Plant phenotyping methods.

WheatScoper: A lightweight organ-based framework for multi-view wheat phenotyping using time-series RGB images ↗

Accurate and dynamic monitoring of wheat phenotypes is essential for breeding decision-making and crop management. However, RGB image-based phenotyping still suffers from expensive pixel-level annotation, unstable organ-level segmentation across growth stages, and limited multi-trait extraction under complex field conditions. To address these issues, a high-throughput phenotyping framework (WheatScoper) was proposed, enabling organ-level segmentation and plot-level multi-trait extraction. To reduce annotation cost, a structure-aware geometry-assisted annotation (SAGA) algorithm was developed, yielding an approximately 7.6-fold improvement in annotation efficiency over fully manual annotation. To enable efficient organ-level segmentation, a lightweight semantic segmentation network (WheatScopeNet) was developed by integrating parallel hybrid spatial modeling with cross-scale feature fusion. On the held-out test set from the same site and growing season, WheatScopeNet achieved an mIoU of 0.869 and an mDice of 0.930. Leveraging the segmentation results, an automated system was established to extract 41 multi-view image-derived traits (I-traits) across four core phenotypic dimensions. The extracted I-traits supported the estimation of eight manually measured agronomic traits, with R 2 values ranging from 0.477 to 0.697. Notably, the correlations between stay-green-related-traits and yield varied distinctly with viewing-position. Only upper side-view indicators remained significantly correlated with yield, with Side-up final GPAR showing the strongest association, whereas top-view GPAR-derived indicators showed weak associations. Finally, a web-based platform integrating cascaded inference, segmentation visualization, and automatic I-trait extraction was developed. The platform provides an end-to-end solution for field wheat phenotyping and supports breeding decision-making and crop management.

Why it matches plant phenotyping methodsRGB画像から小器官を分割し、多数の植物形質を自動抽出・推定する手法とプラットフォーム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明確に採用。

abstracta high-throughput phenotyping framework (WheatScoper) was proposed, enabling organ-level segmentation and plot-level multi-trait extraction.

Vision Transformers Enable Advanced Plant Phenotyping in Controlled Environments ↗

Reliable plant segmentation in high-throughput phenotyping must transfer across species and imaging conditions without repeated model tuning or extensive reannotation. We compare three segmentation strategies using images from Oak Ridge National Laboratory's Advanced Plant Phenotyping Laboratory: (i) fixed color-based thresholding, (ii) supervised U-Nets trained from scratch, and (iii) pretrained vision transformers fine-tuned for binary segmentation. Models were evaluated on a held-out test set and a generalization set that comprised unseen species. On the held-out test set, thresholding, the best U-Net, and the best vision transformer achieved mean Dice scores of 58.3, 96.6, and 97.3, respectively. On the generalization set, the corresponding Dice scores were 56.5, 86.2, and 95.7. Thresholding remained effective on some datasets but failed when plant appearance changed. Supervised U-Net training resolved within-distribution errors but failed to generalize to novel species and backgrounds. Pretrained vision transformers consistently produced high-accuracy segmentations across the evaluated species, views, soil backgrounds, and tray types. These results benchmark the practical progression from fixed rules to task-specific supervision and pretrained visual representations for controlled-environment plant phenotyping.

Why it matches plant phenotyping methods植物フェノタイピングにおける画像セグメンテーション手法を比較・検証し、異なる種や撮像条件への汎化性能をベンチマークしているため、方法が研究の中心である。

abstractReliable plant segmentation in high-throughput phenotyping must transfer across species and imaging conditions without repeated model tuning or extensive reannotation.

Deep learning technique for rice leaf disease classification and severity level identification via Hybrid ResConvolutional Neural Network ↗

Rice leaf diseases significantly reduce agricultural yield and pose a major challenge for sustainable food production, particularly owing to the limitations associated with manual and visual inspection methods that are subjective and often ineffective in early-stage detection. This investigation proposes a new Hybrid ResConvolutional Neural Network (HyResCN-Net) for effective classification and severity identification of rice plant leaf diseases. The proposed framework integrates an Internet of Things (IoT) -based data acquisition and routing simulation using CrowWhale Energy Trust Routing (CrowWhale-ETR) for efficient data handling. Initially, preprocessing is done by an averaging filter to reduce noise. Then, plant leaves are segmented using the Eff-UNet++ method. Augmentation techniques like rotation, scaling, and color change are applied to expand the dataset. Features, like entropy with Gradient Directional Pattern (GDP), Complete Local Binary Pattern (CLBP), and histogram features, are extracted to enhance feature representation. These features are then used within the proposed HyResCN-Net model, which integrates Parallel Convolutional Neural Network (PCNN) and ResNeXt to improve discriminative learning for disease classification and severity estimation. Experimental evaluation is conducted on the Rice Leaf Bacterial and Fungal Disease Dataset. Considering a k-value of 8, the HyResCN-Net gains an accuracy of 94.258%, a True Positive Rate (TPR) of 96.479%, a True Negative Rate (TNR) of 92.898%, a precision of 91.312% and an F1-score of 93.824% compared to existing methods. The HyResCN-Net efficiently enhances rice leaf disease identification and severity analysis, supporting its applicability in precision agriculture applications.

Why it matches plant phenotyping methodsイネ葉の病害分類と重症度という植物の状態を、画像取得・分割・特徴抽出・深層学習により推定する手法を開発・評価しており、フェノタイピング手法が中心である。

abstractThis investigation proposes a new Hybrid ResConvolutional Neural Network (HyResCN-Net) for effective classification and severity identification of rice plant leaf diseases.

MC-SlotNet: Multiplicity-Consistent Slot-Based Full-Cell Instance Segmentation for Overlapping Plant Suspension-Culture Microscopy ↗

Overlapping cells in plant suspension-culture microscopy pose a particular challenge, for instance, segmentation because a single pixel may belong to more than one cell. Most standard instance-segmentation methods are not designed for this setting and tend to treat overlapping objects as mutually exclusive regions. We instead represent each cell as an independent full-cell instance and introduce MC-SlotNet, an architecture that separates competitive object-slot feature assignment from mask decoding. This allows multiple predicted masks to occupy the same image region. We further introduce a mask-level multiplicity-consistency loss that encourages the predicted number of masks covering a pixel to agree with the underlying cell occupancy. We evaluate MC-SlotNet on a newly annotated dataset of 53 Siraitia grosvenorii suspension-culture micrographs containing 4131 full-cell instances acquired at 4×–40× magnification. Using grouped five-fold cross-validation and an overlap-preserving evaluation protocol, we compare the method with Mask R-CNN, SOLOv2, and Mask2Former. MC-SlotNet achieves the best performance on AP50 (0.800), mAP50:95 (0.565), F150 (0.842), all-ground-truth Dice (0.761), AJI+ (0.754), overlap-region Dice (0.705), and overlap-instance recall (0.828). Its AP75 (0.649) is comparable to Mask2Former’s (0.651). MC-SlotNet also has the lowest inference time among the evaluated methods, at 1.113 s/image. These results indicate that decoding full-cell masks independently, rather than enforcing an exclusive partition of image pixels, is well-suited to instance segmentation in plant suspension-culture microscopy images with substantial cell overlap.

Why it matches plant phenotyping methods植物細胞の重複画像から個々の細胞を分割・抽出する新規モデルを開発し、データセット上で既存手法と比較評価しており、植物表現型取得法が研究の中心である。

abstractWe instead represent each cell as an independent full-cell instance and introduce MC-SlotNet, an architecture that separates competitive object-slot feature assignment from mask decoding.

A dynamic multi-scale feature fusion and hierarchical attention network for leaf segmentation ↗

Abstract Accurate leaf instance segmentation is fundamental to quantifying morphological and structural traits in image-based plant phenotyping. However, substantial variations in leaf scale, shape, and orientation, together with dense overlap and occlusion, often lead to ambiguous instance boundaries. In addition, repeated downsampling and feature reconstruction can progressively erode fine structural details, hindering contour preservation and the separation of adjacent leaves. To address these interrelated challenges, we propose DMSHA-Net, a dynamic multi-scale feature fusion and hierarchical attention network for leaf instance segmentation. Its direction-aware Multi-Scale Feature Aggregation (MSFA) encoder captures complementary horizontal and vertical contextual information across multiple receptive-field scales, thereby improving the representation of diverse leaf morphologies. The Dense Feature Aggregation (DFA) decoder selectively integrates deep semantic and shallow structural features through stage-specific attention mechanisms, where self-attention at coarse resolutions models long-range dependencies, whereas lightweight channel recalibration at high resolutions refines local structures and boundaries. The Learnable Feature Fusion (LFF) module subsequently integrates multi-level semantic and boundary features using normalized learned weights. DMSHA-Net achieves Best Dice (BD) scores of 93.17%, 85.12%, and 90.91% on KOMATSUNA, MSU-PID, and the CVPPP-A1 subset, respectively, with corresponding foreground–background Dice (FBD) scores of 98.19%, 91.02%, and 98.24%. These results indicate that DMSHA-Net achieves competitive segmentation performance across the three datasets, particularly in scenarios involving pronounced scale variation and dense leaf overlap.

Why it matches plant phenotyping methods植物画像から葉の個体セグメンテーションを行い、形態・構造形質の定量化に用いる新規ネットワークを開発・評価しており、表現型取得手法が中心です。

abstractAccurate leaf instance segmentation is fundamental to quantifying morphological and structural traits in image-based plant phenotyping.

