best performance, with a relative root mean square error of 19.01%. The results demonstrate that the integration of multispectral variables and machine learning techniques increases diagnostic accuracy, highlighting the potential of these technologies for nutritional monitoring of potato crops in precision agriculture.

Why it matches plant phenotyping methodsマルチスペクトル画像と機械学習により、ジャガイモ葉のリン含量という植物生理形質を非破壊推定する手法が研究の中心である。

abstractrapid and non-destructive methods for estimating foliar phosphorus content are important

Two-Dimensional LiDAR-Based Visualization of Crop Canopy Structure in Green Pepper →

施設園芸における環境制御では，温度や湿度の空間変動など環境の不均一性を考慮せずに，平均化された指標に基づいた制御が行われており，作物の生育にばらつきが生じる問題があった．これらを解決するためには，主に日照や温度・湿度などの不均一の原因となっている作物群落のキャノピー構造を可視化することが重要である．本研究では，低コストの2D LiDAR（Light Detection and Ranging）計測により，作物のキャノピー構造の可視化を試み，薄い葉や細い茎によるレーザー反射の有効性と適切なスキャン条件を検証した．機器を設置した台車を移動プラットフォームとして，圃場の畝に沿って移動させることで，畝に沿った作物のキャノピー構造を把握する．2つのLiDARの走査面を変えて用いることとし，水平スキャンにより，台車進行方向の作物及び障害物の2Dマッピング，垂直スキャンにより作物の高さ方向のスキャンを時系列的に重ねることで，3Dマッピングを行う．結果として，水平スキャンのデータは，台車の走行制御のための状況把握としては十分な精度で利用可能である．垂直スキャンのデータは，作物の高さ方向の構造を把握できることが確認された．2つのLiDARを搭載したシステムを用いて，圃場で定期的に移動計測を行うことで，作物のキャノピー構造を把握することができ，環境の不均一の要因として利用可能となることが期待される．

Why it matches plant phenotyping methods低コスト2D LiDARによる作物キャノピー構造の可視化手法を開発し、反射の有効性と走査条件を検証しているため、植物表現型取得が研究の中心である。

abstract本研究では，低コストの2D LiDAR（Light Detection and Ranging）計測により，作物のキャノピー構造の可視化を試み，薄い葉や細い茎によるレーザー反射の有効性と適切なスキャン条件を検証した．

Comparative Evaluation of Allometric, Machine Learning, and Ensemble Approaches for Modeling Dynamic Structure-Fresh Weight Relationships in Sweet Pepper. →

Accurate fresh weight (FW) estimation is essential for growth monitoring and yield prediction in greenhouse fruit vegetables, but remains challenging due to the dynamic allocation between vegetative and reproductive organs. This study aimed to systematically evaluate modeling strategies for FW estimation in sweet pepper and identify which approach is most suitable under conditions of dynamic biomass partitioning. Non-destructive morphological measurements were collected under greenhouse cultivation, and allometric models based on geometric equations were established as baselines. Their performance was compared with machine learning (ML) models and ensemble learning frameworks. To address limited data availability, numerical data augmentation with Gaussian noise and a variational autoencoder was applied. Among the allometric models, the stick model combined with a sigmoid function showed the highest performance, with an R2 of 0.80 for shoot FW and 0.54 for fruit FW. All ML models outperformed the allometric models, and the ensemble model achieved the highest predictive accuracy, with an R2 of 0.96 for shoot FW and 0.89 for fruit FW. Data augmentation further improved predictive performance across all ML models, particularly for fruit FW prediction. Feature contribution analysis revealed that temporal progression was the dominant predictor of fruit FW, while structural traits played the primary role in shoot FW estimation. Ensemble-based ML, combined with data augmentation, provides a methodological framework for non-destructive FW estimation of sweet pepper in controlled environments such as greenhouses and smart farming systems.

Why it matches plant phenotyping methods非破壊形態計測からピーマンの地上部・果実の生重を推定するアロメトリック／機械学習／アンサンブル手法を比較・評価しており、表現型取得・推定手法が研究の中心である。

abstractThis study aimed to systematically evaluate modeling strategies for FW estimation in sweet pepper

Autonomous Plant Health Monitoring and Climate Actuation using YOLOv8 and ESP32-based Mobile Rover →

Maintaining plant health and ensuring suitable environmental conditions are essential aspects for modern agriculture. This work introduces an integrated system that combines artificial intelligence, mobile robotics, and Internet of Things (IoT) technologies to enable automated plant monitoring and greenhouse management. The proposed system employs a mobile robotic rover equipped with a vision unit to capture images of plant leaves. These images are processed using a YOLOv8-based deep learning algorithm to identify and classify plant diseases with high accuracy. In parallel, environmental parameters such as soil moisture, temperature, and humidity are continuously measured through embedded sensor modules via ESP32.The system adopts a distributed control framework using ESP32 microcontrollers, allowing seamless interaction between sensing components and actuators. When the soil moisture level falls below a predefined threshold, the system automatically activates a water pump to watering the plants. Along with, if the ambient temperature exceeds the desired limit, a cooling fan is triggered to lower the temperature. These automated control actions ensure that plants are consistently maintained under optimal growth conditions in disease free environment. Real-time data processing enables intelligent decision-making for irrigation and climate control. Furthermore, a mobile application interface allows users to remotely monitor system status, receive instant notifications, and make informed decisions based on collected data.

Why it matches plant phenotyping methods葉画像をYOLOv8で解析して植物病害を分類する観測手法が、移動ローバーによる植物健康モニタリングの中心的機能として記述されているため、画像ベースの植物状態 phenotyping として含める。

abstractThis work introduces an integrated system that combines artificial intelligence, mobile robotics, and Internet of Things (IoT) technologies to enable automated plant monitoring and greenhouse management.

Screening Methods for Downy Mildew Resistance in Maize: A Systematic Review. →

Background/Objectives: Downy mildew, caused by Peronosclerospora and Sclerophthora species, is a major constraint to maize production in tropical and subtropical regions, with yield losses of 30-100%. This systematic review synthesised evidence on methods used to screen maize for downy mildew resistance and assessed their effectiveness, reliability, and associated markers. Methods: PubMed, Google Scholar, ScienceDirect, and CAB Abstracts were searched (last searched 22 October 2025) for English-language studies (1990-2025) evaluating phenotypic or molecular screening methods. Risk of bias was assessed using the RoB 2 framework. Narrative synthesis was conducted following a protocol registered on the Open Science Framework. Results: Twelve studies met the inclusion criteria, predominantly from India and Cambodia. Spreader row systems (seven studies) and conidial spray inoculation (six studies) were the most common field methods, while the glasshouse sandwich technique generated the highest disease pressure. Cross-method correlations were strong (r = 0.92-0.99), and heritability estimates ranged from 0.50 to 0.97. QTL mapping identified resistance loci on chromosomes 2, 3, and 6, with chromosome 6 stable across multiple pathogen species. Evidence certainty was moderate for method effectiveness and low for molecular markers. Conclusions: Established phenotypic screening methods reliably discriminate resistant germplasm; however, standardised protocols, broader geographic validation, and independent molecular marker confirmation are needed.

Why it matches plant phenotyping methodsトウモロコシのべと病抵抗性という植物状態を評価する表現型スクリーニング法を体系的にレビューし、方法の有効性・信頼性を比較しているため、手法レビューとして収載する。

titleScreening Methods for Downy Mildew Resistance in Maize: A Systematic Review.

Neural 3D reconstruction and immersive VR visualization of row crops across phenological growth stages →

Plant phenotyping in precision agriculture increasingly requires high-fidelity three-dimensional reconstruction and accessible visualization methods. This study presents an integrated pipeline combining Neural Radiance Fields (NeRF), 3D Gaussian Splatting (G-Splat), and Virtual Reality (VR) visualization for comprehensive plant analysis across developmental stages. We collected multi-view imagery of finger millet, proso millet, mungbean, and field pea under controlled greenhouse conditions, aligning data acquisition with standardized BBCH phenological scales. Camera pose estimation was performed using GLOMAP, followed by reconstruction via both Nerfacto and G-Splat implementations. Quantitative evaluation using PSNR, SSIM, and LPIPS metrics revealed complementary strengths of the two approaches: G-Splat achieved superior structural fidelity, while NeRF provided enhanced perceptual realism. Both reconstruction methods were successfully integrated into an immersive VR greenhouse environment deployed on Meta Quest headsets, maintaining consistently high framerates. This framework establishes a practical foundation for incorporating neural reconstruction and immersive technologies into agricultural phenotyping workflows, supporting both research applications and educational engagement.

Why it matches plant phenotyping methods植物の多視点画像からNeRFと3D Gaussian Splattingで3D形状を再構成し、画質指標で比較評価する統合フェノタイピング基盤の開発・検証が中心である。

abstractThis study presents an integrated pipeline combining Neural Radiance Fields (NeRF), 3D Gaussian Splatting (G-Splat), and Virtual Reality (VR) visualization for comprehensive plant analysis across developmental stages.

A Three-Year Multimodal Holistic Dataset For Horticultural Tomato Cultivation. →

Existing tomato datasets often focus on short-term experiments or lack integrated environmental and agronomic data. We present Horti-M3-Tomato, a comprehensive three-year dataset collected in Northeast China's greenhouse, including high-resolution RGB images, environmental sensor data (recorded every 30 minutes), soil conditions, and detailed agronomic records such as yield data and management practices. Spanning three growing seasons (2023-2025), the dataset integrates temporal imaging, environmental monitoring, soil data, and manual phenotypic and yield records. Horti-M3-Tomato supports research on growth dynamics, genotype-environment interactions, and provides a benchmark for AI-based phenotyping and precision horticulture. The dataset is openly available for further research in controlled-environment agriculture.

Why it matches plant phenotyping methodsトマトの画像・環境センサーデータ・手動表現型記録を統合したデータセットであり、AIベースの表現型解析のベンチマークとして明示されているため、表現型データ基盤が中心です。

abstractincluding high-resolution RGB images, environmental sensor data (recorded every 30 minutes), soil conditions, and detailed agronomic records such as yield data and management practices.

Real-time multi-attribute quality grading of tabletop strawberries under occlusions for harvesting robots →

• Modular RGB–D pipeline for real-time multi-attribute grading of strawberries. • ResNet-101 multi-head classifier predicted maturity, disease, and deformity jointly. • CycleGAN restored strawberry shape and texture from partially occluded views. • QH and MADM strategies converted multi-attribute predictions to grading decisions. • Field tests validated end-to-end perception-to-placement pipeline in farms. Strawberry grading was critical for meeting market standards, yet manual post-harvest sorting remained labor-intensive, damage-prone, and inconsistent, while most vision-based methods targeted single attributes and lacked integrated in-field operation. We presented a real-time RGB–D grading framework for tabletop-cultivated strawberries in greenhouse environments. The system combined instance segmentation (YOLOv11–Seg), occlusion-aware completion via CycleGAN, and a three-branch multi-task network based on ResNet-101 to simultaneously infer maturity, disease status (including asymptomatic fruit), and deformity. Pose normalization and depth alignment supported calibrated volume-to-mass regression for non-destructive weight estimation. To improve robustness to rare morphology, 500 deformed-fruit samples were synthesized with a Gemini-based generative model to mitigate class imbalance. Built upon this perception stack, we implemented two grading strategies: a deterministic Quality Hierarchy (QH) for real-time robotic routing and a weighted multi-attribute decision-making (MADM) scheme for flexible batch evaluation. The multi-attribute classifier achieved 93.65% overall accuracy (disease 94.09%, maturity 94.07%, shape 94.42%) with an inference latency of 33.65 ms (29.7 FPS). Depth-assisted mass estimation yielded average errors of 8.11% for complete fruits and 10.47% under occlusion after completion; in field deployment on marketable fruits routed to size grading, it achieved MAE/RMSE of 1.85/2.20 g with R 2 = 0.9384 (MAPE 8.48%) and a three-bin size-grade accuracy of 90.91% (100/110). In single-target harvesting mode on an RTX 4060 GPU (640x480, 30 fps), end-to-end latency was 87.56 ms per harvested target in complete mode and 197.56 ms when completion was invoked (CycleGAN 110.00 ms/instance). These results demonstrated a practical, non-destructive, occlusion-aware, and deployable multi-attribute grading solution for intelligent strawberry harvesting in real greenhouse scenarios.

Why it matches plant phenotyping methodsRGB-D画像解析でイチゴの成熟度、病徴、形状、重量を推定し、性能検証とロボット実装まで行う中心的なフェノタイピング手法研究。

abstractModular RGB–D pipeline for real-time multi-attribute grading of strawberries.

Fine-grained identification of greenhouse crop leaf diseases based on reconstruction-generation network. →

There are few data labels in the agricultural field, and accurate annotation of existing data requires professional knowledge and is time-consuming and laborious, especially the images collected in the actual greenhouse scene, which lack accurate annotation by professionals. Fine-grained refers to the highly detailed division or analysis of data or tasks, with a particular emphasis on capturing micro-level differences. In order to improve the accuracy of greenhouse crop disease identification, the crop disease identification problem is regarded as a fine-grained classification problem, and the attention mechanism is introduced into the classification network. The VAE enhancement strategy is introduced into the disease identification network model to improve the accuracy when the annotation is insufficient. Aiming at the problem that the actual environmental background of greenhouse is complex, there are many disturbances, the disease spot area is small, and the difference between leaf disease and wilt and soil is not obvious, a fine-grained identification model of leaf disease based on reconstruction-generation is further proposed. The attention mechanism was used to increase the recognition ability. During training, the VAE strategy was first used to make full use of a large number of labeled and unlabeled data to realize unsupervised learning, and then the labeled data was used for supervised disease identification, and the Reconstruction-Generation Network(RGN) was used to force the classification network to pay more attention to discriminative regions to find differences. Reconstruction-generation belongs to self-supervised learning, which uses the unsupervised information in the data to construct supervised signals, and can generate useful feature representations by learning the structure and pattern in the data. Experimental results show that the classification recognition accuracy of the proposed fine-grained leaf disease identification model based on reconstruction-generation adopts the attention mechanism reached 98.03%. The proposed method is applied to the detection model, the correct recognition rate of diseased leaves was 95.07%, and the correct recognition rate of healthy leaves was 98.46%, which can realize the end-to-end detection and identification of diseased leaves and meet the practical requirements.

Why it matches plant phenotyping methods葉の病徴を画像から直接識別・検出する深層学習手法を開発し、認識性能を評価しており、植物状態の取得・抽出方法が研究の中心である。

abstracta fine-grained identification model of leaf disease based on reconstruction-generation is further proposed.

PlaneSegNet: A deep learning network with plane attention for plant point cloud segmentation in agricultural environments →

Accurately extracting plant point clouds from complex agricultural environments is essential for high-throughput phenotyping in smart farming. However, existing methods face significant challenges when processing large-scale agricultural point clouds owing to high noise levels, dense spatial distribution, and blurred structural boundaries between plant and non-plant regions. To address these issues, this study proposes PlaneSegNet, a voxel-based semantic segmentation network that incorporates an innovative plane attention module. This module aggregates projection features from the XZ and YZ planes, enhancing the model's ability to detect vertical geometric variations and thereby improving segmentation performance in boundary regions. Extensive experiments across representative agricultural scenarios at multiple scales, including open-field populations, greenhouse cultivation environments, and large-scale rural landscapes, demonstrate that PlaneSegNet significantly outperforms traditional geometry-based approaches and deep-learning models in plant and non-plant separation. By directly generating high-quality plant-only point clouds, PlaneSegNet significantly reduces reliance on manual pre-processing, offering a practical and generalisable solution for automated plant extraction across a wide range of agricultural applications. The dataset and source code used in this study are publicly available at https://github.com/yangxin6/PlaneSegNet.

Why it matches plant phenotyping methods植物点群を農業環境から抽出する深層学習手法を開発し、高スループット表現型解析への利用と複数環境での性能評価を行っており、植物表現型取得の中核手法である。

abstractAccurately extracting plant point clouds from complex agricultural environments is essential for high-throughput phenotyping in smart farming.

ELSF-DETR: an efficient lightweight network for detecting strawberry flowers pollination status in non-structured greenhouse environments →

Accurate and efficient detection of the pollination status of strawberry flowers is essential for intelligent pollination robots, as it directly affects the determination of optimal pollination timing and improves fruit set rates. However, the small size of strawberry anthers, their visual similarity, varied opening states, and complex field environments make pollination status detection highly formidable. To overcome these constraints, this paper presents a streamlined and resource-efficient detection approach (ELSF-DETR), built upon the Real-Time DEtection Transformer (RT-DETR) and specially refined for detecting densely packed and visually similar small objects in agricultural scenes. A lightweight LS-ResNet backbone is constructed to better capture small and densely clustered anther structures in strawberry flowers while reducing model complexity for improved deployment efficiency. In addition, the integration of a P2 detection head with full-kernel convolution enhance the network’s capacity to focus on delicate anther contours and cracking characteristics. Furthermore, the Hierarchical Attention Fusion Block (HAFB) is employed to balance local detail extraction with global context understanding, reducing misjudgments caused by misleading fine-grained features. Lastly, by employing the Wise-IoU (WIoU) loss mechanism, the model achieves improved sensitivity to minor positional discrepancies in visually similar anther objects. Experiments conducted on a self-built strawberry flower dataset demonstrate that ELSF-DETR achieves superior performance, it achieves 88.2 % accuracy, 85.8 % recall, 87.1 % mAP@50, and F1 score of 86.98 %. Relative to the baseline architecture, mAP@50 and F1 improved by 7.1 % and 4.33 %, respectively, while the model parameters and GFLOPs were reduced by 6.86 MB and 13.7 G, meeting the requirements of high precision and low complexity. This work provides practical support for intelligent pollination systems in precision agriculture.

Why it matches plant phenotyping methodsイチゴ花の受粉状態という植物状態を画像から推定する検出モデルを開発・評価しており、植物フェノタイピング手法が中心である。

abstractthis paper presents a streamlined and resource-efficient detection approach (ELSF-DETR)

Non-destructive monitoring method for protected-lettuce yield using deep learning →

Accurate acquisition of phenotypic characteristics in protected crops is a crucial prerequisite for intelligent control and digital breeding in greenhouses. To accurately assess the phenotypic traits of protected lettuce, a specialized in situ phenotypic detection method has been developed. The Multimodal Features and Attention Mechanism for Phenotype Detection Model (MFAMNet) was developed for protected lettuce, employing a segmented multi-source image dataset for synchronous regression testing. The results revealed that the predicted values generated by MFAMNet exhibited a strong correlation with the measured values, achieving coefficients of determination of 0.96, 0.92, 0.95, 0.94, and 0.95 for plant height, crown width, leaf area, fresh weight, and dry weight, respectively. Ablation tests demonstrated that the deep learning detection framework based on multi-modal feature fusion significantly outperformed single-feature detection models, highlighting the advantages of integrating diverse data modalities. In addition, the multi-modal feature attention mechanism (MMF) facilitates both inter-modality and intra-modality interactions by capturing the global correlations between modalities and employing dynamic sparse spatial attention. The effectiveness of MMF has been validated through comparative experiments, demonstrating its suitability for the phenotypic detection of artificially cultivated lettuce. In summary, the method proposed in this study facilitates real-time monitoring of facility crops, enabling precise control of environmental parameters in protected agriculture and optimizing resource allocation. This approach contributes to the development of a comprehensive intelligent agriculture system and establishes a foundation for unmanned farms.

Why it matches plant phenotyping methodsレタスの草丈、株幅、葉面積、 fresh weight、dry weightを推定するマルチモーダル画像ベース手法を開発し、実測値との比較およびアブレーション・比較実験で検証しており、フェノタイピング手法が研究の中心である。

abstracta specialized in situ phenotypic detection method has been developed

Evaluating Medicago spp. plant genetic resources for resistance to spring black stem and leaf spot pathogen →

Alfalfa (Medicago sativa L.), also known as lucerne, is the fourth most widely grown crop in the U.S. and plays key roles in animal nutrition and crop rotations. Several foliar diseases reduce yield and quality of herbage, impacting both plant and animal production and farm economy. Spring black stem and leaf spot, caused by Ascochyta medicaginicola (formerly Phoma medicaginis), is a damaging fungal leaf spot disease of alfalfa and needed levels resistance is lacking in commercial cultivars. To identify potential sources of resistance in alfalfa germplasm, an optimized greenhouse seedling inoculation protocol was developed. Several A. medicaginicola isolates were tested for pathogenicity and spore concentrations were optimized for ideal disease pressure. A rating scale, modified from an established protocol, with improved resolution was used to distinguish differences observed in disease phenotypes. After protocol improvements, 78 standard check alfalfa cultivars and 188 Medicago spp. accessions were screened for disease reaction in replicated trials and 2832 alfalfa accessions were screened for disease reaction in non-replicated evaluations. An ideal concentration of 5 × 10⁴ spores mL⁻¹ was determined by measuring the reaction of standard susceptible (Lahontan) and moderately resistant (Ramsey) check cultivars. Several cultivars and related Medicago species appeared to be more resistant than the moderately resistant checks. Many of the alfalfa accessions originating from colder and wetter environments (e.g., northern latitudes) also showed improved resistance compared to reference cultivars. Resistant germplasm selections were made from these screening efforts for further development of improved alfalfa populations.

Why it matches plant phenotyping methodsアルファルファ葉斑病抵抗性の評価に用いる接種プロトコルと、病徴表現型を識別する改良評価尺度を開発し、検証・大規模適用しているため、植物表現型取得法が中心である。

abstractan optimized greenhouse seedling inoculation protocol was developed

Innovative photosynthesis model twinning after intelligent interpretation of complex sensor analytics →

Accurate canopy photosynthesis modeling is essential for understanding and optimizing crop growth and yield in greenhouse agriculture. Current models have limited predictive capability due to inadequate responsiveness to dynamic environments and delays in parameter acquisition, making accurate predictions challenging under the complex conditions of solar greenhouses. This study aimed to develop a dynamic canopy photosynthesis model for greenhouse tomatoes, leveraging an IoT sensor network for real-time biological feedback and parameterization. By integrating real-time monitoring with dynamic feedback, the model facilitates precision management of greenhouse tomato cultivation, thereby optimizing plant growth, resource use efficiency, and yield predictability. To achieve this, a non-destructive inversion method based on a dual weighing system was developed, enabling accurate dynamic monitoring of tomato canopy leaf area index (LAI, R² ≥ 0.94) and the photosynthetic leaf area index (LAIₚ, R² ≥ 0.91), continuously providing parameters for updating modelling (validated against destructive sampling and actual measurements for trait specifics). Based on accurate parameter acquisition, a dynamic canopy photosynthesis model was developed using LAIₚ as the core variable, integrating above-canopy radiation. A newly developed parameter, which integrates the radiation component of transpiration, serves as a key factor for estimating photosynthesis. This innovative approach allows for accurate daily prediction and assessment of assimilated biomass. Experimental results from 2022 and 2023 showed that the LAIₚ model performed better than the comparison model, showing higher accuracy and adaptability (R² = 0.87 and 0.89, NRMSE = 0.17 and 0.12 vs. R² = 0.70 and 0.80, NRMSE = 0.26 and 0.15). These results confirmed the reliability of the integrated modeling framework, which forms a closed-loop system connecting real-time plant monitoring, statistical parameter inversion, online model adaptation, and biomass feedback verification. This modeling approach provides a solid foundation for precise growth simulation, sustainably improving yield and quality in solar greenhouse tomatoes, and advancing digital twin-enabled intelligent production.

Why it matches plant phenotyping methods植物キャノピーのLAIおよび光合成LAIを非破壊・連続推定するセンサー／逆解析法を開発し、破壊サンプリング等で検証している。植物形質取得とモデル連携が研究の中心である。

abstracta non-destructive inversion method based on a dual weighing system was developed, enabling accurate dynamic monitoring of tomato canopy leaf area index (LAI, R² ≥ 0.94) and the photosynthetic leaf area index (LAIₚ, R² ≥ 0.91)

Image processing–assisted evaluation of yeast-encapsulated clove formulations against tomato brown rugose fruit virus →

Tomato brown rugose fruit virus is an emerging threat to tomato and other solanaceous crops, demanding eco-friendly antiviral approaches. Plant-derived clove products, including essential oil and ethanolic extract, possess antiviral potential but are limited by instability and delivery challenges. In this study, clove essential oil and extract were encapsulated in plasmolysed and non-plasmolysed yeast cells (Saccharomyces cerevisiae) through an environmentally friendly process to enhance their stability and effectiveness. The encapsules were analysed by gas chromatography–mass spectrometry, Fourier-transform infrared spectroscopy, and scanning electron microscopy. Their antiviral activity against tomato brown rugose fruit virus infection was evaluated under greenhouse conditions, and virus presence was confirmed by reverse transcription–polymerase chain reaction. Treatment efficacy was assessed via image-based lesion quantification, including area, count, and color parameters. Image-derived results were consistent with manual measurements, validating the reliability of digital evaluation. Treated plants exhibited reduced lesion formation and color alterations associated with symptom suppression. Yeast encapsulation thus improved the antiviral performance of clove-based products, while image processing provided a non-destructive and straightforward tool for early detection and monitoring of plant virus infections.

Why it matches plant phenotyping methods画像処理による植物ウイルス症状（病斑）の定量化と手動測定との信頼性検証が研究の中心的要素であり、植物病害状態の表現型測定に該当する。

abstractTreatment efficacy was assessed via image-based lesion quantification, including area, count, and color parameters.

A Data-Driven Image Extraction and Analysis Pipeline for Plant Phenotyping in Controlled Environments →

Abstract Advances in automation, imaging, and artificial intelligence have enabled large-scale plant phenotyping, but image analysis remains a critical bottleneck for crop improvement and biological discovery. We developed an integrated multispectral phenotyping framework using imagery from the Texas A&M AgriLife Precision Automated Phenotyping Greenhouse and expanded Plant Growth and Phenotyping (PGP v2) data across maize, cotton, rice, and sorghum. The pipeline integrates pseudo-RGB generation, plant detection and segmentation, image stitching, vegetation-index analysis, texture analysis, morphological trait extraction, and temporal comparison of image-derived features to quantify changes in plant structure, spectral reflectance, and texture over time. Among the evaluated segmentation approaches, SAM v3 provided the highest and most consistent accuracy across diverse crop structures, although it required greater computational time than classical methods. SAM2Long maintained plant-instance associations across vertically stacked frames, while Scale-Invariant Feature Transform (SIFT)-based stitching reconstructed plant mosaics when individual plants extended beyond a single field of view. For each plant and imaging date, the pipeline generated an 863-dimensional feature vector spanning vegetation indices, spectral statistics, texture descriptors, and morphological traits. The framework was evaluated through two case studies: treatment-level temporal analysis of mutagenized sorghum lines and cold-stress phenotyping of maize using a separate imaging system. In both studies, the extracted features supported statistical and multivariate analyses of phenotypic variation and enabled separation of plants based on treatmentor stress-related responses. The combined dataset and workflow provide structured, automated, and well-documented phenotypic analysis across multiple crops, experimental settings, and imaging systems for controlledenvironment plant science and crop improvement. Plain Language Summary Temporal imaging of plants in controlled environments helps scientists better understand growth and biological processes. However, analyzing large volumes of images has been limited by a lack of automated tools. Multispectral imagery captures additional information about plant pigments, structure, and stress beyond standard color images. We developed an automated analysis pipeline that identifies individual plants, tracks their growth over time, and measures traits such as height, area, shape, texture, and vegetation indices. Using artificial intelligence, the system efficiently processes thousands of images to provide consistent and repeatable measurements. By integrating engineering and plant biology, this work supports data-driven decisions for crop improvement and agricultural research.

Why it matches plant phenotyping methods植物画像から形態・スペクトル・テクスチャ形質を抽出する統合パイプラインの開発と評価が中心であり、植物フェノタイピング手法として明確に該当する。

abstractWe developed an integrated multispectral phenotyping framework

Advancements and prospects in key technologies for robotic pollination in greenhouse pepper breeding: a review. →

Robotic pollination represents a pivotal component of smart agriculture, with foundational architectures for target recognition, path planning, and motion control having been progressively established. However, developing an efficient and robust pollination system that integrates perception, decision-making, and execution within real-world scenarios remains confronted with complex challenges. This study systematically reviews recent advancements in the field and distills the core technical issues of greenhouse robotic pollination into three primary domains: target detection and pose estimation, end-effector design, and pollination strategies combined with motion control. Focusing on the visual perception of flowers, actuator architecture, and operational tactics, this review synthesizes existing academic findings to evaluate the state-of-the-art in flower detection and pose estimation, characterize diverse end-effector designs, and analyze the evolutionary trajectory of motion control techniques. Specifically, the analysis encompasses the impact of detection algorithms on recognition accuracy and robustness, the structural classification and performance attributes of pollination mechanisms, and the optimization of control strategies. Furthermore, the study categorizes global research backgrounds, technical methodologies, and paradigmatic system cases, offering a critical evaluation of experiences in constructing automated pollination systems. Despite these advances, current robotic pollination technologies for peppers (chili) face significant bottlenecks characterized by immature methods for precise flower detection and pose estimation, the need for optimized specialized end-effector designs, and insufficient robustness in decision-making systems under dynamic environmental conditions. To address these issues, future development should prioritize constructing diverse, large-scale flower image and pose datasets while developing detection algorithms adaptable to complex environments to achieve high-precision identification. Additionally, implementing this system requires a hierarchical architecture where perception drives adaptive actuation. Deep learning models must localize flower targets and assess maturity in real-time, feeding coordinates to path planners that generate collision-free trajectories through foliage. These trajectories are executed via multimodal motion control, synchronizing the rigid manipulator with soft end-effectors. By embedding tactile feedback into the machine learning loop, the system creates a unified sensorimotor framework. This enables dynamic force modulation based on physical resistance, ensuring precise, non-destructive pollination tailored to chili plants.

Why it matches plant phenotyping methods温室コショウの花の検出・姿勢推定など、植物器官の観測・形質抽出を中核とするロボット受粉技術のレビューであり、方法論的貢献が中心。

abstractThis study systematically reviews recent advancements in the field and distills the core technical issues of greenhouse robotic pollination into three primary domains: target detection and pose estimation, end-effector design, and pollination strategies combined with motion control.

An Integrated YOLOv7–Fuzzy Reasoning Framework for Interpretable and Robust Cantaloupe (Cucumis melo) Growth-Stage Assessment →

Abstract Background Precision agriculture increasingly relies on computer vision systems to monitor crop growth; however, most existing approaches remain limited to frame-level object detection and do not support agronomic decision-making under uncertainty. To address this limitation, this study develops an interpretable and robust framework for cantaloupe ( Cucumis melo ) growth-stage assessment by integrating deep learning–based visual perception with fuzzy reasoning. Results A YOLOv7 detector was fine-tuned to identify healthy leaves, wilted leaves, flowers, and fruits from greenhouse imagery collected across eleven cultivation cycles at three production sites. The detected class counts were temporally aggregated and used as inputs to a Mamdani-type fuzzy inference system encoding expert agronomic knowledge and growth-stage expectations. Experimental evaluation showed that YOLOv7 achieved the highest mAP@0.5 (0.771) and balanced precision–recall performance compared with other YOLO variants, while the fuzzy reasoning layer transformed noisy object-level outputs into consistent crop-condition states with associated confidence levels. Real-world deployment on an edge device further demonstrated the system’s ability to generate actionable alerts, such as “Check Flower” and “Abnormal Condition,” aligned with expected phenological trends. Conclusions The proposed framework advances beyond conventional detection pipelines by enabling decision-level crop assessment that is interpretable, temporally aware, and robust to visual uncertainty. This approach provides a practical decision-support tool for greenhouse crop monitoring and supports the broader adoption of intelligent, confidence-aware systems in precision agriculture.

Why it matches plant phenotyping methodsカンタロープの葉・花・果実を画像から検出し、時系列集約とファジー推論で生育段階・作物状態を推定する手法が研究の中心であり、検出精度と実運用も評価している。

abstractthis study develops an interpretable and robust framework for cantaloupe ( Cucumis melo ) growth-stage assessment by integrating deep learning–based visual perception with fuzzy reasoning.

Zone-Aware Greenhouse Control and Multitask Crop Yield Prediction Using ConvLSTM and EMMYP-Net →

In the new age of greenhouse management, smart space adaptive systems are required to allow environmental control and crop analytics. This study presents an end-to-end deep learning architecture for spatiotemporal prediction and control in agriculture, which enables seamless integration between the different components of a decision loop. A ConvLSTM model predicts zone-specific microclimate variations, and a Dueling DQN agent selects the optimal actions for irrigation, ventilation, and fertilization according to energy demand, emission prediction, and soil moisture balance. The proposed EMMYP-Net (Enhanced Multimodal Multitask Yield Prediction Network) involves a CNN-BiLSTM-attention architecture that combines visual canopy data with multi-sensor sequences to co-classify growth stages and estimate yield. Experimental tests in a 1,200 m² four-zone greenhouse showed remarkable improvements, as ConvLSTM decreased RMSE by 45±2.3% compared to ARIMA and by 31±1.8% compared to LSTM. EMMYP-Net achieved an accuracy of 96.0% for classification, as well as an R² of 0.912±0.007 in predicting yields. This process-integrated approach enhanced resource sustainability by achieving savings of 19.3% in energy, 16.5% in water, and 15.2% in fertilizers relative to a conventional system. Combining predictive control and crop intelligence offers a scalable basis for sustainable data-driven greenhouse management. The key novelty of this work lies in the seamless integration of ConvLSTM-based spatiotemporal forecasting with the EMMYP-Net multimodal crop analytics within a unified reinforcement-learning-driven decision loop, enabling both predictive control and biological feedback in real time.

Why it matches plant phenotyping methods視覚的キャノピー情報とマルチセンサー系列から生育段階と収量を推定するEMMYP-Netが技術的中核であり、植物の状態・形質の計測手法として評価されている。温室制御全体を扱うが、フェノタイピング部分も実質的に記述・検証されている。

abstractThe proposed EMMYP-Net (Enhanced Multimodal Multitask Yield Prediction Network) involves a CNN-BiLSTM-attention architecture that combines visual canopy data with multi-sensor sequences to co-classify growth stages and estimate yield.

Unified Few Shot Detection and Zero Shot Segmentation Framework for Ripe Strawberry Phenotyping →

Precision agriculture requires accurate fruit outlining to support automated harvesting and yield assessment. Manual pixel annotation limits scalability and slows deployment in farm environments. An annotation light approach is presented for ripe strawberry detection and instance segmentation across greenhouse and field imagery. The primary claim states reliable masks emerge from coupling few sample trained detectors with prompt driven foundation segmentation. A fast object locator trained with limited images provides region proposals, while a large pretrained segmenter generates masks without pixel supervision. Evaluation uses two datasets with controlled and natural conditions and reports precision recall, intersection over union, and Dice statistics. Results show high detection accuracy under sparse supervision and stable segmentation scores above 0.92 across datasets. These findings advance annotation efficient phenotyping by demonstrating scalability with minimal labeling effort. Applications include real time monitoring, ripeness assessment, and robotic harvesting support. Future work targets multiclass maturity analysis, improved occlusion handling, and multimodal sensing integration.

Why it matches plant phenotyping methodsイチゴ果実の検出・インスタンスセグメンテーションによる輪郭・成熟度推定手法を開発し、複数データセットで性能検証しており、表現型取得が研究の中心である。

abstractAn annotation light approach is presented for ripe strawberry detection and instance segmentation across greenhouse and field imagery.

Standardization and Comparative Evaluation of quick Inoculation Techniques for Screening Pigeonpea genotype Resistance to Phytophthora cajani. →

Phytophthora stem blight (PSB), caused by Phytophthora cajani, is a destructive disease of pigeonpea (Cajanus cajan L.) that can lead to complete crop loss under favorable conditions. Effective resistance breeding is constrained by the lack of reliable and reproducible screening methods. The present study aimed to standardize and compare artificial inoculation techniques for consistent induction of Phytophthora blight under controlled conditions. Ten inoculation methods targeting different infection pathways were evaluated in greenhouse pot experiments over two consecutive seasons (2023-24 and 2024-25) using susceptible (UPAS-120, ICP-7119, ICP-2376) and moderately resistant (KPBR-80-2-1, IPAC-79, IPAB-7-2-1-7) pigeonpea cultivars. Disease incidence was recorded to assess the efficiency and reproducibility of each technique. All methods successfully established infection; however, disease severity varied significantly among techniques and genotypes. The leaf-lamina inoculation method consistently produced the highest and most uniform disease incidence, recording 97.7% and 96.6% in the susceptible cultivar UPAS-120 and 83.3% and 86.6% in the moderately resistant cultivar KPBR-80-2-1 across the two seasons. Node inoculation emerged as the second most reliable method. The study identifies most efficient and quick, reproducible inoculation techniques that enable rapid and high-throughput resistance screening, providing a robust methodological framework to support pigeonpea breeding and Phytophthora blight management.

Why it matches plant phenotyping methods植物病害抵抗性の表現型（発病 incidence/severity）を取得する人工接種法を標準化・比較評価しており、フェノタイピング手法自体が中心である。

abstractThe present study aimed to standardize and compare artificial inoculation techniques for consistent induction of Phytophthora blight under controlled conditions.

Diversity of root system architecture and root-shoot biomass allocation in industrial hemp (Cannabis sativa L.). →

Roots are major contributors to nutrient acquisition, water absorption, and plant anchoring and stability. However, little is known about the root system of industrial hemp (Cannabis sativa L.), an increasingly important crop worth $16 billion annually. Hemp is commonly cultivated for grain as an oilseed, stalk biomass for fiber and industrial materials, but has also had growing interest for its carbon sequestration potential due to its reported deep rooting profile. The objectives of this research were to (1) phenotype a panel of 46 industrially-relevant hemp genotypes, (2) quantify the phenotypic differences of shoot and root traits through 2D image analysis, (3) and to investigate genotype grouping strategies and gene targets that could be useful for crop improvement. To phenotype the root system architecture of multiple hemp genotypes representative of production hemp, a large format raised-bed was developed in a greenhouse in which hemp was planted in rows. Root and shoot traits varied across genotypes, with a difference of 175% in total root length between the largest and smallest genotype, and heritability values ranging from 0.51 to 0.88 for key root traits. A strong positive correlation was found between root and shoot biomass (R = 0.93) suggests coordinated resource allocation strategies across genotypes. Of the 46 genotypes studied, two genotypes consistently showed the greatest differences across most of the traits analyzed in the panel. A root-to-shoot quadrant framework was applied to classify hemp ideotypes based on biomass allocation and architectural traits. In addition, comparative genomic analysis identified 74 candidate root architecture genes in hemp that are orthologous to known regulators in maize, rice, and Arabidopsis. These findings highlight substantial phenotypic diversity in hemp root systems and provide a foundation for developing genotype grouping strategies and selecting breeding targets for mapping populations.