PlantC2USeg: Cross-Scale Consistent Pre-Training for Few-Shot Unified Plant Point Cloud Segmentation ↗

Modern crop breeding demands precise organ-level analysis for trait quantification, making plant point cloud segmentation (PPCS) increasingly important. However, conventional deep learning approaches rely heavily on densely annotated datasets that are labor-intensive to acquire. Unified PPCS adaptation from distribution-shifted examples with minimal additional training remains challenging. To address this, we propose PlantC2USeg, a deep transfer learning framework featuring cross-scale consistency learning to explicitly align features across spatial scales and an information-restricted decoding strategy that prevents reconstruction shortcuts and promotes robust adaptation. The resulting pre-training enables stable few-shot generalization across species and sensing conditions, while unified fine-tuning with inherited thresholds further reduces adaptation overhead. Under full supervision on Soybean3D, PlantC2USeg achieves the highest semantic IoU and instance mWCov among compared methods, at 91.91% and 94.62%. With 20 labeled samples, it leads both metrics at 89.78% and 90.27%; with only 10 samples, it retains the highest mWCov of 83.23% while achieving 83.19% IoU. Across HR3D, 10-shot transfer to tobacco, tomato, and sorghum averages 78.41% IoU and 79.42% mWCov, while 22-shot transfer to SYAU-Maize achieves the highest IoU and mRec at 92.75% and 93.51%. Furthermore, a leading category-averaged mIoU of 85.0% on ShapeNet Part demonstrates the framework's capability to handle diverse shape variations beyond agricultural domains. These results demonstrate that PlantC2USeg reduces overall adaptation effort under distribution shifts, enabling scalable plant phenotyping and transferable 3D representation learning beyond agriculture.

Why it matches plant phenotyping methods植物点群の器官レベル形質定量を目的とするセグメンテーション手法を開発し、複数データセット・作物・ショット条件で性能評価しているため、植物フェノタイピング手法が中心である。

abstractwe propose PlantC2USeg, a deep transfer learning framework featuring cross-scale consistency learning

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.

iPheno: A Novel Dual-Aware Vision-Language Model for Multi-Task Fine-Scale Crop Phenotyping. ↗

Crop phenotyping is crucial for advancing plant breeding, yet remains a significant challenge. Manual approaches are labor-intensive and do not scale to the analysis of large datasets, while computational methods like Vision-Language Models (VLMs) lack the adaptability for fine-scale spatial reasoning and diverse phenotyping scenarios. To bridge the gaps, we present iPheno, a fully open-source, domain-specialized multimodal VLM for fine-scale crop phenotyping. A key innovation of iPheno is its dual-aware architecture. First, a spatial-aware feature extractor samples mask regions into local K-Nearest Neighbors (KNN) graphs and enables fine-scale analysis of arbitrary-shaped regions; second, a task-aware Mixture-of-Experts (MoE) routing mechanism activates specialized modules for each phenotyping task. To train iPheno and achieve rigorous benchmarking, we constructed iPheno-120K, a large-scale high-precision dataset designed for multiple phenotyping tasks. Evaluations on iPheno-120k test set and other publicly available datasets showed that iPheno outperformed all fine-tuned baselines, by improving F1-score by 17.1% (LLaVA-1.6-13B) to 28.9% (MiniCPM-o-9B), while achieving the highest inference speed and memory efficiency. A web server (https://ipheno.ai4bread.com), a mobile application (www.ipheno.cn), and a stand-alone PC client (https://github.com/2997029323/iPheno-PC-Client) are available for iPheno.

Why it matches plant phenotyping methods植物表現型を対象とするVLMの開発、マルチタスク評価、専用データセット構築が研究の中心であり、明確な方法論的貢献がある。

abstractwe present iPheno, a fully open-source, domain-specialized multimodal VLM for fine-scale crop phenotyping.

MoeBi-ViT: Non-destructive shoot-stage phenotyping of lettuce in plant factory via dual-branch mixture-of-experts network and enhanced segmentation ↗

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

Why it matches plant phenotyping methodsレタスのシュート段階を対象とした非破壊フェノタイピング手法と、強化セグメンテーションを含む画像解析モデルの開発が題名で明示されており、表現型取得・抽出が中心です。

titleMoeBi-ViT: Non-destructive shoot-stage phenotyping of lettuce in plant factory via dual-branch mixture-of-experts network and enhanced segmentation

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

Integrating scanning X-ray scattering and fluorescence for multi-scale analysis of seed structure supported by machine learning tools. ↗

Background Understanding the structure of plant seeds cultivated for human consumption and food manufacturing is vital to provide sustainable products as well as to investigate early growth stages. This includes structural variation between different plant species, varieties and cultivars depending on genetic setup, as well as structural modifications upon germination, aging and storing or seed treatment during processing. For plant seeds as multi-component biological materials, structural characterization must extend across multiple length scales, from molecular organization to cellular architecture. Results We apply scanning Small- and Wide-Angle X-ray Scattering (SWAXS) and X-ray Fluorescence (XRF) on yellow pea seeds to combine local structural information on the molecular scale with imaging of cellular structures on the micrometer scale, enabling a comprehensive analysis of hierarchical organization. To identify and characterize heterogeneous regions within the pea seeds, we implement a fitting-free, data-driven segmentation and analysis workflow based on machine learning tools. This approach allows for classification of structurally distinct domains and enables quantitative comparison across samples without relying on predefined models. Furthermore, we incorporate multi-modal analysis by combining structural imaging with complementary elemental information obtained from XRF. The integration of compositional and structural data provides deeper insight into structure-composition relationships. Conclusions This multi-scale, multi-modal approach opens new possibilities for investigating hierarchical structures and their development under diverse conditions and enables systematic comparison between different species or seeds at different developmental stages or exposed to different processing steps. The approach is broadly applicable to various kinds of samples and other hierarchically organized biological materials, which makes it a valuable technique for plant science as well as plant-based food science.

Why it matches plant phenotyping methods種子の構造・細胞領域をX線散乱／蛍光イメージングと機械学習ベースのセグメンテーションで定量解析する手法が研究の中心であり、植物器官の構造形質を抽出するため採用。

abstractWe apply scanning Small- and Wide-Angle X-ray Scattering (SWAXS) and X-ray Fluorescence (XRF) on yellow pea seeds to combine local structural information on the molecular scale with imaging of cellular structures on the micrometer scale

Three-dimensional organ segmentation and structural phenotyping of salt-stressed coriander seedlings using the optimized point transformer-based model PTV-SegCo ↗

Salt stress can markedly alter seedling architecture, creating a need for non-destructive three-dimensional (3D) phenotyping methods capable of resolving fine plant structures. However, organ-level segmentation of plant point clouds remains challenging because of leaf overlap, slender stems, ambiguous stem–leaf boundaries, and severe class imbalance. In this study, we developed PTV-SegCo, a task-adapted Point Transformer model for organ segmentation and structural phenotyping of coriander seedlings under salt stress. PTV-SegCo integrates efficient channel attention, gated shallow–deep feature fusion, and a combined cross-entropy–Dice loss to improve representation of fine and minority organ structures. The dataset comprised 60 manually annotated 3D point-cloud samples from 12 cultivation trays repeatedly observed over five acquisition dates under six NaCl concentrations (0, 50, 100, 150, 200, and 250 mmol L −1 ). Because the earliest acquisition represented a particularly challenging developmental stage, these 12 samples were used as a fixed early-stage model-selection set, while samples from the remaining four dates were organized into four date-blocked training–validation configurations. Under this internal model-development protocol, PTV-SegCo achieved mean mAcc and mIoU values of 93.05% and 89.05%, respectively, and showed numerically higher performance than its direct backbone PTV-Seg50. These values should be interpreted as internal comparative results rather than as an unbiased estimate of generalization to unseen cultivation trays, and the present results should not be interpreted as establishing the broad competitiveness of PTV-SegCo against other point-based, convolution-based, graph-based, transformer-based, or plant-specific segmentation architectures. After semantic segmentation, reconstructed scenes were metrically calibrated using the known cultivation-tray dimensions, followed by individual-plant separation and quality control. Four reconstruction-derived structural descriptors—plant height, projected area, voxel occupancy volume, and leaf point ratio—were extracted to characterize temporal structural variation under different NaCl treatments. For treatment-level inference, individual-plant measurements were aggregated within each cultivation tray at each acquisition time, with the cultivation tray treated as the independent experimental unit. Independent manual validation showed close agreement for plant height and projected area, with R 2 values of 0.9969 and 0.986, respectively. Overall, the proposed workflow provides a feasible approach for organ-level segmentation and automated 3D structural analysis of small coriander seedlings under salt stress. The extracted descriptors primarily represent reconstruction-derived spatial characteristics and should not be interpreted as direct indicators of physiological status; voxel occupancy volume and leaf point ratio remain without direct external validation.

Why it matches plant phenotyping methods3D点群による器官セグメンテーションと構造形質抽出の手法開発・内部比較・手動検証が研究の中心であり、塩ストレスは適用対象である。

abstractwe developed PTV-SegCo, a task-adapted Point Transformer model for organ segmentation and structural phenotyping of coriander seedlings under salt stress.

YOLOv12-RSLW: An Efficient Detection and Severity Grading Framework for Rice False Smut via Count-Area Calibration ↗

Rice false smut is a major panicle disease that affects rice yield and grain quality and is an important target for resistance evaluation in breeding programs. Accurate field phenotyping is important for disease assessment and resistance screening, yet current assessment relies heavily on manual visual scoring and smut ball counting, which are laborious and subject to evaluator variation. In close-range single-panicle images, false smut balls are often small, dense, occluded, adhered, making automatic detection and severity grading difficult. To address these challenges, we developed a YOLOv12-RSLW detector by integrating RepGhost, SimAM, LSCD, and WIoU into YOLOv12. Detection boxes were then used to guide the Segment Anything Model for panicle and lesion mask extraction, allowing calculation of the lesion-to-panicle area ratio as a supplementary indicator for count-based severity grading. A total of 1911 original field images were collected. After augmentation, the dataset contained 5663 images, including 4531 training images, 566 validation images, and 566 test images. Detection performance was evaluated on the test set, while SAM segmentation was assessed using 80 manually annotated original images. YOLOv12-RSLW achieved 92.06% mAP@0.5, 91.46% precision, and 87.01% recall, with 3.45 M parameters and 6.0 GFLOPs. Compared with the baseline YOLOv12, mAP@0.5 and recall increased by 3.60 and 4.37 percentage points, respectively. Within the augmented dataset, 41.2% of samples initially assigned to Grade 1 and 28.1% of those assigned to Grade 2 met the area-ratio criteria for potential reassignment to higher grades. The framework provides a quantitative approach to rice false smut severity phenotyping and may support future resistance breeding after further validation.

Why it matches plant phenotyping methodsイネいもち病の病徴を画像から検出・分割し、病斑面積比に基づく重症度を定量化するフェノタイピング手法を開発・評価しており、方法が研究の中心である。

abstractTo address these challenges, we developed a YOLOv12-RSLW detector by integrating RepGhost, SimAM, LSCD, and WIoU into YOLOv12.

Methodical approaches to the analysis of the state of soybean crops based on the results of aerial photography from UAV ↗

Goal. To substantiate the methodical approaches to analyzing the state of soybean crops based on the results of aerial photography with UAV by comparing manual vectorization, controlled classification according to the algorithm of maximum similarity, and uncontrolled classification of K-Means, as well as to determine the feasibility of their combination with expert visual interpretation to assess the spatial structure of the vegetation cover. Methods. Aerial photography of the test proving ground was performed with the help of the unmanned aerial vehicle DJI Phantom 4 Advanced with the subsequent photogrammetric study of materials and the formation of a highly detailed orthophotoplane. In the QGIS environment, visual decryption and manual vectorization of the main objects of the agrolandscape were carried out with the creation of polygonal layers. For automated mapping, methods of controlled classification according to the algorithm of maximum similarity and uncontrolled classification based on the K-Means algorithm were used. The accuracy of the results was evaluated by comparing the data of automated classifications with the data of manual digitization, which was used as a reference (control) method. On the basis of the results obtained, empirical data were summarized to justify practical recommendations for the application of the studied approaches. Results. The study was conducted on the territory of the research farm of the Separate subdivision of the National University of Life and Environmental Sciences of Ukraine «Berezhany Agrotechnical Institute» (vil. Pavliv, Ternopil district, Ternopil oblast) (49.452057°N; 24,805818°E) in may – august 2025. The obtained cartographic materials made it possible to quantify the areas of the main objects of the agro-landscape and identify problem areas with sparse shoots. Methods of controlled classification showed greater compliance with the digitization data (average deviation — 6.7%) compared to uncontrolled (14.7%), which were effective from the point of view of preliminary assessment of spectrally homogeneous sections, but did not provide an accurate division of shoots by density. Analysis of the spatial structure of coverage made it possible to plan local agrotechnical measures and assess the potential yield. Conclusions. Methodical approaches to analyzing the state of soybean crops based on the results of aerial photography with a UAV equipped with RGB cameras are promising and economically feasible. Automated classification methods are effective for highlighting hard and contrasting objects and small-contoured areas, while a detailed assessment of the structure of the vegetation cover is advisable to carry out using a controlled classification in combination with expert visual interpretation.

Why it matches plant phenotyping methodsUAV画像を用いて大豆作物の植生被覆構造や疎な出芽域を抽出し、複数の分類法を手動ベクトル化と比較・精度評価している。植物状態の取得手法自体が研究の中心である。

abstractTo substantiate the methodical approaches to analyzing the state of soybean crops based on the results of aerial photography with UAV by comparing manual vectorization, controlled classification according to the algorithm of maximum similarity, and uncontrolled classification of K-Means

Autonomous Quadcopter Flight Path Generation via MAVLink and Ground Control Station Architecture for Precision Agricultural Crop Monitoring ↗

This paper presents an integrated system design for autonomous quadcopter flight path generation using the MAVLink protocol and a custom Ground Control Station (GCS) for precision agricultural crop monitoring. The system combines three coverage path algorithms (Boustrophedon, Spiral, and Energy-Optimized), a Pixhawk 4 / ArduPilot flight stack, a MicaSense RedEdge-P multispectral payload, and a ROS2-based GCS for mission planning, telemetry, and vegetation-index-based crop health assessment. The 2.8 kg quadcopter (450 mm frame, 4-cell LiPo) achieves 22–25 minutes of flight time. Across five field sizes (0.5–10 ha), the Energy-Optimized path achieved 96.5% coverage efficiency with 4.2% overlap and a 12.4% energy reduction over the Boustrophedon baseline. NDVI-based crop segmentation achieved pixel accuracy of 92.5% (maize), 94.1% (rice), and 90.8% (wheat), and four-class crop-health classification achieved a weighted F1-score of 90.0%. MAVLink 2.0 command latency averaged 15.8 ms with 99.3% packet delivery at ranges up to 800 m. An ablation study showed additional gains of 1.5–3.1% coverage from wind compensation and 2.1–2.8% from terrain-following.

Why it matches plant phenotyping methods自律ドローン、マルチスペクトル撮像、NDVIセグメンテーションによる作物健康状態推定を統合し、飛行・画像解析性能を定量評価しているため、植物状態の取得・抽出が技術的に実質的な構成要素である。

abstractThe system combines three coverage path algorithms (Boustrophedon, Spiral, and Energy-Optimized), a Pixhawk 4 / ArduPilot flight stack, a MicaSense RedEdge-P multispectral payload, and a ROS2-based GCS for mission planning, telemetry, and vegetation-index-based crop health assessment.

OccPepSeg-YOLO for Instance Segmentation of Occluded Peppers in Field Images ↗

Agricultural operations such as pepper harvesting, fruit counting, and field phenotyping rely on accurate visual recognition and instance segmentation algorithms. However, pepper fruits in complex field environments often exhibit slender and curved shapes, partial occlusion, ambiguous boundaries, and adhesion between adjacent instances. Existing object detection and instance segmentation methods therefore struggle to obtain complete fruit masks, which adversely affects subsequent fruit counting, contour measurement, and picking-point localization. To improve the instance segmentation accuracy of occluded peppers in complex field scenes, this study proposes OccPepSeg-YOLO, an improved model based on YOLO11n-seg. First, a P2FreqFusion module is introduced to fuse shallow, high-resolution detail features with deep semantic features, thereby enhancing the representation of fruit edges and tip regions. Second, an ASC module is designed to model the directional and scale-related morphological characteristics of pepper fruits, while a BoundaryGate module strengthens responses at occlusion interfaces and boundaries between adjacent instances. Finally, an OccPepSegment multi-scale prototype segmentation head is constructed, and a BDoU loss function is introduced to improve the boundary consistency of instance masks. Experiments on a self-constructed field-pepper instance segmentation dataset showed that OccPepSeg-YOLO achieved M-P, M-R, M-mAP50, and M-mAP50–95 values of 93.87%, 92.09%, 97.17%, and 82.31%, respectively, representing improvements of 5.59, 3.18, 3.83, and 9.52 percentage points over YOLO11n-seg. Further comparisons with representative YOLO-based instance segmentation models, including YOLOv8n-seg, YOLOv9c-seg, YOLO12n-seg, and YOLOv26n-seg, demonstrated that OccPepSeg-YOLO achieved the best overall segmentation performance. In particular, its M-mAP50–95 exceeded the best competing result obtained by YOLOv9c-seg by 8.35 percentage points. Under a unified repeated-inference protocol on an RTX 3090 GPU using FP32 precision, a batch size of 1, and 640 × 640 inputs, OccPepSeg-YOLO achieved a mean inference latency of 15.801 ± 1.238 ms, a P95 latency of 17.323 ms, and a throughput of 63.29 FPS. These results demonstrate that the proposed model can produce more complete pepper instance masks under leaf occlusion, fruit overlap, and complex background conditions, providing technical support for field-pepper recognition, fruit counting, and visual perception by agricultural robots.

Why it matches plant phenotyping methods圃場画像からピーマン果実のインスタンスマスクを抽出する手法を開発・比較検証しており、果実カウントや輪郭計測に利用可能な植物形質取得が中心である。

abstractAgricultural operations such as pepper harvesting, fruit counting, and field phenotyping rely on accurate visual recognition and instance segmentation algorithms.