Why it matches plant phenotyping methods複数遺伝子型の根系形態を2D画像解析で定量し、温室内の大規模 raised-bed フェノタイピング基盤も開発しているため、植物形質取得が研究の中心である。

abstractTo phenotype the root system architecture of multiple hemp genotypes representative of production hemp, a large format raised-bed was developed in a greenhouse

From pixels to points: An AI framework with weaker-and-fewer-labels for lightweight 3D phenotyping using 2D-3D coordinate mapping and VLMs →

3D phenotyping of seedlings is crucial to tomato cultivation in greenhouse facilities. Current studies focus on high-quality point cloud reconstruction and artificial intelligence (AI) 3D segmentation to derive phenotypic traits like plant height and crown width, which heavily rely on manual annotation and possess high complexity in deployment. This study proposes a novel AI framework from pixels to points, for efficient 3D plant phenotyping of tomato seedlings. Through the integration of 2D-3D coordinate mapping and AI vision language models, the proposed method enables accurate reconstruction and analysis of 3D phenotypic traits from single-view data. Top-down RGB images and corresponding point clouds with spatial alignment are captured using a binocular camera. Vision language models are employed with the text prompt “plant” to automatically generate bounding boxes and masks, thereby minimizing manual annotation. These outputs are further transferred to a lightweight YOLO11-segment model. The core innovation is established in our 2D-3D mapping strategy, through which plant-specific 3D points are efficiently extracted using only 2D masks. Non-plant points within initial masks are repurposed to determine ground height for improved plant height estimation, while masks are refined using the Excess Green Index to enhance crown width measurement. An mAP₅₀ of 96.0% is achieved by the YOLO11-segment model. Concerning sparse canopy, highly accurate results are yielded by our phenotyping approach, with RMSE values of 1.7 cm for plant height and 1.0 cm for crown width, and R 2 values of 0.93 and 0.95 against manual measurements. For dense canopy, the usage of a reference chessboard improves the performance (RMSE was reduced from 9.57 cm to 2.07 cm). Annotation dependency is significantly reduced, computational complexity is decreased, edge deployment is supported, and efficient technology transfer is enabled by the presented method. Considerable potential is offered for high-throughput screening of elite tomato varieties with desirable agronomic traits. • Real-time low-cost 3D phenotyping of tomato plants is proposed. • Weak labels simplify the 3D plant segmentation. • Segment the 3D point cloud using 2D pixel-masks with spatial alignment. • Vision language models and knowledge transfer further simplify the AI application.

Why it matches plant phenotyping methodsトマト苗の3D表現型を抽出する画像・点群・AI統合手法を開発し、手動測定との精度検証も行っており、表現型取得法が研究の中心である。

abstractThis study proposes a novel AI framework from pixels to points, for efficient 3D plant phenotyping of tomato seedlings.

Leaf color skewed-distribution parameters enhance the stability of phenotype-environment model across different growth cycles of cabbage →

Greenhouse cultivation enables high yields through multi-cropping under controlled environments. Research on the association between crop growth and environmental meteorological factors is crucial for achieving precise dynamic regulation of environmental factors and efficient crop growth management within greenhouse. To address the stability problems of inversion model of crop phenotype-accumulated temperature during different sowing dates, this study analyzed the relationship between color skewed-distribution parameters of cabbage canopy and environmental accumulated temperature during different sowing dates. Three types of canopy color parameters (depth, distribution, and mixed parameters) were used as independent variables to construct inversion models of canopy color-accumulated temperature, and the model’s stability was tested across various growth cycles. The results showed that the skewed-distribution parameters of canopy images were significantly correlated with the environmental accumulated temperature, and the correlation coefficient was generally above 0.8. Among the models, the one using distribution parameters as the main independent variable demonstrated the highest fitting accuracy. For the same sowing date, the fitting accuracy was 87.11% and 91.16%, while for different sowing dates, it remained approximately 85%. These findings provide a useful theoretical basis and practical reference for stable and accurate inversion of accumulated temperature based on crop canopy color phenotype during different growth cycles, offering new insights for intelligent, high-quality and efficient management of facility agriculture.

Why it matches plant phenotyping methodsキャベツ冠層画像の色パラメータから積算温度を推定するモデルを構築し、異なる作型・生育周期で安定性を検証しており、表現型取得・推定手法が研究の中心です。

abstractThree types of canopy color parameters (depth, distribution, and mixed parameters) were used as independent variables to construct inversion models of canopy color-accumulated temperature, and the model’s stability was tested across various growth cycles.

Transferability and Robustness in Proximal and UAV Crop Imaging →

AI-driven imaging is becoming central to crop monitoring, with proximal and unmanned aerial vehicle (UAV) platforms now routinely used for disease and stress detection, yield estimation, canopy structure, and fruit counting. Yet, as these models move from plots to farms, the main bottleneck is no longer raw accuracy but robustness under distribution shift. Systems trained in one field, season, cultivar, or sensor often fail when the scene, sensor, protocol, or timing changes in realistic ways. This review synthesizes recent advances on robustness and transferability in proximal and UAV imaging, drawing on a corpus of 42 core studies across field crops, orchards, greenhouse environments, and multi-platform phenotyping. Shift types are organized into four axes, namely scene, sensor, protocol, and time. The article also maps the empirical evidence on when RGB imaging alone is sufficient and when multispectral, hyperspectral, or thermal modalities can potentially improve robustness. This serves as a basis to synthesize acquisition and evaluation practices that often matter more than architectural tweaks, which include phenology-aware flight planning, radiometric standardization, metadata logging, and leave-one-field/season-out splits. Adaptation options are consolidated into a practical symptom/remedy roadmap, ranging from lightweight normalization and small target-set fine-tuning to feature alignment, unsupervised domain adaptation, style translation, and test-time updates. Finally, a benchmark and dataset agenda are outlined with emphasis on object-oriented splits, cross-sensor and cross-scale collections, and longitudinal datasets where the same fields are followed across seasons under different management regimes. The goal is to outline practices and evaluation protocols that support progress toward deployable and auditable systems, noting that such claims require standardized out-of-distribution testing and transparent reporting as emphasized in the benchmark specification and experiment suite proposed here.

Why it matches plant phenotyping methods植物の近接・UAV画像による病害・ストレス・収量・キャノピー構造・果実数の推定について、頑健性、転移性、取得・評価プロトコル、ベンチマークを体系化する方法論レビューであり、フェノタイピング手法が中心です。

abstractThis review synthesizes recent advances on robustness and transferability in proximal and UAV imaging, drawing on a corpus of 42 core studies across field crops, orchards, greenhouse environments, and multi-platform phenotyping.

Characterising Multi-Pathogen Grapevine Dieback in Subtropical Australia: Field Symptomatology and Fungal Morphology Reveal Dominance of Botryosphaeriaceae and Phomopsis Species →

Grapevine trunk diseases in subtropical climates show complex patterns of multi-pathogen co-infection and spatial clustering, while current diagnosis still relies mainly on expert judgement with limited quantification and functional testing. This study investigated an 18-acre vineyard in south-eastern Queensland and used 7,440 vine records from 744 plots to build quantitative indices for symptoms and cross-section necrosis, followed by comprehensive characterisation of 46 fungal isolates through isolation, microscopy, physiological assays and greenhouse pathogenicity tests. Analyses identified three spatial disease regions, with wedge- and semi-ring-shaped necrosis strongly enriched in high-disease plots, and showed that Botryosphaeriaceae and Phomopsis groups dominated the pathogen community and had much higher composite pathogenicity indices than other fungi. Even without molecular data, the integrated pipeline of disease quantification, microscopic and physiological traits, pathogenicity testing and computational analysis allowed robust identification of dominant pathogen combinations in a subtropical vineyard and provided a methodological basis for regional risk assessment and targeted management.

Why it matches plant phenotyping methodsブドウ樹の症状と壊死を定量化する指標および統合解析パイプラインが研究の中心で、植物の病害状態を直接測定・評価しているため。

abstractused 7,440 vine records from 744 plots to build quantitative indices for symptoms and cross-section necrosis

Water status diagnosis in greenhouse drip-irrigated tomato and celery using leaf turgor dynamics and machine learning. →

Introduction Accurate crop water status monitoring is crucial for optimized irrigation in controlled environments, but traditional approaches relying on damaging measurements or sporadic sampling frequently restrict real-time evaluation. Methods This study explored the non-invasive leaf patch clamp pressure (LPCP) probe to evaluate the water status of drip-irrigated tomato and celery. Leaf turgor dynamics analysis enabled the characterization of the LPCP probe's output parameter (P p ) and its environmental drivers, and the development of predictive machine learning models. Results The results indicated that diurnal patterns of P p in drip-irrigated tomato and celery exhibited two distinct states: State I (unimodal) and State II (troughed), corresponding to moisture conditions with no or mild stress, and severe stress, respectively. The soil water content (SWC) thresholds for State I were set at SWC > 20% (tomato) and SWC > 19% (celery), whereas those for State II were set at SWC p was positively associated with solar radiation but negatively associated with SWC (in tomato) and wind speed (in celery). For State II, the associations between P p and environmental parameters were less than those in State I. Interestingly, compared to full irrigation, non-full irrigation treatments not only showed a higher proportion of State II but also resulted in an increase in both P p,max and P p,min by 15.39%-138.39% in tomato and 3.44%-94.02% in celery. These analytical results yielded four model parameter combinations based on the inclusion of SWC and the management of distinct P p states. The prediction model that integrated Combination 4 (substate P p prediction based on meteorological factors and SWC) with the random forest approach exhibited the highest accuracy (R 2 = 0.995, MSE = 2.419, RMSE = 1.540, and MAE = 0.531), with SWC identified as its key feature parameter. Discussion These findings provide a scientific foundation for optimizing the precision irrigation of greenhouse vegetables in drip systems.

Why it matches plant phenotyping methodsLPCPプローブによる葉の膨圧動態（水分状態）の非破壊測定と、機械学習による予測モデル開発が研究の中心であり、植物生理状態を抽出するフェノタイピング手法に該当する。

abstractThis study explored the non-invasive leaf patch clamp pressure (LPCP) probe to evaluate the water status of drip-irrigated tomato and celery.

Lightweight Vision-Transformer Network for Early Insect Pest Identification in Greenhouse Agricultural Environments. →

This study addresses the challenges of early recognition of fruit and vegetable diseases and pests in facility horticultural greenhouses and the difficulty of real-time deployment on edge devices, and proposes a lightweight cross-scale intelligent recognition network, Light-HortiNet, designed to achieve a balance between high accuracy and high efficiency for automated greenhouse pest and disease detection. The method is built upon a lightweight Mobile-Transformer backbone and integrates a cross-scale lightweight attention mechanism, a small-object enhancement branch, and an alternative block distillation strategy, thereby effectively improving robustness and stability under complex illumination, high-humidity environments, and small-scale target scenarios. Systematic experimental evaluations were conducted on a greenhouse pest and disease dataset covering crops such as tomato, cucumber, strawberry, and pepper. The results demonstrate significant advantages in detection performance, with mAP@50 reaching 0.872, mAP@50:95 reaching 0.561, classification accuracy reaching 0.894, precision reaching 0.886, recall reaching 0.879, and F1-score reaching 0.882, substantially outperforming mainstream lightweight models such as YOLOv8n, YOLOv11n, MobileNetV3, and Tiny-DETR. In terms of small-object recognition capability, the model achieved an mAP-small of 0.536 and a recall-small of 0.589, markedly enhancing detection stability for micro pests such as whiteflies and thrips as well as early-stage disease lesions. In addition, real-time inference performance exceeding 20 FPS was achieved on edge platforms such as Jetson Nano, demonstrating favorable deployment adaptability.

Why it matches plant phenotyping methods植物の病変・病害状態を画像から検出する軽量モデルの開発と性能評価が中心であり、単なる生物学的実験の routine 測定ではない。害虫検出も含むが、早期病変検出という植物状態の推定を技術的に評価しているため含める。

abstractproposes a lightweight cross-scale intelligent recognition network, Light-HortiNet, designed to achieve a balance between high accuracy and high efficiency for automated greenhouse pest and disease detection.

Agricultural robot plant automatic detection integrating visual navigation and phenotype recognition →

With the continuous improvement of the intelligence level of facility agriculture, agricultural robots are undertaking more and more autonomous tasks in greenhouse environments, and the multifunctional integration of visual perception systems has become a key technological bottleneck. A perception system for agricultural robots that integrates visual navigation and phenotype recognition is developed to address issues such as path recognition being susceptible to environmental interference and poor real-time plant detection. The system consists of a path navigation module and a plant detection module. The former introduces an image segmentation method based on visual transformation structure to extract agricultural path information. The latter adopts a lightweight instance segmentation structure to achieve precise segmentation and structural localization of crop phenotype regions. In the navigation model test, in the rain and fog disturbance scene, the average delay is 51.0 ms, the frame rate is 44.2 FPS, and the control jitter amplitude is 1.36°. The test results of the detection module show that its boundary F1 values for Tomato, Cucumber, Pepper, and Lettuce crops are 90.2%, 87.6%, 88.8%, and 86.3%, respectively. The experimental results show that the proposed scheme reduces inference delay while ensuring accuracy, has good environmental adaptability and edge deployment potential, and demonstrates good robustness and practicality in complex greenhouse environments.

Why it matches plant phenotyping methods植物の表現型領域を画像分割・認識する手法を開発し、複数作物で精度と実時間性能を評価しており、表現型取得が中心的な技術貢献です。

abstractA perception system for agricultural robots that integrates visual navigation and phenotype recognition is developed

A lightweight hybrid transformer approach for hyperspectral imaging-based drought tolerance evaluation in tea plants. →

Background In Shandong Province of China, where annual precipitation is below 800 mm, tea plants face persistent drought stress exacerbated by global warming. Breeding drought-tolerant tea cultivars is one of the effective ways to cope with this challenge. However, traditional breeding approaches are still limited by prolonged cycles, low efficiency, and subjective evaluation. To overcome these limitations, the development of rapid and objective germplasm evaluation methods has become critical‌. Results In this study, hyperspectral images of leaves from 12 widely cultivated 'Lucha series' tea cultivars in Shandong Province during different drought periods were collected, and the drought-related physiological indicators were measured simultaneously. Then, a tea drought tolerance index (TDTI) with enhanced accuracy was established by integrating the rate of change of indicators with temporal weights and indicator weights. Subsequently, we developed a novel lightweight Transformer-based hybrid integrated architecture to establish prediction models for the physiological indicators and TDTI. The Transformer-based models synergistically combined a Transformer encoder with XGBoost and LightGBM within a lightweight framework that leverages ensemble learning, data augmentation, and regularization to ensure robustness on limited datasets. Finally, we compared the performance of Transformer-based models against traditional machine learning models.​ The optimal models for MRP, MDA, Pro, SS, ChlT and TDTI were identified as 1D-CARS-TF, 2D-UVE-SVM, 2D-UVE-BRR, 2D-CARS-SVM, 1D-UVE-TF-CNN, and 2D-UVE-TF, respectively, achieving determination coefficient (R²) of 0.8992, 0.8307, 0.8929, 0.8373, 0.7894, and 0.7614, on an independent test set.​ The results demonstrated that the lightweight Transformer-based models equipped with multi-head self-attention mechanism exhibited outstanding capabilities in processing indicators requiring multi-band correlation mining. ​​Simultaneously, feature selection algorithms and overfitting-mitigation optimization strategies played a critical role in enhancing both the accuracy and stability of the Transformer-based models.​. Conclusions This study established a robust technical foundation for rapid, accurate, and non-destructive comprehensive evaluation of drought tolerance for tea plant germplasm resources. However, it should be noted that they were based on a specific set of greenhouse-cultivated samples, and further validation under field conditions with expanded germplasm resources would strengthen generalizability. Anyway, the demonstrated potential of the Transformer-based model in our study advances phenomics of tea plants toward greater intelligence and efficiency.

Why it matches plant phenotyping methods茶植物葉のハイパースペクトル画像から生理指標と干ばつ耐性指数を推定するモデルを開発・独立検証しており、植物フェノタイピング手法が中心である。

abstractwe developed a novel lightweight Transformer-based hybrid integrated architecture to establish prediction models for the physiological indicators and TDTI

Noninvasive Sensing of Foliar Moisture in Hydroponic Crops Using Leaf-Based Electric Field Energy Harvesters →

Large-scale wireless sensor networks with electric field energy harvesters (EFEHs) offer self-powered, eco-friendly, and scalable crop monitoring in hydroponic greenhouses. However, their practical adoption is limited by the low power density of current EFEHs, which restricts the reliable operation of external sensors. To address this challenge, this work presents a noninvasive EFEH assembled with hydroponic leafy vegetables that harvests electric field energy and estimates plant functional traits directly from the electrical response. The device operates through electrostatic induction produced by an external alternating electric field, which induces surface charge redistribution on the leaf. These charges are conducted through an external load, generating an AC voltage whose amplitude depends on the dielectric properties of the leaf. A low-voltage prototype was designed, built, and evaluated under controlled electric field conditions. Two representative species, Beta vulgaris (chard) and Lactuca sativa (lettuce), were electrically characterized by measuring the open-circuit voltage (VOC) and short-circuit current (ISC) of EFEHs. Three regression models were developed to determine the relationship between foliar moisture content (FMC) and fresh mass with electrical parameters. Empirical results disclose that the plant functional traits are critical predictors of the electrical output of EFEHs, achieving coefficients of determination of R2=0.697 and R2=0.794 for each species, respectively. These findings demonstrate that EFEHs can serve as self-powered, noninvasive indicators of plant physiological state in living leafy vegetable crops.

Why it matches plant phenotyping methods葉の電気応答を用いて葉面水分量と生体重量を推定する非侵襲センシング手法を開発・評価しており、植物表現型の取得が研究の中心である。

abstractthis work presents a noninvasive EFEH assembled with hydroponic leafy vegetables that harvests electric field energy and estimates plant functional traits directly from the electrical response.

IoT-Based Solar Powered Smart Pesticide Sprinkling System Determined by Plant Infection Level for Home Gardening and Greenhouses →

This paper introduces a solar-powered, IoT-enabled smart pesticide-spraying system designed for accurate pest management in small-scale environments such as home gardens and greenhouse setups. Traditional sprayers apply chemicals uniformly, which often leads to unnecessary pesticide usage. In contrast, the proposed system minimizes wastage by directing the spray only to areas that genuinely require treatment. An ESP32-CAM module continuously observes plant conditions by capturing leaf images and evaluating them for early indications of disease, nutrient stress, or pest activity. When the system detects an abnormal region, it automatically activates the pump to deliver pesticide precisely to the affected spot. The entire setup is powered through a 10-watt solar panel paired with a 12-volt battery, ensuring uninterrupted operation even in remote or off-grid locations. IoT connectivity allows users to monitor plant health, system status, and spraying activity from a distance, improving convenience and safety. By applying chemicals only when and where needed, the system is capable of cutting pesticide consumption by roughly 30–40%. It also lowers manual effort and reduces human exposure to toxic substances. Overall, this approach efficient, intelligent maintaining plant health and managing pests. By merging automation, renewable energy, and intelligent image-based detection, the system represents a forward-looking solution for modern plant care. It not only enhances plant protection but also encourages responsible pesticide use, making it a valuable tool for both hobbyists and small agricultural operations.

Why it matches plant phenotyping methods植物葉画像から病害・栄養ストレス・害虫活動の異常領域を検出し、検出結果に基づき局所散布する画像ベースの植物状態取得システムが中心であるため、植物フェノタイピングの応用として含める。

abstractAn ESP32-CAM module continuously observes plant conditions by capturing leaf images and evaluating them for early indications of disease, nutrient stress, or pest activity.

AI-Driven Smart Farming for Automated Plant Health Monitoring and Nutrient Deficiency Detection →

Precision agriculture is transitioning to continuous, data-driven monitoring. Affordable sensors and edge intelligence enable near real-time crop oversight. Manual scouting is labor-intensive and inconsistent. Delayed detection of nutrient stress leads to increased yield loss and input waste. Legacy systems monitor soil or weather in isolation and depend on periodic human checks. Vision pipelines often use shallow models and are not connected to field actuators. Proposed work: We combine soil moisture, temperature, and humidity sensing with camera-based leaf analysis using a DenseNet 121 classifier. A microcontroller executes closed-loop irrigation and localized cooling, with a mobile app for telemetry and alerts. RGB leaf images were captured in field conditions and labeled by experts into healthy and deficiency classes. Images were resized to 224×224 and split into training, validation, and test sets by plot to avoid leakage. DenseNet 121 achieved 89.0% accuracy on a held-out test set and surpassed a MobileNet V2 baseline of 82.0% under identical training conditions. Prototype deployments reduced manual checks and improved response to moisture and heat stress. The integrated IoT and AI pipeline is practical for early detection of nutrient deficiencies and autonomous actuation in small plots and greenhouses.

Why it matches plant phenotyping methods葉画像から植物の健康状態・栄養欠乏を推定する画像解析手法を開発し、データ分割、ベースライン比較、独立テストで性能評価しているため、フェノタイピング手法が中心的です。

abstractcamera-based leaf analysis using a DenseNet 121 classifier

Semi-automated image analysis of root architecture and early root development in faba bean and white clover and genomic estimation of breeding values and correlations →

Abstract Protein-rich leguminous plants, such as faba bean and white clover are prospectively interesting crops in the North-European countries for reducing dependence on soybean import. Significant expansion of the production area of leguminous crops is challenged by the sub-optimal climatic conditions in this region, especially by the increasing probability of year-to-year fluctuation of extreme weather conditions due to global climate change. To overcome these challenges, development of new climate-resilient varieties suitable for growing under Northern-European conditions are needed. Root architecture and early root development, as well as the availability of efficient root phenotyping technologies are crucial factors of advancing in breeding of adequate varieties. We report a study of a simple and affordable screening technology of early root development using rhizoboxes in connection with semi-automated image analysis and provide a conceptual pipeline for estimation of Genomic Estimated Breeding Values (GEBVs) and correlating greenhouse and field phenotype data. Based on bivariate models, high genetic correlation (r=0.83) could be detected between total root length values recorded in greenhouse rhizobox experiments and field grain yield in faba bean. In white clover, moderately positive genetic correlation (r=0.17) between estimated breeding values of rhizobox-detected total root length and field yield could be identified. Our results suggest that phenotyping and selection of early root development components could potentially be useful in breeding programs to increase the genetic gain for field yield.

Why it matches plant phenotyping methods根系形態を対象に、rhizoboxと半自動画像解析による早期根発達の表現型取得技術を提示し、育種価推定へのパイプラインも示しているため、フェノタイピング手法が中心的である。

abstractWe report a study of a simple and affordable screening technology of early root development using rhizoboxes in connection with semi-automated image analysis and provide a conceptual pipeline for estimation of Genomic Estimated Breeding Values (GEBVs) and correlating greenhouse and field phenotype data.

Plant-specific crop evapotranspiration estimation system for greenhouse tomatoes using convolutional neural network and rail-based monitoring device →

Accurately estimating individual plant evapotranspiration is essential for precise management and sustainable resource use in greenhouse cultivation. Integrating evapotranspiration models with crop-monitoring devices capable of acquiring images and solar radiation data may enable plant-level estimation of crop evapotranspiration. In this study, a plant-specific crop evapotranspiration estimation system was developed for hydroponic tomato cultivation in greenhouses during the harvest season. The evapotranspiration was estimated using a simplified Penman–Monteith model based on the leaf area index (LAI), solar radiation, air temperature, and relative humidity. The model was subsequently generalized through z-score normalization. To acquire side-view RGB images of individual tomato plants and measure the solar radiation distribution, a rail-based crop-monitoring device was employed. A ResNet-based convolutional neural network model was developed to estimate the LAI from the acquired images. The images were augmented via permutations with repetition to enhance the model’s accuracy. An image-merging method and a You Only Look Once version 8 Nano-based object detection model were used for rapid and automated image acquisition. The system calculated the crop evapotranspiration for each plant, and its performance was evaluated in a tomato cultivation greenhouse. Validation tests revealed strong correlations between the estimated and measured LAI (R² = 0.89, RMSE = 0.06) and between the predicted and actual evapotranspiration values (R² = 0.88, RMSE = 26.43 g h⁻¹ plant⁻¹). Distribution maps for the LAI and evapotranspiration were generated using the developed system. The system can accurately assess plant-specific evapotranspiration, thereby supporting precision crop management and helping improve productivity in greenhouse cultivation.

Why it matches plant phenotyping methods個体別のLAI画像推定と蒸発散量推定を中核とする監視システムを開発し、実測値との相関で検証しているため、植物表現型取得・推定手法として対象に含める。

abstracta plant-specific crop evapotranspiration estimation system was developed for hydroponic tomato cultivation in greenhouses

DELTA-SoyStage: A Lightweight Detection Architecture for Full-Cycle Soybean Growth Stage Monitoring. →

The accurate identification of soybean growth stages is critical for optimizing agricultural interventions, where mistimed treatments can result in yield losses ranging from 2.5% to 40%. Existing deep learning approaches remain limited in scope, targeting isolated developmental phases rather than providing comprehensive phenological coverage. This paper presents a novel object detection architecture DELTA-SoyStage, combining an EfficientNet backbone with a lightweight ChannelMapper neck and a newly proposed DELTA (Denoising Enhanced Lightweight Task Alignment) detection head for soybean growth stage classification. We introduce a dataset of 17,204 labeled RGB images spanning nine growth stages from emergence (VE) through full maturity (R8), collected under controlled greenhouse conditions with diverse imaging angles and lighting variations. DELTA-SoyStage achieves 73.9% average precision with only 24.4 GFLOPs computational cost, demonstrating 4.2× fewer FLOPs than the best-performing baseline (DINO-Swin: 74.7% AP, 102.5 GFLOPs) with only 0.8% accuracy difference. The lightweight DELTA head combined with the efficient ChannelMapper neck requires only 8.3 M parameters-a 43.5% reduction compared to standard architectures-while maintaining competitive accuracy. Extensive ablation studies validate key design choices including task alignment mechanisms, multi-scale feature extraction strategies, and encoder-decoder depth configurations. The proposed model's computational efficiency makes it suitable for deployment on resource-constrained edge devices in precision agriculture applications, enabling timely decision-making without reliance on cloud infrastructure.

Why it matches plant phenotyping methods大豆の生育ステージという植物状態をRGB画像から推定する検出アーキテクチャを開発し、データセット、比較評価、アブレーション検証まで行っており、植物フェノタイピング手法が中心である。

abstractThis paper presents a novel object detection architecture DELTA-SoyStage, combining an EfficientNet backbone with a lightweight ChannelMapper neck and a newly proposed DELTA (Denoising Enhanced Lightweight Task Alignment) detection head for soybean growth stage classification.

Data-driven localization of the TOMGRO model: Cultivar-specific parameter optimization for Shanghai greenhouse tomato production →

Crop models are an integral component in greenhouse control systems, enabling the simulation of plant responses to environmental conditions and facilitating optimal operational decisions for high productivity with low energy use. However, existing crop models often lack transferability beyond their original development conditions. Additionally, cultivar-specific parameterization remains challenging, as some parameters can be empirically determined while others require complex calibration. This study adapted the reduced TOMGRO model to simulate growth and yield for four local tomato cultivars under Shanghai greenhouse conditions. Through Sobol’s global sensitivity analysis and Bayesian optimization, four highly influential parameters were identified and optimized, including growth efficiency (E), maintenance respiration coefficient (rₘ), extinction light coefficient (K), and leaf quantum efficiency (Qₑ). This combined approach provides an effective framework for model calibration, with the calibrated model achieving an average R² > 0.94 for node number, plant dry weight, fruit dry weight, and leaf area index predictions in all cultivars. Model validation using 2023–2024 greenhouse data confirmed model effectiveness for the target variables (average R² > 0.92 for cultivar QX and > 0.88 for LZ), whereas the model showed limitations in simulating mature fruit growth. This calibrated model offers reliable predictions of key growth variables, informing both plant breeding and greenhouse management.

Why it matches plant phenotyping methods作物モデルの感度分析・ベイズ最適化によるパラメータ校正と、植物成長形質予測の検証が研究の中心であり、再利用可能な計算フェノタイピング手法に該当する。

abstractThrough Sobol’s global sensitivity analysis and Bayesian optimization, four highly influential parameters were identified and optimized

A Cross-Crop and Cross-Regional Generalized Deep Learning Framework for Intelligent Disease Detection and Economic Decision Support in Horticulture →

In facility horticultural production, intelligent disease recognition and precise intervention are vital for crop health and economic efficiency. We construct a multi-source dataset from Bayan Nur, Weifang, and Honghe that integrates handheld camera photos, drone field images, and laboratory-controlled samples. Handheld images capture fine lesion texture for close-up diagnosis common in greenhouses; drone images provide canopy-scale patterns and spatial context suited to open-field management; laboratory images offer controlled illumination and background for stable supervision and cross-crop feature learning. Our objective is robust cross-crop, cross-regional diagnosis and economically rational control. To this end, a model named CCGD-Net is proposed. It is designed as a multi-task framework. The framework incorporates a multi-scale perception module (MSFE) to produce hierarchical representations. It includes a cross-domain alignment module (CDAM) that reduces distribution shifts between greenhouse and open-field environments. The training follows an unsupervised domain adaptation setting that uses unlabeled target-region images. When such images are not available, the model functions in a pure generalization mode. The framework also integrates a regional economic strategy module (RESM) that transforms recognition outputs and local cost information into optimized intervention intensity. Experiments show an accuracy of 91.6%, an F1-score of 89.8%, and an mAP of 88.9%, outperforming Swin Transformer and ConvNeXt; removing RESM reduces F1 to 87.2%. In cross-regional testing (Weifang training → Honghe testing), the model attains an F1 of 88.0% and mAP of 86.5%. These results indicate that integrating complementary imaging modalities with domain alignment and economic optimization provides an effective solution for disease diagnosis across greenhouse and field systems.

Why it matches plant phenotyping methods植物病斑・冠層画像から病害状態を推定するマルチモーダル深層学習法を開発し、データセット、ドメイン適応、交差地域検証を含むため、植物フェノタイピング手法が中心である。

abstractWe construct a multi-source dataset from Bayan Nur, Weifang, and Honghe that integrates handheld camera photos, drone field images, and laboratory-controlled samples.

Explainable AI-driven interpretation of environmental drivers of tomato fruit expansion in smart greenhouses using IoT sensing. →

Tomato fruit expansion is a key physiological process that determines fruit size, marketability, and yield, yet its quantitative and threshold-based response to microclimatic factors in smart greenhouses has been insufficiently studied. This study develops an IoT-driven sensing framework combined with explainable artificial intelligence (XAI) to interpret the environmental drivers of fruit expansion. A robust environmental monitoring system continuously captured key factors including air and soil temperature, humidity, light intensity, CO 2 concentration, soil moisture, and soil electrical conductivity. These variables were fed into a Random Forest regression model enhanced with SHapley Additive exPlanations (SHAP) and Partial Dependence Plots (PDPs) for interpretability. Results revealed that soil temperature (~ 21.8 °C), light intensity, and soil electrical conductivity were the most influential drivers of fruit expansion, each exhibiting distinct threshold behaviors, and the proposed IoT-XAI framework achieved R 2 = 0.82 with an MSE of 0.0046, confirming both predictive accuracy and interpretability. Our approach transforms raw sensor data into actionable insights for precision climate and fertigation management, supporting sustainable smart agriculture through interpretable machine learning.

Why it matches plant phenotyping methodsトマト果実の膨張という植物形質を対象に、IoTセンシングと機械学習・XAIによる推定および環境要因解析を中心的に行っているため、フェノタイピング手法の応用として含める。

abstractThis study develops an IoT-driven sensing framework combined with explainable artificial intelligence (XAI) to interpret the environmental drivers of fruit expansion.

Tomato Growth Monitoring and Phenological Analysis Using Deep Learning-Based Instance Segmentation and 3D Point Cloud Reconstruction →

Accurate and nondestructive monitoring of tomato growth is essential for large-scale greenhouse production; however, it remains challenging for small-fruited cultivars such as cherry tomatoes. Traditional 2D image analysis often fails to capture precise morphological traits, limiting its usefulness in growth modeling and yield estimation. This study proposes an automated phenotyping framework that integrates deep learning-based instance segmentation with high-resolution 3D point cloud reconstruction and ellipsoid fitting to estimate fruit size and ripeness from daily video recordings. These techniques enable accurate camera pose estimation and dense geometric reconstruction (via SfM and MVS), while Nerfacto enhances surface continuity and photorealistic fidelity, resulting in highly precise and visually consistent 3D representations. The reconstructed models are followed by CIELAB color analysis and logistic curve fitting to characterize the growth dynamics. When applied to real greenhouse conditions, the method achieved an average size estimation error of 8.01% compared to manual caliper measurements. During summer, the maximum growth rate (gmax) of size and ripeness were 24.14%, and 95.24% higher than in winter, respectively. Seasonal analysis revealed that winter-grown tomatoes matured approximately 10 days later than summer-grown fruits, highlighting environmental influences on phenological development. By enabling precise, noninvasive tracking of size and ripeness progression, this approach is a novel tool for smart and sustainable agriculture.

Why it matches plant phenotyping methods深層学習によるインスタンスセグメンテーション、3D再構成、色解析を統合し、トマト果実のサイズと成熟度を推定するフェノタイピング手法の開発・評価が中心である。

abstractThis study proposes an automated phenotyping framework that integrates deep learning-based instance segmentation with high-resolution 3D point cloud reconstruction and ellipsoid fitting to estimate fruit size and ripeness from daily video recordings.

Hyperspectral-based classification of individual wheat plants into fine-scale reproductive stages. →

Field trials play an essential role in developing genetically modified and genome-edited biotechnology plants, as they assess plant growth, yield, and potential unintended effects. Australian biotechnology field trials are regulated by federal protocols that mandate accurate forecasting of flowering times. Currently, this relies on labour-intensive and subjective visual field inspections of individual wheat plants at defined growth stages (Zadoks growth stages Z37, Z39, and Z41). To enable automatic forecasting, hyperspectral and red-green-blue (RGB) images were captured in the greenhouse, and hyperspectral reflectance data were acquired in a semi-natural environment. Support Vector Machine classification achieved F1 scores (0.832) for pre-anthesis growth stage classification through the combined use and systematic comparison of three spectral transformations, including Standard Normal Variate, Hyper-hue, or Principal Component Analysis, which together outperformed reliance on any single transformation. After feature selection, F1 scores (0.752) could be achieved with only five wavelengths. Furthermore, the SNV transformation demonstrated robust performance under limited training conditions, maintaining high classification accuracy and strong generalizability across varying data sizes. These findings highlight the effectiveness of transformation-enriched data and optimized feature selection for accurate growth stage classification, providing a low-cost approach to reduce manual inspection burdens and strengthen biosafety during biotechnology field trial practices.

Why it matches plant phenotyping methodsハイパースペクトル/RGB画像と機械学習により、個体の小麦生育段階を自動推定する手法を開発・比較・検証しており、植物表現型取得が中心である。

abstractTo enable automatic forecasting, hyperspectral and red-green-blue (RGB) images were captured in the greenhouse, and hyperspectral reflectance data were acquired in a semi-natural environment.

Non-invasive imaging and biochemical profiling reveal genotypic variation in Tagetes erecta L. to cold stress →

Aim: This study aimed to establish a phenomic-based screening protocol for cold tolerance in African marigold (Tagetes erecta L.) by integrating non-invasive imaging with physiological and biochemical analyses, addressing the gap between field crop and ornamental breeding applications where cold stress significantly constrains cultivation by affecting growth, development, and productivity. Methodology: Ten marigold genotypes were evaluated under controlled polyhouse and natural cold stress conditions across two growing seasons. High-throughput plant phenotyping utilizing RGB, near-infrared, and thermal imaging quantified key traits including morphological characteristics (via RGB), tissue water content (via near-infrared), and thermal regulation (via thermal imaging), complemented by targeted physiological and biochemical analyses. Results: Significant genotypic variation was observed, as cold stress caused 70.7% reduction in plant area and 24.3% decrease in the photosynthetic rate. Genotype Af./W-4 exhibited superior cold tolerance through enhanced photosynthetic maintenance, minimal reductions in greenness (4.4%), membrane stability (11%), and photosynthetic rate (14.2%), followed by genotypes PB and Af./W-6. Multivariate analysis indicated that key determinants of cold stress performance include traits like plant area, caliper length, greenness, and photosynthetic rate. Interpretation: Integration of non-invasive imaging with biochemical analysis successfully differentiated cold-tolerant from the susceptible genotypes. This comprehensive approach provides an efficient screening methodology for identifying climate-resilient genotypes in ornamental crops, potentially accelerating cold-tolerant genotype development for sustainable floriculture production. Key words: African marigold, Cold tolerance, Genotypic-variation, High through put phenotyping, Tagetes erecta L.

Why it matches plant phenotyping methods非侵襲イメージングを用いた高スループット植物表現型解析とスクリーニングプロトコルの確立が中心であり、冷ストレス耐性の形質抽出・評価に実質的に関与している。

abstractThis study aimed to establish a phenomic-based screening protocol for cold tolerance in African marigold (Tagetes erecta L.) by integrating non-invasive imaging with physiological and biochemical analyses

Tracking plant growth using image sequence analysis →

Automated plant phenotyping can help to monitor the growth process of crops, eliminating the high costs associated with traditional manual approaches. Using low-cost devices (e.g., digital cameras), RGB images can be captured under field or greenhouse conditions to track various phenotypes. In this paper, we focused on a particular task – tracking plant growth by identifying and monitoring plant nodes in greenhouse-grown crops. We used a setup where a digital camera captured images at one-hour intervals, with object detection algorithms employed to facilitate rapid and cost-effective tracking of nodes. The main challenge addressed in this paper involved tracking nodes that were hidden temporarily caused by diurnal leaf movements– leaves obscure some nodes at different times throughout the day. Because a node may be hidden for a few hours but visible at other times during the day, one can predict its location while it is hidden. We proposed two approaches, clustering and linear interpolation, for estimating hidden node locations. We collected a set of greenhouse datasets for different crops and conducted empirical comparisons of our methods. Results showed that our approach predicted the node location with an average error of less than 4 cm. • Automated plant phenotyping reduces the cost of traditional manual monitoring. • Object detection handles challenges caused by leaf movement and occlusion. • Hidden node locations are predicted using clustering and linear interpolation. The proposed methods achieve an average prediction error of less than 4 centimeters.

Why it matches plant phenotyping methods植物ノードを画像から検出・追跡し、遮蔽時の位置を推定する手法の開発と比較検証が中心であり、再利用可能な植物表現型取得ワークフローに該当する。

abstractAutomated plant phenotyping can help to monitor the growth process of crops

Identification and selection of evaluation indices for soybean shade tolerance via high-throughput phenotyping platforms and machine learning →

• High-throughput phenotyping of 202 soybean accessions across two growth stages identified key shade tolerance indicators. • A two-stage framework assessed symbiotic shade tolerance, recovery ability, and overall performance. • Machine learning–based trait mining was validated across multiple environments. Intercropping is a promising cultivation strategy that enhances the sustainable use of water and land resources while contributing to national food and oil security. To improve the yield stability of soybeans in intercropping systems, there is an urgent need to develop a scientific and efficient framework for evaluating shade tolerance. In this study, we propose an integrated shade tolerance assessment method based on high-throughput phenotyping, multienvironment trials, and machine learning (ML) approaches. Utilizing multivariate analysis, we evaluated 202 soybean accessions and partitioned their performance under intercropping into two distinct capacities, namely, shade tolerance during the cogrowth stage and recovery ability during the independent growth stage, each of which was classified into five levels from weak to strong. Preliminary trait selection was performed through correlation analysis and broad-sense heritability estimation, followed by the application of six ML models to identify the key shade tolerance traits across different growth stages. The robustness and generalizability of the selected traits were validated in three environments—a field pot, an open field, and a greenhouse—using soybean varieties with known shade tolerance levels. The results revealed that three traits—the side canopy area (SCA), top canopy area at stage 3 (TCA3), and top-view mixed entropy (TME)—were strongly associated with shade-tolerant varieties. These traits presented two distinguishing features: significantly higher values under shaded conditions and greater increases during the recovery phase. The prediction models constructed with these three traits achieved strong performance, with coefficients of determination of R ²=0.776 for shade tolerance and R ²=0.959 for recovery ability. In summary, this study demonstrates the potential for integrating high-throughput phenotyping with ML to efficiently identify the key indicators of shade tolerance. By measuring only three indicators—SCA, TCA3, and TME—soybean shade tolerance at the seedling stage, recovery ability during later growth, and overall shade tolerance across the full growth period can be rapidly and accurately evaluated. This method offers a powerful and practical tool for implementing shade tolerance evaluations, gene discovery, and targeted breeding of soybean cultivars that are suitable for intercropping systems.