Integrated semantically guided spatial fragmentation and biomorphological forest segmentation using terrestrial laser scanning data: layer-wise dynamic connectivity features as the key factor in stem structure reconstruction accuracy ↗

The separation of a forest plot into individual trees and the automatic extraction of their stem structures from terrestrial laser scanning data are complicated by dense stands, occlusions, and the diversity of biomorphological forms. Existing algorithms usually solve scene partitioning, voxel classification, and tree growing as independent tasks, which leads to error accumulation at subsequent processing stages. This paper proposes a unified model for spatial fragmentation and biomorphological forest segmentation comprising three interrelated stages: scene partitioning by estimated stem coordinates using a Voronoi diagram, probabilistic voxel- or point-level classification, and bottom-up tree growing guided by spatial connectivity and stem membership criteria. For the semantic module, tabular, volumetric, and point-based approaches are compared: gradient boosting with layer-by-layer inference, TabNet, a three-dimensional convolutional neural network, PointNet2, and two-stage pipelines in which gradient boosting builds an initial stem mask for subsequent neural segmentation. The experiment was conducted on 567 mixed-species trees. Considering both quality and computational performance, the {CatBoost; CNN3D} pipeline was selected as the preferred solution, achieving AUC = 0.9966 and IoU = 0.9831. The obtained results show that combining interpretable layer-by-layer classification with subsequent spatial analysis improves the quality of stem structure reconstruction, which is important for automatic forest inventory tasks.

Why it matches plant phenotyping methods地上レーザースキャンから個体樹木と幹構造を自動抽出する統合セグメンテーション手法を開発・比較しており、植物形態の取得が研究の中心である。

abstractThe separation of a forest plot into individual trees and the automatic extraction of their stem structures from terrestrial laser scanning data are complicated by dense stands, occlusions, and the diversity of biomorphological forms.

Herbarium specimens in the age of artificial intelligence: from herbarium image identification to Integrative Taxonomic AI. ↗

Herbarium specimens are physical, verifiable records that form the basis of taxonomic knowledge and biodiversity research. Their large-scale digitization has produced extensive collections of high-resolution images and associated specimen metadata, creating conditions in which artificial intelligence (AI) can play an important role in plant taxonomy, collection management, and ecological research. Early AI applications have primarily focused on automated species identification based on individual specimen images. Although increasingly accurate, such approaches remain limited by their emphasis on single-specimen label prediction and by treating identification outputs as final analytical decisions. Recent methodological advances-including segmentation-based preprocessing, automated trait extraction, structured extraction of label data, detection of potentially misidentified specimens, and multimodal integration of visual, textual, and genetic information-extend AI applications beyond species identification toward broader analytical frameworks, encompassing taxonomic interpretation as well as ecological and biodiversity research. In these approaches, specimens are placed within a shared analytical space, and identification results are used to support comparisons across multiple specimens rather than being treated as final decisions for single individuals. This multi-specimen perspective enables quantitative examination of species boundaries, morphological variation, data inconsistencies, and taxonomic stability within curated collections. In this context, AI serves not as an ultimate decision-maker but as a decision-support tool embedded in expert-guided workflows and biodiversity knowledge infrastructures. These developments can be summarized as Integrative Taxonomic AI, an approach that employs learned morphospaces to interpret and refine taxonomic categories by integrating multimodal evidence and curated specimen data under expert guidance.

Why it matches plant phenotyping methods植物標本画像から形態形質を抽出するAI手法と統合的解析枠組みを中心に扱うレビューであり、植物表現型取得・抽出法との関連が明確。

abstractRecent methodological advances-including segmentation-based preprocessing, automated trait extraction, structured extraction of label data, detection of potentially misidentified specimens, and multimodal integration of visual, textual, and genetic information-extend AI applications beyond species identification

SolanAPP: An Offline-First Mobile Framework for Segmentation-Based Diagnosis of Solanaceae Crop Diseases ↗

Abstract Purpose : The system for diagnosing diseases in Solanaceae crops (SolanAPP), including tomatoes, potatoes, peppers, and eggplants, represents a promising tool for supporting decision-making in agricultural fields using AI. This system reconciles the computational intensity of multitasking models with the infrastructural limitations of rural environments, thereby increasing digital literacy. Its architecture is based on two fundamental pillars: (i) autonomous, offline operation for the detection and classification of diseases in Solanaceae crops; (ii) a georeferenced epidemiological surveillance network with agricultural recommendations for crop monitoring. Methods : The core diagnostic process combines crop-specific semantic segmentation and disease classification models exported to TensorFlow Lite, enabling on-device visual inference and pixel-level severity estimation. An optional online layer integrates Groq’s large language model (LLM)-based reasoning and Firebase services to generate structured agronomic explanations and facilitate the creation of georeferenced community reports when a connection is available. Preprocessing and management of the dataset were performed using the Roboflow platform. The mobile app was developed natively in Kotlin. Model performance was rigorously evaluated using accuracy, recall, F1 score, mean IoU, mPA, inference latency, model size, and decision matrix. The optimal model for the crop was selected using Simple Additive Weighting (SAW). Finally, the overall framework quality and usability were evaluated in Cuba through a user validation survey using a 5-point Likert scale and aligned with the ISO/IEC 25010 software quality model. Results : The model that yielded the best results for most crops was DeepLabV3+ with MobileNetV2, which achieved a classification accuracy of over 97\% while operating with lower inference latency. Beyond individual diagnoses, the system incorporates a collaborative georeferencing feature that allows users to share observations and precise geographic coordinates of detected pathologies to facilitate regional epidemiological monitoring. The user satisfaction survey yielded a satisfaction rating of 4.5/5, with users highlighting the importance of offline diagnosis. Conclusion : Plant disease diagnosis using computer vision can support earlier intervention in resource-constrained agricultural settings, but practical deployment requires models that are accurate, lightweight, interpretable, and usable under limited connectivity. SolanAPP, an offline-first Android framework for detecting foliar pathologies in Solanaceae crops, not only establishes a framework for disease identification in complex natural environments but also provides a theoretical and practical foundation for automated agronomic treatment recommendations and community-based crop surveillance. Impact SolanAPP is a free framework that supports the synergy between multitask deep learning for offline disease diagnosis and LLM-driven reasoning for decision-making in the field. Beyond the quantitative metrics obtained from the selected models, the deployment of SolanAPP in rural contexts serves a fundamental socio-technical purpose: it acts as a catalyst for open access, digital literacy, and agronomic decision-making under unfavorable development conditions. It also represents a strong effort to foster a collaborative epidemiological surveillance network in the agricultural sector. Although it faces challenges, such as the use of field images for model training, this framework marks a promising step in the deployment of edge AI, balancing technical accuracy with practical utility.

Why it matches plant phenotyping methods植物病害を画像からセグメンテーションし、病害のピクセル単位の重症度を推定する手法と、オフライン実装・性能評価を中心とした研究であり、植物状態の計測方法が中核です。

abstractThe core diagnostic process combines crop-specific semantic segmentation and disease classification models exported to TensorFlow Lite, enabling on-device visual inference and pixel-level severity estimation.

FitoView: A Decision Support Application Integrating Weather Forecasts and CNNs for Plant Disease Classification and Severity Assessment - Case Study on Cercospora Leaf Spot in Chili Pepper ↗

Abstract Plant diseases represent major constraints on agricultural productivity, often resulting in significant yield losses. This study presents FitoView, a cloud-based mobile decision support system that integrates deep learning with real-time weather forecasting for sustainable plant disease management. Demonstrated through a case study on Cercospora leaf spot in chili pepper, the system employs custom YOLOv8 models for automated disease detection, classification, and pixel-level severity quantification, combined with meteorological data from the OpenMeteo API. The core innovation lies in an integrated decision matrix that considers three dimensions: AI-assessed disease severity, 48-hour climatic risk forecasts, and optimal spraying conditions, generating four contextualized management scenarios with tailored re-evaluation periods (3-10 days). OpenMeteo API validation across four cities in Sergipe demonstrated very strong correlations, with Pearson coefficients (r) of 0.90-0.97 for temperature, 0.81-0.95 for humidity, and 0.92-0.95 for solar radiation, corresponding to R² values of 0.65-0.94. The YOLOv8 object detection model achieved perfect precision (100%) and macro-averaged recall of 89% across all disease classes, with Cercospora leaf spot detection reaching perfect metrics (100% precision, recall, and F1-score). Field validation in Lagarto, Sergipe, confirmed the system’s practical use: it accurately detected Cercospora leaf spot, estimated severity, and, combined with climatic risk, generated recommendations for alternative treatment and short-term re-evaluation. The Progressive Web Application architecture, deployed on a Cloud Platform, ensures accessibility without installation requirements, while the modular design enables scalability to additional crops and diseases, representing a significant advancement toward democratizing AI-powered precision agriculture tools for smallholder farmers in Brazil.

Why it matches plant phenotyping methods植物病害の検出・分類と病斑のピクセルレベル重症度推定をYOLOv8で実装・検証したシステムであり、植物状態の取得・定量化が中心的な技術貢献です。

abstractThe core innovation lies in an integrated decision matrix that considers three dimensions: AI-assessed disease severity, 48-hour climatic risk forecasts, and optimal spraying conditions

Automated Drought-Stress Assessment in Lettuce: A Detection-Guided Segmentation Approach for Multi-Plant RGB Imagery ↗

Accurate and non-destructive assessment of drought stress is important for improving lettuce production and supporting timely crop management. This study presents a detection-guided deep learning framework for plant-level drought-stress assessment in hydroponically grown lettuce using bird’s-eye-view RGB images. The study further investigates whether canopy segmentation can improve classification performance by reducing irrelevant background information. The framework was evaluated using 2190 images collected across three independent cultivation cycles in which drought stress was induced by isolating the plant root zones from the nutrient solution. In the first stage, YOLO-based object detection was used to localize individual plants, with YOLO26m achieving the highest detection performance of 99.4% mAP@0.5. The detected regions were subsequently used as spatial prompts for zero-shot canopy segmentation using the Segment Anything Model (SAM), with SAM ViT-B achieving a mean IoU of 0.9864. Six convolutional, transformer-based, and hybrid classification architectures were then evaluated independently using YOLO-cropped and SAM-segmented plant images. Segmented inputs consistently improved classification performance, with MaxViT-S achieving the highest binary test accuracy of 96.3%. The framework further distinguished time-defined pre-stress, early-stress, and late-stress periods with an accuracy of 92.4%. Plant-level generalization was further assessed using six-fold leave-one-plant-out cross-validation, resulting in a mean test accuracy of 90.25 ± 1.78% on unseen plants. These findings demonstrate that RGB-based plant-level analysis can support non-destructive drought-stress assessment and that canopy segmentation improves classification by reducing background influence.

Why it matches plant phenotyping methodsRGB画像からレタス個体の乾燥ストレス状態を推定する検出・セグメンテーション・分類フレームワークを開発し、複数サイクル、未見個体、性能指標で検証しており、表現型取得手法が中心である。

abstractThis study presents a detection-guided deep learning framework for plant-level drought-stress assessment in hydroponically grown lettuce using bird’s-eye-view RGB images.

Field-based estimation of cotton seedling agronomic traits: Using UAV-LiDAR and weakly supervised semantic segmentation ↗

Accurate estimation of the cotton seedling Leaf Area Index (LAI) is essential for yield prediction and precision crop management. Traditional manual methods are limited by low throughput, while two-dimensional remote sensing techniques often struggle with sparse canopy cover and soil background interference. Although three-dimensional LiDAR presents a promising alternative, existing deep learning approaches typically depend on costly fully supervised point-wise annotations. To address this challenge, this study proposes an end-to-end framework that integrates UAV-based LiDAR, weakly supervised segmentation, and physical parameter inversion. A weakly supervised network, termed CogNet, was developed—incorporating self-distillation and structure-aware label propagation—to achieve precise segmentation of cotton plants using only 10% sparse annotations. Following instance segmentation via Density-Based Spatial Clustering of Applications with Noise (DBSCAN), individual plant phenotypic traits were extracted. A nonlinear Extreme Gradient Boosting (XGBoost) model was then constructed to invert LAI by leveraging allometric relationships between 3D structural parameters and leaf area. Experimental results showed that CogNet achieved an Intersection over Union (IoU) of 85.34%, effectively mitigating overfitting to label noise and achieving performance competitive with the fully supervised RandLA-Net (82.13%). Notably, under the specific conditions of this cotton seedling dataset characterized by strong geometric priors, the weakly supervised model demonstrated enhanced robustness against annotation inconsistencies. The framework attained a plant detection rate of 96.2%, and the XGBoost model delivered high estimation accuracy (R² = 0.879, RMSE = 0.138). This study demonstrates that weakly supervised learning can substantially reduce annotation costs while maintaining model performance, providing an efficient and cost-effective solution for field-scale crop phenotyping.

Why it matches plant phenotyping methodsUAV-LiDAR、弱教師ありセグメンテーション、個体形質抽出、LAI推定を統合した作物フェノタイピング手法の開発・評価が研究の中心である。

abstractthis study proposes an end-to-end framework that integrates UAV-based LiDAR, weakly supervised segmentation, and physical parameter inversion.

A Simple and Reproducible ImageJ Workflow for Measuring Areas of Irregularly Shaped Necrotic Lesions on Plant Leaves. ↗

Accurately quantifying the areas of necrotic lesions on plant leaves is essential for evaluating plant-pathogen interactions and disease resistance. Although digital image analysis methods using ImageJ are widely employed, they often require case-specific optimization and may not be readily applicable across different experimental conditions. Furthermore, many studies have used ImageJ for lesion measurement without providing methodological details, which limits reproducibility. Here, we present a simple, step-by-step ImageJ workflow for measuring irregular necrotic lesions using a standard personal computer and mouse. The procedure relies on manual lesion selection using the freehand selection tool, followed by Gaussian smoothing, binarization, and automated particle analysis to extract lesion area measurements. By balancing manual isolation with computational thresholding, this protocol eliminates the need for extensive parameter tuning. This approach provides an accessible, reliable alternative to time-consuming color thresholding methods, thereby improving transparency and reproducibility in lesion quantification. The workflow's reproducibility has been confirmed through both intra-user and inter-user analyses. Key features • Relies on simple manual freehand selection combined with minimal image processing, requiring only a standard computer and mouse without specialized software or advanced training. • Enables accurate quantification of irregular necrotic lesions in conditions where automated thresholding methods require time-consuming optimization. • Provides a fully detailed, reproducible ImageJ workflow addressing common gaps in published methods, facilitating direct implementation. • Demonstrates high reproducibility, validated by intra-user and inter-user statistical analyses, ensuring reliable lesion quantification regardless of the operator.

Why it matches plant phenotyping methods植物葉の壊死病斑面積を画像から抽出するImageJワークフローを開発し、ユーザー内・ユーザー間解析で再現性を検証しており、病害表現型の取得手法が中心である。

abstractHere, we present a simple, step-by-step ImageJ workflow for measuring irregular necrotic lesions using a standard personal computer and mouse.

Lightweight and high-fidelity 3DGS fruit reconstruction via geometric-semantic joint constraints ↗

High-fidelity and lightweight 3D fruit models are a crucial foundation for phenotypic analysis and automated agricultural robotic operations. However, in complex agricultural scenarios characterized by varying illumination and foliage occlusion, existing 3D reconstruction methods struggle to balance reconstruction accuracy and model size, often generating massive redundant background primitives. To address this challenge, this paper proposes a novel framework for lightweight and high-fidelity 3DGS fruit reconstruction via geometric-semantic joint constraints. Specifically, the method first integrates depth priors and semantic information through a Depth-Guided Semantic Segmentation module to extract accurate target fruit masks. Next, it eliminates background noise points from the initial point cloud using a multi-view Reprojection Consistency Voting mechanism. Simultaneously, a Stochastic Background Regularized Hybrid Loss is introduced during the 3DGS training phase to decouple density and color optimization, thereby suppressing the regeneration of background Gaussian primitives. Experimental results on a multi-category fruit dataset demonstrate that while maintaining a high novel view synthesis quality (PSNR of 31.87 dB), our proposed method reduces the average model size from 230.42 MB to 62.66 MB (a 72.8% reduction), achieving robust, high-fidelity, and lightweight 3D fruit reconstruction.

Why it matches plant phenotyping methods果実の3D形状を抽出・再構成する画像ベース手法が研究の中心であり、果実形態のフェノタイピングに直接利用可能な方法を開発・評価している。

abstractHigh-fidelity and lightweight 3D fruit models are a crucial foundation for phenotypic analysis

A two-dimensional axis estimation method for pickable canopy apples based on YOLO cascade network. ↗

Introduction In a complex orchard environment, canopy apples are obscured by various factors, making it hard for apple harvesting robots to accurately determine which apples can be directly harvested. Furthermore, the complex obstruction leads to difficulties in identifying keypoints on the apples and caculating the axis direction, directly affecting the robot's determination of grasping positions. Methods To solve these issues, a two-dimensional (2D) axis estimation method for pickable canopy apples based on a YOLO cascade network was proposed. Firstly, the study introduced SPDConv for lossless downsampling and adopts dynamic upsampling to improve segmentation boundary accuracy, constructing an instance segmentation network named the YOLO-SD model to select pickable apples according to different occlusion conditions and growth states. Secondly, the geometric center of the mask image was located using its minimum enclosing circle, and the region of interest was extracted through morphological dilation. Then, by integrating the RFAConv, SCSA attention, and MBConv modules, a keypoint detection network YOLO-RSM was constructed to extract keypoints of pickable apples. Finally, a 2D axis construction strategy was proposed, which adaptively constructs the growth axis based on the visibility of keypoints. Results Experimental results show that the overall average accuracy mAP50 of the YOLO-SD model for apple segmentation reached 95.2%, and the parameter quantity was reduced to 2.47 M. The average accuracy of the YOLO-RSM model for keypoint detection has reached 90.3%, which is 2.4%, 2.6%, and 4.7% higher than that of the YOLOv8n, YOLO11n, and YOLO12n models respectively. The 2D axis estimation algorithm has an average axis angular error of 7.23° ± 16.73°, and an axis estimation accuracy of 92.68%. Discussion The proposed method can achieve high-precision canopy apple segmentation, keypoint detection, and 2D axis estimation, thus offering technical support for the picking operations of apple harvesting robots.

Why it matches plant phenotyping methodsリンゴ果実のセグメンテーション、キーポイント抽出、成長軸（器官形態）の推定を中心に新規画像解析法を開発・検証しており、単なる収穫対象の検出を超える植物器官形質の推定に該当する。

abstracta two-dimensional (2D) axis estimation method for pickable canopy apples based on a YOLO cascade network was proposed.