Why it matches plant phenotyping methods高スループット表現型解析と機械学習を統合し、画像由来の植物形質からダイズの遮陰耐性・回復能を評価する方法を提案・検証しており、表現型取得と抽出が研究の中心である。

abstractwe propose an integrated shade tolerance assessment method based on high-throughput phenotyping, multienvironment trials, and machine learning (ML) approaches.

Drought stress prediction in Camellia oleifera seedlings using a deep learning hybrid model with temporal-spatial feature fusion →

Camellia oleifera, a distinctive and economically vital woody oil species in China, holds significant ecological and economic importance. However, the increasing frequency and intensity of drought events due to global climate change severely threaten its growth and yield stability. This study established controlled drought conditions in a greenhouse environment, and measured Soil and Plant Analysis Development (SPAD) values of two-year-old grafted container-grown seedlings to assess chlorophyll content and photosynthetic potential. Substrate moisture content (Volumetric Water Content, VWC, %), substrate temperature (℃) at upper, middle, and lower container positions, as well as greenhouse air temperature (℃) and relative humidity (RH, %), were monitored. A hybrid deep learning model, Temporal Convolutional Network-Bidirectional Long Short-Term Memory with dual attention mechanisms (TCN-BiLSTM-D2), was developed to predict SPAD values using these environmental variables. Results identified a critical substrate moisture threshold: plant mortality reached 100 % when VWC dropped below 5 %. Substrate temperature exhibited strong positive correlations with air temperature (r = 0.85–0.86) but negative correlations with relative humidity (r = -0.55 to −0.56), while substrate moisture exhibited strong negative correlations with both air temperature and substrate temperature (r = -0.82 to −0.67) and positive correlation with relative humidity (r = 0.30–0.37). SPAD values were significantly correlated with moisture in the middle and lower substrate layers (r = 0.16–0.63). Cultivars CL40 and CL53 exhibited significant negative SPAD responses to rising temperatures (r = -0.36 to −0.06). The model incorporated Feature Focus Attention (FFA) and Multiple Soft Attention (MSA), collectively termed D2, to dynamically weight input features based on their predictive relevance. This enhancement achieved exceptional performance, with a coefficient of determination (R²) of 0.982, Mean Squared Error (MSE) of 0.001, and Mean Absolute Percentage Error (MAPE) of 3.79 %. The TCN-BiLSTM-D2 model substantially outperformed conventional methods, including Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), Recurrent Neural Network (RNN), and Temporal Convolutional Network (TCN). This framework enables non-destructive, high-throughput phenotypic monitoring and early warning of dynamic environmental stress, providing a robust tool for drought-resistance research in C. oleifera and practical support for the optimization of irrigation, the improvement of cultivation, and drought-tolerant breeding.

Why it matches plant phenotyping methodsSPADという植物生理形質を環境変数から推定する深層学習モデルを開発し、既存モデルとの性能比較・検証を行っており、表現型取得・推定手法が研究の中心である。

abstractA hybrid deep learning model, Temporal Convolutional Network-Bidirectional Long Short-Term Memory with dual attention mechanisms (TCN-BiLSTM-D2), was developed to predict SPAD values using these environmental variables.

Visual-language transformer-based tomato leaf disease detection for portable greenhouse monitoring device. →

Tomato leaf diseases pose a significant threat to global food security, necessitating accurate and efficient detection methods. This paper introduces the Tomato Leaf Disease Visual Language Model (TLDVLM), a novel approach based on the BLIP-2 architecture enhanced with Low-Rank Adaptation (LoRA), for precise classification of 10 distinct tomato leaf diseases. Our methodology integrates a sophisticated image preprocessing pipeline, utilizing GroundingDINO for robust leaf detection and SAM-2 for pixel-level segmentation, ensuring that the model focuses solely on relevant plant tissue. The TLDVLM leverages the powerful multimodal understanding of BLIP-2, with LoRA applied to its Q-Former module, enabling parameter-efficient fine-tuning without compromising performance. Comparative experiments demonstrate that the TLDVLM significantly outperforms baseline models, including CLIP-LoRA and ConvNeXT-tiny, achieving an accuracy of 97.27%, a precision of 0.9587, a recall of 0.9789, and an F1-score of 0.9681. Beyond classification, the finetuned TLDVLM checkpoints are integrated into a practical application for new image inference. This application displays the raw and segmented images, the predicted disease, and offers functionalities to fetch comprehensive information on disease causes and remedies using external APIs (e.g., OpenAI), with an option to download a PDF summary for offline access on a portable device. This research highlights the potential of LoRA-adapted Vision-Language Models in developing highly accurate, efficient, and user-friendly agricultural diagnostic tools.

Why it matches plant phenotyping methodsトマト葉の病害状態を画像から分類する手法を開発・比較評価しており、植物病害表現型の取得が中心である。

abstractThis paper introduces the Tomato Leaf Disease Visual Language Model (TLDVLM), a novel approach based on the BLIP-2 architecture enhanced with Low-Rank Adaptation (LoRA), for precise classification of 10 distinct tomato leaf diseases.

Non-Destructive Monitoring of Postharvest Hydration in Cucumber Fruit Using Visible-Light Color Analysis and Machine-Learning Models →

Water loss during storage is a major cause of postharvest quality deterioration in cucumber, yet existing methods to monitor hydration are often destructive or require expensive instrumentation. We developed a low-cost, non-destructive approach for estimating fruit relative water content (RWC) using visible-light color imaging combined with an ensemble machine-learning model (Random Forest). A total of 1200 fruits were greenhouse-grown, harvested at market maturity, and equally divided between optimal and ambient storage temperature (10 and 25 °C, respectively). Digital images were acquired at harvest and at 7 d intervals during storage, and color parameters from four standard color systems (RGB, CMYK, CIELAB, HSV) were extracted separately for the neck, mid, and blossom regions as well as for the whole fruit. During storage, fruit RWC decreased from 100% (fully hydrated condition) to 15.3%, providing a broad dynamic range for assessing color–hydration relationships. Among the 16 color features evaluated, the mean cyan component (μC) of the CMYK space showed the strongest relationship with measured RWC (R2 up to 0.70 for whole-fruit averages), reflecting the cyan region’s heightened sensitivity to dehydration-induced changes in pigments, cuticle properties and surface scattering. The Random Forest regression model trained on these features achieved a higher predictive accuracy (R2 = 0.89). Predictive accuracy was also consistently higher when μC was calculated over the entire fruit surface rather than for individual anatomical regions, indicating that whole-fruit color information provides a more robust hydration signal than region-specific measurements. Our findings demonstrate that simple visible-range imaging coupled with ensemble learning can provide a cost-effective, non-invasive tool for monitoring postharvest hydration of cucumber fruit, with direct applications in quality control, shelf-life prediction and waste reduction across the fresh-produce supply chain.

Why it matches plant phenotyping methodsキュウリ果実の相対含水量という植物状態を、可視光画像と機械学習で非破壊推定する手法を開発しており、表現型取得・推定が研究の中心である。

abstractWe developed a low-cost, non-destructive approach for estimating fruit relative water content (RWC) using visible-light color imaging combined with an ensemble machine-learning model (Random Forest).

Comparative assessment of genomic, phenomic, and metabolomic prediction models in biparental grapevine breeding populations →

Accelerating grapevine breeding for disease resistance and climate adaptation remains constrained by long generation cycles. We benchmarked genomic (SNP), phenomic (NIRS), and metabolomic (untargeted LC-MS) prediction for 24 agronomic traits in a biparental population phenotyped over three years. Seven statistical frameworks and four tissue x timepoint combinations (wood; vineyard leaves at budbreak and flowering; greenhouse leaves at flowering) were evaluated, together with feature-wise BLUPs across samples. Cross-year and cross-population analyses with two additional populations assessed temporal robustness and transferability. Genomic prediction was most accurate (up to r = 0.83), metabolomic prediction was intermediate (up to r = 0.59), and phenomic prediction was lowest (up to r = 0.39) despite its lower acquisition cost. Metabolite features were more heritable than NIR wavelengths, for which most unexplained variation remained residual under the fitted model. Multi-omics integration produced limited overall gains. These results support genomic selection as the primary approach, with metabolomic or phenomic screening considered only for traits and sampling designs that show reproducible predictive signal.

Why it matches plant phenotyping methodsブドウ育種集団の複数形質について、NIRSによるフェノミック測定を含む予測モデルを比較・検証し、交差年・集団で頑健性と転移性も評価しているため、形質推定法の技術的ベンチマークが中心である。

abstractWe benchmarked genomic (SNP), phenomic (NIRS), and metabolomic (untargeted LC-MS) prediction for 24 agronomic traits in a biparental population phenotyped over three years.

Early Detection and Quantification of Fusarium Wilt in Greenhouse-Grown Tomato Plants Using Water-Relation Measurements. →

Visual estimates of plant symptoms are traditionally used to quantify disease severity. Yet, the methodologies used to assess these phenotypes are often subjective and do not allow tracking of disease progression from very early stages. Here, we hypothesized that quantitative analysis of whole-plant physiological vital functions can be used to objectively determine plant health, providing a more sensitive way to detect disease. We studied the tomato wilt that is caused by Fusarium oxysporum f. sp. lycopersici . Physiological performance of infected and noninfected tomato plants was compared using a whole-plant pot-based lysimeter functional phenotyping system in a semi-environmentally controlled greenhouse. Water-balance traits of the plants were measured continuously and simultaneously in a quantitative manner. Infected plants exhibited early reductions in transpiration and biomass gain, which preceded visual disease symptoms. These changes in transpiration proved to be effective quantitative indicators for assessing both plant susceptibility to infection and virulence of the fungus. Physiological changes linked to fungal outgrowth and toxin release contributed to reduced hydraulic conductance during initial infection stages. The functional phenotyping method objectively captures early-stage disease progression, advancing plant disease research and management. This approach emphasizes the potential of quantitative whole-plant physiological analysis over traditional visual estimates for understanding and detecting plant diseases.

Why it matches plant phenotyping methods全植物の水収支を連続定量する機能的フェノタイピング法を用い、Fusarium萎凋病の早期進行と感受性を客観評価する手法が中心である。

abstractusing a whole-plant pot-based lysimeter functional phenotyping system

Severity of Charcoal Rot Disease in Soybean Genotypes Inoculated with Macrophomina phaseolina Isolates Differs Among Growth Environments. →

Charcoal rot of soybean caused by Macrophomina phaseolina is a major disease of economic significance around the world. The objective of this test is to evaluate and identify new method(s) that can identify resistant and susceptible (S) genotypes when inoculated with the fungus that causes charcoal rot in nonfield environments. Four independent experiments were performed to determine the variability in disease severity when soybean genotypes are inoculated with isolates up to a total of 100 different variants of the charcoal rot fungus in laboratory, greenhouse, and growth chamber tests. Linear mixed models were fit to area under the disease progress curve values from the four experiments and model predictions of disease progress were used to determine the best method to classify moderately resistant (MR) and S genotypes. In a growth chamber study using a modified cut-tip inoculation method, 28 of the 32 M. phaseolina isolates tested differentiated MR and S with >87% accuracy. In a study where 16 field-grown soybean genotypes were stem-wound inoculated with one isolate, the MR genotypes were correctly classified, but not all S genotypes were. Correct classification of MR genotypes dramatically increased with plant age, approaching 100% accuracy at 120 days after planting. In a study of stem-wound inoculation of field-grown soybean genotypes with 20 M. phaseolina isolates, MR were identified with more than half the isolates having >75% accuracy in detecting MR genotypes. In a study of greenhouse-grown soybeans stem-wound-inoculated with 100 isolates, classification was less accurate than samples grown in the field, with median correct classification P = 0.0006), and the rank correlations with the growth chamber study were weak. The results showed that, except for the growth chamber study, the nonfield environments did not consistently identify the same soybean lines as being S or MR to charcoal rot as were identified as in naturally infested field testing because of differences in isolates, environment, soybean varieties, and methods (or all the above). Stakeholders will benefit more from the use of the field assessment method in naturally infested soil to identify reliable sources of resistance than from the nonfield methods.

Why it matches plant phenotyping methodsダイズの炭腐病重症度を用いて、接種法・栽培環境・分離株による抵抗性判別法を比較検証しており、植物病害表現型の取得と分類性能が研究の中心である。

abstractThe objective of this test is to evaluate and identify new method(s) that can identify resistant and susceptible (S) genotypes when inoculated with the fungus that causes charcoal rot in nonfield environments.

Robust real-time strawberry maturity detection using UAV-mounted deep learning for precision agriculture. →

Background To address the challenge of real-time plant monitoring in greenhouse environments, this industry-driven research focuses on developing an autonomous quadrotor UAV system specifically designed for monitoring strawberry plants. Traditional methods for greenhouse monitoring are labor-intensive and lack scalability, particularly in precision agriculture applications. Method This research introduces a mature strawberry detection model specifically designed for greenhouse environments. The proposed YOLOv9-GLEAN approach enables the identification of small mature strawberries through an onboard camera mounted on the quadrotor. Additionally, a hybrid trajectory tracking controller for the quadrotor is developed and tested in both simulated and real-world conditions. The UAV navigates through the greenhouse using predetermined waypoints, operating as a semi-autonomous system for navigation while maintaining full autonomy in mature strawberry detection tasks. The system incorporates an integrated onboard vision platform that utilizes an innovative YOLOv9-GLEAN-based algorithm to perform real-time and offline detection and counting of mature strawberries. Results The YOLOv9-GLEAN model achieves high detection accuracy, as confirmed by evaluation metrics such as precision, recall, and F1-score. The proposed hybrid (PID+LQR) controller demonstrates superior tracking performance compared to other conventional controllers. The integrated control and perception system proves effective in both simulated and real-world greenhouse environments. Discussion The research validates the efficacy of deep learning models, with YOLOv9-GLEAN showing exceptional performance in enabling rapid, precise, and automated detection of ripe strawberries through quadrotor deployment in greenhouse environments. Such agricultural monitoring technologies represent a substantial advancement beyond conventional manual inspection approaches, empowering farmers and greenhouse operators to execute well-informed, time-sensitive management decisions that minimize crop losses and optimize production yields. This investigation underscores the revolutionary impact that deep learning technologies can have within greenhouse agriculture.

Why it matches plant phenotyping methodsイチゴ果実の成熟状態を画像から検出・計数する深層学習モデルとUAV搭載視覚プラットフォームの開発・評価が研究の中心であり、植物器官の状態を直接推定している。

abstractThis research introduces a mature strawberry detection model specifically designed for greenhouse environments.

Efficient View Planning Guided by Previous-Session Reconstruction for Repeated Plant Monitoring →

Repeated plant monitoring is essential for tracking crop growth, and 3D reconstruction enables consistent comparison across monitoring sessions. However, rebuilding a 3D model from scratch in every session is costly and overlooks informative geometry already observed previously. We propose efficient view planning guided by a previous-session reconstruction, which reuses a 3D model from the previous session to improve active perception in the current session. Based on this previous-session reconstruction, our method replaces iterative next-best-view planning with one-shot view planning that selects an informative set of views and computes the globally shortest execution path connecting them. Experiments on real multi-session datasets, including public single-plant scans and a newly collected greenhouse crop-row dataset, show that our method achieves comparable or higher surface coverage with fewer executed views and shorter robot paths than iterative and one-shot baselines.

Why it matches plant phenotyping methods植物の反復モニタリング向けに、過去セッションの3D再構成を利用した視点計画とロボット撮影経路を開発・評価しており、植物形状取得の方法が中心です。

abstractWe propose efficient view planning guided by a previous-session reconstruction, which reuses a 3D model from the previous session to improve active perception in the current session.

Integrating Load-Cell Lysimetry and Machine Learning for Prediction of Daily Plant Transpiration. →

ABSTRACT We conducted research to predict daily transpiration in crops by utilising a combination of machine learning (ML) models combined with extensive transpiration data from gravimetric load cells and ambient sensors. Our aim was to improve the accuracy of transpiration estimates. Data were collected from hundreds of plant specimens growing in two semi‐controlled greenhouses over 7 years, automatically measuring key physiological traits (serving as our ground truth data) and meteorological variables with high temporal resolution and accuracy. We trained Decision Tree, Random Forest, XGBoost and Neural Network models on this data set to predict daily transpiration. The Random Forest and XGBoost models demonstrated high accuracy in predicting the whole plant transpiration, with R 2 values of 0.89 on the test set (cross‐validation) and R 2 = 0.82 on holdout experiments. Ambient temperature was identified as the most influential environmental factor affecting transpiration. Our results emphasise the potential of ML for precise water management in agriculture, and simplify some of the complex and dynamic environmental forces that shape transpiration.

Why it matches plant phenotyping methods植物の個体蒸散量を荷重セル・環境センサーと機械学習で推定し、複数モデルの精度検証を行うことが研究の中心であるため。

abstractWe conducted research to predict daily transpiration in crops by utilising a combination of machine learning (ML) models combined with extensive transpiration data from gravimetric load cells and ambient sensors.

Automated generation of ground truth images of greenhouse-grown plant shoots using a GAN approach. →

The generation of a large amount of ground truth data is an essential bottleneck for the application of deep learning-based approaches to plant image analysis. In particular, the generation of accurately labeled images of various plant types at different developmental stages from multiple renderings is a laborious task that substantially extends the time required for AI model development and adaptation to new data. Here, generative adversarial networks (GANs) can potentially offer a solution by enabling widely automated synthesis of realistic images of plant and background structures. In this study, we present a two-stage GAN-based approach to generation of pairs of RGB and binary-segmented images of greenhouse-grown plant shoots. In the first stage, FastGAN is applied to augment original RGB images of greenhouse-grown plants using intensity and texture transformations. The augmented data were then employed as additional test sets for a Pix2Pix model trained on a limited set of 2D RGB images and their corresponding binary ground truth segmentation. This two-step approach was evaluated on unseen images of different greenhouse-grown plants. Our experimental results show that the accuracy of GAN predicted binary segmentation ranges between 0.88 and 0.95 in terms of the Dice coefficient. Among several loss functions tested, Sigmoid Loss enables the most efficient model convergence during the training achieving the highest average Dice Coefficient scores of 0.94 and 0.95 for Arabidopsis and maize images. This underscores the advantages of employing tailored loss functions for the optimization of model performance.

Why it matches plant phenotyping methods植物シュート画像のセグメンテーション用にGANで教師データを自動生成し、Dice係数で性能評価する手法開発が中心である。

abstractwe present a two-stage GAN-based approach to generation of pairs of RGB and binary-segmented images of greenhouse-grown plant shoots.

Detection of Abiotic Stress in Potato and Sweet Potato Plants Using Hyperspectral Imaging and Machine Learning. →

As climate extremes increasingly threaten global food security, precision tools for early detection of crop stress have become vital, particularly for root crops such as potato ( Solanum tuberosum L.) and sweet potato ( Ipomoea batatas L. Lam.), which are especially susceptible to environmental stressors throughout their life cycles. In this study, plants were monitored from the initial onset of seasonal stressors, including spring drought, heat, and episodes of excessive rainfall, through to harvest, capturing the full range of physiological and biochemical responses under seasonal, simulated conditions in greenhouses. The spectral data were obtained from regions of interest (ROIs) of each cultivar's leaves, with over 3000 data points extracted per cultivar; these data were subsequently used for model development. A comprehensive classification framework was established by employing machine learning models, Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), and Partial Least Squares-Discriminant Analysis (PLS-DA), to detect stress across various growth stages. Furthermore, severity levels were objectively defined using photoreflectance indices and principal component analysis (PCA) data visualizations, which enabled consistent and reliable classification of stress responses in both individual cultivars and combined datasets. All models achieved high classification accuracy (90-98%) on independent test sets. The application of the Successive Projections Algorithm (SPA) for variable selection significantly reduced the number of wavelengths required for robust stress classification, with SPA-PLS-DA models maintaining high accuracy (90-96%) using only a subset of informative bands. Furthermore, SPA-PLS-DA-based chemical imaging enabled spatial mapping of stress severity within plant tissues, providing early, non-invasive insights into physiological and biochemical status. These findings highlight the potential of integrating hyperspectral imaging and machine learning for precise, real-time crop monitoring, thereby contributing to sustainable agricultural management and reduced yield losses.

Why it matches plant phenotyping methods植物葉のハイパースペクトル画像からストレス状態・重症度を抽出し、機械学習で分類・空間マッピングする方法が研究の中心であり、独立テストによる性能評価も行っている。

abstractA comprehensive classification framework was established by employing machine learning models, Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), and Partial Least Squares-Discriminant Analysis (PLS-DA), to detect stress across various growth stages.

Plant stem occlusion inpainting with Deep Reinforcement Learning →

Growth monitoring of tomato plants in large greenhouse environments is critical for quality and efficient production. Stem diameter and elongation are key phenotypic traits for plant growth monitoring. Traditional methods, however, rely on manual operations, which are time-consuming and labor-intensive and do not apply to large-scale greenhouses. Currently, automated image-based methods exemplified by three-dimensional (3D) point cloud technology are among the preferred solutions. Nevertheless, the occlusion of plant structures during the information acquisition process is challenging for practical applications. To address this challenge, this study proposes a novel method for plant stem occlusion inpainting using Deep Reinforcement Learning (DRL). Unlike most existing 3D reconstruction approaches that require depth data from multiple viewpoints, our solution captures 3D point cloud data from a single direction. The DRL model is applied to inpaint the incomplete stem for accurate stem reconstruction and phenotypic measurements. Specifically, our approach consists of two parts, structural completion and stem diameter completion. First, we extract the point cloud of incomplete stems from the RGB-D camera data. Second, we obtain the spatial structure of the stems by inpainting the 3D stem centerline with the DRL model. Finally, we add shape features (stem diameters) by inpainting the two edge lines of the stem occlusion part with the DRL model. For stem inpainted 3D point cloud data, we conducted validation experiments by measuring several commonly used stem phenotypic traits in tomato plants, including stem diameter, stem length, and stem inclination. The experimental results show that the Mean Absolute Percentage Error (MAPE) of the occluded main stem diameter is 9.7%, stem length is 5.7%, and tilt angle is 1%. For the occluded branch stem, the MAPE of stem diameter is 23.1%, stem length is 7.9%, and tilt angle is 1.5%. The accuracy of these measurements for occluded stems is acceptable compared to that obtained from 3D point clouds of unoccluded stems. This highlights the significant potential of using DRL to effectively inpaint occluded 3D point cloud data of plants.

Why it matches plant phenotyping methods植物茎の遮蔽部分を3D点群と深層強化学習で補完し、茎径・茎長・傾斜角という表現型形質の測定精度を検証しており、フェノタイピング手法が中心的です。

abstractTo address this challenge, this study proposes a novel method for plant stem occlusion inpainting using Deep Reinforcement Learning (DRL).

Temporal semantic multispectral point cloud generation and feature fusion pipeline for comprehensive trait estimation in greenhouse tomatoes →

Accurate estimation of comprehensive traits such as yield and quality is crucial for optimizing agricultural management practices across the tomato industry chain. Traditional manual methods are time-consuming, labor-intensive, and prone to errors, reducing estimation accuracy. In contrast, modern intelligent estimation approaches based on multi-temporal spatial and spectral feature fusion offer improved efficiency and accuracy but still face challenges such as non-generalizable segmentation models, asynchronous feature extraction and weak correlations. This study proposes a novel pipeline for estimating yield and quality of greenhouse tomatoes using temporal semantic multispectral (TSM) point clouds. An unsupervised deep learning model was designed to register RGB-D images and multispectral (MS) images collected by an unmanned ground vehicle (UGV) plant phenotyping platform. The digital number (DN) point clouds of tomato organs were reconstructed based on the masks predicted by SegFormer with fusion of multispectral and depth modalities (MSD-SF). These point clouds were then radiometrically calibrated using neural reference field with sparse viewpoints (NeREF-S) to generate accurate reflectance point clouds. Finally, multi-temporal spatial-spectral features of tomatoes were extracted from the TSM point clouds, and random forest regression models were developed to estimate traits such as fruit flavor preference, water content, brix, acidity, brix-to-acid ratio, vitamin C content, single-fruit mass, and single-plant yield. The image registration model achieved high accuracy on the test set, with average structural similarity index measure, peak signal-to-noise ratio and learned perceptual image patch similarity of 0.238, 13.116 dB, and 0.374, respectively. The MS point clouds calibrated by NeREF-S significantly improved the signal-to-noise ratio to 11.56 dB. The average rRMSE for all trait estimations was 9.03 %. The results indicate that the proposed estimation method is efficient and accurate, holding promise to become a new paradigm for estimating the comprehensive traits of greenhouse tomatoes.

Why it matches plant phenotyping methods温室トマトの収量・品質形質を推定するため、UGVフェノタイピングプラットフォーム、マルチスペクトル点群生成、画像登録・放射較正、特徴抽出および回帰推定パイプラインを中心的に開発・評価している。

abstractThis study proposes a novel pipeline for estimating yield and quality of greenhouse tomatoes using temporal semantic multispectral (TSM) point clouds.

Using 3D reconstruction from image motion to predict total leaf area in dwarf tomato plants →

Accurate estimation of total leaf area (TLA) is essential for assessing plant growth, photosynthetic activity, and transpiration, but remains a challenge for bushy plants like dwarf tomatoes. Traditional destructive methods and imaging-based techniques often fall short due to labor intensity, plant damage, or the inability to capture complex canopies. This study evaluated a non-destructive method combining sequential 3D reconstructions from RGB images and machine learning to estimate TLA for three dwarf tomato cultivars—Mohamed, Hahms Gelbe Topftomate, and Red Robin—grown under controlled greenhouse conditions. Two experiments, conducted in spring–summer and autumn–winter, included 73 plants, yielding 418 TLA measurements using an “onion” approach, where layers of leaves were sequentially removed and scanned. High-resolution videos were recorded from multiple angles for each plant, and 500 frames were extracted per plant for 3D reconstruction. Point clouds were created and processed, four reconstruction algorithms (Alpha Shape, Marching Cubes, Poisson’s, and Ball Pivoting) were tested, and meshes were evaluated using seven regression models: Multivariable Linear Regression (MLR), Lasso Regression (Lasso), Ridge Regression (Ridge-Reg), Elastic Net Regression (ENR), Random Forest (RF), extreme gradient boosting (XGBoost), and Multilayer Perceptron (MLP). The Alpha Shape reconstruction (α = 3) combined with XGBoost yielded the best performance, achieving an R² of 0.80 and MAE of 489 cm², with significant results across other model combinations. Results were lower when using data from different experiments as train and test datasets (R² = 0.56 and MAE = 579 cm²). Feature importance analysis identified height, width, and surface area as the most predictive features. These findings demonstrate the robustness of our approach across variable environmental conditions and canopy structures. This scalable, automated TLA estimation method is particularly suited for urban farming and precision agriculture, offering practical implications for automated pruning, improved resource efficiency, and sustainable food production.

Why it matches plant phenotyping methodsRGB画像からの3D再構成と機械学習により植物の総葉面積を推定する手法を開発・評価しており、表現型取得が研究の中心です。

abstractThis study evaluated a non-destructive method combining sequential 3D reconstructions from RGB images and machine learning to estimate TLA

Visible-near infrared hyperspectral imaging for non-destructive estimation of leaf nitrogen content under water-saving irrigation in protected tomato cultivation. →

Accurate estimation of leaf nitrogen content (LNC) is critical for optimizing fertilization strategies in greenhouse tomato production. This study developed a robust hyperspectral-based framework for non-destructive LNC prediction by combining advanced spectral preprocessing, feature selection, and machine learning. Hyperspectral reflectance data were collected across five nitrogen and irrigation treatments over key growth stages. Signal quality was enhanced through Savitzky-Golay smoothing (SG) and Standard Normal Variate normalization (SNV). Key nitrogen-sensitive wavelengths-centered around 725 nm and 730 - 780 nm-were identified using Competitive Adaptive Reweighted Sampling (CARS) and Principal Component Analysis (PCA). Four predictive models were compared, among which a hybrid Stacked Autoencoder-Feedforward Neural Network (SAE-FNN) achieved the highest accuracy (test R² = 0.77, RPD = 2.06), effectively capturing nonlinear spectral-nitrogen interactions. In contrast, Support Vector Machine (SVM) exhibited overfitting and Partial Least Squares Method (PLSR) underperformed due to its linear constraints. These results underscore the potential of integrating hyperspectral sensing with deep learning for intelligent nitrogen monitoring in controlled-environment agriculture.

Why it matches plant phenotyping methods植物の葉窒素含量という形質を、ハイパースペクトル画像と機械学習で非破壊推定する手法を開発・比較検証しており、フェノタイピング手法が中心である。

abstractThis study developed a robust hyperspectral-based framework for non-destructive LNC prediction by combining advanced spectral preprocessing, feature selection, and machine learning.

Development of a nondestructive prediction model for nutrient content of orchid leaves using different hyperspectral sensors →

Cymbidium hybrids has the advantages of strong growth, large number of flowers, and high market share. However, most orchid cultivation has problems such as over-reliance on artificial experience cultivation, lack of scientific basis for water and fertilizer application, and low degree of precision and intelligent cultivation. Monitoring the levels of N, P, and K in plant leaves facilitates real-time assessment of nutritional status while guiding optimization fertilization, thereby enhancing fertilizer efficiency and plant growth quality. Nevertheless, conventional nutrient detection methods are invasive, time-consuming, and expertise-dependent, necessitating advanced non-destructive alternatives. This study explores hyperspectral sensing technology for non-destructive monitoring of N, P, and K in hybrid orchid under greenhouse conditions. Three water-fertilization regimes were applied at strategic growth stages of hybrid orchids, with spectral data collected across four seasons using a spectrometer and a hyperspectral imaging device. Through the analysis of 720 combinations of ten spectral preprocessing methods and four modeling approaches, an optimal algorithm combination was identified. This optimal combination was integrated with the Stable Competitive Adaptive Reweighted Sampling algorithm to select spectral feature bands. Predictive models were then constructed to estimate the contents of N, P, and K in the orchid leaves. The results showed the utilization of Stable Competitive Adaptive Reweighted Sampling method, between 14.2% and 25.0% of the feature wavelengths significantly reduced the root mean square error of the models. By incorporating these methodologies, the predictive model for leaf N, P, and K contents utilizing the hyperspectral imaging device achieved determination coefficients (R²) of 0.7395, 0.7213, and 0.7055, respectively, on the test sets. For the spectrometer-based models predicting leaf N, P, and K contents, the corresponding R² values for the test sets reached 0.8708, 0.8747, and 0.8557. These results validate hyperspectral sensing as a robust tool for non-destructive nutrient monitoring. The findings of this study provide a theoretical basis and effective methodology for the accurate and non-destructive detection of nutrient content in orchid leaves through hyperspectral sensing technology.

Why it matches plant phenotyping methodsランの葉内N・P・K含量という植物状態を、ハイパースペクトルセンシングで非破壊推定するモデルを開発・検証しており、表現型取得手法が中心的である。

abstractThis study explores hyperspectral sensing technology for non-destructive monitoring of N, P, and K in hybrid orchid under greenhouse conditions.

P3DFusion: A cross-scene and high-fidelity 3D plant reconstruction framework empowered by vision foundation models and 3D Gaussian splatting →

Efficient acquisition of 3D plant structures is crucial for investigating growth mechanisms and phenotype analysis. Traditional 3D reconstruction methods exhibited significant limitations when faced with complex background interference, leading to low reconstruction efficiency and compromised result integrity. To address these challenges, a cross-scene 3D plant reconstruction framework P3DFusion was proposed with two key technological modules: (1) GSAM2 multi-view image processing method with Vision Foundation Models, which combines Grounding DINO and Segment Anything Model 2 (SAM2) to achieve high-precision plant segmentation under zero-shot conditions; (2) High-fidelity modeling based on 3D Gaussian splatting (3DGS) to generate high-quality, measurable meshes optimized for plant structural analysis. We evaluated P3DFusion using two datasets: Dataset1 (greenhouse-potted plants) and Dataset2 (open-field sugar beets). The P3DFusion exhibited significant improvements in reconstruction efficiency (SfM-Time reductions of 8.5 %/47.9 %, Total processing time reductions of 60.9 %/65.2 %) and quality metrics (SSIM increases of 12.9 %/19.8 %, PSNR increases of 11.8 %/13 % reaching 24.26 dB/24.75 dB, and LPIPS reductions of 70 %/85 %) for Dataset 1 and Dataset 2, respectively, compared to the original 3DGS. The P3DFusion outperforms InstantNGP (PSNR: 22.3 %/32.9 % increase) and COLMAP (PSNR: 231.4 %/266.1 % increase). Phenotype trait extraction from reconstructed models shows strong consistency with ground truth measurements (R² > 0.93). The proposed method not only provides an effective solution for cross-scene 3D plant reconstruction but also establishes a robust technical foundation for advanced plant phenotype research.

Why it matches plant phenotyping methods植物の3D再構成・セグメンテーションと形質抽出を中核とする手法開発および比較検証であり、植物フェノタイピング手法として明確に該当する。

abstractEfficient acquisition of 3D plant structures is crucial for investigating growth mechanisms and phenotype analysis.

Precise 3D evaluation of light microclimate for summer production in insulated plastic greenhouses →

Solar greenhouses are energy-efficient facilities for year-round crop production. To better understand the effects of shading caused by the insulation quilts on the microclimate and canopy light interception, this study systematically investigated summer cucumber production inside an insulated plastic greenhouse in Beijing, China. Monitoring experiments were conducted across the seedling, flowering, fruiting, and maturity stages, and were combined with 3D simulation modeling. Specifically, the radiation transmittance of greenhouse roof was analyzed at different solar altitude angles. A functional-structural plant model (FSPM) was employed to evaluate the spatiotemporal distribution of light within the greenhouse. Shaded areas resulting from the insulation quilts were calculated, and the daily light integral (DLI) on the canopy under various shading patterns was quantified. Results showed that insulation quilt shading reduced indoor temperature by an average of 4.2 °C and increased relative humidity by 7.5 %, but also caused a significant reduction in canopy light availability. The average DLI during the seedling, flowering, fruiting, and maturity stages was merely 9.1, 10.8, 16.8 and 20.8 mol/m²/d, respectively, which was significantly lower than the commonly recommended range of 20–30 mol/m²/d for optimal growth. Considering the combined effects of temperature, humidity and photosynthetic requirements, supplementary lighting at night is necessary to ensure optimal crop development. The modeling framework proposed in this study represents an initial step toward quantitatively evaluating shading effects in greenhouse. This approach is not constrained by geographic location and can be directly applied to other greenhouse types and crop species.

Why it matches plant phenotyping methods温室内のキャノピー光環境・光遮蔽を3Dモデルで定量化する再利用可能な計算手法が中心であり、植物キャノピーの光利用状態を推定しているため。

abstractA functional-structural plant model (FSPM) was employed to evaluate the spatiotemporal distribution of light within the greenhouse.

CGA-ASNet: an RGB-D amodal segmentation network for restoring occluded tomato regions →

Obtaining the complete morphology of tomato fruits under non-destructive conditions is essential for phenotype research, yet fruit occlusions often hinder deep learning-based image segmentation methods from capturing the true shape of occluded regions. This limitation reduces prediction accuracy and adversely impacts phenotype data acquisition. To overcome this challenge, we propose CGA-ASNet, an RGB-D amodal segmentation network incorporating a Contextual and Global Attention (CGA) module. A synthetic tomato dataset (Tomato-sim) was constructed using NVIDIA Isaac Sim's Replicator Composer (ISRC) to realistically simulate tomato morphology and greenhouse environments, and the network was trained on this dataset. To evaluate generalization, CGA-ASNet was tested on both the synthetic and a separate real-world dataset. While no explicit domain adaptation techniques were adopted, diverse lighting conditions (strong, normal, and weak illumination) were simulated to implicitly reduce the domain gap, and a mean coordinate fusion algorithm was introduced to improve annotation completeness in real-world occlusion scenarios. By leveraging contextual information among feature input keys for self-attention learning, capturing global information, and expanding the receptive field, CGA-ASNet enhanced representation capacity, semantic understanding, and localization accuracy. Experimental results demonstrated that CGA-ASNet achieved an F@0.75 score of 94.2 and a mean Intersection over Union (mIoU) of 82.4% in greenhouse amodal segmentation tasks. These findings indicate that training with well-designed synthetic datasets can effectively support accurate occlusion-aware segmentation in real environments, providing a practical solution for tomato phenotyping in greenhouse conditions.

Why it matches plant phenotyping methodsトマト果実の遮蔽領域を復元して完全形態を取得するRGB-D画像解析手法を開発し、合成・実画像データセットで技術検証しているため、植物表現型取得が中心的である。

abstractObtaining the complete morphology of tomato fruits under non-destructive conditions is essential for phenotype research

Spatio-Temporal 4D Phenotyping for Automated Morphological Genotype Differentiation of Sugar Beet →

Abstract 3D models are used in plant phenotyping for non-destructive quantification and analysis of morphological characteristics. Analyzing plant structure allows breeders to select for desirable traits, associated with e.g. drought tolerance or increased productivity. In sugar beet, morphological parameters depict an essential element of the variety approval for distinguishing between genotypes. However, only a limited number of measured or scored parameters are considered at a single time point. This study aims to disclose the benefit of incorporating dynamic spatio-temporal development of 3D parameters for automated crop genotype differentiation. A greenhouse experiment was conducted covering twelve sugar beet genotypes. High-resolution 3D models were generated twice a week over the course of two months and both common and novel 3D morphological parameters were extracted. The importance of these parameters was assessed over time, and the dataset was analyzed using unsupervised pointwise clustering and time series clustering. Varying importance of parameters depending on the time point and the noticeable higher importance of plant parameters compared to leaf parameters are demonstrated by our results. Moreover, increased and more stable genotype differentiation is archived using time series clustering compared to pointwise clustering. Furthermore, taproot formation of sugar beet was found to have a crucial impact on morphological development. Substantial genotypic variations in the dynamic development of 3D morphological parameters could be demonstrated. The higher and more stable clustering performance using time series analysis underlines the importance of 4D data for plant genotype differentiation. Future work should focus on identifying important growth stages for data collection.

Why it matches plant phenotyping methods3Dモデルを用いた時系列植物形態計測、形態パラメータ抽出、クラスタリングによる遺伝型識別が研究の中心であり、4Dフェノタイピング手法の実質的な応用・評価に該当する。

abstractHigh-resolution 3D models were generated twice a week over the course of two months and both common and novel 3D morphological parameters were extracted.