Ultrastructural characterization of secretory canals in Peucedanum praeruptorum roots using microscopic sectioning, transmission electron microscopy, and computed tomography. ↗

Plant secondary metabolites are mainly synthesized and stored in secretory tissues. Secretory canal development has been mainly characterized in Apiaceae. The secretory canals of Peucedanum praeruptorum contain pharmacologically active coumarins, but their organ-specific distribution and developmental dynamics remain poorly understood. This study integrated light microscopy (LM), transmission electron microscopy (TEM), X-ray microcomputed tomography (µ-CT), and high-performance liquid chromatography (HPLC) to investigate canal development, distribution, ultrastructure, 3D architecture, and coumarin accumulation in P. praeruptorum roots. Histological analysis showed that canals adjacent to the periderm originate from pericycle cells, whereas those in secondary phloem arise from parenchyma differentiation; both develop schizogenously. Canal quantity and dimensions varied temporally. Canals located in phloem showed density increasing toward the cambial zone, where cross-sectional areas were smaller. The canal density index increased from September to November, peaking on November 15, then declined. HPLC revealed dynamic accumulation of five major coumarins: content increased from September, peaked on November 15, then gradually decreased. TEM showed that epithelial cells surrounding the canal lumen were rich in Golgi, ER, mitochondria, plastids, starch grains, and osmiophilic droplets. µ-CT volumetric analysis and segmentation generated detailed 3D models, revealing spatial organization and enabling size-based grouping of canals (1000-3000 μm). These dimensional characteristics aligned with developmental progression. This study characterizes the ontogeny, distribution, ultrastructure, and 3D architecture of secretory canals, providing a structural foundation for investigating correlations between secretory tissues and compound synthesis.

Why it matches plant phenotyping methods根の分泌道の密度・寸法・3D構造という植物器官形質を、µ-CTの体積解析・セグメンテーションと顕微鏡法で取得・抽出しており、画像計測が研究の中心的要素である。

abstractµ-CT volumetric analysis and segmentation generated detailed 3D models, revealing spatial organization and enabling size-based grouping of canals (1000-3000 μm).

An Efficient Attention-Gated Hybrid Transformer-CNN Framework for Plant Disease Segmentation In-the-Wild ↗

Abstract In real field scenarios in agriculture, automatic segmentation of plant diseases is an important technique for precision farming. However, it remains exceptionally challenging due to blurred lesions, complex morphological structures, irregular backgrounds, and severe class imbalance. While traditional convo lutional networks struggle to capture long-range semantic context and standard vision transformers fail to preserve sharp localized boundaries, this paper proposes an efficient, attention-gated hybrid framework optimized for field deployment. Our architecture leverages a hierarchical Mix Transformer (MiT-B2) encoder stream integrated with an Atrous Spatial Pyramid Pooling (ASPP) scale-space context bridge and a custom Cross-Scale Multimodal Attention Gate (CMAG) to isolate discriminative disease markers selectively. Evaluated on the highly challenging and unbalanced PlantSeg dataset, our framework achieves competitive mean Intersection over Union (mIoU) of 66.57% and an F1-score of 79.93%, while maintaining a highly compact parameter footprint of only 30.37 M. Experimental evaluations demonstrate that the proposed system establishes a new performance milestone, outperforming current competitive architectures and proving highly viable for resource-constrained edge devices. To further enhance out-of-distribution stability, we outline future directions to extend our top-performing candidate variants into a Level 1 meta-stacking ensemble optimized via few-shot learning and partial backbone fine-tuning.

Why it matches plant phenotyping methods植物病害領域の画像セグメンテーション手法を開発・評価し、病変の分割性能を定量検証しているため、植物の病害状態を推定するフェノタイピング手法が中心です。

abstractautomatic segmentation of plant diseases is an important technique for precision farming.

Scale Matters: Adaptive Granularity Selection for Cross-Species 3D Plant Organ Segmentation ↗

Recent 3D foundation models provide powerful feature representations for point cloud learning by controlling spatial granularity. However, relying on a fixed spatial granularity severely limits generalization in applications like plant phenotyping, where organ morphology and size vary substantially across species and growth stages. To address this, we propose AGS-PlantSeg, a few-shot 3D plant organ segmentation method that leverages the frozen Utonia (arXiv:2603.03283) foundation model combined with Adaptive Granularity Selection. By dynamically selecting the best granularity levels for each specific plant model, our method extracts optimized geometric features for a lightweight MLP segmentation head. Extensive experiments across PLANesT-3D (arXiv:2407.21150), Pheno4D , and Crops3D demonstrate that AGS-PlantSeg significantly improves cross-species generalization, achieving 88.9% average mIoU performance and outperforming fixed-granularity baselines by 2.5 mIoU points. Despite requiring minimal annotated data, our approach is highly competitive with fully supervised, plant-specific architectures.

Why it matches plant phenotyping methods植物器官の3Dセグメンテーション手法を開発し、複数の植物フェノタイピングデータセットで性能検証しているため、フェノタイピング手法が中心です。

abstractwe propose AGS-PlantSeg, a few-shot 3D plant organ segmentation method

Non-destructive durian locule counting from rotational RGB imaging using rotation-synchronized 2D-to-1D morphological energy inference ↗

The edible yield and commercial value of durian are strongly determined by the number of fully developed internal locules, yet their assessment still relies largely on subjective manual inspection or costly destructive analysis. Existing non-destructive approaches, including tapping-based evaluation and X-ray imaging, are either insufficiently standardized or impractical for high-throughput phenotyping. This study proposes the Rotation-Synchronized Structural Locule Evaluator (RS-SLE). The framework integrates convolutional spatial learning with deterministic signal processing to estimate internal locule number from rotational RGB imaging. The proposed system learns frame-wise spatial morphology using convolutional heatmap regression and performs temporal inference through deterministic kinematic signal processing over a mechanically bounded 360° rotation, thereby avoiding reliance on data-intensive recurrent video models. Specifically, sequential 2D locule-probability heatmaps are transformed into a synchronized 1D morphological energy signal, which is subsequently refined using gradient-based integration, Tikhonov regularization, and adaptive morphological thresholding to recover cycle-consistent structural peaks corresponding to fertile locules. This design provides a transparent and computationally efficient alternative to learned temporal memory while maintaining robustness to viewpoint variation, partial occlusion, and high-frequency spine noise. Evaluated on 260 fruits of the ‘Monthong’ cultivar, the proposed framework achieved a mean absolute error of 0.289 locules and a 71.1% exact-match rate on independent rotational videos. When combined with morphological correlation analysis, the framework attained a 100% tolerance accuracy (±1 locule) on the test set with destructive ground-truth measurements. These results demonstrate that dynamic external morphology can serve as a reliable optical proxy for internal locule development. Crucially, the final locule count is derived entirely from the CNN-generated one-dimensional morphological signal. This demonstrates the necessity of localized structural analysis over simple macroscopic shape indices. The findings highlight the value of explainable, kinematics-informed vision systems for practical precision agriculture.

Why it matches plant phenotyping methods回転RGB画像からドリアン内部のlocule数という植物器官状態を推定する画像ベース表現型計測法を開発し、独立動画と破壊的グラウンドトゥルースで検証しているため、方法が研究の中心である。

abstractThis study proposes the Rotation-Synchronized Structural Locule Evaluator (RS-SLE).

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

BFMambaNet: Boundary-Frequency-Guided Global Semantic Mamba Network for Fine-Grained Camellia oleifera Leaf Disease Segmentation. ↗

Camellia oleifera leaf disease segmentation under natural field conditions is important for precision plant protection but remains challenging because lesions often show small target areas, blurred boundaries, uneven illumination, complex backgrounds, and coexisting symptoms. To address these problems, this paper proposes BFMambaNet, a Boundary-Frequency-guided Global Semantic Mamba Network for fine-grained disease segmentation. The model adopts an encoder-decoder framework and introduces a Global Semantic Mamba-based spatial selective feature modeling block to capture long-range lesion context and reduce semantic confusion. A gated wavelet spatial enhancement block is further designed to strengthen high-frequency boundary details while suppressing noisy responses. During training, boundary-frequency auxiliary supervision guides contour localization and pathological texture recovery without additional manual boundary labels. A reinforcement-learning-guided adaptive loss controller adjusts class-wise reweighting factors and loss-component weights according to the training state, improving optimization stability. A pixel-level dataset containing 1400 images and seven disease categories was constructed for evaluation. Experimental results show that BFMambaNet achieves 92.39% Precision, 91.43% Recall, 91.26% Dice, and 85.46% mIoU, outperforming representative CNN-based, Transformer-based, and Mamba-based models. Evaluations on environmental subsets confirm superior robustness, outperforming VMamba by 3.70% mIoU under uneven illumination, 3.55% mIoU under complex backgrounds, and 5.10% mIoU under coexisting symptoms. Cross-dataset validation on Apple leaf diseases further proves its generalization with 3.39% mIoU and 3.84% Dice improvements over U-Mamba, while maintaining a competitive inference speed of 30 FPS. Qualitative results also show clearer boundaries, fewer missed small lesions, and more stable predictions in complex field scenarios.

Why it matches plant phenotyping methods植物葉の病斑・病害状態を画像から画素単位で推定するセグメンテーション手法を開発し、データセット構築、性能評価、環境別評価、クロスデータセット検証まで行っており、病害フェノタイピング手法が中心である。

abstractA pixel-level dataset containing 1400 images and seven disease categories was constructed for evaluation.