Multi-Trait Phenotypic Extraction and Fresh Weight Estimation of Greenhouse Lettuce Based on Inspection Robot →

In situ detection of growth information in greenhouse crops is crucial for germplasm resource optimization and intelligent greenhouse management. To address the limitations of poor flexibility and low automation in traditional phenotyping platforms, this study developed a controlled environment inspection robot. By means of a SCARA robotic arm equipped with an information acquisition device consisting of an RGB camera, a depth camera, and an infrared thermal imager, high-throughput and in situ acquisition of lettuce phenotypic information can be achieved. Through semantic segmentation and point cloud reconstruction, 12 phenotypic parameters, such as lettuce plant height and crown width, were extracted from the acquired images as inputs for three machine learning models to predict fresh weight. By analyzing the training results, a Backpropagation Neural Network (BPNN) with an added feature dimension-increasing module (DE-BP) was proposed, achieving improved prediction accuracy. The R2 values for plant height, crown width, and fresh weight predictions were 0.85, 0.93, and 0.84, respectively, with RMSE values of 7 mm, 6 mm, and 8 g, respectively. This study achieved in situ, high-throughput acquisition of lettuce phenotypic information under controlled environmental conditions, providing a lightweight solution for crop phenotypic information analysis algorithms tailored for inspection tasks.

Why it matches plant phenotyping methods温室内ロボット、複数センサー、画像解析、形質抽出、重量推定を一体化した植物表現型取得手法の開発が中心である。

abstractthis study developed a controlled environment inspection robot

Application of non-destructive imaging techniques to evaluate cold tolerance in French marigold (Tagetes patula) genotypes →

Climate change-induced erratic weather patterns necessitate the development of cold-tolerant marigold cultivars for sustainable floricultural production. The present study was carried out during winter (rabi) season 2021–22 and 2022–23 at ICAR-Indian Agricultural Research Institute, New Delhi to evaluate the efficacy of high-throughput, non-destructive image-based phenotyping techniques, including Red-Green-Blue (RGB), Near-Infrared (NIR), and Infrared (IR) imaging, for quantitative assessment of essential plant traits such as plant area, greenness, water content, and temperature. Ten French marigold (Tagetes patula L.) genotypes (Pusa Deep, Pusa Arpita, Dainty Marietta, Valencia Yellow, Orange Winner, Hisar Beauty, Hisar Jafri, Gulzafri Orange, Fr./W-20, Fr./W-21) were evaluated. The experiment was laid out in a complete randomized design (CRD) with two factors (genotype and environment) and three replications, with 18 plants/environment and 6 plants/replication. Technologies were applied to assess cold tolerance during the early reproductive phase of French marigold genotypes, grown under contrasting environments: Controlled conditions (polyhouse, 30.1°-33.7°C/3.4°-3.7°C) and cold stress (open field, 26.4°-28°C/0.8°-1.2°C) during winter season. Comparative analysis revealed that cold stress significantly impacted morpho-physiological parameters: Plant area decreased by 1.38-fold, caliper length by 1.07-fold, and compactness by 2.10-fold compared to the polyhouse environment. Convex hull area and circumference were reduced by 1.22-fold and 1.05-fold, respectively. Additionally, greenness and plant temperature decreased by approximately 1.03-fold, roundness by 2.07-fold, and plant water content by 1.44-fold. Statistical analysis revealed that open field conditions significantly decreased all measured morpho-physiological parameters, with plant compactness showing the greatest reduction compared to controlled conditions. Notably, genotypes including ‘Hisar Beauty’ and ‘Hisar Jafri ’ exhibited superior cold tolerance, demonstrating the least reductions in measured parameters under cold stress, while maintaining higher water content (NIR reflectance, 140.98%) and lower plant surface temperatures (19.06°C) compared to other genotypes. These findings underscore the potential of non-destructive image-based phenotyping as an efficient tool in screening for cold tolerance in marigold breeding programmes, offering a viable and precise alternative to traditional screening methods for accelerated cultivar development.

Why it matches plant phenotyping methodsRGB・NIR・IRによる非破壊画像計測を用いて植物形態・水分・温度などの形質を定量化し、耐寒性スクリーニングへの有効性を評価しており、表現型取得法が研究の中心です。

abstractevaluate the efficacy of high-throughput, non-destructive image-based phenotyping techniques, including Red-Green-Blue (RGB), Near-Infrared (NIR), and Infrared (IR) imaging, for quantitative assessment of essential plant traits such as plant area, greenness, water content, and temperature

Smart Greenhouse Management: Harnessing Artificial Intelligence for Sustainable Farming →

Abstract Greenhouse farming plays a vital role in enhancing agricultural productivity, yet it often suffers from inefficient resource management and delayed disease detection. This paper presents a novel solar-powered Smart Greenhouse Management System (SGHMS) that integrates IoT-based environmental monitoring, machine learning for real-time disease detection, and a Raspberry Pi-controlled autonomous sprayer into a unified platform. Unlike existing systems, our approach combines a CNN-based plant health classifier deployed locally on Raspberry Pi with an energy-efficient solar power source to ensure reliable off-grid operation. A user-friendly web and mobile application enables real-time monitoring, alert generation, and remote control of environmental parameters and spraying actions. The system was deployed in a real greenhouse for 30 days and demonstrated a 92% disease detection accuracy while significantly reducing water and energy consumption. This integrated solution offers a scalable and cost-effective approach to sustainable precision agriculture, particularly in resource-constrained regions.

Why it matches plant phenotyping methodsCNNによる植物健康・病害検出を中核機能として実 greenhouse で展開し、検出精度も評価しているため、植物状態の画像ベース表現型計測を含む実質的なプラットフォーム研究である。

abstractmachine learning for real-time disease detection

Mapping QTLs for PHS resistance and development of a deep learning model to measure PHS rate in japonica rice. →

Rice (Oryza sativa L.) is a staple food for more than half of the global population. Preharvest sprouting (PHS), which reduces yield and grain quality, presents a major challenge for rice production. The development of PHS-resistant varieties is a major goal in japonica rice breeding. A deep learning model to automate PHS rate measurement was developed using the YOLOv8 algorithm. The model had high mean average precision (0.974). PHS rate measurements made using the model correlated strongly with manual measurements (R 2 = 0.9567). A population of 182 F 8 recombinant inbred lines (RILs) was derived from a cross between the japonica rice cultivars, Junam and Nampyeong. The RIL genotypes at 763 single nucleotide polymorphism markers were determined using a rice target capture sequencing system and used to create a genetic map. The RILs were cultivated in the field (summer season) and the greenhouse (winter season) and their PHS rates were measured in both environments. Quantitative trait loci (QTLs) associated with PHS were present on chromosomes 3, 6, and 7 in the field, and on chromosomes 1, 2, 3, 6, 7, 8, and 11 in the greenhouse. Three QTLs on chromosomes 3, 6, and 7 showed stable effects in both environments. A search for candidate genes in the QTL qPHS6 identified Os06g0317200. This gene encodes a glycine-rich protein resembling qLTG3-1, which controls PHS. The QTLs identified in this study and the deep learning model developed for measuring PHS rates will accelerate the development of rice varieties with enhanced resistance to PHS.

Why it matches plant phenotyping methodsイネの穂発芽率という植物状態を画像から自動測定する深層学習モデルを開発し、手動測定との相関で検証しているため、表現型取得法が研究の中心的貢献である。

abstractA deep learning model to automate PHS rate measurement was developed using the YOLOv8 algorithm.

Deep learning-driven IoT solution for smart tomato farming. →

The rising food demand and challenges with respect to the climate have made precision agriculture (PA) vital for sustainable crop production. This study presents an IoT-based smart greenhouse platform tailored for tomato farming, integrating environmental sensing and deep learning. The system employs ESP32-based wireless sensors to collect real-time data on soil moisture, temperature, and humidity; this data is transmitted to a cloud dashboard (ThingsBoard) for remote monitoring. A Raspberry Pi equipped with a Pi Camera and a YOLOv8 model classifies tomato ripeness stages-green, half-ripened, and fully ripened-using real greenhouse images. Model optimizations, including quantization, pruning, and TensorRT, improved inference speed by 35% while maintaining 52.8% classification accuracy during our initial stage of the project. Energy profiling revealed daily consumption of 8.91 Wh for the ESP32 sensors and 78 Wh for the Raspberry Pi. This prototype demonstrates real-time monitoring, high model precision, and practical energy insights, paving the way for multi-node scalability and edge AI enhancements. Future work will explore incorporating Edge TPU for faster on-device processing, LoRa for low-power, long-distance data transfer, and automated control of irrigation and ventilation systems to realize a fully autonomous smart greenhouse.

Why it matches plant phenotyping methodsトマト果実の成熟段階という植物状態をカメラ画像とYOLOv8で推定し、モデル最適化・精度・推論速度を評価しているため、画像ベースの表現型取得が中心的です。

abstractA Raspberry Pi equipped with a Pi Camera and a YOLOv8 model classifies tomato ripeness stages-green, half-ripened, and fully ripened-using real greenhouse images.

AFBF-YOLO: An Improved YOLO11n Algorithm for Detecting Bunch and Maturity of Cherry Tomatoes in Greenhouse Environments. →

Accurate detection of cherry tomato clusters and their ripeness stages is critical for the development of intelligent harvesting systems in modern agriculture. In response to the challenges posed by occlusion, overlapping clusters, and subtle ripeness variations under complex greenhouse environments, an improved YOLO11-based deep convolutional neural network detection model, called AFBF-YOLO, is proposed in this paper. First, a dataset comprising 486 RGB images and over 150,000 annotated instances was constructed and augmented, covering four ripeness stages and fruit clusters. Then, based on YOLO11, the ACmix attention mechanism was incorporated to strengthen feature representation under occluded and cluttered conditions. Additionally, a novel neck structure, FreqFusion-BiFPN, was designed to improve multi-scale feature fusion through frequency-aware filtering. Finally, a refined loss function, Inner-Focaler-IoU, was applied to enhance bounding box localization by emphasizing inner-region overlap and focusing on difficult samples. Experimental results show that AFBF-YOLO achieves a precision of 81.2%, a recall of 81.3%, and an mAP@0.5 of 85.6%, outperforming multiple mainstream YOLO series. High accuracy across ripeness stages and low computational complexity indicate it excels in simultaneous detection of cherry tomato fruit bunches and fruit maturity, supporting automated maturity assessment and robotic harvesting in precision agriculture.

Why it matches plant phenotyping methods画像ベースの深層学習手法を開発し、トマト果実の成熟段階という植物状態を検出・評価しているため、収穫対象の単なる定位を超えた中心的な表現型計測研究である。

abstractan improved YOLO11-based deep convolutional neural network detection model, called AFBF-YOLO, is proposed in this paper.

Intelligent deep learning architecture for precision vegetable disease detection advancing agricultural new quality productive forces. →

In the context of advancing agricultural new quality productive forces, addressing the challenges of uneven illumination, target occlusion, and mixed infections in greenhouse vegetable disease detection becomes crucial for modern precision agriculture. To tackle these challenges, this study proposes YOLO-vegetable, a high-precision detection algorithm based on improved You Only Look Once version 10 (YOLOv10). The framework incorporates three innovative modules. The Adaptive Detail Enhancement Convolution (ADEConv) module employs dynamic parameter adjustment to preserve fine-grained features while maintaining computational efficiency. The Multi-granularity Feature Fusion Detection Layer (MFLayer) improves small target localization accuracy through cross-level feature interaction mechanisms. The Inter-layer Dynamic Fusion Pyramid Network (IDFNet) combines with Attention-guided Adaptive Feature Selection (AAFS) mechanism to enhance key information extraction capability. Experimental validation on our self-built Vegetable Disease Dataset (VDD, 15,000 images) demonstrates that YOLO-vegetable achieves 95.6% mean Average Precision at IoU threshold 0.5, representing a 6.4 percentage point improvement over the baseline model. The method maintains efficiency with 3.8M parameters and 18.6ms inference time per frame, providing a practical solution for intelligent disease detection in facility agriculture and contributing to the development of agricultural new quality productive forces.

Why it matches plant phenotyping methods植物の病徴・病害状態を画像から検出する深層学習手法を開発し、自作データセットで性能検証しており、植物フェノタイピング手法が中心である。

abstractaddressing the challenges of uneven illumination, target occlusion, and mixed infections in greenhouse vegetable disease detection becomes crucial

Cherry Tomato Bunch and Picking Point Detection for Robotic Harvesting Using an RGB-D Sensor and a StarBL-YOLO Network →

For fruit harvesting robots, rapid and accurate detection of fruits and picking points is one of the main challenges for their practical deployment. Several fruits typically grow in clusters or bunches, such as grapes, cherry tomatoes, and blueberries. For such clustered fruits, it is desired for them to be picked by bunches instead of individually. This study proposes utilizing a low-cost off-the-shelf RGB-D sensor mounted on the end effector and a lightweight improved YOLOv8-Pose neural network to detect cherry tomato bunches and picking points for robotic harvesting. The problem of occlusion and overlap is alleviated by merging RGB and depth images from the RGB-D sensor. To enhance detection robustness in complex backgrounds and reduce the complexity of the model, the Starblock module from StarNet and the coordinate attention mechanism are incorporated into the YOLOv8-Pose network, termed StarBL-YOLO, to improve the efficiency of feature extraction and reinforce spatial information. Additionally, we replaced the original OKS loss function with the L1 loss function for keypoint loss calculation, which improves the accuracy in picking points localization. The proposed method has been evaluated on a dataset with 843 cherry tomato RGB-D image pairs acquired by a harvesting robot at a commercial greenhouse farm. Experimental results demonstrate that the proposed StarBL-YOLO model achieves a 12% reduction in model parameters compared to the original YOLOv8-Pose while improving detection accuracy for cherry tomato bunches and picking points. Specifically, the model shows significant improvements across all metrics: for computational efficiency, model size (−11.60%) and GFLOPs (−7.23%); for pickable bunch detection, mAP50 (+4.4%) and mAP50-95 (+4.7%); for non-pickable bunch detection, mAP50 (+8.0%) and mAP50-95 (+6.2%); and for picking point detection, mAP50 (+4.3%), mAP50-95 (+4.6%), and RMSE (−23.98%). These results validate that StarBL-YOLO substantially enhances detection accuracy for cherry tomato bunches and picking points while improving computational efficiency, which is valuable for resource-constrained edge-computing deployment for harvesting robots.

Why it matches plant phenotyping methodsRGB-D画像と改良YOLOv8-Poseを用いて、収穫対象となるトマト房と摘採点を検出・位置推定する手法を開発し、実データセットで性能検証している。単なる収穫対象の位置検出に見えるが、房の可収穫性と摘採点という植物器官の状態・位置を抽出する技術的貢献が中心である。

abstractThis study proposes utilizing a low-cost off-the-shelf RGB-D sensor mounted on the end effector and a lightweight improved YOLOv8-Pose neural network to detect cherry tomato bunches and picking points for robotic harvesting.

Spatio-Temporal Consistent Semantic Mapping for Robotics Fruit Growth Monitoring →

Automatic fruit growth monitoring plays a vital role in advancing precision agriculture. Tracking the evolution of fruits over time is essential to monitor their development and optimize production. The ability to recognize fruits over periods of time, even with drastic scene changes, is a required capability of agricultural robots. This paper presents a system that allows long-term fruit tracking in 3D data. It generates instance-segmented 3D representations of plants at various growth stages over time, utilizing only consumer-grade RGB-D cameras installed on a mobile robot. Our approach first performs instance segmentation on each image in a sequence. Then, by exploiting geometric information and depth maps, we track the same instances throughout the sequence. We produce a 3D point cloud containing instances, exploiting odometry information and 3D semantic mapping. Once our robot performs a new recording at a different plant growth stage, it associates each fruit with the previously built 3D cloud and update the model. We validate the system in a real-world glasshouse environment in Bonn, Germany. Experimental results demonstrate that our system outperforms existing baselines even though it relies only on annotated images and operates at frame-rate, allowing the deployment on a real robot.

Why it matches plant phenotyping methodsRGB-D画像と3Dセマンティックマッピングによる果実の長期追跡・成長モニタリング手法が研究の中心であり、植物器官の成長状態を抽出するため、植物フェノタイピング手法として適格です。

abstractThis paper presents a system that allows long-term fruit tracking in 3D data.

Multi-Trait Phenotypic Analysis and Biomass Estimation of Lettuce Cultivars Based on SFM-MVS →

To address the problems of traditional methods that rely on destructive sampling, the poor adaptability of fixed equipment, and the susceptibility of single-view angle measurements to occlusions, a non-destructive and portable device for three-dimensional phenotyping and biomass detection in lettuce was developed. Based on the Structure-from-Motion Multi-View Stereo (SFM-MVS) algorithms, a high-precision three-dimensional point cloud model was reconstructed from multi-view RGB image sequences, and 12 phenotypic parameters, such as plant height, crown width, were accurately extracted. Through regression analyses of plant height, crown width, and crown height, and the R2 values were 0.98, 0.99, and 0.99, respectively, the RMSE values were 2.26 mm, 1.74 mm, and 1.69 mm, respectively. On this basis, four biomass prediction models were developed using Adaptive Boosting (AdaBoost), Support Vector Regression (SVR), Gradient Boosting Decision Tree (GBDT), and Random Forest Regression (RFR). The results indicated that the RFR model based on the projected convex hull area, point cloud convex hull surface area, and projected convex hull perimeter performed the best, with an R2 of 0.90, an RMSE of 2.63 g, and an RMSEn of 9.53%, indicating that the RFR was able to accurately simulate lettuce biomass. This research achieves three-dimensional reconstruction and accurate biomass prediction of facility lettuce, and provides a portable and lightweight solution for facility crop growth detection.

Why it matches plant phenotyping methodsレタスの3次元画像計測、形質抽出、バイオマス推定を行う携帯型フェノタイピング手法を開発し、精度検証まで実施しており、方法自体が研究の中心である。

abstracta non-destructive and portable device for three-dimensional phenotyping and biomass detection in lettuce was developed

Evaluation of evapotranspiration models integrating convolutional neural network-predicted leaf area for Pak Choi (Brassica campestris ssp. chinensis) in greenhouse environments →

This study evaluates how predicted leaf area index (LAI) affects evapotranspiration (ET) model performance and uncertainty in greenhouse Pak Choi cultivation. Five ET models (Penman-Monteith, Stanghellini, Fynn, Shin, and Baille) were compared using both measured and Convolutional Neural Network-Predicted LAI data. Greenhouse environment experiments from June to August 2021 provided validation data under controlled conditions. LAI was estimated using image analysis with high accuracy (R² = 0.9986, RMSE = 0.0547 m²·m⁻²). Sensitivity analysis revealed that ET models were most responsive to radiation and LAI variations, with lower sensitivity to air temperature and relative humidity. Among physical models, the Fynn model demonstrated superior performance based on ET prediction accuracy (R² > 0.87), while the Shin model excelled among simplified approaches (R² > 0.92). Uncertainty propagation analysis revealed that the Stanghellini model exhibited the highest sensitivity to LAI estimation errors (12.55 W·m⁻² error when LAI error = 1.0 m²·m⁻²), whereas the Penman–Monteith model showed minimal sensitivity. Model performance remained consistent when using predicted versus measured LAI (R² > 0.99 for all models), indicating the robustness of image-based LAI estimation for ET modelling. This research provides quantitative insights into model selection and uncertainty assessment for precision irrigation management in protected cultivation systems, with particular applicability to leafy vegetable crops under controlled greenhouse conditions.

Why it matches plant phenotyping methodsCNN画像解析による植物のLAI推定を高精度に検証し、推定LAIの誤差・頑健性をETモデル比較で評価しており、植物形質取得法が技術的に中心的である。

abstractLAI was estimated using image analysis with high accuracy (R² = 0.9986, RMSE = 0.0547 m²·m⁻²).

Phenotypic data related to seedling traits of hexaploid spring wheat panel evaluated under salinity stress →

Salt stress is a major abiotic stress affecting wheat at various developmental stages and significantly reduces grain yield. Developing salt resilient wheat cultivars alleviate the negative impacts of salt stress and helps in maintaining sustainable grain yield under salt stress. A study was undertaken to assess the response of various seedling traits in a genetically, phenotypically, and geographically diverse panel of 228 hexaploid spring wheat accessions using greenhouse lysimeter system with two irrigation treatments: control (electrical conductivity of irrigation water as deci-Siemens per meter., (ECᵢ𝓌 = 14 dSm⁻¹) and saline (ECᵢ𝓌 = 14 dSm⁻¹). Salt stress was given on 18 days old seedlings and the targeted salinity level (ECᵢ𝓌 = 14 dSm⁻¹) was achieved gradually over two days period, to overcome any osmotic shock. Data on various seedling traits [such as shoot height (SH; inches), root length (RL; inches), tiller number (TN), shoot weight (SW; grams), and root weight (RW; grams)] were collected after three weeks of salt treatment from control and salt stress environment. Shoot and root traits were used to calculate root length by shoot height (RL-by-SH) and root weight by shoot weight (RW-by-SW) ratios. Furthermore, the salt tolerance index (STI), was calculated for each trait by dividing trait values of each accession from salt-treated tanks by those from control tanks. Raw data was subjected to mixed linear analysis to derive best linear unbiased prediction (BLUP). BLUP values were also used for Pearson's correlation coefficient analysis and principal component analysis (PCA), which gives intrinsic relationship among various seedling traits. Dataset presented here is a valuable source for identifying tolerant lines for salt stress environment. Moreover, researchers can utilize this information to identify potential genomic regions associated with salt stress tolerance and can be utilized in developing salt resilient wheat cultivars.

Why it matches plant phenotyping methods塩ストレス下のコムギ幼植物について、複数の形態・生体重形質を体系的に収集した再利用可能な表現型データセットであり、植物表現型データの提供が中心です。

titlePhenotypic data related to seedling traits of hexaploid spring wheat panel evaluated under salinity stress

Model prediction of plant morphology, water flows and xylem water potential in a growing tomato plant under heterogeneous growing conditions →

We present a comprehensive mathematical model to calculate stem water potential in tomato plants cultivated under greenhouse conditions. Stem water potential is one of the variables that determines the growth of fruit as water potential gradients between the fruit and the stem are the driving forces for import of water and solutes into the fruit. Notably, the model integrates growth dynamics, environmental conditions, and plant management strategies to improve the accuracy of water potential estimation throughout the canopy. Environmental factors (i.e., temperature, relative humidity, light irradiance) were implemented at plant compartment levels, allowing for precise microclimate representation. Plant structure was used to calculate water flows and, ultimately, stem water potential by utilizing a hydraulic resistance model. The model was calibrated and validated using data collected from five growing seasons (2020 – 2024). The precision of water potential estimates across different growth stages was improved by including plant morphology dynamics. This, together with discretisation into compartments, allowed for unique realistic predictions for the whole season. Accurate predictions required accounting for growth dependency in root and xylem resistance. Temperature was the main predictor of plant growth for the investigated conditions of tomato production in Belgium. The greenhouse environment and plant management significantly influenced water fluxes and subsequent water potential estimations and should always be considered, especially for whole-season scenarios. Two hypothetical scenarios were analyzed based on 2019 environmental data, exploring the impact of greenhouse management and climate change. Simulations revealed that an increase in the greenhouse minimum temperature set points (+2 °C) had a greater positive effect on yield than a hypothetical climate change scenario with a larger temperature increase (+4 °C). The latter resulted in a higher prevalence of suboptimal growth conditions, presenting a real challenge for efficient future greenhouse management. Additionally, controlling the vapour pressure deficit instead of relative humidity was shown to significantly reduce water demand due to decreased transpiration rates. This water potential model for tomato growth can be used conjointly with fruit growth models for better crop prediction and optimisation of growing conditions. The presented model is modular and extendable, allowing integration not just with fruit growth models, but also potential inclusion of additional plant organs.

Why it matches plant phenotyping methodsトマトの茎水ポテンシャルや形態を推定する数学モデルを開発し、5作期のデータで較正・検証しており、植物状態の取得・推定手法が研究の中心である。

abstractWe present a comprehensive mathematical model to calculate stem water potential in tomato plants cultivated under greenhouse conditions.

Hyperspectral-Based Classification of Individual Wheat Plants into Fine-Scale Reproductive Stages for Anthesis Prediction →

Abstract Field trials are critical in the development of genetically modified and genome-edited biotechnology plants to evaluate the growth and yield of breeding lines and to test commercial viability or any potential off-target effects. In Australia, conducting field trials of biotechnology derived crops requires compliance with federally mandated regulations, including strict protocols for forecasting flowering times. Conventional practices are based on time consuming, subjective and costly visual field inspections of individual wheat plants at respective growth stages (Zadoks growth stages Z37, Z39, and Z41). To enable automatic forecasting, hyperspectral and RGB images were captured in the greenhouse, and hyperspectral reflectance data were acquired in a semi-natural environment. In the greenhouse, imaging was conducted under controlled lighting with a fixed top-view setup; in semi-natural environments, spectral data were collected manually from multiple oblique angles under supplemented natural light. Support Vector Machine classification achieved F1 scores above 0.8 for anthesis prediction when reflectance data were transformed using Standard Normal Variate, Hyper-hue, or Principal Component Analysis. After feature selection, F1 scores above 0.75 could be achieved with only five wavelengths. Furthermore, the SNV transformation demonstrated robust performance under limited training conditions, maintaining high classification accuracy and strong generalizability across varying data sizes. These findings highlight the effectiveness of transformation-enriched data and optimized feature selection for accurate growth stage classification. This study provides a low-cost approach to alleviate manual inspection burdens, improve regulatory compliance, and increase biosafety during biotechnology field trial practices.

Why it matches plant phenotyping methods個体コムギの生殖生長段階をハイパースペクトル/RGB画像と機械学習で自動推定する方法が研究の中心であり、検証性能も報告しているため。

titleHyperspectral-Based Classification of Individual Wheat Plants into Fine-Scale Reproductive Stages for Anthesis Prediction

Visual-Language Transformer-Based Tomato Leaf Disease Detection for Portable Greenhouse Monitoring Device →

Abstract Tomato leaf diseases pose a significant threat to global food security, necessitating accurate and efficient detection methods. This paper introduces the Tomato Leaf Disease Visual Language Model (TLDVLM), a novel approach based on the BLIP-2 architecture enhanced with Low-Rank Adaptation (LoRA), for precise classification of 10 distinct tomato leaf diseases. Our methodology integrates a sophisticated image preprocessing pipeline, utilizing GroundingDINO for robust leaf detection and SAM-2 for pixel-level segmentation, ensuring that the model focuses solely on relevant plant tissue. The TLDVLM leverages the powerful multimodal understanding of BLIP-2, with LoRA applied to its Q-Former module, enabling parameter-efficient fine-tuning without compromising performance. Comparative experiments demonstrate that the TLDVLM significantly outperforms baseline models, including CLIP-LoRA and ConvNeXT-tiny, achieving an accuracy of 97.27%, a precision of 0.9587, a recall of 0.9789, and an F1-score of 0.9681. Beyond classification, the finetuned TLDVLM checkpoints are integrated into a practical application for new image inference. This application displays the raw and segmented images, the predicted disease, and offers functionalities to fetch comprehensive information on disease causes and remedies using external APIs (e.g., OpenAI), with an option to download a PDF summary for offline access on a portable device. This research highlights the potential of LoRA-adapted Vision-Language Models in developing highly accurate, efficient, and user-friendly agricultural diagnostic tools.

Why it matches plant phenotyping methodsトマト葉の病害状態を画像から分類する手法を開発し、複数モデルとの比較実験で性能を検証しているため、植物病害フェノタイピング手法が中心である。

abstractThis paper introduces the Tomato Leaf Disease Visual Language Model (TLDVLM), a novel approach based on the BLIP-2 architecture enhanced with Low-Rank Adaptation (LoRA), for precise classification of 10 distinct tomato leaf diseases.

Optimization of a multi-environmental detection model for tomato growth point buds based on multi-strategy improved YOLOv8. →

Tomato growing points and flower buds serve as vital physiological indicators influencing yield quality, yet their detection remains challenging in complex facility environments. This study develops an improved YOLOv8 model for robust flower bud detection by first constructing a comprehensive multi-environment dataset covering 10 typical growing conditions with enhanced annotations. Three key innovations address YOLOv8's limitations: (1) an SE attention module boosts feature representation in cluttered environments, (2) GhostConv replaces standard convolution to reduce computational load by 19% while preserving feature discrimination, and (3) a scale-adaptive WIoU_v2 loss function optimizes gradient allocation for variable-quality data. Ablation experiments confirm these modifications synergistically improve adaptability to scale and environmental variations, achieving 97.8% mAP@0.5 (+ 0.5%) and 85.1% mAP@0.5:0.95 (+ 5.1%) with 11% fewer parameters. Practical deployment on agricultural robots in operational greenhouses demonstrated 93.6% detection accuracy, validating the model's effectiveness for precision agriculture applications. The proposed system achieves an optimal balance of accuracy, speed, and lightweight design while providing immediately applicable solutions for automated tomato monitoring.

Why it matches plant phenotyping methodsトマトの生長点・花蕾という植物器官を対象に、複雑な環境での画像検出モデルを開発し、データセット構築、アブレーション、実環境ロボットでの検証まで行っており、植物フェノタイピング手法が中心である。

abstractThis study develops an improved YOLOv8 model for robust flower bud detection by first constructing a comprehensive multi-environment dataset covering 10 typical growing conditions with enhanced annotations.

Temporal semantic multispectral point cloud generation and feature fusion pipeline for comprehensive trait estimation in greenhouse tomatoes →

Abstract has not been obtained from indexed metadata or an accessible article page.

Why it matches plant phenotyping methods温室トマトの複数形質推定を目的とするマルチスペクトル点群生成・特徴融合パイプラインが研究の中心であり、植物フェノタイピング手法に該当する。

titleTemporal semantic multispectral point cloud generation and feature fusion pipeline for comprehensive trait estimation in greenhouse tomatoes

Thermography reveals the potential of traditional bean varieties against common bacterial blight →

Abstract The common bean ( Phaseolus vulgaris L.) is of great socioeconomic importance in Brazil, being widely cultivated by family farmers who preserve traditional varieties adapted to regional conditions. These varieties represent a strategic source of genetic variability for breeding programs. Among the main phytosanitary obstacles to cultivation, common bacterial blight (CBB), caused by Xanthomonas phaseoli pv. phaseoli stands out as it compromises bean productivity. This study aimed to evaluate 54 traditional genotypes for resistance to CBC, using visual severity scales and infrared thermography as a complementary tool. The experiment was carried out in a greenhouse, in a randomized block design with three replicates, in two seasons (May and October 2019). Inoculation was performed by two methods (cutting with scissors at 10⁷ CFU·mL -1 and infiltration with a syringe at 10⁶ CFU·mL -1 ) with the strain Xpp ‘139-y’. The variables analyzed included area under the disease progress curve (AUDPC), incubation period (IP), and final score (FS). Thermal images were obtained up to three days after inoculation, allowing the calculation of the mean temperature difference (MTD) between healthy and infected tissues. Thermographic analysis enabled early detection of infection, before the appearance of visual symptoms, distinguishing resistant genotypes such as BAC-6 and UENF 2599. The results highlight the potential of thermography as a fast, accurate, and non-destructive method for selecting resistant genotypes, contributing to the modernization and sustainability of bean breeding programs.

Why it matches plant phenotyping methods赤外線サーモグラフィーで感染植物組織の温度差を測定し、視覚症状前の病害状態を推定する方法を、抵抗性選抜へ実質的に適用しているため含める。

abstractusing visual severity scales and infrared thermography as a complementary tool

Advances in Precision Farming: a contribute for estimating crop health and water stress by comparing UAV Multispectral and Thermal Imagery →

Abstract. Current climate change is largely due to the continuing increase in the anthropogenic greenhouse effect, with major environmental repercussions, especially in agriculture. The increase of global warming, salinity of water resources and frequency of extreme weather events has devastating consequences on the primary sector, in particular on the photosynthetic activity of crops and, therefore, their agricultural yield. The current climate crisis, in fact, leads to an increase in water requirements, the proliferation of weeds, and the depletion of nutrients in the soil, necessitating the massive use of fertilisers, herbicides and pesticides, which, in turn, trigger substantial alterations in ecosystem balances. In response to these critical issues, precision agriculture (PA) constitutes a data-driven approach based on the interpretation of multispectral and thermal datasets obtained by different remote sensing techniques and the use of latest-generation sensors to recognise the state of health of crops and, therefore, optimise agricultural production with a more rational and sustainable management of resources.This paper presents the results of a survey campaign carried out in October 2023 on two citrus fields located in south-eastern Sicily (Italy) to highlight the health status of crops just before the harvesting period. By using multispectral and thermal sensors installed on a drone, different vegetation indices have been calculated to identify, in each field, the areas with the highest photosynthetic activity and the zones characterised by a lack of water or other nutrients, on which targeted agronomic interventions should be planned as a priority.

Why it matches plant phenotyping methodsUAVマルチスペクトル・熱画像を用いて、柑橘作物の健康状態、光合成活性、水ストレスを推定するセンシング手法の適用が中心であり、単なるルーチン測定ではない。

titleestimating crop health and water stress by comparing UAV Multispectral and Thermal Imagery

Prediction of Rice Chlorophyll Index (CHI) Using Nighttime Multi-Source Spectral Data →

The chlorophyll index (CHI) is a crucial indicator for assessing the photosynthetic capacity and nutritional status of crops. However, traditional methods for measuring CHI, such as chemical extraction and handheld instruments, fall short in meeting the requirements for efficient, non-destructive, and continuous monitoring at the canopy level. This study aimed to explore the feasibility of predicting rice canopy CHI using nighttime multi-source spectral data combined with machine learning models. In this study, ground truth CHI values were obtained using a SPAD-502 chlorophyll meter. Canopy spectral data were acquired under nighttime conditions using a high-throughput phenotyping platform (HTTP) equipped with active light sources in a greenhouse environment. Three types of sensors—multispectral (MS), visible light (RGB), and chlorophyll fluorescence (ChlF)—were employed to collect data across different growth stages of rice, ranging from tillering to maturity. PCA and LASSO regression were applied for dimensionality reduction and feature selection of multi-source spectral variables. Subsequently, CHI prediction models were developed using four machine learning algorithms: support vector regression (SVR), random forest (RF), back-propagation neural network (BPNN), and k-nearest neighbors (KNNs). The predictive performance of individual sensors (MS, RGB, and ChlF) and sensor fusion strategies was evaluated across multiple growth stages. The results demonstrated that sensor fusion models consistently outperformed single-sensor approaches. Notably, during tillering (TI), maturity (MT), and the full growth period (GP), fused models achieved high accuracy (R2 > 0.90, RMSE < 2.0). The fusion strategy also showed substantial advantages over single-sensor models during the jointing–heading (JH) and grain-filling (GF) stages. Among the individual sensor types, MS data achieved relatively high accuracy at certain stages, while models based on RGB and ChlF features exhibited weaker performance and lower prediction stability. Overall, the highest prediction accuracy was achieved during the full growth period (GP) using fused spectral data, with an R2 of 0.96 and an RMSE of 1.99. This study provides a valuable reference for developing CHI prediction models based on nighttime multi-source spectral data.

Why it matches plant phenotyping methods夜間マルチソース分光データと高スループット表現型解析プラットフォームを用い、イネ群落のクロロフィル指数を機械学習で推定する方法の開発・評価が中心である。

abstractThis study aimed to explore the feasibility of predicting rice canopy CHI using nighttime multi-source spectral data combined with machine learning models.

Leaf Area Estimation in High-Wire Tomato Cultivation Using Plant Body Scanning →

Accurate estimation of the leaf area index (LAI), a key indicator of canopy development and light interception, is essential for improving productivity in greenhouse tomato cultivation. This study presents a non-destructive LAI estimation method using side-view images captured by a vertical scanning system. The system recorded the full vertical profile of tomato plants grown under two deleafing strategies: modifying leaf height (LH) and altering leaf density (LD). Vegetative and leaf areas were extracted using color-based masking and semantic segmentation with the Segment Anything Model (SAM), a general-purpose deep learning tool. Regression models based on leaf or all vegetative pixel counts showed strong correlations with destructively measured LAI, particularly under LH conditions (R2 > 0.85; mean absolute percentage error ≈ 16%). Under LD conditions, accuracy was slightly lower due to occlusion and leaf orientation. Compared with prior 3D-based methods, the proposed 2D approach achieved comparable accuracy while maintaining low cost and a labor-efficient design. However, the system has not been tested in real production, and its generalizability across cultivars, environments, and growth stages remains unverified. This proof-of-concept study highlights the potential of side-view imaging for LAI monitoring and calls for further validation and integration of leaf count estimation.

Why it matches plant phenotyping methodsトマトのLAIという植物形質を、垂直スキャン画像・画像分割・回帰モデルで非破壊推定する手法を開発し、破壊測定との精度検証も行っており、フェノタイピング手法が研究の中心である。

abstractThis study presents a non-destructive LAI estimation method using side-view images captured by a vertical scanning system.

Exploring plant stress-reducing ventilation in greenhouses with plant sensors and decision tree analysis →

In spring and summer, tomato plants grown in greenhouses often experience high levels of (solar) irradiation in a dry atmosphere during the day. On such hot and sunny days, the resulting high transpiration rates greatly deplete the internal water storage pools (i.e., living cells) of the plant, which gives the plant higher daily stress and may result in irreversible plant or fruit damage. To facilitate the replenishment of internal water storage pools of a plant, greenhouse farmers in Belgium and the Netherlands employ a targeted ventilation strategy, which we have dubbed the ‘plant stress-reducing ventilation’ strategy. This is a commonly used, though scientifically largely understudied, technique in greenhouse cultivation. This makes the strategy difficult to master, leaving growers divided on its effectiveness. To better understand and quantify the effects of the stress-reducing ventilation strategy, we equipped tomato plants (Solanum lycopersicum L.) in a commercial Belgian greenhouse with sap flow and stem diameter variation sensors to continuously measure the plant response to the technique. Climate and greenhouse control data were recorded by the climate computer. This plant response was classified and used to generate a decision tree using machine learning, pointing out the most important factors that reduced plant stress when applying the technique. Our approach is novel in the sense that it incorporates plant sensor measurements into a decision tree algorithm for climate control. This integration has proven crucial in comprehending the practical application of the plant stress-reducing ventilation strategy, now better understood from an ecophysiological perspective.

Why it matches plant phenotyping methods植物センサーでストレス応答を連続測定し、機械学習による意思決定木で解析する手法統合が研究の中心であり、単なる生理測定ではない。

abstractwe equipped tomato plants (Solanum lycopersicum L.) in a commercial Belgian greenhouse with sap flow and stem diameter variation sensors to continuously measure the plant response to the technique.

Transpiration Insights: Estimating Transpiration Through Advanced Modeling →

O_LIWe conducted research to predict daily transpiration in crops by utilizing a combination of machine learning (ML) models combined with extensive transpiration data from gravimetric load cells and ambient sensors. Our aim was to improve the accuracy of transpiration estimates. C_LIO_LIData were collected from hundreds of plant specimens growing in two semi-controlled greenhouses over seven years, automatically measuring key physiological traits (serves as our ground truth data) and meteorological variables with high temporal resolution and accuracy. We trained Decision tree, Random Forest, XGBoost, and Neural Network models on this dataset to predict daily transpiration. C_LIO_LIThe Random Forest and XGBoost models demonstrated high accuracy in predicting the whole plant transpiration, with R{superscript 2} values of 0.89 on the test set (cross-validation) and R2 = 0.82 on holdout experiments. Ambient temperature was identified as the most influential environmental factors affecting transpiration. C_LIO_LIOur results emphasize the potential of ML for precise water management in agriculture, and simplify some of the complex and dynamic environmental forces that shape transpiration. C_LI

Why it matches plant phenotyping methods機械学習モデルにより植物個体の蒸散量を推定する手法を開発・検証しており、植物生理形質の取得・推定が研究の中心である。

abstractWe conducted research to predict daily transpiration in crops by utilizing a combination of machine learning (ML) models combined with extensive transpiration data from gravimetric load cells and ambient sensors.