Optimizing cell segmentation and downstream processing for plant probe-based spatial transcriptomics ↗

Abstract Probe-based spatial transcriptomics platforms use predefined oligonucleotide panels to detect selected RNAs in tissue sections while preserving transcript spatial coordinates. Accurate cell segmentation is required for reliable transcript-to-cell assignments. This analytical process is affected in plant tissues by cell walls, large vacuoles, and strong autofluorescence, which often reduce boundary contrast and elevate background. Nucleus-only segmentation with fixed-distance expansion can be an alternative approach, but it underestimates cellular area and morphology and reduces the number of assignable transcripts per cell. Here, we present a practical workflow for segmentation and downstream processing in plant probe-based spatial transcriptomics. Using the soybean nodule, soybean seed, rice root, and wheat inflorescence, we demonstrate the applicability of our workflow across species, tissues, and technological platforms. In brief, candidate cell masks are generated from available fluorescence signals and then selected and corrected using two napari plugins. Transcript-informed refinement with Baysor is included as an optional step. Upon benchmarking our approach using a collection of metrics (assignment yield, background/negative controls, and per-cell transcript/gene distributions) and linked segmentation choices to expression-matrix quality and downstream clustering, we demonstrate the potential of our workflow to support the analysis of plant probe-based spatial transcriptomics.

Why it matches plant phenotyping methods植物組織の細胞セグメンテーションとトランスクリプト割当てを改善する実用ワークフローを開発し、複数種・組織でベンチマークしている。植物形態そのものの測定ではないが、細胞レベルの空間状態を抽出する解析手法が中心である。

abstractHere, we present a practical workflow for segmentation and downstream processing in plant probe-based spatial transcriptomics.

SporaScan: cost-effective, high-precision leaf-disc disease severity assessment for grapevine downy mildew. ↗

Background Accurate assessment of disease severity is essential for evaluating fungicide performance and breeding disease-resistant crop varieties. Manual scoring of infection on individual leaf discs is labor-intensive and variable, while traditional computer vision methods require manual parameter tuning and lack robustness. Existing deep learning approaches often struggle to simultaneously localize leaf discs and accurately segment disease symptoms, limiting their practical application. Results We developed SporaScan, an automated pipeline combining YOLO v8n for leaf disc localization, Mobile SAM for background removal, and UNet for sporulation segmentation. It achieved high accuracy (mAP@50 >99%, mIoU@50 >96%), with background removal reducing misclassification (0.21% for sporulation and 2.75% for leaf discs). Severity estimates showed strong agreement with manual annotations (R 2 = 0.99). In a blind test, technicians selected SporaScan as superior in 37.2% of cases, manual annotation in 26.2%, and equal performance in 36.6% (P Conclusion These results demonstrate that SporaScan provides an efficient and practical approach for automated assessment of downy mildew severity, supporting applications in disease evaluation, breeding, and fungicide assessment (http://116.10.197.212:9060/segment/#/). © 2026 Society of Chemical Industry.

Why it matches plant phenotyping methodsブドウ葉ディスク上のべと病症状を画像から自動分割し、病害重症度を推定する手法を開発・検証しており、植物表現型取得が中心である。

abstractWe developed SporaScan, an automated pipeline combining YOLO v8n for leaf disc localization, Mobile SAM for background removal, and UNet for sporulation segmentation.

APLICAÇÃO DE REDES NEURAIS CONVOLUCIONAIS PARA DETECÇÃO DE DOENÇAS EM FOLHAS DE MACIEIRAS ↗

O cultivo de maçãs tem grande importância econômica no setor agropecuário brasileiro, especialmente na região Sul do país. No entanto, a produtividade dos pomares é frequentemente comprometida por doenças foliares que, se não tratadas, podem resultar em perdas substanciais. Nesse contexto, os avanços em técnicas de Aprendizado de Máquina têm possibilitado o desenvolvimento de soluções computacionais que auxiliam no diagnóstico agropecuário com maior precisão e agilidade. Este trabalho propõe uma abordagem baseada em Redes Neurais Convolucionais que utiliza aprendizado por transferência para detectar automaticamente sintomas de doenças em folhas de macieira. A metodologia desenvolvida inclui a segmentação e análise de regiões sintomáticas para reduzir o ruído proveniente de áreas saudáveis ​​e direcionar o aprendizado do modelo para sinais relevantes. Um total de 32.382 manchas de sintomas foram extraídas de 1.995 imagens originais, abrangendo cinco classes de distúrbios foliares: glomerela, sarna, danos por herbicidas, deficiência de magnésio e deficiência de potássio. A rede MobileNetV2, treinada por meio de aprendizado por transferência, alcançou um F1-score de 0,926 e 93,8% de acurácia no conjunto de teste reservado. Os resultados indicam um bom desempenho no contexto avaliado, sugerindo o potencial da abordagem como ferramenta de apoio ao diagnóstico da saúde das plantas e à tomada de decisões em campo. Palavras-chave: aprendizado de máquina; visão computacional; doenças em plantas. Application of convolutional neural networks for disease detection in apple tree leaves ABSTRACT: Apple cultivation holds significant economic importance in the Brazilian agricultural sector, especially in the southern region of the country. However, orchard productivity is often compromised by foliar diseases, which, if left untreated, can lead to substantial losses. In this context, advances in Machine Learning techniques have enabled the development of computational solutions that support agricultural diagnostics with greater accuracy and agility. This work proposes an approach based on Convolutional Neural Networks that uses transfer learning to automatically detect disease symptoms in apple leaves. The developed methodology includes segmentation and analysis of symptomatic regions to reduce noise from healthy areas and focus the model’s learning on relevant signals. A total of 32,382 symptom patches were extracted from 1,995 original images, covering five foliar disorder classes: glomerella, scab, herbicide damage, magnesium deficiency, and potassium deficiency. The MobileNetV2, trained via transfer learning, achieved a F1-score of 0.926 and 93.8% accuracy on the held-out test set. The results indicate good performance in the evaluated setting, suggesting the approach’s potential as a tool to support plant-health diagnosis and field decision-making. Keywords: machine learning; computer vision; plant disease.

Why it matches plant phenotyping methods葉の病徴を画像から自動検出・分類するCNNと、症状領域のセグメンテーションを中心的に開発・評価しており、植物病害状態の画像ベース表現型計測に該当する。

abstractEste trabalho propõe uma abordagem baseada em Redes Neurais Convolucionais que utiliza aprendizado por transferência para detectar automaticamente sintomas de doenças em folhas de macieira.

An Intelligent Morphology-Driven Framework for Leaf Venation Analysis and Plant Classification Using Advanced Digital Image Processing and Machine Learning ↗

Automated plant identification based on leaf morphology has gained significant attention in recent years due to its wide range of applications in precision agriculture, biodiversity conservation, environmental monitoring, and botanical informatics. Advances in digital image processing and machine learning have enabled the development of intelligent systems capable of identifying plant species from leaf characteristics with minimal human intervention. Despite these advancements, achieving reliable and accurate classification remains challenging because leaf images are often affected by variations in illumination, complex backgrounds, image noise, differences in orientation and scale, as well as natural leaf deformation. These factors can obscure important morphological features, reduce the effectiveness of feature extraction, and ultimately decrease the accuracy and robustness of automated plant classification systems. Consequently, there is a growing need for intelligent frameworks that can effectively handle these challenges while preserving critical leaf morphology and venation information for reliable plant identification. This study proposes an Intelligent Morphology-Driven Framework that integrates advanced digital image processing and machine learning for robust leaf venation analysis and plant classification. The proposed framework integrates multiple digital image processing and machine learning techniques to enable accurate and automated leaf venation analysis and plant classification. Initially, leaf images undergo preprocessing using grayscale conversion, histogram equalization, Contrast Limited Adaptive Histogram Equalization (CLAHE), Gaussian filtering, Laplacian sharpening, Gabor filtering, and homomorphic filtering to improve image quality and enhance venation and structural details. The enhanced images are then processed through threshold-based segmentation followed by morphological operations, including erosion, dilation, opening, closing, convex hull generation, and skeletonization, to accurately isolate leaf regions while preserving their geometric structure.To characterize leaf morphology, the framework extracts a comprehensive set of features, including geometric descriptors such as area, perimeter, circularity, aspect ratio, solidity, eccentricity, and vein density, together with Hu invariant moments that provide rotation-, translation-, and scale-invariant shape representation. In addition, the framework investigates the influence of image compression by comparing lossless PNG and lossy JPEG formats to evaluate their impact on preserving morphological features and venation details. The extracted feature vectors are subsequently classified using a Random Forest classifier to categorize leaf venation patterns into parallel, reticulate-pinnate, and reticulate-palmate classes.Experimental evaluation demonstrates that the proposed framework achieves an overall classification accuracy of 93.2%, while effectively preserving important morphological characteristics and maintaining computational efficiency. The combination of adaptive image enhancement, morphology-preserving segmentation, comprehensive feature extraction, and robust machine learning classification makes the proposed approach reliable, interpretable, and scalable. Consequently, the framework has significant potential for applications in digital herbarium systems, automated plant identification, biodiversity monitoring, botanical informatics, and precision agriculture.

Why it matches plant phenotyping methods葉画像から形態・葉脈形質を抽出し分類する画像処理・機械学習フレームワーク自体が研究の中心であり、植物表現型の取得・解析手法として適格。

abstractThis study proposes an Intelligent Morphology-Driven Framework that integrates advanced digital image processing and machine learning for robust leaf venation analysis and plant classification.