Remote Sensing of Strawberry Plants Using UAVs and Deep Learning →

Abstract Background To address the challenge of real-time plant monitoring in greenhouse environments, this industry-driven research focuses on developing an autonomous quadrotor UAV system specifically designed for monitoring strawberry plants. Traditional methods for greenhouse monitoring are labor-intensive and lack scalability, particularly in precision agriculture applications. Method The study begins by proposing the mature strawberry detection model for greenhouse environment. The YOLOv9 with GLEAN advantage is proposed to detect small mature strawberries via on board camera on the quadrotor. Also the hybrid trajectory tracking controller for quadrotor is proposed and validated in both simulation and real time environment. The UAV follows predefined way points for navigation in the greenhouse environment. An onboard vision system is integrated, employing a novel YOLOv9-GLEAN-based algorithm for online and offline mature strawberry detection and counting. Results The YOLOv9-GLEAN model achieves high detection accuracy, as confirmed by evaluation metrics such as precision, recall, and F1-score. The proposed hybrid (PID+LQR) controller demonstrates superior tracking performance compared to other conventional controllers. The integrated control and perception system proves effective in both simulated and real-world greenhouse environments. Discussion The research validates the efficacy of deep learning models, with YOLOv9-GLEAN showing exceptional performance in enabling rapid, precise, and automated detection of ripe strawberries through quadrotor deployment in greenhouse environments. Such agricultural monitoring technologies represent a substantial advancement beyond conventional manual inspection approaches, empowering farmers and greenhouse operators to execute well-informed, time-sensitive management decisions that minimize crop losses and optimize production yields. This investigation underscores the revolutionary impact that deep learning technologies can have within greenhouse agriculture.

Why it matches plant phenotyping methods温室イチゴの成熟果実を画像認識で検出・計数する手法とUAV搭載システムが研究の中心であり、果実の成熟状態・数量という植物器官の形質を抽出しているため含める。

abstractThe YOLOv9 with GLEAN advantage is proposed to detect small mature strawberries via on board camera on the quadrotor.

Spatio-Temporal 4D Phenotyping for Automated Morphological Genotype Differentiation of Sugar Beet →

Abstract 3D models are used in plant phenotyping for non-destructive quantification and analysis of morphological characteristics. Analyzing plant structure allows breeders to select for desirable traits, associated with e.g. drought tolerance or increased productivity. In sugar beet, morphological parameters depict an essential element of the variety approval for distinguishing between genotypes. However, only a limited number of measured or scored parameters are considered at a single time point. In contrast, 4D data adds a temporal component and can depict the dynamic development of 3D parameters. To explore the potential of spatio-temporal 4D phenotyping for automated crop genotype differentiation, a greenhouse experiment was conducted by us covering twelve sugar beet genotypes. High-resolution 3D models were generated twice a week over the course of two months and both common and novel 3D morphological parameters were extracted. The importance of these parameters was assessed by us, and the dataset was analyzed using unsupervised pointwise clustering and time series clustering. Varying importance of parameters depending on the time point and significantly higher importance of plant parameters compared to leaf parameters are demonstrated by our results. Moreover, increased and more stable genotype differentiation is archived using time series clustering compared to pointwise clustering. Furthermore, taproot formation of sugar beet was found to have a crucial impact on morphological development. Substantial variations in the dynamic development of 3D morphological parameters underline the importance of 4D data for plant genotype differentiation. Thus, a novel foundation for genotype differentiation in plant phenotyping is provided by our findings.

Why it matches plant phenotyping methods4Dの3Dモデルから植物形態形質を時系列抽出し、遺伝型識別のためのクラスタリング手法を評価することが研究の中心である。

titleSpatio-Temporal 4D Phenotyping for Automated Morphological Genotype Differentiation of Sugar Beet

Prediction of harvest-related traits in barley using high-throughput phenotyping data and machine learning →

Abstract Developing crop varieties that maintain productivity under drought is essential for future food security. Here, we investigated the potential of time-resolved high-throughput phenotyping to predict harvest-related traits and identify drought-stressed plants. Six barley lines ( Hordeum vulgare ) were grown in a greenhouse environment with well-watered and drought treatments, and phenotyped using RGB, thermal infrared, chlorophyll fluorescence and hyperspectral imaging sensors. Temporal phenomic classification model accurately distinguished between drought-treated and control plants, achieving high accuracy (R 2 ≥ 0.97) even when exclusively using predictors only from the early phase after drought induction. Canopy temperature depression at the early stage and RGB-derived plant size estimates at the late stage were identified as key classification features. Temporal phenomic prediction model of harvest-related traits achieved particularly high mean R 2 values for total biomass dry weight (0.97) and total spike weight (0.93), with RGB plant size estimators emerging as important predictors. Prediction accuracy for these traits remained high (R 2 ≥ 0.84) when using only predictors from the first half of the experiment. Models trained on pooled drought and control data outperformed single-treatment models and retained high accuracy when applied across treatments. These findings support the integration of high-throughput phenotyping and temporal modelling to enable timely and more cost-effective selection of drought-resilient genotypes, and illustrate the broader potential of phenomics-driven approaches in accelerating crop improvement under stress-prone conditions.

Why it matches plant phenotyping methodsRGB・熱赤外・蛍光・ハイパースペクトルによる高スループット表現型取得と、時系列モデルによる干ばつ状態および収穫形質の予測が研究の中心である。

abstractwe investigated the potential of time-resolved high-throughput phenotyping to predict harvest-related traits and identify drought-stressed plants

SSP-MambaNet: An automated system for detection and counting of missing seedlings in glass greenhouse-grown virus-free strawberry →

Precisely identifying missing virus-free strawberry mother plants in nutrient pots post-transplantation is crucial for optimizing seedling management and maximizing yields in glass greenhouses. Thus, we present an automated method for detecting and counting missing seedlings based on SSP-MambaNet. Challenges in this process include the variable growth morphology of seedlings and complex environmental conditions in the greenhouse. Our approach starts with SPDFFA (Spatial-to-Depth Feature Fusion Attention) to enhance feature representation while retaining critical information, ensuring the preservation of key details. Additionally, the multi-scale CVSSB(Complex Visual State Space) and CVSSB-E(Expanded CVSSB) modules combine multi-scale and multi-directional spatial features, augmenting the model's capacity to recognize inter-image dependencies. Secondly, the MPDIoU is a novel loss function to tackle the optimization challenge of bounding boxes with similar shapes but different sizes, which enhances the accuracy of localizing strawberry seedlings and nutrient pots. Finally, Distance Intersection over Union is utilized for establishing a belongingness relationship between strawberry seedlings and pots, accurately identifying missing seedlings and counting the corresponding pots. Experimental results demonstrate that SSP-MambaNet achieves 94.9 %in average precision, 92.8 ​% in recall rate,88.1 ​% in precision, and 90.4 ​% F1 score for strawberry seedlings and pots. It outperforms the YOLOv7 by 4.7 ​% in average precision, and 2.6 ​% in recall rate while reducing 66.7 f/s in FPS. Furthermore, the proposed method shows 94.29 ​% accuracy in detecting missing seedlings and 97.14 ​% accuracy in counting nutrient pots with missing seedlings. These results showcase its effectiveness in improving overall seedling quality and providing timely replanting guidance in glass greenhouses.

Why it matches plant phenotyping methods温室内のイチゴ苗の欠損状態を画像から検出・計数する自動手法を開発し、精度比較・検証しており、植物状態の取得方法が研究の中心です。

abstractwe present an automated method for detecting and counting missing seedlings based on SSP-MambaNet.

Comparison of multiple plant sensors aimed at early detection of drought stress in the greenhouse →

With a growing world population and mounting pressure on natural resources, the need for efficient, sustainable food production is becoming increasingly urgent. A promising route towards improving agricultural productivity is to expand the use of sensors to monitor plants and their environment with high accuracy and temporal resolution. Data generated by such sensors is useful for optimizing irrigation, nutrition and illumination in the context of autonomous greenhouses, while allowing mitigation of plant stress due to pests, diseases and extreme climate conditions. We simultaneously tested ten different types of sensors for monitoring early signs of drought stress in mature, high-wire tomato plants grown in rockwool. Sensors ranged from high-density climate sensors to novel sensors for monitoring plant-specific parameters like acoustic emissions, stomatal dynamics, sap flow and stem diameter. Withholding water for two days led to a quick and complete depletion of water in the rockwool slabs, and strongly affected whole-plant transpiration, resulting in strong changes in: acoustic emissions, stomatal pore area, stomatal conductance, and stem diameter, all of which were found to be significant indicators of early drought stress. This work demonstrates the usefulness of these sensors in a greenhouse environment and provides a comparison between measured parameters in magnitude and onset time, aimed at the early detection of drought stress. Our study aims to facilitate sensor selection and implementation in precision agriculture.

Why it matches plant phenotyping methods複数の植物センサーを比較し、トマトの早期乾燥ストレス指標を測定・評価することが研究の中心であり、センサー選択と実装に再利用可能な技術的知見を提供している。

abstractWe simultaneously tested ten different types of sensors for monitoring early signs of drought stress in mature, high-wire tomato plants grown in rockwool.

Comprehensive plant health monitoring: expert-level assessment with spatio-temporal image data. →

Maintaining crop health is essential for global food security, yet traditional plant monitoring methods based on manual inspection are labor-intensive and often inadequate for early detection of stressors and diseases, and insufficient for timely, proactive interventions. To address this challenge, we propose a deep learning-based framework for expert-level, spatiotemporal plant health assessment using sequential RGB images. Our method categorizes plant health into five levels, ranging from very poor to optimal, based on visual and morphological indicators observed throughout the cultivation cycle. To validate the approach, we collected a custom dataset of 12,119 annotated images from 200 tomato plants across three varieties, grown in semi-open greenhouses over multiple cultivation seasons within one year. The framework leverages state-of-the-art CNN and transformer architectures to produce accurate, stage-specific health predictions. These predictions closely align with expert annotations, demonstrating the model's reliability in tracking plant health progression. In addition, the system enables the generation of dynamic cultivation maps for continuous monitoring and early intervention, supporting data-driven crop management. Overall, the results highlight the potential of this framework to advance precision agriculture through scalable, automated plant health monitoring, guided by an understanding of key visual indicators and stressors affecting crop health throughout the cultivation period.

Why it matches plant phenotyping methodsRGB画像から植物の形態指標に基づく健康状態を推定する深層学習フレームワークを開発・検証しており、植物表現型の取得・抽出が研究の中心です。

abstractwe propose a deep learning-based framework for expert-level, spatiotemporal plant health assessment using sequential RGB images.

Forecasting growth dynamics of hydroponic kale in controlled environment agriculture through vision-based phenotyping and time-series modeling →

In controlled environment agriculture (CEA), accurate yield forecasting remains challenging due to reliance on environmental sensor data, which fails to capture plants’ dynamic morphological responses to growth conditions. This study bridges the gap by establishing a vision-based framework to forecast plant growth dynamics over prediction windows of 2, 4, and 8 days using automated phenotyping and time-series modelling. A plant phenotype monitoring framework was implemented using commercially available cameras and off-the-shelf deep learning-based models (YOLO). The robustness of the YOLO and time-series models was rigorously evaluated under a range of treatment conditions, including a control, salt stress levels at 3, 6, and 9 ppt, and different root architectures (single-root and split-root) in hydroponic greenhouse trials conducted over two growing seasons. Top-view images of the plants were collected using GoPro and Raspberry Pi cameras, and different YOLOv8 instance segmentation model variants were trained on four image datasets to extraction of morphological traits such as area, major, and minor axes. Results indicated that YOLOv8 generalized well, achieving mAP50 for bounding boxes and masks in the range of 0.897 – 0.952 and 0.896 – 0.947, respectively. Model-derived morphological parameters effectively captured growth differences across salt levels and root architectures, with split-root plants showed resiliency under salt stress compared to single-root. Comparisons between physical measurements and image-derived parameters such as major and minor axes yielded high R² values of 0.85 and 0.92 for single-root systems, and 0.90 and 0.84 for split root systems. Additionally, the area parameter obtained from images showed an R² of 0.882 when compared with plant fresh weight. ARIMA model used to forecast the plant area parameters over 2-, 4-, and 8-days windows and evaluated using MAPE. Notably, the 2-day forecasts for single-root plants under 9 ppt salt stress yielded the lowest MAPE values (3.99 in the fall and 1.70 in the spring), although 8-day forecasts at higher salt concentrations exhibited generally larger errors. For split-root plants, the 4 days forecast under 3 ppt salt stress produced a MAPE of 7.13 in the fall, while in the spring, the 8 days forecast at 9 ppt achieved a MAPE of 2.08. The forecasted area values demonstrated R² values of 0.623, 0.671, and 0.75 for the 2-, 4-, and 8-day forecast windows respectively when compared with fresh weight, indicating that the area parameter is a reliable predictor of yield. These findings confirm that morphological changes capture environmental influences and can be reliably forecasted, introducing a scalable, data-driven method to predict yield in CEA while helping growers optimize resource usage and reduce productivity risks.

Why it matches plant phenotyping methods画像ベースの植物表現型取得と時系列予測を中心に、形態形質の抽出、モデル性能評価、物理測定との検証を行っているため、方法論文として適格。

abstractThis study bridges the gap by establishing a vision-based framework to forecast plant growth dynamics over prediction windows of 2, 4, and 8 days using automated phenotyping and time-series modelling.

Real-time semantic SLAM-based 3D reconstruction robot for greenhouse vegetables →

Abstract has not been obtained from indexed metadata or an accessible article page.

Why it matches plant phenotyping methods温室野菜を対象とするリアルタイム意味SLAM・3D再構成ロボットの開発が主題であり、植物形状の取得・再構成を担うフェノタイピング基盤と判断できる。

titleReal-time semantic SLAM-based 3D reconstruction robot for greenhouse vegetables

Analysis of Irrigation, Crop Growth and Physiological Information in Substrate Cultivation Using an Intelligent Weighing System →

The online dynamic collection of irrigation and plant physiological information is crucial for the precise irrigation management of nutrient solutions and efficient crop cultivation in vegetable soilless substrate cultivation facilities. In this study, an intelligent weighing system was installed in a tomato substrate cultivation greenhouse. The monitored values from the intelligent weighing system’s pressure-type module were used to calculate irrigation start–stop times, frequency, volume, drainage volume, drainage rate, evapotranspiration, evapotranspiration rate, and stomatal conductance. In contrast, the monitored values of the suspension-type weighing module were used to calculate the amount of weight change in the plants, which supported the dynamic and quantitative characterization of substrate cultivation irrigation and crop growth based on an intelligent weighing system. The results showed that the monitoring curves of pressure and flow sensors based on the pressure-type module could accurately identify the irrigation start time and number of irrigations and calculate the irrigation volume, drainage volume, and drainage rate. The calculated irrigation amount was closely aligned with that determined by an integrated-water–fertilizer automatic control system (R2 = 0.923; mean absolute error (MAE) = 0.105 mL; root-mean-square error (RMSE) = 0.132 mL). Furthermore, transpiration rate and leaf stomatal conductance were obtained through inversion, and the R2, MAE, and RMSE of the extinction coefficient correction model were 0.820, 0.014 mol·m−2·s−1, and 0.017 mol·m−2·s−1, respectively. Compared to traditional estimation methods, the MAE and RMSE decreased by 12.5% and 15.0%, respectively. The measured values of fruit picking and leaf stripping linearly fitted with the calculated values of the suspended weighing module, and R2, MAE, and RMSE were 0.958, 0.145 g, and 0.143 g, respectively. This indicated that data collection based on the suspension-type weighing module could allow for a dynamic analysis of plant weight changes and fruit yield. In summary, the intelligent weighing system could accurately analyze irrigation information and crop growth physiological indicators under the practical application conditions of facility vegetable substrate cultivation, providing technical support for the precise management of nutrient solutions.

Why it matches plant phenotyping methodsインテリジェント計量システムを用いて植物重量変化、蒸散、気孔コンダクタンス、果実収量などの形質を取得・推定し、精度検証しているため、植物フェノタイピング手法が中心である。

abstractFurthermore, transpiration rate and leaf stomatal conductance were obtained through inversion

Use of low-cost RGB images to estimate nitrogen, chlorophyll, and leaf area status in basil ‘Nufar’ →

Nitrogen is a critical nutrient for basil (Ocimum basilicum L.), significantly influencing chlorophyll synthesis, leaf area development, and plant productivity. Traditional nitrogen assessment methods are destructive, time-consuming, and costly, limiting their practicality. Low-cost red-green-blue (RGB) imaging offers a promising alternative for the rapid, nondestructive estimation of plant nutritional status; however, its applicability in aromatic herbs like basil remains underexplored. This study evaluated using RGB imaging to estimate leaf area, nitrogen, and chlorophyll status in basil ‘Nufar’ as a tool for precision nutrient management. Using the Steiner nutrient solution, the basil plants were grown in a greenhouse under five nitrogen levels (0, 4, 8, 12, and 16 [mEq∙L−1] of NO3−NO3−). Weekly RGB images were acquired and processed through photogrammetric restitution to generate scaled orthomosaics. Seventeen spectral vegetation indices were obtained and correlated with reference measurements of nitrogen, chlorophyll, and leaf area by regression analysis. Results showed that a nitrogen level of 16 mEq∙L−1 NO3− significantly enhanced plant growth, development, and green coloration. Among the indices evaluated, the Normalized Green-Red Difference Index (NGRDI), Red Index (RI), and Color Index of Vegetation Extraction (CIVE) exhibited the strongest correlations with nitrogen concentration (r = 0.92–0.93), chlorophyll concentration (r = 0.94–0.97), and leaf area (r = 0.93–0.97). These findings confirm that low-cost RGB imaging provides an accurate and efficient method for monitoring nitrogen status, chlorophyll content, and leaf area in basil ‘Nufar.’ This approach offers a valuable tool for optimizing nutrient management and yield prediction in this economically important medicinal and aromatic species.

Why it matches plant phenotyping methods低コストRGB画像とフォトグラメトリによる植物栄養状態・葉面積・クロロフィル推定が研究の中心であり、画像取得・処理と指標の技術評価を実施している。

abstractLow-cost red-green-blue (RGB) imaging offers a promising alternative for the rapid, nondestructive estimation of plant nutritional status

Spectroscopic detection of cotton Verticillium wilt by spectral feature selection and machine learning methods. →

Introduction Verticillium wilt is a severe soil-borne disease that affects cotton growth and yield. Traditional monitoring methods, which rely on manual investigation, are inefficient and impractical for large-scale applications. This study introduces a novel approach combining machine learning with feature selection to identify sensitive spectral features for accurate and efficient detection of cotton Verticillium wilt. Methods We conducted comprehensive hyperspectral measurements using handheld devices (350-2500 nm) to analyze cotton leaves in a controlled greenhouse environment and employed Unmanned Aerial Vehicle (UAV) hyperspectral imaging (400-995 nm) to capture canopy-level data in field conditions. The hyperspectral data were pre-processed to extract wavelet coefficients and spectral indices (SIs), enabling the derivation of disease-specific spectral features (DSSFs) through advanced feature selection techniques. Using these DSSFs, we developed detection models to assess both the incidence and severity of leaf damage by Verticillium wilt at the leaf scale and the incidence at the canopy scale. Initial analysis identified critical spectral reflectance bands, wavelet coefficients, and SIs that exhibited dynamic responses as the disease progressed. Results Model validation demonstrated that the incidence detection models at the leaf scale achieved a peak classification accuracy of 85.83%, which is about 10% higher than traditional methods without feature selection. The severity detection models showed improved precision as disease severity of damage increased, with accuracy ranging from 46.82% to 93.10%. At the canopy scale, UAV-based hyperspectral data achieved a remarkable classification accuracy of 93.0% for disease incidence detection. Discussion This study highlights the significant impact of feature selection on enhancing the performance of hyperspectral-based remote sensing models for cotton wilt monitoring. It also explores the transferability of sensitive spectral features across different scales, laying the groundwork for future large-scale early warning systems and monitoring cotton Verticillium wilt.

Why it matches plant phenotyping methods綿花の病害状態をハイパースペクトル計測と特徴選択・機械学習で葉および群落レベルに推定し、モデル性能も検証しているため、病害フェノタイピング手法が中心です。

abstractThis study introduces a novel approach combining machine learning with feature selection to identify sensitive spectral features for accurate and efficient detection of cotton Verticillium wilt.

Plant stem occlusion inpainting with Deep Reinforcement Learning →

Growth monitoring of tomato plants in large greenhouse environments is critical for quality and efficient production. Stem diameter and elongation are key phenotypic traits for plant growth monitoring. Traditional methods, however, rely on manual operations, which are time-consuming and labor-intensive and do not apply to large-scale greenhouses. Currently, automated image-based methods exemplified by three-dimensional (3D) point cloud technology are among the preferred solutions. Nevertheless, the occlusion of plant structures during the information acquisition process is challenging for practical applications. To address this challenge, this study proposes a novel method for plant stem occlusion inpainting using Deep Reinforcement Learning (DRL). Unlike most existing 3D reconstruction approaches that require depth data from multiple viewpoints, our solution captures 3D point cloud data from a single direction. The DRL model is applied to inpaint the incomplete stem for accurate stem reconstruction and phenotypic measurements. Specifically, our approach consists of two parts, structural completion and stem diameter completion. First, we extract the point cloud of incomplete stems from the RGB-D camera data. Second, we obtain the spatial structure of the stems by inpainting the 3D stem centerline with the DRL model. Finally, we add shape features (stem diameters) by inpainting the two edge lines of the stem occlusion part with the DRL model. For stem inpainted 3D point cloud data, we conducted validation experiments by measuring several commonly used stem phenotypic traits in tomato plants, including stem diameter, stem length, and stem inclination. The experimental results show that the Mean Absolute Percentage Error (MAPE) of the occluded main stem diameter is 9.7%, stem length is 5.7%, and tilt angle is 1%. For the occluded branch stem, the MAPE of stem diameter is 23.1%, stem length is 7.9%, and tilt angle is 1.5%. The accuracy of these measurements for occluded stems is acceptable compared to that obtained from 3D point clouds of unoccluded stems. This highlights the significant potential of using DRL to effectively inpaint occluded 3D point cloud data of plants.

Why it matches plant phenotyping methods植物茎の遮蔽部分を3D点群と深層強化学習で補完し、茎径・茎長・傾斜角という表現型形質を推定・検証する手法が研究の中心である。

abstractthis study proposes a novel method for plant stem occlusion inpainting using Deep Reinforcement Learning (DRL).

Optimizing Indoor Farm Monitoring Efficiency Using UAV: Yield Estimation in a GNSS-Denied Cherry Tomato Greenhouse →

As the agricultural workforce declines and labor costs rise, robotic yield estimation has become increasingly important. While unmanned ground vehicles (UGVs) are commonly used for indoor farm monitoring, their deployment in greenhouses is often constrained by infrastructure limitations, sensor placement challenges, and operational inefficiencies. To address these issues, we develop a lightweight unmanned aerial vehicle (UAV) equipped with an RGB-D camera, a 3D LiDAR, and an IMU sensor. The UAV employs a LiDAR-inertial odometry algorithm for precise navigation in GNSS-denied environments and utilizes a 3D multi-object tracking algorithm to estimate the count and weight of cherry tomatoes. We evaluate the system using two dataset: one from a harvesting row and another from a growing row. In the harvesting-row dataset, the proposed system achieves 94.4\% counting accuracy and 87.5\% weight estimation accuracy within a 13.2-meter flight completed in 10.5 seconds. For the growing-row dataset, which consists of occluded unripened fruits, we qualitatively analyze tracking performance and highlight future research directions for improving perception in greenhouse with strong occlusions. Our findings demonstrate the potential of UAVs for efficient robotic yield estimation in commercial greenhouses.

Why it matches plant phenotyping methodsUAV上のRGB-D・LiDAR・追跡アルゴリズムにより、トマト果実数と重量を推定する手法を開発・評価しており、植物形質取得が研究の中心です。

abstractwe develop a lightweight unmanned aerial vehicle (UAV) equipped with an RGB-D camera, a 3D LiDAR, and an IMU sensor.

End-to-End Deep Learning Approach to Automated Phenotyping of Greenhouse-Grown Plant Shoots →

High-throughput image analysis is a key tool for the efficient assessment of quantitative plant phenotypes. A typical approach to the computation of quantitative plant traits from image data consists of two major steps including (i) image segmentation followed by (ii) calculation of quantitative traits of segmented plant structures. Despite substantial advancements in deep learning-based segmentation techniques, minor artifacts of image segmentation cannot be completely avoided. For several commonly used traits including plant width, height, convex hull, etc., even small inaccuracies in image segmentation can lead to large errors. Ad hoc approaches to cleaning ’small noisy structures’ are, in general, data-dependent and may lead to substantial loss of relevant small plant structures and, consequently, falsified phenotypic traits. Here, we present a straightforward end-to-end approach to direct computation of phenotypic traits from image data using a deep learning regression model. Our experimental results show that image-to-trait regression models outperform a conventional segmentation-based approach for a number of commonly sought plant traits of plant morphology and health including shoot area, linear dimensions and color fingerprints. Since segmentation is missing in predictions of regression models, visualization of activation layer maps can still be used as a blueprint to model explainability. Although end-to-end models have a number of limitations compared to more complex network architectures, they can still be of interest for multiple phenotyping scenarios with fixed optical setups (such as high-throughput greenhouse screenings), where the accuracy of routine trait predictions and not necessarily the generalizability is the primary goal.

Why it matches plant phenotyping methods植物画像から形態・健康形質を直接推定する深層学習手法を開発し、従来のセグメンテーション法と比較検証しており、表現型取得・抽出法が研究の中心である。

abstractHere, we present a straightforward end-to-end approach to direct computation of phenotypic traits from image data using a deep learning regression model.

SmartBerry for AI-based growth stage classification and precision nutrition management in strawberry cultivation. →

Agriculture is vital for human sustenance and economic stability, with increasing global food demand necessitating innovative practices. Traditional farming methods have caused significant environmental damage, highlighting the need for sustainable practices like nutrition management. This paper addresses the emerging integration of artificial intelligence (AI) in agriculture, focusing on the specific challenge of growth stage classification of strawberry plants for optimized nutrition management. While AI has been successfully applied in various agricultural domains, such as plant stress detection and growth monitoring, the precise classification of strawberry growth stages remains underexplored. Accurate growth stage identification is vital for timely nutrient application, directly impacting yield and fruit quality. Our research identifies common gaps in existing literature, including limited or inaccessible datasets, outdated methodologies, and insufficient benchmarking. To overcome these shortcomings, we introduce a robust greenhouse-based dataset covering seven distinct strawberry growth stages, captured under diverse conditions. We then benchmark multiple state-of-the-art models on this dataset, finding that EfficientNetB7 achieves a testing accuracy of 0.837-demonstrating the promise of AI-driven approaches for precise and sustainable nutrient management in horticulture.

Why it matches plant phenotyping methodsイチゴの生育段階という植物状態を画像データセットで分類し、複数モデルをベンチマークすることが研究の中心であるため、植物フェノタイピング手法として収載する。

abstractwe introduce a robust greenhouse-based dataset covering seven distinct strawberry growth stages, captured under diverse conditions.

Artificial Intelligence‐Driven Robotic Sensing System for Noninvasive Crop Health Monitoring and Autonomous Irrigation Management →

This study introduces an artificial intelligence (AI)‐driven robotic system utilizing a 3D‐printed electrophysiological (EP) sensor for noninvasive, real‐time monitoring of plant health signals across different irrigation levels, highlighting the crucial role of these technologies in enhancing smart agriculture and sustainability. The sensing system consists of a mobile robot with a 3D EP sensor and portable Faraday cage for data acquisition, using an AI‐powered convolution neural network to analyze EP data in greenhouses and categorize irrigation levels to optimize water usage for scalable agricultural management. The findings reveal that the 3D EP sensor displays lower and more stable contact resistance (2.10 ± 0.52 MΩ) compared to flat thin‐film sensors (2.96 ± 1.45 MΩ), ensuring high electrical reliability due to effective contact with hairy tomato leaves. The 3D EP sensor's high sensitivity (signal resolution of 0.0122 mV) detects subtle EP signal changes linked to irrigation levels, aiding water optimization and crop yield enhancement. For the first time, this study employs scalogram images for detailed analysis of plant EP signals, achieving a classification accuracy of 86.91%, comparable to red, gren, and blue image‐based methods (86.37%). This system is a reliable tool for long‐term monitoring in smart farming and provides insights into plant signal dynamics.

Why it matches plant phenotyping methods植物の電気生理信号を非侵襲的に取得・解析するセンサー、移動ロボット、AI解析システムを開発し、灌漑状態という植物状態を推定する手法が研究の中心である。

abstractThis study introduces an artificial intelligence (AI)‐driven robotic system utilizing a 3D‐printed electrophysiological (EP) sensor for noninvasive, real‐time monitoring of plant health signals across different irrigation levels

Predicting the greenhouse crop morphological parameters based on RGB-D Computer Vision →

Accurate data acquisition of crop morphological parameters is crucial for effective greenhouse management decision-making and remote sensing technologies are increasingly being applied to automate the data collection process. This research utilised an RGB-D based computer vision method to investigate the correlation between the computer vision features and the lettuce morphological parameters, including leaf area, plant height, diameter, and fresh weight. A dataset of lettuce containing over 300 RGB images and depth images of the 3rd Autonomous Greenhouse Challenge was used, and Random Forest, XGBoost and linear regression models were applied in the prediction. The best NRMSE values for diameter, dry matter content, dry weight, fresh weight, height, and leaf area are 0.08, 0.08, 0.07, 0.07, 0.08, and 0.07, which showed a promising accuracy compared to similar studies. This research demonstrates a novel approach to non-destructively estimate greenhouse leafy vegetable morphological parameters.

Why it matches plant phenotyping methodsRGB-D画像と機械学習によりレタスの形態形質を非破壊推定する手法が研究の中心であり、植物フェノタイピング方法に該当する。

abstractThis research utilised an RGB-D based computer vision method to investigate the correlation between the computer vision features and the lettuce morphological parameters

A 3D point cloud instance segmentation method for strawberry based on SGC →

With effective protective covering and microclimate control, greenhouse crops offer significant advantages, such as high yield and quality, remaining unaffected by seasonal variations and meeting the demand for diverse agricultural products. Leaf area is a critical growth parameter influencing the indoor microclimate and the transport of nutrients within plants. This study introduces a strawberry 3D point cloud instance segmentation method based on SGC to address the challenge of stem and leaf instance segmentation in calculating plant leaf area using 3D point cloud data. High-quality point cloud data were obtained using a 3D scanner, and feature enhancement was achieved through the Leaf Vein and Boundary Preserving Sampling (LVBPS) method. The SGC network achieved an average precision of 90.41% (AP25) and 89.47% (AP50) for instance segmentation, with the precision of leaf segmentation reaching 93.63% (AP25) and 92.80% (AP50). These findings provide valuable technical support and references for greenhouse cultivation and smart agriculture applications. The source code and dataset can be accessed at https://github.com/suyangsuluo/SGC.

Why it matches plant phenotyping methodsイチゴの3D点群から茎・葉をインスタンス分割し、葉面積算出に用いる画像解析手法を開発・評価しており、植物表現型取得が中心である。

abstractThis study introduces a strawberry 3D point cloud instance segmentation method based on SGC to address the challenge of stem and leaf instance segmentation in calculating plant leaf area using 3D point cloud data.

Facility of tomato plant organ segmentation and phenotypic trait extraction via deep learning →

In facility tomato cultivation, analyzing and managing crop phenotypic traits across different growth stages is vital for improving quality and yield. Traditional manual methods are time-consuming and labor-intensive, particularly in densely cultivated environments. This study presents an automated pipeline for extracting key phenotypic parameters, including plant height, stem diameter, and fruit clusters, through three-dimensional (3D) model construction, organ segmentation, and phenotypic analysis. Point cloud data were captured at the seedling, flowering, and fruiting stages using Kinect v2 cameras and registered with the FPFH-ICP algorithm to mitigate occlusion-induced data loss. To better extract phenotypic parameters such as stem diameter and fruit clusters, constructed four multi-feature point clouds datasets, incorporating geometric coordinates, normal vectors, and color information (XYZ, XYZ-RGB, XYZ-Normal, and XYZ-Normal-RGB). RGB data highlighted regions with distinct color contrasts, such as fruits and leaves, while normal vectors captured surface details, enhancing the description of fine structures. To improve segmentation performance, we introduced CAFPoint, a modified PointNet++ model incorporating a multibranch structure and a CrossAttentionFusion (CAF) module. This structure can extract and fuse XYZ, normal and color information in a targeted manner. When applied to XYZ-Normal-RGB data, CAFPoint achieved an accuracy of 0.959 and a mean intersection over union (mIoU) of 0.863, demonstrating its capacity to enhance boundary delineation and feature representation. Phenotypic parameters derived from the segmentation, including stem diameter, fruit cluster count, and plant height, showed strong correlations with manual measurements (R² > 0.79 for stem diameter and fruit cluster count; R² > 0.92 for plant height). The proposed method enables efficient and accurate phenotypic trait extraction for tomatoes at various growth stages in greenhouse facilities, offering a valuable reference for automated trait analysis in controlled agricultural environments.

Why it matches plant phenotyping methods3D点群取得、器官セグメンテーション、深層学習モデルを統合し、トマトの草丈・茎径・果房数を自動抽出して手測定と検証しており、表現型取得手法が研究の中心である。

abstractThis study presents an automated pipeline for extracting key phenotypic parameters, including plant height, stem diameter, and fruit clusters, through three-dimensional (3D) model construction, organ segmentation, and phenotypic analysis.

RLK-YOLOv8: multi-stage detection of strawberry fruits throughout the full growth cycle in greenhouses based on large kernel convolutions and improved YOLOv8. →

Introduction In the context of intelligent strawberry cultivation, achieving multi-stage detection and yield estimation for strawberry fruits throughout their full growth cycle is essential for advancing intelligent management of greenhouse strawberries. Addressing the high rates of missed and false detections in existing object detection algorithms under complex backgrounds and dense multi-target scenarios, this paper proposes an improved multi-stage detection algorithm RLK-YOLOv8 for greenhouse strawberries. The proposed algorithm, an enhancement of YOLOv8, leverages the benefits of large kernel convolutions alongside a multi-stage detection approach. Method RLK-YOLOv8 incorporates several improvements based on the original YOLOv8 model. Firstly, it utilizes the large kernel convolution network RepLKNet as the backbone to enhance the extraction of features from targets and complex backgrounds. Secondly, RepNCSPELAN4 is introduced as the neck network to achieve bidirectional multi-scale feature fusion, thereby improving detection capability in dense target scenarios. DynamicHead is also employed to dynamically adjust the weight distribution in target detection, further enhancing the model's accuracy in recognizing strawberries at different growth stages. Finally, PolyLoss is adopted as the loss function, which effectively improve the localization accuracy of bounding boxes and accelerating model convergence. Results The experimental results indicate that RLK-YOLOv8 achieved a mAP of 95.4% in the strawberry full growth cycle detection task, with a precision and F1-score of 95.4% and 0.903, respectively. Compared to the baseline YOLOv8, the proposed algorithm demonstrates a 3.3% improvement in detection accuracy under complex backgrounds and dense multi-target scenarios. Discussion The RLK-YOLOv8 exhibits outstanding performance in strawberry multi-stage detection and yield estimation tasks, validating the effectiveness of integrating large kernel convolutions and multi-scale feature fusion strategies. The proposed algorithm has demonstrated significant improvements in detection performance across various environments and scenarios.

Why it matches plant phenotyping methodsイチゴ果実の生育段階検出と収量推定を目的に、改良YOLOv8アルゴリズムを開発・評価しており、画像から植物器官の状態・数量を推定する方法が中心である。

titlemulti-stage detection of strawberry fruits throughout the full growth cycle in greenhouses

Feasibility of Little Cherry/X-Disease Detection in Prunus avium Using Field Asymmetric Ion Mobility Spectrometry. →

Little cherry disease (LCD) and X-disease have critically impacted the Pacific Northwest sweet cherry ( Prunus avium ) industry. Current detection methods rely on laborious visual scouting or molecular analyses. This study evaluates the suitability of field asymmetric ion mobility spectrometry (FAIMS) for rapid detection of LCD and X-disease infection in three sweet cherry cultivars ('Benton', 'Cristalina', and 'Tieton') at the post-harvest stage. Stem cuttings with leaves were collected from commercial orchards and greenhouse trees. FAIMS operated at 1.5 L/min and 50 kPa, was used for headspace analysis. Molecular analyses confirmed symptomatic and asymptomatic samples. FAIMS data were processed for ion current sum (I sum ), maximum ion current (I max ), and area under the curve (I AUC ). Symptomatic samples showed higher ion currents in specific FAIMS regions ( p < 0.05), with clear differences between symptomatic and asymptomatic samples across compensation voltage and dispersion field ranges. Cultivar-specific variation was also observed in the data. FAIMS spectra for LCD/X-disease symptomatic samples differed from those for asymptomatic samples in other Prunus species, such as peach and nectarines. These findings support FAIMS as a potential diagnostic tool for LCD/X disease. Further studies with controlled variables and key growth stages are recommended to realize early-stage detection.

Why it matches plant phenotyping methodsFAIMSを用いてサクランボ樹体の感染症状を非破壊的に識別し、症候性・無症候性試料を比較評価した診断手法の検証研究であり、植物状態の取得方法が中心である。

abstractThis study evaluates the suitability of field asymmetric ion mobility spectrometry (FAIMS) for rapid detection of LCD and X-disease infection in three sweet cherry cultivars

Whole-Plant Physiological Identification and Quantification of Disease Progression →

Visual estimates of plant symptoms are traditionally used to quantify disease severity. Yet, the methodologies used to assess these phenotypes are often subjective and do not allow tracking of disease progression from very early stages. Here, we hypothesized that quantitative analysis of whole-plant physiological vital functions can be used to objectively determine plant health, providing a more sensitive way to detect disease. We studied the tomato wilt that is caused by Fusarium oxysporum f. sp. lycopersici. Physiological performance of infected and non-infected tomato plants was compared using a whole-plant pot-based lysimeter functional-phenotyping system in a semi-environmentally controlled greenhouse. Water-balance traits of the plants were measured continuously and simultaneously in a quantitative manner. Infected plants exhibited early reductions in transpiration and biomass gain, which preceded visual disease symptoms. These changes in transpiration proved to be effective quantitative indicators for assessing both plant susceptibility to infection and virulence of the fungus. Physiological changes linked to fungal outgrowth and toxin release contributed to reduced hydraulic conductance during initial infection stages. The functional-phenotyping method objectively captures early-stage disease progression, advancing plant disease research and management. This approach emphasizes the potential of quantitative whole-plant physiological analysis over traditional visual estimates for understanding and detecting plant diseases.

Why it matches plant phenotyping methods全植物の生理機能を連続測定する機能的フェノタイピング手法を用いて、植物病害の早期進行を定量化しており、表現型取得法が研究の中心である。

abstractwhole-plant pot-based lysimeter functional-phenotyping system

Using 3D reconstruction from image motion to predict total leaf area in dwarf tomato plants →

Accurate estimation of total leaf area (TLA) is crucial for evaluating plant growth, photosynthetic activity, and transpiration. However, it remains challenging for bushy plants like dwarf tomatoes due to their complex canopies. Traditional methods are often labor-intensive, damaging to plants, or limited in capturing canopy complexity. This study evaluated a non-destructive method combining sequential 3D reconstructions from RGB images and machine learning to estimate TLA for three dwarf tomato cultivars: Mohamed, Hahms Gelbe Topftomate, and Red Robin -- grown under controlled greenhouse conditions. Two experiments (spring-summer and autumn-winter) included 73 plants, yielding 418 TLA measurements via an "onion" approach. High-resolution videos were recorded, and 500 frames per plant were used for 3D reconstruction. Point clouds were processed using four algorithms (Alpha Shape, Marching Cubes, Poisson's, Ball Pivoting), and meshes were evaluated with seven regression models: Multivariable Linear Regression, Lasso Regression, Ridge Regression, Elastic Net Regression, Random Forest, Extreme Gradient Boosting, and Multilayer Perceptron. The Alpha Shape reconstruction ($α= 3$) with Extreme Gradient Boosting achieved the best performance ($R^2 = 0.80$, $MAE = 489 cm^2$). Cross-experiment validation showed robust results ($R^2 = 0.56$, $MAE = 579 cm^2$). Feature importance analysis identified height, width, and surface area as key predictors. This scalable, automated TLA estimation method is suited for urban farming and precision agriculture, offering applications in automated pruning, resource efficiency, and sustainable food production. The approach demonstrated robustness across variable environmental conditions and canopy structures.

Why it matches plant phenotyping methodsRGB画像からの3D再構成と機械学習により、植物形質である総葉面積を非破壊・自動推定する方法を開発・検証しており、フェノタイピング手法が研究の中心です。

abstractThis study evaluated a non-destructive method combining sequential 3D reconstructions from RGB images and machine learning to estimate TLA for three dwarf tomato cultivars

Monocular Depth Estimation of Tomato in Greenhouse Environment Using the Tomato-MDE Model →

Currently, greenhouse tomato picking robots highly rely on stereo vision cameras to obtain the depth information of the objects. However, due to the inherent flaws of the stereo vision camera, the accuracy of the obtained depth value is extremely susceptible to environmental variations, thus affecting the stability of the picking. In this context, we propose a lightweight monocular depth estimation model for tomatoes (Tomato-MDE) that combines real and virtual datasets, capable of adapting to greenhouse environments with transparent objects. In the encoder, it comprises a simple stacking of the proposed fast self-attention module (FSAM) and depthwise convolution (DWConv), which effectively improves the inference speed of the model. In the decoder, the proposed Integrate module extracts the output of the encoder into image feature representations at different resolutions, and the proposed Merge module then gradually fuses these representations into the final dense depth prediction. The resulting model was tested on 3500 images in the collected greenhouse tomato test dataset, showing that the proposed Tomato-MDE achieved the Depth Error Metric (δ1、δ2、δ3), Absolute Relative Error (Abs Rel) and Root Mean Squared Error (RMSE) of 0.883, 0.934, 0.949, 0.107 and 0.371, with an inference speed of 31.62 FPS under the NVIDIA Tesla V100 GPU environment. In the transparent dataset, Tomato-MDE reached the δ1, δ2, δ3, Abs Rel and RMSE of 0.818, 0.887, 0.907, 0.177 and 0.45, respectively. In addition, this method could be further developed into a perception system for a greenhouse tomato picking robot in the future.

Why it matches plant phenotyping methodsトマトの画像から深度という植物・器官状態を推定するモデルを開発し、実環境および透明物体データセットで性能検証しており、フェノタイピング手法が中心である。

abstractwe propose a lightweight monocular depth estimation model for tomatoes (Tomato-MDE)

Hyperspectral indicators and characterization of glyphosate-induced stress in common lambsquarters (Chenopodium album L.) →

· Treatments induced both lethal and sub-lethal hormetic CHEAL response to glyphosate · 31 key wavelengths capture CHEAL spectral response to glyphosate · Four vegetation indices best described glyphosate-induced herbicide injury in CHEAL · Regression modeling failed to capture CHEAL's biphasic dose-response to glyphosate · Random forest minimized model residual and predictive errors Hyperspectral sensors are increasingly used to develop optimized vegetation indices (VIs) that capture plant spectral response to specific stressors. The project goal was to develop quantitative metrics for characterization of weed response to herbicide application. This work applied hyperspectral sensing to describe and predict the spectral response of common lambsquarters ( Chenopodium album L., CHEAL) to glyphosate application. Thirteen treatments, including one glyphosate rate used alone or in combination with eleven adjuvants plus one nontreated control, were applied to CHEAL seedlings cultivated in a greenhouse. Visible injury ratings and non-imaging hyperspectral data were collected 14 days after treatment application. Sensor data processing included cleaning, normalization, smoothing, and spectral reduction. The treatments resulted in a significant (P < 0.001) gradient of injury ranging from 0 to 98%, with visible differences in leaf spectral signatures. Thirty-one key wavelengths were identified using principal component analysis, relief-f feature selection, and Bayesian discriminant analysis and used to create 45,732 VIs. No single VI accurately described CHEAL injury (minimum mean absolute error (MAE) = 14.0%). A random forest algorithm developed using four VIs adequately described CHEAL injury with an MAE of 7.7%. Post-calibration was not needed to improve the random forest model performance (P ≥ 0.05). Therefore, hyperspectral sensing could be used to quantify weed response to herbicide application and overcome the limitations of visual methods current in use. Further development of this method and validation will allow development of a platform for high-throughput phenotyping of weed response to herbicide application and screening for herbicide resistance.

Why it matches plant phenotyping methods薬剤誘発ストレスによる植物傷害を、ハイパースペクトルセンシングと機械学習で定量化する指標・予測手法を開発・評価しており、表現型取得法が研究の中心である。

abstractThe project goal was to develop quantitative metrics for characterization of weed response to herbicide application.

Development of a Short-Range Multispectral Camera Calibration Method for Geometric Image Correction and Health Assessment of Baby Crops in Greenhouses →

Multispectral imaging plays a key role in crop monitoring. A major challenge, however, is spectral band misalignment, which can hinder accurate plant health assessment by distorting the calculation of vegetation indices. This study presents a novel approach for short-range calibration of a multispectral camera, utilizing stereo vision for precise geometric correction of acquired images. By using multispectral camera lenses as binocular pairs, the sensor acquisition distance was estimated, and an alignment model was developed for distances ranging from 500 mm to 1500 mm. The approach relied on selecting the red band image as a reference, while the remaining bands were treated as moving images. The stereo camera calibration algorithm estimated the target distance, enabling the correction of band misalignment through previously developed models. The alignment models were applied to assess the health status of baby leaf crops (Lactuca sativa cv. Maverik) by analyzing spectral indices correlated with chlorophyll content. The results showed that the stereo vision approach used for distance estimation achieved high accuracy, with average reprojection errors of approximately 0.013 pixels (4.485 × 10−5 mm). Additionally, the proposed linear model was able to explain reasonably the effect of distance on alignment offsets. The overall performance of the proposed experimental alignment models was satisfactory, with offset errors on the bands less than 3 pixels. Despite the results being not yet sufficiently robust for a fully predictive model of chlorophyll content in plants, the analysis of vegetation indices demonstrated a clear distinction between healthy and unhealthy plants.

Why it matches plant phenotyping methods植物の健康状態・クロロフィル関連形質を推定するマルチスペクトル画像の幾何補正・校正法を開発し、精度検証と作物への適用を行っており、フェノタイピング手法が中心である。

abstractThis study presents a novel approach for short-range calibration of a multispectral camera, utilizing stereo vision for precise geometric correction of acquired images.

A Robust Tomato Counting Framework for Greenhouse Inspection Robots Using YOLOv8 and Inter-Frame Prediction →

Accurate tomato yield estimation and ripeness monitoring are critical for optimizing greenhouse management. While manual counting remains labor-intensive and error-prone, this study introduces a novel vision-based framework for automated tomato counting in standardized greenhouse environments. The proposed method integrates YOLOv8-based detection, depth filtering, and an inter-frame prediction algorithm to address key challenges such as background interference, occlusion, and double-counting. Our approach achieves 97.09% accuracy in tomato cluster detection, with mature and immature single-fruit recognition accuracies of 92.03% and 91.79%, respectively. The multi-target tracking algorithm demonstrates a MOTA (Multiple Object Tracking Accuracy) of 0.954, outperforming conventional methods like YOLOv8+DeepSORT. By fusing odometry data from an inspection robot, this lightweight solution enables real-time yield estimation and maturity classification, offering practical value for precision agriculture.

Why it matches plant phenotyping methods温室ロボット向けの画像解析フレームワークを中心に、トマト果実の計数、成熟度分類、収量推定という植物器官・状態の定量手法を開発・評価しているため。

abstractthis study introduces a novel vision-based framework for automated tomato counting in standardized greenhouse environments.

Quantification of canopy heterogeneity and light interception difference within greenhouse cucumbers based on terrestrial laser scanning →

Reconstructing 3D architecture of cucumber populations for multi-scale phenotypic analysis poses significant challenges in greenhouse crop research. Cucumber canopy architecture directly impacts light interception and the plant growth conditions. Terrestrial Laser Scanning (TLS) was employed to capture the 3D point cloud of cucumber plants at various growth stages, named as real plant canopy (RPC). A novel method, CP-FEC-RG, combining Fast Euclidean Clustering with Region Growing algorithm, was developed to segment cucumber plants and extract phenotypic traits both at plant and leaf scales. The virtual plant canopies (VPCs), namely VPC-H, VPC-M and VPC-L were constructed representing high, medium, and low growth potentials based on the data collected via TLS. A radiative transfer model was adopted to compare the radiation interception capabilities of both RPC and VPCs. An average recall rate of 92.2% was achieved for leaf segmentation. Growth differences were observed among the segmented individual plants and leaves, with coefficients of variations for phenotypic traits ranging from 0.13 to 0.48 for individual plants and from 0.21 to 0.54 for leaves. For daily cumulative light interception, VPC-L showed a reduction of 17.1% compared to RPC, whereas VPC-M and VPC-H exhibited increases of 18.2% and 30.1%, respectively. These findings highlight the importance of using the RPC for the accurate calculations of light interception and provide a solid foundation for applying TLS in the 3D phenotypic analysis of crops in solar greenhouses.

Why it matches plant phenotyping methodsTLSによる3D形状取得、植物・葉の分割、表現型形質抽出手法を開発・評価しており、フェノタイピング手法が研究の中心である。

abstractA novel method, CP-FEC-RG, combining Fast Euclidean Clustering with Region Growing algorithm, was developed to segment cucumber plants and extract phenotypic traits both at plant and leaf scales.

Novel method for crop growth tracking with deep learning model on an Edge Rail Camera →

Yield prediction is an essential part of farm management and has been investigated with various kinds of data and technologies in the last decades. With the advent of deep learning technology, recent studies are focusing on crop growth analysis with image processing. Instead of measuring crops in a destructive way, image analysis enables crop measurement without manipulation of the crop itself. Counting crops using tracker algorithms such as DeepSORT is one of the famous approaches for yield prediction and analysis. However, to enable crop growth monitoring and analysis, it needs consideration of temporal analysis along with spatial analysis. It should be able to compare the previous status of the target crop to the current status to analyze the growth, for example, from bud to flower to strawberry. This paper proposes a novel method for monitoring crop growth with crop clustering. Instead of counting the crops from the images, the proposed methods recognized a crop cluster from the image and measured how it changed during its lifespan. Further, the proposed method is implemented in an edge device for a greenhouse that is able to collect and measure. The proposed method has been validated on a strawberry greenhouse for around a year, which shows MoTA score from 0.57 to 0.86, with respect to the dataset.

Why it matches plant phenotyping methods画像から作物クラスターの成長変化を追跡・測定する手法を開発し、エッジデバイスに実装してイチゴ温室で約1年間検証しており、植物表現型の取得が中心です。

abstractThis paper proposes a novel method for monitoring crop growth with crop clustering.

Chlorophyll content estimation in radiata pine using hyperspectral imagery: A comparison between empirical models, scaling-up algorithms, and radiative transfer inversions →

Radiata pine (Pinus radiata D. Don) is a widely planted tree species. Fertilizers, especially those containing leaf nitrogen (N) and phosphorous (P), are essential for maximizing growth. Nutrient deficiencies and excessive fertilization can limit growth, so monitoring is crucial. Leaf pigments such as chlorophyll a+b (Cₐ₊b) can be used to assess plant nutrition, specifically leaf N. Remote sensing approaches can be used to monitor forest condition by estimating Cₐ₊b content as a proxy for leaf N. Conventional methods for Cₐ₊b estimation are based on empirical relationships using sensitive spectral indices or inversions of Radiative Transfer Models (RTMs). However, the structural complexity of tree crowns composed of multiple layers of clumped leaves/needles and background and shadow effects challenge the use of the indices proposed for both leaf Cₐ₊b and leaf nitrogen assessment. This study compares the accuracy of methods for Cₐ₊b estimation in radiata pine using hyperspectral data collected from a greenhouse experiment over the growing season and from a field trial representing a stand with a complex structure. The methods used to predict needle Cₐ₊b from tree-crown spectra included: 1) empirical relationships between Cₐ₊b measurements and hyperspectral indices; 2) scaling-up of hyperspectral index-based Cₐ₊b predictive relationships through RTM simulations; and 3) RTM inversions of Cₐ₊b content. These methods were tested over two different segmentation strategies, including sunlit-vegetation and full-crown spectra, to assess the effects of the increased structural complexity. Predictions of Cₐ₊b from the greenhouse experiment were generally higher for empirical models that used TCARI/OSAVI (Transformed Chlorophyll Absorption in Reflectance Index normalized by the Optimized Soil-Adjusted Vegetation Index) and CI (Chlorophyll index) hyperspectral indices when looking at full-crown rather than sunlit-vegetation pixels. RMSE measurements for full-crown models based on TCARI/OSAVI and CI across the three seasons ranged between 3.60 and 8.71 µg/cm² and between 3.70 and 7.86 µg/cm², respectively. Using the scaling-up methodology, the TCARI-OSAVI-derived models were more stable across different methods of pixel extraction than the CI-derived models were, showing the smallest variations across measurement dates. Predictions of Cₐ₊b in the field trial showed that PRO4SAIL2, which combines the PROSPECT-D model with the 4SAIL2 model and accounts for clumping and a more complex tree structure, was more accurate than PRO4SAIL, which couples PROSPECT-D with the original 4SAIL model, across both crown segmentation methods. Using PRO4SAIL2, predictions were more accurate for the full-crown spectra (R² = 0.82; RMSE = 3.35 µg/cm²) than for the sunlit-vegetation pixels (R² = 0.69; RMSE = 4.03 µg/cm²).These results obtained in greenhouse and field trials reinforce the superior performance with forest species of simpler RTM strategies like 4SAIL2, as compared to more complex 3-D approximations, to accurately characterize pine tree-crown traits by integrating multi-layer and clumping effects.

Why it matches plant phenotyping methodsハイパースペクトル画像と放射伝達モデルを用いてマツ樹冠のクロロフィル含量という植物形質を推定し、複数手法・セグメンテーション戦略の精度を比較検証しており、フェノタイピング手法が中心である。

abstractThis study compares the accuracy of methods for Cₐ₊b estimation in radiata pine using hyperspectral data collected from a greenhouse experiment over the growing season and from a field trial representing a stand with a complex structure.

Root restriction accelerates genomic target identification in quinoa under controlled conditions. →

Quinoa (Chenopodium quinoa) is a nutritious and resilient crop that displays a high genetic and phenotypic variation. As the popularity of this crop increases, there is a growing need to integrate classic and modern breeding tools to favor its improvement. We tested root restriction as a method to reduce plant size and enable high-throughput phenotypic screening of large sets of quinoa plants under controlled conditions. We verified how increasing root restriction does not affect the prediction of field behavior with respect to other standard greenhouse cultivation procedures. We then combined the phenotypic information obtained with our root restriction system with whole-genome re-sequencing data to characterize a quinoa diversity panel of 100 accessions and showed that phenotypic data obtained from root-restricted plants provide real insights into quinoa genetics. Finally, we carried out a genome-wide association study (GWAS) and identified a previously described locus for betalain biosynthesis, as well as other candidate loci linked to betalain biosynthesis and seed size. Overall, we showed that a phenotyping system based on root restriction can aid the identification of genomic targets in quinoa, which can complement and inform field trials for certain traits. This work supports further breeding and faster improvement of quinoa.

Why it matches plant phenotyping methods根域制限を利用したハイスループット表現型スクリーニング系の構築・検証と、圃場挙動予測との比較が研究の中心であり、単なる生物学的測定ではない。

abstractWe tested root restriction as a method to reduce plant size and enable high-throughput phenotypic screening of large sets of quinoa plants under controlled conditions.

Leaf-Whorl Inoculation with Sporisorium reilianum May Overcome Field Resistance of Maize →

Maize yield is threatened by increasing incidences of head smut disease caused by Sporisorium reilianum . To help breeders identify S. reilianum -resistant maize lines, the availability of efficient screening systems would be an advantage. Here we assessed maize lines with distinct levels of field resistance against head smut disease in greenhouse experiments using two different inoculation techniques. Addition of mixtures of mating-compatible sporidia to the soil at the seedling stage of the plant did not lead to plant disease, and we could detect only marginal amounts of fungal DNA in apical meristems at 18 days after inoculation. Inoculation of the maize lines by leaf-whorl inoculation led to both high disease incidence and prominent levels of fungal DNA in apical meristems in all tested maize lines regardless of their field resistance levels. Thus, S. reilianum entering the plant via the leaf whorl can escape existing resistance mechanisms of currently known field-resistant maize lines. Since field-resistant lines are also resistant to inoculation via teliospore-contaminated soil, we propose teliospore addition to seeds at the time of sowing (rather than leaf-whorl inoculation of seedlings) combined with quantitative detection of fungal DNA in apical meristems, as an efficient screening procedure to discover field-resistant lines. However, screening maize plants for resistance against the leaf-whorl inoculation method might be promising for the discovery of novel resistance mechanisms needed to develop durably resistant maize lines.

Why it matches plant phenotyping methodsトウモロコシの病害抵抗性を評価する接種・スクリーニング手順を比較検証し、効率的な抵抗性評価法を提案しており、病害状態の取得方法が研究の中心です。

abstractTo help breeders identify S. reilianum -resistant maize lines, the availability of efficient screening systems would be an advantage.

Robustness of high-throughput prediction of leaf ecophysiological traits using near infra-red spectroscopy and poro-fluorometry →

ABSTRACT Water scarcity is a major threat to crop production and quality. Improving drought tolerance through variety selection requires a deeper understanding of plant ecophysiological responses, but large-scale phenotyping remains a bottleneck. This study assessed the potential of high-throughput tools (spectroscopy and poro-fluorometry) to predict leaf morphological and ecophysiological traits in a grapevine diversity panel grown in pots under well-watered outdoor conditions and under three contrasting soil water treatments in a greenhouse. We found a certain complementarity between measuring devices. Spectrometers could accurately predict leaf mass per area, water content, and water quantity (R² > 0.58), while the poro-fluorometer was efficient for predicting net CO₂ assimilation (R² > 0.72), regardless of the water treatment. The prediction of leaf mass per area using spectrometers appeared to be quite robust across both outdoor and greenhouse experiments, while the prediction of water use efficiency was dependent on the water treatment, with much better predictions under moderate (R² > 0.73) than severe water deficit. Calibrated models were then applied to the full diversity panel using only high-throughput measurements to estimate trait values and their broad-sense heritability. Leaf mass per area, also measured directly, showed similar heritability whether based on observed or predicted data. Heritability estimates for predicted traits reached up to 0.5. Overall, our findings support the use of spectroscopy and poro-fluorometry as reliable, non-destructive tools for high-throughput phenotyping, enabling genetic studies on drought-related traits in grapevine.

Why it matches plant phenotyping methods分光法とポロフルオロメトリーによる葉の形態・生理形質の高スループット推定を開発・評価し、予測精度と頑健性を検証しているため、植物フェノタイピング手法が中心である。

abstractThis study assessed the potential of high-throughput tools (spectroscopy and poro-fluorometry) to predict leaf morphological and ecophysiological traits

3D time-series phenotyping of lettuce in greenhouses →

Monitoring the growth dynamics of plants in three-dimensional (3D) space is one of the most fundamental data acquisition requirements for plant breeding and cultivation. The rapid development of high-throughput plant phenotyping platforms (HTPPP) makes it possible to obtain big data in plant phenomics. However, how to extract phenotypes from the raw phenotyping data to obtain the agronomic indicators demanded by agronomists has become an urgent issue. In this study, time-series point clouds of potted lettuce plants were generated via multi-view stereo (MVS) method using top-view Red, Green, Blue (RGB) images acquired by a rail-driven HTPPP in a greenhouse. A time-series point cloud registration method was proposed by extracting pots as features, and daily population-individual plant point cloud segmentation was achieved based on the registration information and contrasted with two other different segmentation methods. Then vegetation and pot was segmented using the random forest (RF). Finally, the phenotypes including plant height, crown width, and convex hull volume of each plant were extracted. The results show that the average mean intersection over union (mIoU), mean precision (mPᵣ), mean recall (mRₑ), and mean F1-score (mF₁) of the population-individual plant segmentation were 71.86%, 97.38%, 86.08%, and 91.02%, respectively. The vegetation-pot point cloud segmentation achieved an accuracy of 98.81%. The averaged coefficient of determination (R²) for the extracted plant height and crown width were 0.79 and 0.60, respectively, with the averaged root mean square error (RMSE) being 0.05 m and 0.03 m, respectively. The accuracy of plant height was significantly higher than that of PlantEye. The extracted phenotypes can be used to quantitatively differentiate the growth dynamics of different sub-populations of lettuce plants. This study presents an automated solution for extracting time-series 3D phenotypes under HTPPP in a greenhouse. It provides crucial technological support for efficient phenotype acquisition in plant breeding and cultivation.

Why it matches plant phenotyping methods温室HTPPPの3D点群から植物個体を分割し、草高・冠幅・凸包体積を抽出する手法を開発・検証しており、表現型取得が研究の中心です。

abstractA time-series point cloud registration method was proposed by extracting pots as features, and daily population-individual plant point cloud segmentation was achieved based on the registration information and contrasted with two other different segmentation methods.

Computational wide-field imaging of poplar embolism and wound-response with a deployable microscope. →

Low-cost, minimally invasive microscopy for tracking cellular dynamics in living plants within their natural ecosystems is crucial for addressing fundamental questions in plant ecology and biology. However, existing solutions are constrained by coarse resolution, limited field-of-view (FoV), and poor deployability in natural settings. Here, we utilize a compact, portable microscope ("miniscope") for label-free (autofluorescence) imaging in living poplar wood. We systematically implement and evaluate multiple computational methods to enhance resolution and FoV. Our optimal computational pipeline, comprising maximal intensity projection, deconvolution, and flat-field correction, increases resolution by up to 39% on-axis and up to 49% at the field edges, resolving features of 2.87 μm, averaged over a FoV of ∼1 mm (diameter), compared with a 4.34 μm baseline. We demonstrate microscopy within the tissue of a living poplar plant in our greenhouse, observing the embolism of vessel elements, wound response, and tissue deformation from moisture evaporation.

Why it matches plant phenotyping methods生体ポプラ組織の細胞動態・木部塞栓・創傷応答を観察する携帯型顕微鏡と画像処理パイプラインを開発・評価しており、植物状態の取得手法が中心である。

abstractWe systematically implement and evaluate multiple computational methods to enhance resolution and FoV.

RTR-CNN: Rotated tray region selection and young seedling health status detection by CNN in greenhouse seedbed →

The use of mobile inspection transplanter machines in greenhouse seedling cultivation reduces reliance on manual labor, a critical step in vegetable production. Detecting plug seedlings and assessing their health are essential for automating seedling transplantation. In this study, a two-stage detection algorithm, RTR-CNN, was developed to locate and identify multiple rotating trays at various angles on greenhouse seedbeds and to evaluate the growth status of young seedlings. Focusing on a seedling tray with 200 cells, matching templates were designed based on the trays’ binary morphological features to detect trays at different angles. After locating trays, each cell was segmented and geometrically corrected before being fed into the backbone network for classification. Masked generative distillation was applied to optimize the network for edge computing hardware. Using the WideResNet101_2 teacher network, the deployed model achieved an accuracy of 88.80 %, with a binary classification accuracy of 98.95 %. Deployment on the lightweight MobileNetV2 network achieved an accuracy of 87.45 % through distillation learning, with a binary classification accuracy of 99.15 % at a processing speed of 159.30 fps with a batch size of 200. Distillation learning improved the training accuracy by 0.95 % and binary classification accuracy by 0.5 % compared to models trained without this method.

Why it matches plant phenotyping methods温室苗の生育状態を画像から判定するCNN手法を開発し、エッジ実装・精度・処理速度を評価しており、植物フェノタイピング手法が中心である。

abstracta two-stage detection algorithm, RTR-CNN, was developed to locate and identify multiple rotating trays at various angles on greenhouse seedbeds and to evaluate the growth status of young seedlings.

Spi-VSTL: Image data collection platform using off-the shelf hardware for vertically supported crops in state-of-the-art glasshouses. →

Horticulture crop growers are moving from conventional to protected crops, aiming for quality food production utilising fewer resources. Skilled labour for monitoring and maintaining crops in these compact environments has been identified as a major cost and can be reduced using automated image-based crop monitoring. There is a range of protected cropping infrastructures targeting different types of crops. Image data collection platforms are needed to be tailored according to the infrastructure and nature of the crop. Available research or commercial-purpose image data collection platforms for indoor crops are mostly targeted at movable and small plants compared to vertically supported tall plants. Customising existing commercial systems for this specific type of crop is costly. This paper proposes a low-cost image data collection platform for monitoring vertically supported tall crops in order to reduce labour costs while expanding the monitoring tasks for maintaining better crop growth. Off-the-shelf hardware and electronic components accessible from Australia are used for this development. The proposed platform runs manually on concrete flow and on pipe rail systems found in state-of-the-art commercial glasshouse settings. The proposed motorised platform has been tested with 30 kg, and speed was measured as an average minimum of 0.06 ms -1 and an average maximum of 0.47 ms -1 . The usability of the proposed design has been proved with a published data set and research on plant height estimation. Other use cases and room for further development are also discussed.

Why it matches plant phenotyping methods垂直栽培作物向けの画像データ収集プラットフォームを開発し、植物高推定データセットで実用性を検証しており、植物表現型取得が中心である。

abstractThis paper proposes a low-cost image data collection platform for monitoring vertically supported tall crops

Noninvasive, Presymptomatic Detection of Potato Cyst Nematode Infection in Tomato Using Chlorophyll Fluorescence Analysis. →

Potato cyst nematodes (PCNs) are notorious pathogens in all major potato production areas worldwide. Mainly due to the low mobility of this soil pathogen, PCN infestations are mostly observed as patches ("foci") that only cover a fraction of the acreage. In-field presymptomatic localization of these pathogens is valuable, as it would allow for the localized application of control measures. Although the mapping of foci is technically feasible, it is unpractical, as it would require the analysis of numerous soil samples. We investigated whether chlorophyll fluorescence (Chl-F) could be suitable as a rapid, nondestructive method for early PCN detection. To this end, the impact of four Globodera pallida densities on the Chl-F of tomato was investigated in a phenotyping greenhouse for 26 days. Furthermore, the classical plant performance indicators of biomass and root surface area were compared with Chl-F. Thermal dissipation (NPQ) and an estimate of the photosynthetic rate (Φ PSII ) responded at 1 day postinoculation, and Φ PSII was most sensitive to low PCN infection levels. Chl-F parameters responded more readily to PCN infection than biomass and root surface area. The maximum quantum yield of photosystem II (F v /F m ) and the potential activity of photosystem II (F v /F 0 ) initially increased at low PCN infection levels, whereas a sharp decrease was observed at higher infestation levels. Hence, our data suggest that low PCN levels promoted plant performance before becoming detrimental at higher levels. Although Chl-F allowed for early and sensitive PCN detection, it remains to be investigated whether these signals can be distinguished from those produced by other belowground stressors in the field. [Formula: see text] Copyright © 2025 The Author(s). This is an open access article distributed under the CC BY 4.0 International license.

Why it matches plant phenotyping methodsクロロフィル蛍光を用いたトマトの感染状態の非破壊・早期推定が研究の中心であり、感度や従来指標との比較も評価しているため、植物フェノタイピング手法に該当する。

abstractWe investigated whether chlorophyll fluorescence (Chl-F) could be suitable as a rapid, nondestructive method for early PCN detection.

Design and application of a multi-source sensor data fusion system based on a robot phenotype platform →

The compact, high-throughput phenotyping platform, characterized by its portability and small size, is well-suited for crop phenotyping across diverse environments. However, integrating multi-source sensors to achieve synchronized data acquisition and analysis poses significant challenges due to constraints in load capacity and available space. To address these issues, we developed a robotic platform specifically designed for phenotyping greenhouse strawberries. This system integrates an RGB-D camera, a multispectral camera, a thermal camera, and a LiDAR sensor, enabling the unified analysis of data from these sources. The platform accurately extracted key phenotypic parameters, including canopy width (R² = 0.9864, RMSE = 0.0185 m) and average temperature (R2 = 0.8056, RMSE = 0.1732 °C), with errors maintained below 5%. Furthermore, it effectively distinguished between different strawberry varieties, achieving an Adjusted Rand Index of 0.94, underscoring the value of detailed phenotyping in variety differentiation. Compared to conventional UGV-LiDAR systems, the proposed platform is more cost-effective, efficient, and scalable, with enhanced data consistency, making it a promising solution for agricultural applications.

Why it matches plant phenotyping methods複数センサーを統合したロボット植物フェノタイピング基盤を開発し、キャノピー幅と平均温度の抽出精度を検証しているため、フェノタイピング手法が中心である。

abstractwe developed a robotic platform specifically designed for phenotyping greenhouse strawberries.

Unlocking the Power of Gene Banks: Diversity in Base Growth Temperature Provides Opportunities for Climate‐Smart Agriculture →

ABSTRACT Implementation of context‐specific solutions, including cultivation of varieties adapted to current and future climatic conditions, have been found to be effective in establishing resilient, climate‐smart agricultural systems. Gene banks play a pivotal role in this. However, a large fraction of the collections remains neither genotyped nor phenotyped. Hypothesizing that significant genotypic diversity in Musa temperature responses exists, this study aimed to assess the diversity in the world's largest banana gene bank in terms of base temperature ( T base ) and to evaluate its impact on plant performance in the East African highlands during a projected climate scenario. One hundred and sixteen gene bank accessions were evaluated in the BananaTainer, a tailor‐made high throughput phenotyping installation. Plant growth was quantified in response to temperature and genotype‐specific T base were modelled. Growth responses of two genotypes were validated under greenhouse conditions, and gas exchange capacity measurements were made. The model confirmed genotype‐specific T base , with 30% of the accessions showing a T base below the reference of 14°C. The Mutika/Lujugira subgroup, endemic to the East African highlands, appeared to display a low T base , although within subgroup diversity was revealed. Greenhouse validation further showed low temperature sensitivity/tolerance to be related to the photosynthetic capacity. This study, therefore, significantly advances the debate of within species diversity in temperature growth responses, while at the same time unlocking the power of gene banks. Moreover, with this case study on banana, we provide a high throughput method to reveal the existing genotypic diversity in temperature responses, paving the way for future research to establish climate‐smart varieties.

Why it matches plant phenotyping methodsバナナ遺伝資源の温度応答を高スループットに定量化し、遺伝子型別の基底温度をモデル化・温室で検証しており、表現型取得法と検証が研究の中心です。

abstractOne hundred and sixteen gene bank accessions were evaluated in the BananaTainer, a tailor‐made high throughput phenotyping installation.

Precise 3D measurement of internode elongation just below shoot apex for growth diagnosis of greenhouse cucumber plants using SfM/MVS method →

Measurement of internode elongation just below the shoot apex or growing point of the main stem is important for assessing plant growth. However, it is difficult to directly measure internode elongation on climbing plants with many leaves, such as cucumber plants. It is also difficult to measure the stem length of tall leafy plants in the field, and is prone to measurement errors. In addition, touching plants to measure them can stress them. Here, we measured internodal growth just below the shoot apex by using a 3D point cloud model reconstructed using Structure from Motion and Multi-View Stereo (SfM/MVS) methods under greenhouse conditions. The SfM/MVS method could nondestructively measure the internode elongation of multiple plants accurately and simultaneously with a root mean square error of 3.1 mm. Elongation was most active in the top two internodes and ceased in older internodes. Average elongation lengths of internodes 1 and 2 as counted from the top (6.7-7.7 mm day-1) were significantly greater than that of internode 3 (3.37 mm day-1), which was significantly greater than those of internodes 4 to 6 (0.0-0.5 mm day-1). These growth rates of two top internodes are the indicator of plant growth, which can be used for plant diagnosis. Our quantitative method for assessing internode elongation can be used under normal greenhouse conditions. Traditional 2D measurements face challenges due to occlusion, which this 3D method overcomes by digitally removing leaves for clear node visibility. 3D measurements enable time series analysis of internode elongation, which is difficult to measure in situ. The 3D data can be stored for later reanalysis.

Why it matches plant phenotyping methodsSfM/MVSによるキュウリの節間伸長を非破壊・3D・同時測定する方法を開発し、精度（RMSE）を検証している。植物形質の取得法が研究の中心である。

abstractHere, we measured internodal growth just below the shoot apex by using a 3D point cloud model reconstructed using Structure from Motion and Multi-View Stereo (SfM/MVS) methods under greenhouse conditions.

Development of a tomato functional–structural plant model for digital twin applications →

Abstract Digital-twin technology is a promising decision-support tool in controlled-environment agriculture, that can be applied to optimize agronomic production, improve management decisions, and formulate data-driven breeding strategies. We developed a concept for a digital twin of a tomato crop in a high-tech greenhouse with the aim to help increase resource-use efficiency of greenhouse tomatoes. At the core of the digital twin is a functional–structural plant (FSP) model that can simulate 3D architectural development and growth of young tomato plants and can be used to predict plant responses to environmental factors and management interventions. In this study, we present the newly developed tomato FSP model and procedures to use data from climate sensors and image data of single plants from high-throughput phenotyping, to feed the FSP model to ensure synchronization with the real-world crop development. A greenhouse climate model is used to calculate the indoor climate above the crop based on outdoor weather data, greenhouse properties, and climate control settings. Synchronization of plant architecture between the real and the virtual crop is demonstrated for plant height adjustments, by performing model calibration based on Bayesian optimization. The tomato FSP model is designed to study the role of individual organ traits and assess the effects of architectural manipulations, such as leaf pruning, and lighting strategies. The presented framework addresses a vital component of a digital twin representing the flow of information from the real crop to the virtual crop.

Why it matches plant phenotyping methodsトマトのデジタルツインに接続するFSPモデルと、センサー・ハイスループット画像を用いた植物体情報の同期・校正手順を開発しており、表現型取得・推定ワークフローが中心的である。

abstractWe developed a concept for a digital twin of a tomato crop in a high-tech greenhouse

Root phenotyping and plant breeding of crops for enhanced ecosystem services →

Diversifying and perennializing cropping systems can increase productivity while supporting ecosystem services such as soil protection, nutrient retention, and greenhouse gas mitigation. New crops can help achieve these goals, and advanced computational tools allow plant breeders to rapidly domesticate new crops and select for many traits that support both ecosystem services and profitable production. Intermediate wheatgrass [Thinopyrum intermedium (Host.) Barkworth. & D.R. Dewey; IWG] is a cool‐season perennial grass undergoing domestication to function as a perennial grain crop. Key aboveground domestication traits have been improved to support economically viable yields using genomic selection. However, few studies have quantified belowground traits despite their potential role in conferring ecosystem services. We present a platform for using minirhizotron cameras and machine learning software to analyze rhizotron images for inclusion in genomic selection models. The strength and direction of pairwise correlations between traits were variable with correlation coefficients (r) ranging from −0.27 to 0.99. Grain yield was positively, although weakly, correlated with total root length, area, and volume (r = 0.21, 0.21, and 0.19, respectively). Estimates of narrow sense heritabilities ranged from 0.41 to 0.76 for all traits and 0.46 to 0.66 for root traits. Root trait predictions using a genomic prediction model, measured by correlating model‐predicted values and field‐observed values, ranged from 0.08 to 0.23. Aboveground traits were better predicted (0.17 < r < 0.33). Simply selecting for aboveground traits could result in populations with desirable root traits, but our results demonstrate the potential for genomic selection to aid in advancing populations with specific root traits important for ecosystem services.

Why it matches plant phenotyping methodsミニリゾトロン画像と機械学習による根形質抽出プラットフォームの提示が研究の中心であり、単なる生物学的測定ではない。

abstractWe present a platform for using minirhizotron cameras and machine learning software to analyze rhizotron images for inclusion in genomic selection models.

Root restriction accelerates genomic target identification in quinoa under controlled conditions →

Quinoa (Chenopodium quinoa) is a nutritious and resilient crop that displays a high genetic and phenotypic variation. As the popularity of this crop increases, there is a growing need to integrate classic and modern breeding tools to favor its improvement. We tested root restriction as a method to reduce plant size and enable high‐throughput phenotypic screening of large sets of quinoa plants under controlled conditions. We verified how increasing root restriction does not affect the prediction of field behavior with respect to other standard greenhouse cultivation procedures. We then combined the phenotypic information obtained with our root restriction system with whole‐genome re‐sequencing data to characterize a quinoa diversity panel of 100 accessions and showed that phenotypic data obtained from root‐restricted plants provide real insights into quinoa genetics. Finally, we carried out a genome‐wide association study (GWAS) and identified a previously described locus for betalain biosynthesis, as well as other candidate loci linked to betalain biosynthesis and seed size. Overall, we showed that a phenotyping system based on root restriction can aid the identification of genomic targets in quinoa, which can complement and inform field trials for certain traits. This work supports further breeding and faster improvement of quinoa.

Why it matches plant phenotyping methods根域制限を用いた高スループット表現型スクリーニング系の開発・検証が研究の中心であり、圃場での予測性能も検証しているため。

abstractWe tested root restriction as a method to reduce plant size and enable high‐throughput phenotypic screening of large sets of quinoa plants under controlled conditions.

Temporal Semantic Multispectral Point Cloud Generation and Feature Fusion Pipeline for Comprehensive Trait Estimation in Greenhouse Tomatoes →

Abstract has not been obtained from indexed metadata or an accessible article page.

Why it matches plant phenotyping methods温室トマトの形質推定を目的とするマルチスペクトル点群生成・特徴融合パイプラインであり、植物フェノタイピング手法が中心と明示されています。

titleTemporal Semantic Multispectral Point Cloud Generation and Feature Fusion Pipeline for Comprehensive Trait Estimation in Greenhouse Tomatoes

Virtual Reality-Enabled remote Human-Robot interaction for strawberry cultivation in greenhouses →

This paper investigates the application of a VR-controlled robotic system for yield monitoring in strawberry farming within a greenhouse environment. The study aims to evaluate the effectiveness of the system in identifying and counting ripe strawberries, categorized by size (small and large) and variety (Seascape and Albion), and compares with the obtained results by an onsite human expert. We designed experiments, in a controlled environment agriculture center, and conducted in two trials. The yield monitoring performance of the developed robotic system was evaluated based on two primary metrics of cycle completion times and fruit detection accuracy, 32 strawberry plants which grew 336 ripe fruits. In the first experiment, the system achieved detection rates of 63 % for small strawberries and 72 % for large strawberries, with cycle completion times ranging from 12.5 to 16 s. In the second experiment, improvements were observed, with detection rates increasing to 74 % for both sizes and cycle completion times reduced to between 11.9 and 15.7 s. The developed robotic system demonstrated high accuracy and efficiency, particularly with larger strawberries. However, some limitations were identified, including challenges related to occlusion. These findings suggest that while the VR-controlled robotic system has the potential to complement and even surpass traditional yield monitoring methods managed by human experts, further refinements are necessary. Future research should focus on optimizing the system’s performance and adapting the system to broader applications in agriculture.

Why it matches plant phenotyping methodsVR制御ロボットによるイチゴ果実の検出・計数とサイズ分類を、検出精度および処理時間で評価しており、果実収量関連形質の取得方法と技術性能が研究の中心である。

abstractThis paper investigates the application of a VR-controlled robotic system for yield monitoring in strawberry farming within a greenhouse environment.

Optimizing Corn Tar Spot Measurement: A Deep Learning Approach Using Red-Green-Blue Imaging and the Stromata Contour Detection Algorithm for Leaf-Level Disease Severity Analysis. →

Visual detection of stromata (brown-black, elevated fungal fruiting bodies) is the primary method for quantifying tar spot early in the season because these structures are definitive signs of the disease and essential for effective disease monitoring and management. Here, we present the Stromata Contour Detection Algorithm version 2 (SCDA v2), which addresses the limitations of the previously developed SCDA version 1 (SCDA v1), without the need to empirically search for optimal decision-making input parameters (DMIPs) while achieving higher and consistent accuracy in tar spot stromata detection. SCDA v2 operates in two components: (i) SCDA v1 producing tar spot-like region proposals for a given input corn leaf Red-Green-Blue (RGB) image and (ii) a pretrained convolutional neural network (CNN) classifier identifying true tar spot stromata from the region proposals. To demonstrate the enhanced performance of the SCDA v2, we used datasets of RGB images of corn leaves from field (low, middle, and upper canopies) and glasshouse conditions under variable environments, exhibiting different tar spot severities at various corn developmental stages. Various accuracy analyses (F1 score, linear regression, and Lin's concordance correlation) showed that SCDA v2 had a greater agreement with the reference data (human visual annotation) than SCDA v1. SCDA v2 achieved 73.7% mean Dice values (overall accuracy) compared with 30.8% for SCDA v1. The enhanced F1 score primarily resulted from eliminating overestimation cases using the CNN classifier. Our findings indicate the promising potential of SCDA v2 for glasshouse and field-scale applications, including tar spot phenotyping and surveillance projects.[Formula: see text] Copyright © 2024 The Author(s). This is an open access article distributed under the CC BY-NC-ND 4.0 International license.

Why it matches plant phenotyping methodsトウモロコシ葉のタースポット病重症度をRGB画像から推定する深層学習・輪郭検出アルゴリズムを開発し、既存法および人的アノテーションと精度比較しており、植物表現型取得法が中心である。

abstractHere, we present the Stromata Contour Detection Algorithm version 2 (SCDA v2)

Improved YOLOv8 Model for Phenotype Detection of Horticultural Seedling Growth Based on Digital Cousin →

Crop phenotype detection is a precise way to understand and predict the growth of horticultural seedlings in the smart agriculture era to increase the cost-effectiveness and energy efficiency of agricultural production. Crop phenotype detection requires the consideration of plant stature and agricultural devices, like robots and autonomous vehicles, in smart greenhouse ecosystems. However, collecting the imaging dataset is a challenge facing the deep learning detection of plant phenotype given the dynamic changes among leaves and the temporospatial limits of camara sampling. To address this issue, digital cousin is an improvement on digital twins that can be used to create virtual entities of plants through the creation of dynamic 3D structures and plant attributes using RGB image datasets in a simulation environment, using the principles of the variations and interactions of plants in the physical world. Thus, this work presents a two-phase method to obtain the phenotype of horticultural seedling growth. In the first phase, 3D Gaussian splatting is selected to reconstruct and store the 3D model of the plant with 7000 and 30,000 training rounds, enabling the capture of RGB images and the detection of the phenotypes of the seedlings, overcoming temporal and spatial limitations. In the second phase, an improved YOLOv8 model is created to segment and measure the seedlings, and it is modified by adding the LADH, SPPELAN, and Focaler-ECIoU modules. Compared with the original YOLOv8, the precision of our model is 91%, and the loss metric is lower by approximately 0.24. Moreover, a case study of watermelon seedings is examined, and the results of the 3D reconstruction of the seedlings show that our model outperforms classical segmentation algorithms on the main metrics, achieving a 91.0% mAP50 (B) and a 91.3% mAP50 (M).

Why it matches plant phenotyping methods植物の3D再構成、画像取得、セグメンテーション、計測を組み合わせた生育形質抽出手法の開発と評価が中心であり、単なる生物学的実験ではない。

abstractThus, this work presents a two-phase method to obtain the phenotype of horticultural seedling growth.

Accurate Fruit Phenotype Reconstruction via Geometry-Smooth Neural Implicit Surface →

Accurate collection of plant phenotyping is critical to optimising sustainable farming practices in precision agriculture. Traditional phenotyping in controlled laboratory environments, while valuable, falls short in understanding plant growth under real-world conditions. Emerging sensor and digital technologies offer a promising approach for direct phenotyping of plants in farm environments. This study investigates a learning-based phenotyping method using neural implicit surfaces reconstruction to achieve accurate in situ phenotyping of pepper plants in greenhouse environments. To quantitatively evaluate the performance of this method, traditional point cloud registration on 3D scanning data is implemented for comparison. Experimental result shows that NIR (neural implicit surfaces reconstruction) achieves competitive accuracy compared to the 3D scanning method. The mean distance error between the scanner-based method and the NeRF (neural radiance fields)-based method is 0.811 mm. This study shows that the learning-based NeRF method has similar accuracy to the 3D scanning-based method but with greater scalability and faster deployment capabilities.

Why it matches plant phenotyping methods植物の3D表現型を取得するNeRFベース手法を開発し、3Dスキャン法と精度比較・検証しており、表現型取得法が研究の中心である。

abstractThis study investigates a learning-based phenotyping method using neural implicit surfaces reconstruction to achieve accurate in situ phenotyping of pepper plants in greenhouse environments.

CBAM-ResNet34-based classification and evaluation method for developmental processes of greenhouse strawberries →

Strawberries, known for their economic significance and rich nutritional value, are cultivated extensively worldwide. However, a host of workers need to be employed every year to identify and categorize the developmental stages of the strawberries in the greenhouses, which is not only time-consuming, inefficient, increasing the cultivation cost, but also difficult to guarantee the classification accuracy. Meanwhile, affected by the complicated background, occlusions, and color interference, the features of strawberries are proven challenging to be extracted via the traditional neural networks due to serious gradient disappearance. Therefore, an improved CBAM-ResNet34- based classification evaluation method for developmental processes of greenhouse strawberries is investigated. The procedure of this method is as follows: firstly, the developmental stages of greenhouse strawberries are classified by experts into four stages: Stage I (initial stage), Stage II (green and white fruit stage), Stage III (early ripening stage), and Stage IV (fully ripe stage). The 627, 640, 604, and 340 strawberry images for these four stages are captured. Subsequently, the images are divided into training, validation, as well as testing sets and then undergo image pre- processing, expansion, and augmentation. Whereafter, the 7×7 convolution kernel in the first layer of the network is replaced by three consecutive 3×3 convolution cores to eliminate the redundant weights and unnecessary model parameters, and the BasicBlocks configuration is adjusted. Finally, the CBAM attention mechanism is added to each BasicBlock so as to pinpoint the spatial position of the strawberries and extract their major features such as shape, size, and color. Comparison experiments with the conventional deep neural networks LeNet5, AlexNet, VGG16, ResNet18, ResNet34, and every improved part of CBAM-ResNet34 demonstrated that when the learning rate is 0.001, the Dropout rate is 0.3, and the Adam’s weight decay parameter is 0.001, the accuracies for validation and testing sets can reach to 92.36% and 87.56% with F1 scores of 0.92, 0.87, 0.85 and 0.88.

Why it matches plant phenotyping methodsイチゴの発育段階という植物状態を画像から分類するCBAM-ResNet34手法を開発し、比較実験と精度評価を行っており、フェノタイピング手法が研究の中心である。

abstractan improved CBAM-ResNet34- based classification evaluation method for developmental processes of greenhouse strawberries is investigated.

SGSNet: a lightweight deep learning model for strawberry growth stage detection. →

Introduction Detecting strawberry growth stages is crucial for optimizing production management. Precise monitoring enables farmers to adjust management strategies based on the specific growth needs of strawberries, thereby improving yield and quality. However, dense planting patterns and complex environments within greenhouses present challenges for accurately detecting growth stages. Traditional methods that rely on large-scale equipment are impractical in confined spaces. Thus, the development of lightweight detection technologies suitable for portable devices has become essential. Methods This paper presents SGSNet, a lightweight deep learning model designed for the fast and accurate detection of various strawberry growth stages. A comprehensive dataset covering the entire strawberry growth cycle is constructed to serve as the foundation for model training and testing. An innovative lightweight convolutional neural network, named GrowthNet, is designed as the backbone of SGSNet, facilitating efficient feature extraction while significantly reducing model parameters and computational complexity. The DySample adaptive upsampling structure is employed to dynamically adjust sampling point locations, thereby enhancing the detection capability for objects at different scales. The RepNCSPELAN4 module is optimized with the iRMB lightweight attention mechanism to achieve efficient multi-scale feature fusion, significantly improving the accuracy of detecting small targets from long-distance images. Finally, the Inner-IoU optimization loss function is applied to accelerate model convergence and enhance detection accuracy. Results Testing results indicate that SGSNet performs exceptionally well across key metrics, achieving 98.83% precision, 99.45% recall, 99.14% F1 score, 99.50% mAP@0.5, and a loss value of 0.3534. It surpasses popular models such as Faster R-CNN, YOLOv10, and RT-DETR. Furthermore, SGSNet has a computational cost of only 14.7 GFLOPs and a parameter count as low as 5.86 million, demonstrating an effective balance between high performance and resource efficiency. Discussion Lightweight deep learning model SGSNet not only exceeds the mainstream model in detection accuracy, but also greatly reduces the need for computing resources and is suitable for portable devices. In the future, the model can be extended to detect the growth stage of other crops, further advancing smart agricultural management.

Why it matches plant phenotyping methodsイチゴの生育ステージという植物状態を画像から検出する軽量深層学習モデルを開発し、データセット構築と性能評価を行っており、表現型取得・推定手法が中心である。

abstractThis paper presents SGSNet, a lightweight deep learning model designed for the fast and accurate detection of various strawberry growth stages.

Identification of copper and lead pollution elements based on spectra of corn leaves in different leaf layers. →

With the development of industrialization, environmental heavy metal pollution has become increasingly serious, and the growth of crops has been seriously affected by heavy metal pollution in the soil environment. Therefore, it is necessary to establish methods for distinguishing and monitoring heavy metal pollution. The application of hyperspectral remote sensing in heavy metal pollution monitoring demonstrates the great potential of using crop leaf spectra to accurately distinguish heavy metal pollution elements. At the same time, new spectral processing methods and models are required to provide support for accurate identification. In this study, greenhouse experiments were conducted to simulate the growth of corn plants under heavy metal Cu and Pb stress. Collect hyperspectral data from different leaf layers of maize plants during the heading stage. Multivariate empirical mode decomposition (MEMD) was introduced, and the spectral data were preprocessed using MEMD, First derivative (FD), and second derivative (SD). At the same time, chemical analysis was used to examine the changes in copper (Cu), lead (Pb), and chlorophyll content in corn leaves. Competitive adaptive reweighted sampling (CARS) and iteratively retaining informative variables (IRIV) were used to screen characteristic bands that were sensitive to copper and lead. Finally, machine learning SVM, ELM, and XGBoost were utilized to construct and propose a series of models such as MEMD-CARS-ELM for accurate discrimination of Cu and Pb pollution elements. The results indicated that the discriminative model established after the MEMD transformation of the spectrum exhibited the best performance. Among them, whether it is tender leaves, functional leaves, or basal leaves, the accuracy of the MEMD-CARS-SVM and MEMD-CARS-ELM models in the training group and validation group for distinguishing Cu and Pb elements is greater than 80%. Other models established by MEMD spectral transformation are also significantly better at identifying Cu and Pb than those established by FD and SD transformations. The signal time-frequency analysis method MEMD is feasible and excellent for hyperspectral data processing. Based on this method, the Cu and Pb pollution element identification method proposed in this study was reliable. The research results provide a new method for the preprocessing of hyperspectral data and a new perspective for the accurate identification of soil heavy metal contamination elements. This study showed that corn leaf spectra can be used to accurately identify heavy metal pollution elements, providing a powerful scientific reference for hyperspectral remote sensing to monitor heavy metal pollution in large areas.

Why it matches plant phenotyping methodsトウモロコシ葉のハイパースペクトルから重金属ストレス状態を推定する前処理・特徴帯選択・機械学習手法を開発し、訓練・検証精度を評価しており、植物状態の取得・推定方法が中心である。

abstractnew spectral processing methods and models are required to provide support for accurate identification

Fully automated proximal hyperspectral imaging system for high-resolution and high-quality in vivo soybean phenotyping →

Hyperspectral imaging (HSI) is a prevalent method in crop phenotyping. Nevertheless, current HSI remote sensing techniques are compromised by changing ambient lighting conditions, long imaging distances, and comparatively low resolutions. Proximal HSI sensors such as LeafSpec were developed to improve the imaging quality. However, the application of proximal sensors remains contrained by their low throughput and intensive labor costs. Moreover, few automation solutions were available to use LeafSpec in phenotyping dicot plants. In this paper, a novel robotic system is presented as a sensor platform to operate LeafSpec to collect leaf-level hyperspectral images for in vivo phenotyping of soybean. A machine vision algorithm was developed to detect the top mature trifoliate and estimate the poses of the leaflets. A control and motion planning algorithm was developed for an articulated robotic manipulator to grasp the target leaflets. An experiment was conducted in March 2021 in a greenhouse with 64 soybean plants of 2 genotypes and 2 nitrogen treatments. The machine vision detected the target leaflets with a first trial success rate of 84.13% and an overall success rate of 90.66%. The robotic manipulator operated LeafSpec to image the target leaflets with a first trial success rate of 87.30% and an overall success rate of 93.65%. The average cycle time for one soybean plant was 63.20 s. The PLS predictions from the robot-collected data had an R² of 0.84 with the measured nitrogen content and an R² of 0.82 with the predictions from human-collected data. The results demonstrated the potential of applying the system for automated in vivo leaf-level HSI for soybean phenotyping in the field.

Why it matches plant phenotyping methodsロボットによる近接ハイパースペクトル画像取得システムと葉検出・動作計画アルゴリズムを開発し、豆類の表現型計測性能を検証しており、方法が中心的である。

abstractIn this paper, a novel robotic system is presented as a sensor platform to operate LeafSpec to collect leaf-level hyperspectral images for in vivo phenotyping of soybean.

Optimizing Corn Tar Spot Measurement: A Deep Learning Approach Using Red-Green-Blue Imaging and the Stromata Contour Detection Algorithm for Leaf-Level Disease Severity Analysis →

Visual detection of stromata (brown-black, elevated fungal fruiting bodies) is the primary method for quantifying tar spot early in the season because these structures are definitive signs of the disease and essential for effective disease monitoring and management. Here, we present the Stromata Contour Detection Algorithm version 2 (SCDA v2), which addresses the limitations of the previously developed SCDA version 1 (SCDA v1), without the need to empirically search for optimal decision-making input parameters (DMIPs) while achieving higher and consistent accuracy in tar spot stromata detection. SCDA v2 operates in two components: (i) SCDA v1 producing tar spot-like region proposals for a given input corn leaf Red-Green-Blue (RGB) image and (ii) a pretrained convolutional neural network (CNN) classifier identifying true tar spot stromata from the region proposals. To demonstrate the enhanced performance of the SCDA v2, we used datasets of RGB images of corn leaves from field (low, middle, and upper canopies) and glasshouse conditions under variable environments, exhibiting different tar spot severities at various corn developmental stages. Various accuracy analyses (F1 score, linear regression, and Lin's concordance correlation) showed that SCDA v2 had a greater agreement with the reference data (human visual annotation) than SCDA v1. SCDA v2 achieved 73.7% mean Dice values (overall accuracy) compared with 30.8% for SCDA v1. The enhanced F1 score primarily resulted from eliminating overestimation cases using the CNN classifier. Our findings indicate the promising potential of SCDA v2 for glasshouse and field-scale applications, including tar spot phenotyping and surveillance projects. Copyright © 2024 The Author(s). This is an open access article distributed under the CC BY-NC-ND 4.0 International license.

Why it matches plant phenotyping methodsトウモロコシ葉のタールスポット病の重症度をRGB画像から推定するアルゴリズムを開発し、従来法および人手アノテーションと精度比較しており、植物病害表現型の取得手法が中心である。

abstractHere, we present the Stromata Contour Detection Algorithm version 2 (SCDA v2), which addresses the limitations of the previously developed SCDA version 1 (SCDA v1), without the need to empirically search for optimal decision-making input parameters (DMIPs) while achieving higher and consistent accuracy in tar spot stromata detection.

Development of plant phenotyping system using Pan Tilt Zoom camera and verification of its validity →

Quantitative analysis for plant growth attributes has gained prominence in plant science and agriculture. Despite the availability of automated phenotyping systems as a solution to labor-intensive manual measurement techniques, these systems often require specialized knowledge and face challenges in scaling for high-throughput applications. This research introduces a scalable high-throughput plant phenotyping technique utilizing a Pan Tilt Zoom (PTZ) camera. The primary objective is to assess the application of a PTZ camera in a plant phenotyping system. By integrating open-source software and hardware technologies, the method captures images of cucumber plants in a controlled greenhouse environment. The operational procedure of the robot consists of a series of steps. It begins with the robot’s initial movement to capture infrared images, followed by an analysis to detect Aruco markers serving as location identifiers for capturing plant images. Subsequently, the PTZ camera is adjusted to capture specific plant traits from predefined viewpoints. The captured images with location IDs, preset viewpoints, and timestamps are then sent to a remote server. Validation of the system’s dependability includes manual measurements on fundamental operations and the evaluation of the effectiveness of zoomed images captured by the PTZ camera, tested through plant feature detection. Experimental results demonstrate promising outcomes, achieving a mean average precision (mAP) of 94%, 97.6%, 98.4%, 90.1%, and 97.6% for apical buds, male flowers, female flowers, tiny cucumbers, and mature cucumbers respectively when using the trained YOLOv8s on an augmented dataset tested on highly zoomed images validation set, outperforming less zoomed or less detailed validation sets. These findings underscore the efficacy of this innovative approach in capturing real-time plant images. Leveraging the PTZ camera’s zoom, pan, and tilt capabilities enables comprehensive visualization of plant traits and adaptability to evolving growth patterns, thereby improving the results of plant feature detection. The amassed imagery serves a dual purpose by acting as training data for AI models, highlighting their potential to facilitate future research endeavors demanding extensive and scalable plant information.

Why it matches plant phenotyping methodsPTZカメラとロボットを用いた植物フェノタイピングシステムの開発・検証が研究の中心で、植物器官の画像取得と特徴検出を評価している。

abstractThis research introduces a scalable high-throughput plant phenotyping technique utilizing a Pan Tilt Zoom (PTZ) camera.

Development of plant phenotyping system using Pan Tilt Zoom camera and verification of its validity →

Quantitative analysis for plant growth attributes has gained prominence in plant science and agriculture. Despite the availability of automated phenotyping systems as a solution to labor-intensive manual measurement techniques, these systems often require specialized knowledge and face challenges in scaling for high-throughput applications. This research introduces a scalable high-throughput plant phenotyping technique utilizing a Pan Tilt Zoom (PTZ) camera. The primary objective is to assess the application of a PTZ camera in a plant phenotyping system. By integrating open-source software and hardware technologies, the method captures images of cucumber plants in a controlled greenhouse environment. The operational procedure of the robot consists of a series of steps. It begins with the robot’s initial movement to capture infrared images, followed by an analysis to detect Aruco markers serving as location identifiers for capturing plant images. Subsequently, the PTZ camera is adjusted to capture specific plant traits from predefined viewpoints. The captured images with location IDs, preset viewpoints, and timestamps are then sent to a remote server. Validation of the system’s dependability includes manual measurements on fundamental operations and the evaluation of the effectiveness of zoomed images captured by the PTZ camera, tested through plant feature detection. Experimental results demonstrate promising outcomes, achieving a mean average precision (mAP) of 94%, 97.6%, 98.4%, 90.1%, and 97.6% for apical buds, male flowers, female flowers, tiny cucumbers, and mature cucumbers respectively when using the trained YOLOv8s on an augmented dataset tested on highly zoomed images validation set, outperforming less zoomed or less detailed validation sets. These findings underscore the efficacy of this innovative approach in capturing real-time plant images. Leveraging the PTZ camera’s zoom, pan, and tilt capabilities enables comprehensive visualization of plant traits and adaptability to evolving growth patterns, thereby improving the results of plant feature detection. The amassed imagery serves a dual purpose by acting as training data for AI models, highlighting their potential to facilitate future research endeavors demanding extensive and scalable plant information. • Introducing a high-throughput plant phenotyping method for capturing real-time imagery of plants. • Proposing PTZ camera’s imaging mechanisms for visualizing diverse and detailed plant features. • Improved results arise from applying plant feature detection to zoomed images taken with a PTZ camera.

Why it matches plant phenotyping methodsPTZカメラを用いた植物表現型取得システムを開発し、画像による器官・生育特徴検出で有効性を検証しており、方法が研究の中心である。

abstractThis research introduces a scalable high-throughput plant phenotyping technique utilizing a Pan Tilt Zoom (PTZ) camera.

Y-HRNet: Research on multi-category cherry tomato instance segmentation model based on improved YOLOv7 and HRNet fusion →

Accurate recognition of multi-category targets in cherry tomato images is a technical prerequisite for automated picking. However, in unstructured real-world scenarios, the existing network parameters are numerous and computationally intensive, and the models have low recognition accuracy when deployed on picking robots. Additionally, tomato detection and segmentation face challenges due to variable lighting, tomato overlap, similar backgrounds, and color transitions. In this context, this study focuses on the accurate segmentation of cherry tomato ripeness in large scenarios. This paper proposes a ”coarse detection, fine segmentation” method named Y-HRNet for greenhouse cherry tomatoes, which utilizes a multi-class cherry tomato dataset divided into four categories: green, turning, ripe, and fully ripe, achieving pixel-accurate segmentation of tomatoes of different ripeness levels. Firstly, a lightweight network model is constructed using YOLOv7 to build a lightweight object detection model. The ROI(Regions of Interest) is selected for segmentation, reducing the interference of complex backgrounds in large environments on the second-stage tomato segmentation task. Then, the ECA (Efficient Channel Attention) module and the DR-ASPP module are introduced into the Y-HRNet network. This enhances the model’s segmentation accuracy, enabling more effective capture of cherry tomatoes at four different maturity stages. The experiments demonstrate that Y-HRNet achieves segmentation of cherry tomatoes with the MIoU of 84.69%, MPA of 91.52%, and an overall accuracy of 94.39%. The average processing time of a single cherry tomato image is 0.35s. Compared to classic segmentation methods, our approach significantly improves performance. Therefore, this method provides technical support for the maturity grading and harvest management decisions of cherry tomatoes.

Why it matches plant phenotyping methodsチェリートマトの成熟度という植物状態を画像から画素単位で推定する新規セグメンテーション手法を開発・評価しており、フェノタイピング手法が中心である。

abstractthis study focuses on the accurate segmentation of cherry tomato ripeness in large scenarios.

A high-throughput method for monitoring growth of lettuce seedlings in greenhouses based on enhanced Mask2Former →

Monitoring plant growth is crucial for cultivation management. Agronomists can assess the health status of lettuce seedlings based on monitoring results to implement relevant management measures for improving the quality and yield of lettuce seedlings. This study developed a non-destructive, high-throughput growth monitoring method suitable for large-scale assessment of lettuce seedling quality in nurseries. The method utilizes a plant high-throughput phenotyping platform to acquire 10-day time-series imagery data. An Mask2Former network model enhanced by multidimensional collaborative attention mechanism, combined with sliding window and morphological operations, achieves precise recognition and localization of seedling trays, varieties, and individual seedling plants in a progressive manner. Based on individual seedling localization and segmentation results, the method estimates emergence numbers and rates for each variety, and further achieves instance segmentation and counting of individual seedling leaves, innovatively constructing leaf segmentation results of different varieties across the entire seedling tray. Applied to time-series images, the method automatically monitored seedling emergence changes and growth trends for 1,086 lettuce varieties. In monitoring these varieties, the method achieved a coefficient of determination (R²) of 0.96 for emergence number estimation. The extraction of all six key phenotypic parameters demonstrated exceptionally high correlations: projected area, projected perimeter, convex hull area, and convex hull perimeter all showed R² above 0.99, while leaf compactness R² was 0.9698, and leaf count R² was 0.91. Results demonstrate that this high-throughput, reliable method can effectively monitor the growth status of large-scale lettuce seedlings and provide technical support for lettuce nursery quality assessment.

Why it matches plant phenotyping methods画像解析モデルとハイスループット表現型プラットフォームを開発し、個体・葉の形態形質や出芽を自動抽出することが研究の中心であるため。

abstractThis study developed a non-destructive, high-throughput growth monitoring method suitable for large-scale assessment of lettuce seedling quality in nurseries.

A logistic model for precise tomato fruit-growth prediction based on diameter-time evolution →

Monitoring tomato fruit growth in large greenhouse environments is crucial for estimating harvest volume and maximising labour efficiency. Mathematical modelling is commonly used to characterise crop and fruit growth and to understand crop responses to environmental influences. This study presents a logistic approach for estimating tomato fruit maturity based on fruit diameter. A set of logistic models were evaluated, and their precision and ability to forecast tomato fruit growth were analysed. Non-linear least square regression was used to fit each model to individual tomato fruits from a sample of over 600 fruits of two species (small and large fruit-bearing tomatoes) grown within one year. The focus was on fruit diameter and the necessary measurement precision for fruit maturity estimation. Low-dispersion variables were identified within our logistic model functions, and fruit species-specific model parameters were determined. Furthermore, we reduced the number of regression variables by identifying parameters of low variance. This allowed for high prediction precision (>80%) at the early fruit maturity stages (<30%). The fruit diameter data were collected manually using a caliper. Our results establish an upper limit for the measurement precision of automated fruit size estimation approaches utilising photogrammetry, with an optical range of 98% for 3 mm and 90% for 5 mm precision.

Why it matches plant phenotyping methodsトマト果実径から成熟度・成長を推定するロジスティックモデルを開発・評価し、将来の自動果実サイズ推定に必要な測定精度も検討しており、植物形質抽出手法が中心である。

abstractThis study presents a logistic approach for estimating tomato fruit maturity based on fruit diameter.

Improved YOLOv8 Model for Phenotype Detection of Horticultural Seedling Growth Based on Digital Cousin →

Crop phenotype detection is a precision way to understand and predict the growth of horticul-tural Seedling in smart agriculture era, to make the agricultural production more costly and en-ergy efficiency. And it bridges the plant statues and the agricultural devices, like robots and au-tonomous vehicles in smart greenhouse ecosystem, to know each other well. However, the im-aging data set collection is a neckless of deep learning of phenotype detection, as the dynamic coverings among leaves and time-spatial limits of camara sampling. To address this issue, digital cousin is boosting digital twins and virtual entities of plants, and considered to create dynamical 3D structures, attributes and RGB image data sets in a simulation environment, with the princi-ples of varies and interactions in physical world. Thus, this work presents a two-phase method to obtain the phenotype of horticultural seedling growth. In the first phase, 3D Gaussian Splatting is selected to reconstruct and store the 3D model of the plant, enabling to capture RGB images and detect the phenotypes of seedlings transcending temporal and spatial limitations. In the second phase, an improved the YOLOv8 model is created to segment and measure the seedlings, and it is modified by adding modules of the LADH, SPPELAN and Focaler-ECIOU to the original YOLOv8 model. Moreover, a case study of watermelon seeding is explored, and the results show that 3D Gaussian Splatting has good performance in 3D reconstruction of seedlings, and the peak sig-nal-to-noise ratio (PSNR) of the trained models is generally above 24. As for semantic segmenta-tion, compared with the original YOLOv8, the computation of our model decreased by 7.50%, the convergence speed increased by 31.35%.

Why it matches plant phenotyping methods幼 horticultural seedlings の3D再構成、画像取得、セグメンテーション、表現型測定を統合した手法開発が中心であり、植物表現型の抽出方法を直接扱っている。

abstractthis work presents a two-phase method to obtain the phenotype of horticultural seedling growth.

An Improved 2D Pose Estimation Algorithm for Extracting Phenotypic Parameters of Tomato Plants in Complex Backgrounds →

Phenotypic traits, such as plant height, internode length, and node count, are essential indicators of the growth status of tomato plants, carrying significant implications for research on genetic breeding and cultivation management. Deep learning algorithms such as object detection and segmentation have been widely utilized to extract plant phenotypic parameters. However, segmentation-based methods are labor-intensive due to their requirement for extensive annotation during training, while object detection approaches exhibit limitations in capturing intricate structural features. To achieve real-time, efficient, and precise extraction of phenotypic traits of seedling tomatoes, a novel plant phenotyping approach based on 2D pose estimation was proposed. We enhanced a novel heatmap-free method, YOLOv8s-pose, by integrating the Convolutional Block Attention Module (CBAM) and Content-Aware ReAssembly of FEatures (CARAFE), to develop an improved YOLOv8s-pose (IYOLOv8s-pose) model, which efficiently focuses on salient image features with minimal parameter overhead while achieving a superior recognition performance in complex backgrounds. IYOLOv8s-pose manifested a considerable enhancement in detecting bending points and stem nodes. Particularly for internode detection, IYOLOv8s-pose attained a Precision of 99.8%, exhibiting a significant improvement over RTMPose-s, YOLOv5s6-pose, YOLOv7s-pose, and YOLOv8s-pose by 2.9%, 5.4%, 3.5%, and 5.4%, respectively. Regarding plant height estimation, IYOLOv8s-pose achieved an RMSE of 0.48 cm and an rRMSE of 2%, and manifested a 65.1%, 68.1%, 65.6%, and 51.1% reduction in the rRMSE compared to RTMPose-s, YOLOv5s6-pose, YOLOv7s-pose, and YOLOv8s-pose, respectively. When confronted with the more intricate extraction of internode length, IYOLOv8s-pose also exhibited a 15.5%, 23.9%, 27.2%, and 12.5% reduction in the rRMSE compared to RTMPose-s, YOLOv5s6-pose, YOLOv7s-pose, and YOLOv8s-pose. IYOLOv8s-pose achieves high precision while simultaneously enhancing efficiency and convenience, rendering it particularly well suited for extracting phenotypic parameters of tomato plants grown naturally within greenhouse environments. This innovative approach provides a new means for the rapid, intelligent, and real-time acquisition of plant phenotypic parameters in complex backgrounds.

Why it matches plant phenotyping methodsトマトの草丈・節間長・節数を画像から抽出する2Dポーズ推定法を開発し、既存手法と性能比較・検証しており、植物表現型取得が研究の中心である。

abstractTo achieve real-time, efficient, and precise extraction of phenotypic traits of seedling tomatoes, a novel plant phenotyping approach based on 2D pose estimation was proposed.

Optimizing tomato detection and counting in smart greenhouses: A lightweight YOLOv8 model incorporating high- and low-frequency feature transformer structures. →

Tomato harvesting in intelligent greenhouses is crucial for reducing costs and optimizing management. Agricultural robots, as an automated solution, require advanced visual perception. This study proposes a tomato detection and counting algorithm based on YOLOv8 (TCAttn-YOLOv8). To handle small, occluded tomato targets in images, a new detection layer (NDL) is added to the Neck and Head decoupled structure, improving small object recognition. The ColBlock, a dual-branch structure leveraging Transformer advantages, enhances feature extraction and fusion, focusing on densely targeted regions and minimizing small object feature loss in complex backgrounds. C2fGhost and GhostConv are integrated into the Neck network to reduce model parameters and floating-point operations, improving feature expression. The WIoU (Wise-IoU) loss function is adopted to accelerate convergence and increase regression accuracy. Experimental results show that TCAttn-YOLOv8 achieves an mAP@0.5 of 96.31%, with an FPS of 95 and a parameter size of 2.7 M, outperforming seven lightweight YOLO algorithms. For automated tomato counting, the R 2 between predicted and actual counts is 0.9282, indicating the algorithm's suitability for replacing manual counting. This method effectively supports tomato detection and counting in intelligent greenhouses, offering valuable insights for robotic harvesting and yield estimation research.

Why it matches plant phenotyping methodsトマト果実の検出・計数を行う画像解析手法自体を開発・比較しており、果実数という植物器官形質を抽出する中心的研究である。

abstractThis study proposes a tomato detection and counting algorithm based on YOLOv8 (TCAttn-YOLOv8).

Unlocking the power of gene banks: diversity in base growth temperature provides opportunities for climate-smart agriculture →

Abstract Implementation of context-specific solutions, including cultivation of varieties adapted to current and future climatic conditions, were found to be effective in establishing resilient, climate-smart agricultural systems. Gene banks play a pivotal role in this. However, a large fraction of the collections remains neither genotyped nor phenotyped. Hypothesising that significant genotypic diversity in Musa temperature responses exists, this study aimed to assess the diversity in the world’s largest banana gene bank in terms of base temperature (T base ) and to evaluate its impact on plant performance in the East African highlands during a projected climate scenario. 116 gene bank accessions were evaluated in the BananaTainer, a tailor-made high throughput phenotyping installation. Plant growth was quantified in response to temperature and genotype-specific T base were modelled. Growth response of two genotypes was validated under greenhouse conditions, and gas exchange capacity measurements were made. The model revealed genotype-specific T base , with 30 % of the accessions showing a T base below the reference of 14 °C. The Mutika/Lujugira subgroup, endemic to the East African highlands, appeared to display a low T base , although within subgroup diversity was revealed. Greenhouse validation further showed low T sensitivity/tolerance to be related to the photosynthetic capacity. This study, therefore, significantly advances the debate of within species diversity in temperature growth responses, while at the same time unlocking the power of gene banks. Moreover, we provide a high throughput method to reveal the existing genotypic diversity in temperature responses, paving the way for future research to establish climate-smart varieties.

Why it matches plant phenotyping methodsバナナの温度応答と成長を定量化する高スループット表現型計測設備・手法を提示し、温室条件で検証しているため、表現型取得法が中心的です。

abstract116 gene bank accessions were evaluated in the BananaTainer, a tailor-made high throughput phenotyping installation.

Transcription-Aided Selection (TAS) for Crop Disease Resistance: Strategy and Evidence. →

A transcription-aided selection (TAS) strategy is proposed in this paper, which utilizes the positive regulatory roles of genes involved in the plant immunity pathways to screen crops with high disease resistance. Increased evidence has demonstrated that upon pathogen attack, the expression of diverse genes involved in salicylic acid (SA)-mediated SAR are differentially expressed and transcriptionally regulated. The paper discusses the molecular mechanisms of the SA signaling pathway, which plays a central role in plant immunity, and identifies differentially expressed genes (DEGs) that could be targeted for transcriptional detection. We have conducted a series of experiments to test the TAS strategy and found that the level of GmSAGT1 expression is highly correlated with soybean downy mildew (SDM) resistance with a correlation coefficient R 2 = 0.7981. Using RT-PCR, we screened 2501 soybean germplasms and selected 26 collections with higher levels of both GmSAGT1 and GmPR1 (Pathogenesis-related proteins1) gene expression. Twenty-three out of the twenty-six lines were inoculated with Peronospora manshurica (Pm) in a greenhouse. Eight showed HR (highly resistant), four were R (resistant), five were MR (moderately resistant), three were S (susceptible), and three were HS (highly susceptible). The correlation coefficient R 2 between the TAS result and Pm inoculation results was 0.7035, indicating a satisfactory consistency. The authors anticipate that TAS provides an effective strategy for screening crops with broad-spectrum and long-lasting resistance.

Why it matches plant phenotyping methods遺伝子発現を用いて作物の病害抵抗性を推定・選抜するTAS戦略を提案し、RT-PCRスクリーニングと接種試験で相関・妥当性を検証している。分子測定だが、抵抗性という植物状態の推定法が研究の中心である。

abstractA transcription-aided selection (TAS) strategy is proposed in this paper, which utilizes the positive regulatory roles of genes involved in the plant immunity pathways to screen crops with high disease resistance.

Estimating TYLCV resistance level using RGBD sensors in production greenhouse conditions →

Automated phenotyping is the task of automatically measuring plant attributes to help farmers and breeders in developing and growing strong robust plants. An automated tool for early illness detection can accelerate the process of identifying plant resistance and quickly pinpoint problematic breeding. Many such phenotyping tasks can be achieved by analyzing images from simple, low cost, RGB-D sensors. In this paper we focused on a particular case study — identifying the resistance level of tomato hybrids to the tomato yellow leaf curl virus (TYLCV) in production greenhouses. This is a difficult task, as separating between resistance levels based on images is difficult even for expert breeders. We collected a large dataset of images from an experiment containing many tomato hybrids with varying resistance levels. We used the depth information to identify the topmost part of the tomato plant. We then used deep learning models to classify the various resistance levels. For identifying plants with visual symptoms, our methods achieved an accuracy of 0.928, a precision of 0.934, and a recall of 0.95. In the multi-class case we achieved an accuracy of 0.76 in identifying the correct level, and an error of 0.278. Our methods are not particularly tailored for the specific task, and can be extended to other tasks that identify various plant diseases with visual symptoms such as ToBRFV, mildew, ToMV and others.

Why it matches plant phenotyping methodsRGB-D画像と深度情報、深層学習を用いてトマトのウイルス症状と抵抗性レベルを推定する手法を開発・評価しており、植物表現型取得が中心である。

abstractAutomated phenotyping is the task of automatically measuring plant attributes

NeRF-based 3D reconstruction pipeline for acquisition and analysis of tomato crop morphology →

Recent advancements in digital phenotypic analysis have revolutionized the morphological analysis of crops, offering new insights into genetic trait expressions. This manuscript presents a novel 3D phenotyping pipeline utilizing the cutting-edge Neural Radiance Fields (NeRF) technology, aimed at overcoming the limitations of traditional 2D imaging methods. Our approach incorporates automated RGB image acquisition through unmanned greenhouse robots, coupled with NeRF technology for dense Point Cloud generation. This facilitates non-destructive, accurate measurements of crop parameters such as node length, leaf area, and fruit volume. Our results, derived from applying this methodology to tomato crops in greenhouse conditions, demonstrate a high correlation with traditional human growth surveys. The manuscript highlights the system’s ability to achieve detailed morphological analysis from limited viewpoint of camera, proving its suitability and practicality for greenhouse environments. The results displayed an R-squared value of 0.973 and a Mean Absolute Percentage Error (MAPE) of 0.089 for inter-node length measurements, while segmented leaf point cloud and reconstructed meshes showed an R-squared value of 0.953 and a MAPE of 0.090 for leaf area measurements. Additionally, segmented tomato fruit analysis yielded an R-squared value of 0.96 and a MAPE of 0.135 for fruit volume measurements. These metrics underscore the precision and reliability of our 3D phenotyping pipeline, making it a highly promising tool for modern agriculture.

Why it matches plant phenotyping methodsNeRFとロボットRGB画像を用いてトマトの形態形質を取得・解析する3Dフェノタイピング手法を開発し、従来測定との精度検証も行っており、方法が研究の中心である。

abstractThis manuscript presents a novel 3D phenotyping pipeline utilizing the cutting-edge Neural Radiance Fields (NeRF) technology

Intelligent agricultural robotic detection system for greenhouse tomato leaf diseases using soft computing techniques and deep learning. →

The development of soft computing methods has had a significant influence on the subject of autonomous intelligent agriculture. This paper offers a system for autonomous greenhouse navigation that employs a fuzzy control algorithm and a deep learning-based disease classification model for tomato plants, identifying illnesses using photos of tomato leaves. The primary novelty in this study is the introduction of an upgraded Deep Convolutional Generative Adversarial Network (DCGAN) that creates augmented pictures of disease tomato leaves from original genuine samples, considerably enhancing the training dataset. To find the optimum training model, four deep learning networks (VGG19, Inception-v3, DenseNet-201, and ResNet-152) were carefully compared on a dataset of nine tomato leaf disease classes. These models have validation accuracy of 92.32%, 90.83%, 96.61%, and 97.07%, respectively, when using the original PlantVillage dataset. The system then uses an enhanced dataset with ResNet-152 network design to achieve a high accuracy of 99.69%, as compared to the original dataset with ResNet-152's accuracy of 97.07%. This improvement indicates the use of the proposed DCGAN in improving the performance of the deep learning model for greenhouse plant monitoring and disease detection. Furthermore, the proposed approach may have a broader use in various agricultural scenarios, potentially altering the field of autonomous intelligent agriculture.

Why it matches plant phenotyping methodsトマト葉の画像から病害状態を分類する深層学習手法と、DCGANによるデータ拡張を中心に開発・比較・評価しており、植物病害フェノタイピング手法が主要な貢献である。

abstracta deep learning-based disease classification model for tomato plants, identifying illnesses using photos of tomato leaves

A logistic model for precise tomato fruit-growth prediction based on diameter-time evolution →

Monitoring tomato fruit growth in large greenhouse environments is crucial for estimating harvest volume and maximising labour efficiency. Mathematical modelling is commonly used to characterise crop and fruit growth and to understand crop responses to environmental influences. This study presents a logistic approach for estimating tomato fruit maturity based on fruit diameter. A set of logistic models were evaluated, and their precision and ability to forecast tomato fruit growth were analysed. Non-linear least square regression was used to fit each model to individual tomato fruits from a sample of over 600 fruits of two species (small and large fruit-bearing tomatoes) grown within one year. The focus was on fruit diameter and the necessary measurement precision for fruit maturity estimation. Low-dispersion variables were identified within our logistic model functions, and fruit species-specific model parameters were determined. Furthermore, we reduced the number of regression variables by identifying parameters of low variance. This allowed for high prediction precision ( > 80%) at the early fruit maturity stages ( < 30%). The fruit diameter data were collected manually using a caliper. Our results establish an upper limit for the measurement precision of automated fruit size estimation approaches utilising photogrammetry, with an optical range of 98% for 3 mm and 90% for 5 mm precision. • Long and short term Tomato fruit size prediction. • High precision fruit yield forecasting. • Optimised tomato fruit growth modelling and comparison between models. • Upper limit estimation for growth predictability.

Why it matches plant phenotyping methodsトマト果径から成熟・成長を推定するロジスティック予測モデルを開発・比較し、予測精度と自動果実サイズ推定への測定精度上限を評価しており、植物形質推定手法が中心です。

abstractThis study presents a logistic approach for estimating tomato fruit maturity based on fruit diameter.

Hyperspectral imaging for pest symptom detection in bell pepper. →

Background The automation of pest monitoring is highly important for enhancing integrated pest management in practice. In this context, advanced technologies are becoming increasingly explored. Hyperspectral imaging (HSI) is a technique that has been used frequently in recent years in the context of natural science, and the successful detection of several fungal diseases and some pests has been reported. Various automated measures and image analysis methods offer great potential for enhancing monitoring in practice. Results In this study, the use of hyperspectral imaging over a wide spectrum from 400 to 2500 nm is investigated for noninvasive identification and the distinction of healthy plants and plants infested with Myzus persicae (Sulzer) and Frankliniella occidentalis (Pergande) on bell peppers. Pest infestations were carried out in netted areas, and images of single plants and dissected leaves were used to train the decision algorithm. Additionally, a specially modified spraying robot was converted into an autonomous platform used to carry the hyperspectral imaging system to take images under greenhouse conditions. The algorithm was developed via the XGBoost framework with gradient-boosted trees. Signals from specific wavelengths were found to be associated with the damage patterns of different insects. Under confined conditions, M. persicae and F. occidentalis infestations were distinguished from each other and from the uninfested control for single leaves. Differentiation was still possible when small whole plants were used. However, application under greenhouse conditions did not result in a good fit compared to the results of manual monitoring. Conclusion Hyperspectral images can be used to distinguish sucking pests on bell peppers on the basis of single leaves and intact potted bell pepper plants under controlled conditions. Wavelength reduction methods offer options for multispectral camera usage in high-grown vegetable greenhouses. The application of automated platforms similar to the one tested in this study could be possible, but for successful pest detection under greenhouse conditions, algorithms should be further developed fully considering real-world conditions.

Why it matches plant phenotyping methodsベルペッパー植物の害虫による状態・損傷パターンをハイパースペクトル画像と機械学習で識別する手法を開発・検証し、自律撮像プラットフォームも評価しているため、植物フェノタイピング手法が中心である。

abstractthe use of hyperspectral imaging over a wide spectrum from 400 to 2500 nm is investigated for noninvasive identification and the distinction of healthy plants and plants infested with Myzus persicae (Sulzer) and Frankliniella occidentalis (Pergande) on bell peppers.

Early detection of tomato bacterial spot disease in transplant tomato seedlings utilising remote sensing and artificial intelligence →

Florida is the largest fresh tomato producer in the USA. Due to the subtropical climate, especially the hot and humid weather, the devastating tomato bacterial spot disease (TBS), caused by the bacteria Xanthomonas perforans, has been a threat to tomato crops for decades. Prevention through early disease detection is a crucial management strategy to minimise losses. Diagnostics for this disease that are commonly used are a visual diagnosis of disease symptoms or laboratory assays. These procedures are time-consuming, require specialised personnel, and are inefficient in detecting the disease in its early stages. Hyperspectral imaging provides a non-invasive tool for early disease detection in various crops. In this study, five optimised machine learning algorithms (MLAs), such as Linear Discriminant Analysis (LDA), Partial Least Squares Discriminant Analysis (PLSDA), Weighted K-Nearest Neighbours (W–KNN), Support Vector Machine (SVM), and Ensemble Boosting Tree (EBT), were utilised for early detection of TBS in transplant houses. Two normalisation procedures, a standardisation method, and unit vectorisation, were applied to preprocess the data in a dynamic range expansion process. The input variables to the models included time-lined events of disease progression and reduced datasets. To create the reduced datasets, a novel data reduction methodology was developed, which was able to identify 12 key (significant) wavelengths (from the 300 initial scans of the hyperspectral camera) that carry the highest weighted spectral components for accurately detecting TBS-affected plants. The PLSDA model presented the highest F1 score (90%) on early detection of TBS.

Why it matches plant phenotyping methodsトマト植物の病徴状態をハイパースペクトル画像と機械学習で早期推定する手法を開発・評価しており、植物フェノタイピングが中心的である。

abstractHyperspectral imaging provides a non-invasive tool for early disease detection in various crops.

Spectrum imaging for phenotypic detection of greenhouse vegetables: A review →

Greenhouse vegetables have become increasingly important in global crop production due to their ability to be cultivated out of season and ensure a year-round supply of vegetables. With the rapid advancement of “phenomics”, accurately measuring the phenotypic information of greenhouse vegetables is crucial for enhancing both their yield and quality. Over the past two decades, various technologies have been developed for phenotypic detection of fruits, vegetables, and other crops, based on the interaction between electromagnetic waves and matter. While some articles have investigated these applications, there is a lack of a systematic review specifically focused on the phenotypic detection of greenhouse vegetables. In this review, RGB imaging, Multispectral/Hyperspectral imaging, Chlorophyll fluorescence imaging, Thermal imaging, Raman imaging, X-ray imaging, Magnetic resonance imaging, and Terahertz imaging are collectively referred to as spectrum imaging technologies. We provide a comprehensive review of the origins, research progress over the past twenty years, and current challenges of spectrum imaging in the field of greenhouse vegetable research. It focuses on identifying the most suitable spectrum imaging technologies for detecting four categories of phenotypic traits: biochemical, physiological, morphological, and yield-related traits. Additionally, we highlight the issues that need optimization in the practical application of these technologies and the bottlenecks faced in different trait studies. Finally, based on existing research, we propose several potential solutions and future research directions to maximize the utility of spectrum imaging technologies in the phenotypic detection of greenhouse vegetables.

Why it matches plant phenotyping methods温室野菜の表現型検出に用いる各種スペクトル画像技術を体系的にレビューし、形態・生理・生化学・収量形質への適用と技術的課題を中心に扱っているため。

titleSpectrum imaging for phenotypic detection of greenhouse vegetables: A review

Attention-driven next-best-view planning for efficient reconstruction of plants and targeted plant parts →

Robots in tomato greenhouses need to perceive the plant and plant parts accurately to automate monitoring, harvesting, and de-leafing tasks. Existing perception systems struggle with the high levels of occlusion in plants and often result in poor perception accuracy. One reason for this is because they use fixed cameras or predefined camera movements. Next-best-view (NBV) planning presents an alternate approach, in which the camera viewpoints are reasoned and strategically planned such that the perception accuracy is improved. However, existing NBV-planning algorithms are agnostic to the task-at-hand and give equal importance to all the plant parts. This strategy is inefficient for greenhouse tasks that require targeted perception of specific plant parts, such as the perception of leaf nodes for de-leafing. To improve targeted perception in complex greenhouse environments, NBV planning algorithms need an attention mechanism to focus on the task-relevant plant parts. In this paper, the role of attention in improving targeted perception using an attention-driven NBV planning strategy was investigated. Through simulation experiments using plants with high levels of occlusion and structural complexity, it was shown that focusing attention on task-relevant plant parts can significantly improve the speed and accuracy of 3D reconstruction. Further, with real-world experiments, it was shown that these benefits extend to complex greenhouse conditions with natural variation and occlusion, natural illumination, sensor noise, and uncertainty in camera poses. The results clearly indicate that using attention-driven NBV planning in greenhouses can significantly improve the efficiency of perception and enhance the performance of robotic systems in greenhouse crop production.

Why it matches plant phenotyping methods植物および植物部位の3D再構成を対象に、注意機構付き次善視点計画を開発し、シミュレーションと実環境で精度・速度を検証しているため、植物フェノタイピング手法が中心である。

abstractNext-best-view (NBV) planning presents an alternate approach, in which the camera viewpoints are reasoned and strategically planned such that the perception accuracy is improved.

Artificial Size Slicing Aided Fine Tuning (ASSAFT) and Hyper Inference (ASSAHI) in tomato detection →

In the realm of precision agriculture, accurate harvest prediction is vital, as any discrepancies between forecasted and actual yields can lead to significant commercial and logistical challenges. This paper presents a novel deep learning-based approach for detecting and counting tomato fruits using advanced computer vision techniques. Building upon our previously established framework for ultra-wide image acquisition, this approach focuses on a unique patch-cropping technique tailored to tomatoes. This method aligns with the natural clustering of tomatoes, significantly improving object detection in greenhouse settings and thereby enhancing the model’s performance in identifying individual fruits. The detection results exhibit a precision of 0.85, a recall of 0.93, and an F1-score of 0.89. Our approach’s efficacy is also demonstrated through a case study on harvest prediction in a tomato greenhouse. The proposed methodology exhibited a lower error rate than the agronomist’s estimates and proved its practical applicability. These findings suggest that our methodology could substantially contribute to optimizing sustainable farming practices, offering a promising direction for future research and application in the agricultural sector.

Why it matches plant phenotyping methodsトマト果実の検出・計数という植物器官形質の取得を目的に、画像取得とパッチクロッピングを含む深層学習手法を開発・評価しており、方法が中心的である。

abstractThis paper presents a novel deep learning-based approach for detecting and counting tomato fruits using advanced computer vision techniques.

Evaluating waterlogging stress response and recovery in barley (Hordeum vulgare L.): an image-based phenotyping approach. →

Waterlogging is expected to become a more prominent yield restricting stress for barley as rainfall frequency is increasing in many regions due to climate change. The duration of waterlogging events in the field is highly variable throughout the season, and this variation is also observed in experimental waterlogging studies. Such variety of protocols make intricate physiological responses challenging to assess and quantify. To assess barley waterlogging tolerance in controlled conditions, we present an optimal duration and setup of simulated waterlogging stress using image-based phenotyping. Six protocols durations, 5, 10, and 14 days of stress with and without seven days of recovery, were tested. To quantify the physiological effects of waterlogging on growth and greenness, we used top down and side view RGB (Red-Green-Blue) images. These images were taken daily throughout each of the protocols using the PSI PlantScreen™ imaging platform. Two genotypes of two-row spring barley, grown in glasshouse conditions, were subjected to each of the six protocols, with stress being imposed at the three-leaf stage. Shoot biomass and root imaging data were analysed to determine the optimal stress protocol duration, as well as to quantify the growth and morphometric changes of barley in response to waterlogging stress. Our time-series results show a significant growth reduction and alteration of greenness, allowing us to determine an optimal protocol duration of 14 days of stress and seven days of recovery for controlled conditions. Moreover, to confirm the reproducibility of this protocol, we conducted the same experiment in a different facility equipped with RGB and chlorophyll fluorescence imaging sensors. Our results demonstrate that the selected protocol enables the assessment of genotypic differences, which allow us to further determine tolerance responses in a glasshouse environment. Altogether, this work presents a new and reproducible image-based protocol to assess early stage waterlogging tolerance, empowering a precise quantification of waterlogging stress relevant markers such as greenness, Fv/Fm and growth rates.

Why it matches plant phenotyping methods画像ベース表現型解析を用いた湛水ストレス評価プロトコルの開発と、別施設・異なるセンサーによる再現性検証が中心であるため、収録対象。

abstractwe present an optimal duration and setup of simulated waterlogging stress using image-based phenotyping.

Hyperspectral Imaging for Phenotyping Plant Drought Stress and Nitrogen Interactions Using Multivariate Modeling and Machine Learning Techniques in Wheat →

Accurate detection of drought stress in plants is essential for water use efficiency and agricultural output. Hyperspectral imaging (HSI) provides a non-invasive method in plant phenotyping, allowing the long-term monitoring of plant health due to sensitivity to subtle changes in leaf constituents. The broad spectral range of HSI enables the development of different vegetation indices (VIs) to analyze plant trait responses to multiple stresses, such as the combination of nutrient and drought stresses. However, known VIs may underperform when subjected to multiple stresses. This study presents new VIs in tandem with machine learning models to identify drought stress in wheat plants under varying nitrogen (N) levels. A pot wheat experiment was set up in the glasshouse with four treatments: well-watered high-N (WWHN), well-watered low-N (WWLN), drought-stress high-N (DSHN) and drought-stress low-N (DSLN). In addition to ensuring that plants were watered according to the experiment design, photosynthetic rate (Pn) and stomatal conductance (gs) (which are used to assess plant drought stress) were taken regularly, serving as the ground truth data for this study. The proposed VIs, together with known VIs, were used to train three classification models: support vector machines (SVM), random forest (RF), and deep neural networks (DNN) to classify plants based on their drought status. The proposed VIs achieved more than 0.94 accuracy across all models, and their performance further increased when combined with known VIs. The combined VIs were used to train three regression models to predict the stomatal conductance and photosynthetic rates of plants. The random forest regression model performed best, suggesting that it could be used as a stand-alone tool to forecast gs and Pn and track drought stress in wheat. This study shows that combining hyperspectral data with machine learning can effectively monitor and predict drought stress in crops, especially in varying nitrogen conditions.

Why it matches plant phenotyping methods小麦の乾燥ストレスという植物状態を、ハイパースペクトル画像から新規指標と機械学習で分類・予測する手法が研究の中心であり、光合成速度や気孔コンダクタンスとの検証も行っている。

abstractThis study presents new VIs in tandem with machine learning models to identify drought stress in wheat plants under varying nitrogen (N) levels.

Validation of In-House Imaging System via Code Verification on Petunia Images Collected at Increasing Fertilizer Rates and pHs. →

In a production environment, delayed stress recognition can impact yield. Imaging can rapidly and effectively quantify stress symptoms using indexes such as normalized difference vegetation index (NDVI). Commercial systems are effective but cannot be easily customized for specific applications, particularly post-processing. We developed a low-cost customizable imaging system and validated the code to analyze images. Our objective was to verify the image analysis code and custom system could successfully quantify the changes in plant canopy reflectance. 'Supercascade Red', 'Wave© Purple', and 'Carpet Blue' Petunias ( Petunia × hybridia ) were transplanted individually and subjected to increasing fertilizer treatments and increasing substrate pH in a greenhouse. Treatments for the first trial were the addition of a controlled release fertilizer at six different rates (0, 0.5, 1, 2, 4, and 8 g/pot), and for the second trial, fertilizer solution with four pHs (4, 5.5, 7, and 8.5), with eight replications with one plant each. Plants were imaged twice a week using a commercial imaging system for fertilizer and thrice a week with the custom system for pH. The collected images were analyzed using an in-house program that calculated the indices for each pixel of the plant area. All cultivars showed a significant effect of fertilizer on the projected canopy size and dry weight of the above-substrate biomass and the fertilizer rate treatments ( p p p > 0.05). Manganese and phosphorus had no significance with chlorophyll fluorescence for 'Carpet Blue' and 'Wave© Purple' ( p > 0.05), though 'Supercascade Red' was found to have significance ( p p = 0.005). NDVI as a function of the projected canopy size had no statistical significance. We verified the ability of the imaging system with integrated analysis to quantify nutrient deficiency-induced variability in plant canopies by increasing pH levels.

Why it matches plant phenotyping methods低コスト imaging system と画像解析コードを開発・検証し、植物キャノピーの反射率や投影面積を定量化することが研究の中心であるため。

abstractWe developed a low-cost customizable imaging system and validated the code to analyze images.

Deep learning approach for detecting tomato flowers and buds in greenhouses on 3P2R gantry robot. →

In recent years, significant advancements have been made in the field of smart greenhouses, particularly in the application of computer vision and robotics for pollinating flowers. Robotic pollination offers several benefits, including reduced labor requirements and preservation of costly pollen through artificial tomato pollination. However, previous studies have primarily focused on the labeling and detection of tomato flowers alone. Therefore, the objective of this study was to develop a comprehensive methodology for simultaneously labeling, training, and detecting tomato flowers specifically tailored for robotic pollination. To achieve this, transfer learning techniques were employed using well-known models, namely YOLOv5 and the recently introduced YOLOv8, for tomato flower detection. The performance of both models was evaluated using the same image dataset, and a comparison was made based on their Average Precision (AP) scores to determine the superior model. The results indicated that YOLOv8 achieved a higher mean AP (mAP) of 92.6% in tomato flower and bud detection, outperforming YOLOv5 with 91.2%. Notably, YOLOv8 also demonstrated an inference speed of 0.7 ms when considering an image size of 1920 × 1080 pixels resized to 640 × 640 pixels during detection. The image dataset was acquired during both morning and evening periods to minimize the impact of lighting conditions on the detection model. These findings highlight the potential of YOLOv8 for real-time detection of tomato flowers and buds, enabling further estimation of flower blooming peaks and facilitating robotic pollination. In the context of robotic pollination, the study also focuses on the deployment of the proposed detection model on the 3P2R gantry robot. The study introduces a kinematic model and a modified circuit for the gantry robot. The position-based visual servoing method is employed to approach the detected flower during the pollination process. The effectiveness of the proposed visual servoing approach is validated in both un-clustered and clustered plant environments in the laboratory setting. Additionally, this study provides valuable theoretical and practical insights for specialists in the field of greenhouse systems, particularly in the design of flower detection algorithms using computer vision and its deployment in robotic systems used in greenhouses.

Why it matches plant phenotyping methodsトマトの花・蕾という植物器官の状態を画像から検出する手法を開発・比較評価し、ロボットへの実装まで扱っており、単なる生物実験の routine 測定ではなく、表現型取得法が中心である。

abstractThe performance of both models was evaluated using the same image dataset, and a comparison was made based on their Average Precision (AP) scores

SLAM-PYE: Tightly coupled GNSS-binocular-inertial fusion for pitaya positioning, counting, and yield estimation →

Accurate pre-harvest yield estimation facilitates the more rational allocation of resources. Previous methods of estimating fruit position, either directly from hardware or through Structure from Motion (SFM), encounter challenges such as high hardware costs, extensive computational resources, and repetitive counting. In this paper, we present a graph optimization-based system that tightly couples dual-frequency GNSS raw measurements and visual-inertial data to estimate pitaya state, including its position and radius. Firstly, the system utilizes a coarse-to-fine approach to estimate the transformations on three axes and align three complementary sensors to a unified coordinate system, thus reducing the computational complexity of pure visual navigation. Secondly, for the first time, this system analytically calculates the pitaya state using the single-view measurement output from the binocular camera, replacing expensive lidar. It employs this calculated state as the initial value, then optimizes the pitaya state and eliminates outliers by multiple reprojection residuals from multi-view measurements. Next, for the first time, we integrate ionospheric-free pseudorange and Doppler residuals into the visual-inertial factor graph, thereby mitigating multipath interference in double-layer film greenhouse and providing a unique ID and position for each pitaya. Finally, we calculate the weight of each pitaya using a cubic polynomial based on its radius and estimate the overall greenhouse yield by summing all individual weights. In greenhouse experiments, our system achieved an Root Mean Square Error (RMSE) of 7 cm for position estimation, 7 mm for radius estimation, and a weight Mean Absolute Percentage Error (MAPE) of about 16% for individual pitaya. Overall, our system can provide cost-effective, real-time, non-repetitive, and low-missing pitaya yield estimation to assist greenhouse managers in decision-making.

Why it matches plant phenotyping methodsGNSS・双眼カメラ・慣性センサを統合し、ピタヤの位置・半径・重量を推定する計測システムを開発し、誤差評価まで実施しているため、植物器官の表現型取得が中心である。

abstractwe present a graph optimization-based system that tightly couples dual-frequency GNSS raw measurements and visual-inertial data to estimate pitaya state, including its position and radius.

Early diagnosis of Cladosporium fulvum in greenhouse tomato plants based on visible/near-infrared (VIS/NIR) and near-infrared (NIR) data fusion. →

Plant diseases can inflict varying degrees of damage on agricultural production. Therefore, identifying a rapid, non-destructive early diagnostic method is crucial for safeguarding plants. Cladosporium fulvum (C. fulvum) is one of the major diseases in tomato growth. This work presents a method of data fusion using two hyperspectral imaging systems of visible/near-infrared (VIS/NIR) and near-infrared (NIR) spectroscopy for the early diagnosis of C. fulvum in greenhouse tomatoes. First, hyperspectral images of samples at health and different times of infection were collected. The average spectral data of the image regions of interest were extracted and preprocessed for subsequent spectral datasets. Then different classification models were established for VIS/NIR and NIR data, optimized through various variable selection and data fusion methods. The principal component analysis-radial basis function neural network (PCA-RBF) model established using low-level data fusion achieved optimal results, achieving accuracies of 100% and 99.3% for calibration and prediction, respectively. Moreover, both the macro-averaged F1 (Macro-F1) values reached 1, and the geometric mean (G-mean) values reached 1 and 1, respectively. The results indicated that it was feasible to establish a PCA-RBF model by using the hyperspectral technique with low-level data fusion for the early detection of C. fulvum in greenhouse tomatoes.

Why it matches plant phenotyping methodsトマト葉の感染状態をハイパースペクトル画像から直接推定するデータ融合・分類手法を開発し、精度評価しており、植物病害表現型の取得・判定が中心である。

abstractThis work presents a method of data fusion using two hyperspectral imaging systems of visible/near-infrared (VIS/NIR) and near-infrared (NIR) spectroscopy for the early diagnosis of C. fulvum in greenhouse tomatoes.

Designing an AI-Based Greenhouse Plant Monitoring System to Detect and Classify Plant Diseases from Leaf Images →

Plant diseases can significantly hinder food crop production, leading to substantial economic losses and posing a threat to global food security. Machine learning, particularly deep learning, plays a crucial role in object detection and classification. In this study, we present an AI-based plant monitoring system for detecting and classifying plant diseases using visual images.Our deep learning models are trained on plant images obtained from natural environments. Manual detection and classification are both challenging and labor-intensive, making accurate and timely diagnoses from an automatic system highly beneficial for treating plant diseases. Traditionally, plant disease detection using deep learning has relied on images taken in controlled environments, which do not support in-situ detection for remote monitoring. The Plantdoc dataset, a popular resource consisting of plant images from actual field conditions, is used in our study.We employ the YOLOv5 algorithm from the field of computer vision to the Plantdoc dataset, achieving results that surpass previous work on the same dataset. This success is attributed to our selected model and data augmentation techniques. Our model can classify and detect various diseased and healthy leaf classes with a mean Average Precision (mAP) of 92%. This capability enables farmers and researchers to remotely monitor plant health and diagnose plant diseases, thereby saving time, reducing costs, and minimizing crop loss.

Why it matches plant phenotyping methods葉画像から植物の病害状態を検出・分類するAI手法を開発・評価しており、植物表現型の取得が研究の中心です。

abstractwe present an AI-based plant monitoring system for detecting and classifying plant diseases using visual images.

Visualizing Plant Responses: Novel Insights Possible through Affordable Imaging Techniques in the Greenhouse →

Global climatic pressures and increased human demands create a modern necessity for efficient and affordable plant phenotyping unencumbered by arduous technical requirements. The analysis and archival of imagery have become easier as modern camera technology and computers are leveraged. This facilitates the detection of vegetation status and changes over time. Using a custom lightbox, an inexpensive camera, and common software, turfgrass pots were photographed in a greenhouse environment over an 8-week experiment period. Subsequent imagery was analyzed for area of cover, color metrics, and sensitivity to image corrections. Findings were compared to active spectral reflectance data and previously reported measurements of visual quality, productivity, and water use. Results indicate that Red Green Blue-based (RGB) imagery with simple controls is sufficient to measure the effects of plant treatments. Notable correlations were observed for corrected imagery, including between a percent yellow color area classification segment (%Y) with human visual quality ratings (VQ) (R = -0.89), the dark green color index (DGCI) with clipping productivity in mg d-1 (mg) (R = 0.61), and an index combination term (COMB2) with water use in mm d-1 (mm) (R = -0.60). The calculation of green cover area (%G) correlated with Normalized Difference Vegetation Index (NDVI) (R = 0.91) and its RED reflectance spectra (R = -0.87). A CIELAB b*/a* chromatic ratio (BA) correlated with Normalized Difference Red-Edge index (NDRE) (R = 0.90), and its Red-Edge (RE) (R = -0.74) reflectance spectra, while a new calculation termed HSVi correlated strongest to the Near-Infrared (NIR) (R = 0.90) reflectance spectra. Additionally, COMB2 significantly differentiated between the treatment effects of date, mowing height, deficit irrigation, and their interactions (p < 0.001). Sensitivity and statistical analysis of typical image file formats and corrections that included JPEG (JPG), TIFF (TIF), geometric lens correction (LC), and color correction (CC) were conducted. Results underscore the need for further research to support image corrections standardization and better connect image data to biological processes. This study demonstrates the potential of consumer-grade photography to capture plant phenotypic traits.

Why it matches plant phenotyping methods安価なRGB撮像と画像解析を用いて植物形質を取得し、分光測定や視覚評価との相関、画像補正の感度を検証しており、フェノタイピング手法が中心です。

abstractUsing a custom lightbox, an inexpensive camera, and common software, turfgrass pots were photographed in a greenhouse environment over an 8-week experiment period.

A Stacking Ensemble Learning Model Combining a Crop Simulation Model with Machine Learning to Improve the Dry Matter Yield Estimation of Greenhouse Pakchoi →

Crop models are instrumental in simulating resource utilization in agriculture, yet their complexity necessitates extensive calibration, which can impact the accuracy of yield predictions. Machine learning shows promise for enhancing yield estimations but relies on vast amounts of training data. This study aims to improve the pakchoi yield prediction accuracy of simulation models. We developed a stacking ensemble learning model that integrates three base models—EU-Rotate_N, Random Forest Regression and Support Vector Regression—with a Multi-layer Perceptron as the meta-model for the pakchoi dry matter yield prediction. To enhance the training dataset and bolster machine learning performance, we employed the EU-Rotate_N model to simulate daily dry matter yields for unsampled data. The test results revealed that the stacking model outperformed each base model. The stacking model achieved an R² value of 0.834, which was approximately 0.1 higher than that of the EU-Rotate_N model. The RMSE and MAE were 0.283 t/ha and 0.196 t/ha, respectively, both approximately 0.6 t/ha lower than those of the EU-Rotate_N model. The performance of the stacking model, developed with the expanded dataset, showed a significant improvement over the model based on the original dataset.

Why it matches plant phenotyping methodsパクチョイの乾物収量という植物形質を推定するスタッキング予測モデルを開発し、複数モデルとの性能比較・検証を行っており、形質推定手法が研究の中心である。

abstractWe developed a stacking ensemble learning model that integrates three base models—EU-Rotate_N, Random Forest Regression and Support Vector Regression—with a Multi-layer Perceptron as the meta-model for the pakchoi dry matter yield prediction.

Multisource information fusion method for vegetable disease detection. →

Automated detection and identification of vegetable diseases can enhance vegetable quality and increase profits. Images of greenhouse-grown vegetable diseases often feature complex backgrounds, a diverse array of diseases, and subtle symptomatic differences. Previous studies have grappled with accurately pinpointing lesion positions and quantifying infection degrees, resulting in overall low recognition rates. To tackle the challenges posed by insufficient validation datasets and low detection and recognition rates, this study capitalizes on the geographical advantage of Shouguang, renowned as the "Vegetable Town," to establish a self-built vegetable base for data collection and validation experiments. Concentrating on a broad spectrum of fruit and vegetable crops afflicted with various diseases, we conducted on-site collection of greenhouse disease images, compiled a large-scale dataset, and introduced the Space-Time Fusion Attention Network (STFAN). STFAN integrates multi-source information on vegetable disease occurrences, bolstering the model's resilience. Additionally, we proposed the Multilayer Encoder-Decoder Feature Fusion Network (MEDFFN) to counteract feature disappearance in deep convolutional blocks, complemented by the Boundary Structure Loss function to guide the model in acquiring more detailed and accurate boundary information. By devising a detection and recognition model that extracts high-resolution feature representations from multiple sources, precise disease detection and identification were achieved. This study offers technical backing for the holistic prevention and control of vegetable diseases, thereby advancing smart agriculture. Results indicate that, on our self-built VDGE dataset, compared to YOLOv7-tiny, YOLOv8n, and YOLOv9, the proposed model (Multisource Information Fusion Method for Vegetable Disease Detection, MIFV) has improved mAP by 3.43%, 3.02%, and 2.15%, respectively, showcasing significant performance advantages. The MIFV model parameters stand at 39.07 M, with a computational complexity of 108.92 GFLOPS, highlighting outstanding real-time performance and detection accuracy compared to mainstream algorithms. This research suggests that the proposed MIFV model can swiftly and accurately detect and identify vegetable diseases in greenhouse environments at a reduced cost.

Why it matches plant phenotyping methods植物の病変位置と感染度を画像から推定する疾患検出・認識モデルを開発し、独自データセットで性能比較・検証しているため、植物状態の画像ベース表現型計測が中心的です。

abstractPrevious studies have grappled with accurately pinpointing lesion positions and quantifying infection degrees

Hyperspectral Imaging for Phenotyping Plant Drought Stress Using Univariate and Multivariate Modelling Techniques →

Due to the adverse effect of prolonged drought stress on plants, accurate detection is essential for water use efficiency and maintaining productivity. Hyperspectral imaging is frequently used for non-invasive plant phenotyping, allowing for the long-term monitoring of crop health due to its sensitivity to subtle changes in leaf constituents. The broad spectrum of hyperspectral data enables the development of multiple vegetation indices (Vis) derived from the different spectral regions to estimate plant biophysical and biochemical traits. However, the known VIs often do not generalize well and perform poorly for multiple plant stresses. This study proposes new VIs combined with machine learning models to identify drought stress in wheat species under different nitrogen (N) levels. A wheat experiment was set up in the glasshouse with four treatments: well-watered high-N (WWHN), well-watered low-N (WWLN), drought-stress high N and drought-stress low-N. In addition to ensuring that plants were watered according to the experiment design, photosynthetic rate (Pn) and stomatal conductance (gs) were taken regularly, serving as the ground truth data for this study. Sensitive spectral features were selected using a custom-designed ensemble modelling technique. New drought VIs are proposed using different combinations of the selected features. Three classification models (support vector machines, random forest and deep neural network) were developed and trained using four sets of data: known VIs, proposed VIs, combined VIs (from the known and proposed VIs) and PCA-transformed features (over the whole spectral data). From the results, the proposed VIs outperformed the known VIs, yielding > 0.94 accuracies for all three models, and the performance improved when they were trained with the combined VIs. The combined VIs were used to train three regression models to predict the stomatal conductances and photosynthetic rates of plants. The random forest regression model performed best, suggesting that it could be used as a stand-alone tool to forecast gs and Pn and track drought stress in wheat.

Why it matches plant phenotyping methodsハイパースペクトル画像から乾燥ストレスおよび光合成・気孔コンダクタンスを推定する新規指標と機械学習モデルを開発しており、植物表現型取得・抽出手法が中心である。

abstractHyperspectral imaging is frequently used for non-invasive plant phenotyping

3D pose estimation of tomato peduncle nodes using deep keypoint detection and point cloud →

Greenhouse production of fruits and vegetables in developed countries is challenged by labour scarcity and high labour costs. Robots offer a good solution for sustainable and cost-effective production. Acquiring accurate spatial information about relevant plant parts is vital for successful robot operation. Robot perception in greenhouses is challenging due to variations in plant appearance, viewpoints, and illumination. This paper proposes a keypoint-detection-based method using data from an RGB-D camera to estimate the 3D pose of peduncle nodes, which provides essential information to harvest the tomato bunches. Specifically, this paper proposes a method that detects four anatomical landmarks in the colour image and then integrates 3D point-cloud information to determine the 3D pose. A comprehensive evaluation was conducted in a commercial greenhouse to gain insight into the performance of different parts of the method. The results showed: (1) high accuracy in object detection, achieving an Average Precision (AP) of AP@0.5=0.96; (2) an average Percentage of Detected Joints (PDJ) of the keypoints of PhDJ@0.2 = 94.31%; and (3) 3D pose estimation accuracy with mean absolute errors (MAE) of 11ᵒ and 10ᵒ for the relative upper and lower angles between the peduncle and main stem, respectively. Furthermore, the capability to handle variations in viewpoint was investigated, demonstrating the method was robust to view changes. However, canonical and higher views resulted in slightly higher performance compared to other views. Although tomato was selected as a use case, the proposed method has the potential to be applied to other greenhouse crops, such as pepper, after fine-tuning.

Why it matches plant phenotyping methodsRGB-D画像と深度点群を用いてトマトの器官ランドマークを検出し、ペドンクル節の3D姿勢を推定する手法を開発・評価しており、植物形態の取得が中心である。

abstractThis paper proposes a keypoint-detection-based method using data from an RGB-D camera to estimate the 3D pose of peduncle nodes

Research on Multi-Step Fruit Color Prediction Model of Tomato in Solar Greenhouse Based on Time Series Data →

Color change is the most obvious characteristic of tomato ripening stage and an important indicator of tomato ripening condition, which directly affects the commodity value of tomato. To visualize the color change of tomato fruit in mature stage, a gated recurrent unit network with an encoder-decoder structure that dynamically simulates tomato growth and development with time-dependent lines using tomato color and shape as real-time data was proposed in this paper. Firstly, the .json file was converted into a mask.png file, the tomato mask was extracted, and the tomato was separated from the complex background environment, and the tomato growth and development data set was successfully constructed. Then, a network of gated recurrent units with encoder-decoder structure was constructed to predict the future growth trend of tomato under different greenhouse temperatures. The experimental results showed that for the gated recurrent unit network of encoder-decoder structure proposed, when the hidden layer number was 1 and hidden layer number was 512, a high consistency and similarity between the model predicted image sequence and the actual growth and development image sequence would be realized, and the structural similarity index measure was 0.746. It was proved that when the average temperature was 24.93℃, the average soil temperature was 24.06℃, and the average light intensity was 11.26 Klux, the environment was the most suitable for tomato growth. The environmental data-driven tomato growth model was constructed to explore the growth status of tomato under different environmental conditions, thus to understand the growth status of tomato in time. The statement provided a theoretical foundation for determining the optimal greenhouse environmental conditions to achieve tomato maturity. And it offered recommendations for investigating the growth cycle of tomatoes, as well as technical assistance for standardized cultivation in solar greenhouses.

Why it matches plant phenotyping methodsトマト果実の色・形状画像を抽出し、時系列画像から成熟・成長状態を予測する手法を開発・評価しており、植物表現型の取得と計算的推定が研究の中心である。

abstracta gated recurrent unit network with an encoder-decoder structure that dynamically simulates tomato growth and development with time-dependent lines using tomato color and shape as real-time data was proposed in this paper.

Implementing Digital Multispectral 3D Scanning Technology for Rapid Assessment of Hemp (Cannabis sativa L.) Weed Competitive Traits →

The economic significance of hemp (Cannabis sativa L.) as a source of grain, fiber, and flower is rising steadily. However, due to the lack of registered herbicides effective in hemp cultivation, growers have limited weed management options. Plant height, biomass, and canopy architecture may affect crop–weed competition. Greenhouse experiments conducted at the joint Clemson University Coastal Research and Education Center and USDA-ARS research facility at Charleston, SC, USA used 27 hemp varieties, grown under controlled temperature and light conditions. Weekly plant scans using a digital multispectral phenotyping system, integrated with machine learning algorithms of the PlantEye F500 instrument, (Phenospex, Heerlen, Netherlands) captured high-resolution 3D models and spectral data of the plants. Manual and scanner-based measurements were validated and analyzed using statistical methods to assess plant growth and morphology. This study included validation tests showing a significant correlation (p < 0.001) between digital and manual measurements (R2 = 0.89 for biomass, R2 = 0.94 for height), indicating high precision. The use of 3D multispectral scanning significantly reduces the time-intensive nature of manual measurements, allowing for a more efficient assessment of morphological traits. These findings suggest that digital phenotyping can enhance integrated weed management strategies and improve hemp crop productivity by facilitating the selection of competitive hemp varieties.

Why it matches plant phenotyping methodsデジタルマルチスペクトル3Dスキャンによる植物形態形質の取得と、手測定との技術検証が研究の中心であるため。