RADIX: a deep learning framework that maps root barriers across species and reveals genetic and environmental contributions ↗

Root anatomical barriers, including the suberized and lignified walls of the endodermis and exodermis, and cortical aerenchyma, regulate water and nutrient transport, gas exchange, and rhizosphere interaction. Their adaptive function places them as an important target for breeding environmentally resilient plant species. Quantifying these structures at high resolution is a manual bottleneck that limits experimental scale. We present RADIX (Root Anatomy Deep- learning Image segmentation across species and platforms), a framework that adapts a large self-supervised vision-transformer foundation encoder (DINOv3), pre-trained on billions of natural images, to root anatomy by fine-tuning its encoder with a dense-prediction-transformer decoder. Transferring these general-purpose vision encoders to a specialized biological domain with a high-quality annotated dataset is what allows RADIX to generalize across species and imaging platforms. We train and evaluate it on the first expert-annotated benchmark of root anatomical structures at scale, comprising 1,695 high-quality fluorescence images spanning 17 monocot and dicot species, six anatomical structures, and three imaging platforms. RADIX segments all six structures at inter-annotator-level accuracy and generalizes to unseen species, genotypes, growth conditions, and an imaging platform from an independent laboratory. A single unified model surpasses monocot- and dicot-specialist models without sacrificing in-group accuracy. Predicted masks yield aerenchyma and suberin/lignin measurements matching expert annotation at ∼1.2 s per image with a single GPU, reducing weeks of manual analysis to minutes. Applying RADIX across genotypes, microbial treatments, and growth systems, we show that these cell type features form a coordinated, multidimensional, and context-dependent system shaped by genetic and environmental factors.

Why it matches plant phenotyping methods根の解剖学的構造を画像から自動抽出・定量する深層学習フレームワークを開発し、注釈付きベンチマークで検証しているため、植物フェノタイピング手法が中心である。

abstractQuantifying these structures at high resolution is a manual bottleneck that limits experimental scale.

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.

Time-Resolved Phenotyping Reveals Heterogeneous Rice Seed Germination Dynamics in Shallow-Water Culture ↗

Germination percentage is an endpoint measure and therefore does not describe when an individual seed begins visible growth or how rapidly its radicle and plumule expand. We developed a time-resolved phenotyping workflow to quantify rice seed germination continuously in shallow-water culture. A single industrial camera moved along a 1 m rail and imaged three culture boxes at 1 h intervals for up to 80 h. The archive comprised 1,062 full-frame images and 6,372 seed-level repeated observations under the six-seed field-of-view configuration. A physical grid maintained seed identity through time and enabled individual regions of interest to be extracted. Whole-seed foregrounds were obtained with a pretrained U 2 -Net, and a masked RGB intensity rule separated newly emerging tissue from the darker hull. For each tracked seed, projected emerging-tissue area and interval growth rate were calculated. Three representative normally germinating seeds first showed measurable tissue at 48 h, yet subsequently followed distinct trajectories: final projected areas ranged from 2,605 to 4,700 pixels and peak interval growth rates ranged from 106.88 to 287.92 pixels h −1 . B-1 accumulated 63.71% of its final visible area during 72–80 h, whereas B-3 accumulated 73.51% during 60–72 h. Thus, seeds with the same observed emergence interval can differ substantially in the timing and magnitude of post-emergence expansion. The workflow converts repeated images into biologically interpretable temporal phenotypes and provides a basis for nondestructive studies of rice seed vigor and germination heterogeneity.

Why it matches plant phenotyping methods連続画像から個々のイネ種子の発芽・組織面積・成長速度を抽出する時間分解フェノタイピングワークフローを開発しており、表現型取得と解析手法が研究の中心である。

abstractWe developed a time-resolved phenotyping workflow to quantify rice seed germination continuously in shallow-water culture.

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.

RGB image segmentation for quantitative bud flushing assessment in Norway spruce ↗

Bud flushing timing is a crucial attribute for forest geneticists and physiologists studying adaptive variation in tree species. In clonal populations such as Norway spruce seed orchards, accurate assessment of bud flushing is essential, as this attribute strongly influences survival and fitness. However, traditional bud-flushing assessment relies on visual scoring scales that are inherently subjective and susceptible to observer bias, leading to inconsistencies when multiple technicians collect data. To address these limitations, we introduce a novel quantitative phenotype derived from segmented RGB images for quantifying bud flushing that objectively measures the ratio of light-green current-year needles to the total visible needle area of each grafted ramet. By extracting and summarizing digital image data for each ramet, this approach provides a standardized and reproducible assessment of bud flushing phenology. We evaluated clonally replicated ramets in two sites across two seasons and compared this image-derived flushing ratio with conventional visual scoring and color indices. Using mixed models, we quantified genetic control and cross-orchard stability of clonal performance. The image-derived flushing ratio tracked visual-score progression but showed higher broad-sense heritability (0.54–0.70) than visual scoring (0.45–0.65) and canopy color indices (0.20–0.51). Although site means differed strongly, clonal ranking remained stable between orchards for the image-derived flushing ratio and for visual scoring, whereas color indices showed lower stability and greater uncertainty. Overall, these results support the image-derived flushing ratio as a structure-based phenotype that improves the precision and cross-site transferability of genetic evaluation of bud flushing in Norway spruce seed orchards.

Why it matches plant phenotyping methodsRGB画像のセグメンテーションから bud flushing の定量形質を開発し、従来の視覚評価や色指数と比較検証しており、植物表現型取得法が研究の中心である。

abstractwe introduce a novel quantitative phenotype derived from segmented RGB images for quantifying bud flushing

An intelligent edge AI framework for real-time plant disease detection using deep learning under complex field environments ↗

Purpose Conventional plant disease detection is time-consuming and prone to human error. The purpose of this study is to propose an edge artificial intelligence (AI)-based deep learning framework for plant disease detection under real-field conditions. The model integrates convolutional neural networks (CNNs) with a Sliding Window Mean Absolute Deviation (SWMAD) preprocessing technique to address illumination variability and complex background conditions. Design/methodology/approach A dual-layer CNN model is developed for plant disease classification using HSV segmentation, flood-fill segmentation and SWMAD preprocessing to handle real-field variations. The model is trained on PlantVillage and real farm images and deployed via TensorFlow Lite for real-time offline detection. TensorFlow Lite is used to enable efficient on-device inference for deployment in resource-constrained environments. Findings Benchmark experiments conducted on the PlantVillage dataset achieved a classification accuracy of 99.91% under controlled conditions. On the hybrid dataset comprising PlantVillage and real-field images, the optimized CNN framework achieved a validation accuracy of 95.01% following extensive evaluation of optimizers, layer architectures and worker configurations. The integration of the proposed SWMAD preprocessing technique into the finalized architecture further improved the validation accuracy to 97.38%, demonstrating enhanced robustness and classification performance under practical agricultural conditions in the final deployed model. Originality/value The originality of this study lies in several novel contributions. First, we introduce an SWMAD-based preprocessing technique, which enhances local statistical variations in leaf images by capturing pixel-level deviations from neighborhood intensity means. Unlike, conventional preprocessing methods, SWMAD is specifically designed to handle real-field challenges such as illumination variation, noise and complex backgrounds. The improvement in validation accuracy demonstrates the effectiveness of the proposed approach in capturing more discriminative features compared to existing techniques, thereby improving overall model robustness and reliability in practical agricultural environments.

Why it matches plant phenotyping methods植物病害という植物状態を画像から推定する深層学習・前処理・エッジ展開手法が研究の中心であり、実環境での検証も行っているため。

abstractThe purpose of this study is to propose an edge artificial intelligence (AI)-based deep learning framework for plant disease detection under real-field conditions.

A data-driven approach to automate embolism detection in leaves ↗

1 Summary Embolism, the formation of air bubbles in the plant water transport system, is a mechanistic driver of plant death. The Optical Vulnerability Technique (OVT) is an imaging method for non-invasive quantification of embolism (including P50, a common metric for drought vulnerability), which can also provide detailed spatial and temporal information. Its major cost lies in the post-processing of thousands of images. Here we designed, tested, trained, and make publicly available a neural network model to automate post-processing of OVT images. Using a dataset of 65 leaves from Senecio pterophorous , we compared our model predictions to results obtained via traditional post-processing by an expert. Our model resolved P50 to within 0.027 MPa of the expert-processed data with training taking 30 minutes to 2.5 hours and model-runtime in the order of seconds to minutes, demonstrating its promise for increasing the efficiency and throughput of P50 calculation. The model’s performance in replicating the pixels that constitute embolism events was lower (mean event-frame IoU of 0.38). We invite the community to utilise our model but emphasise that it does not replace the expert-processing pipeline and that care must be taken when considering applying this and similar approaches to OVT data.

Why it matches plant phenotyping methods葉の塞栓を画像から定量化するOVTの後処理を自動化するニューラルネットワークを開発・検証しており、植物生理状態の表現型取得が研究の中心である。

abstractHere we designed, tested, trained, and make publicly available a neural network model to automate post-processing of OVT images.

Deep learning combined with UAV to assist in leaf color breeding of Chinese cabbage ↗

Abstract Leaf color is an important trait affecting vegetable quality, yield, and market value. However, traditional methods for leaf color assessment are often subjective or destructive, which limits accurate and high-throughput phenotyping. In this study, an unmanned aerial vehicle (UAV)–based multispectral imaging platform was used to collect phenotypic data from 214 Chinese cabbage inbred lines at the rosette stage. A multispectral UNet model was applied to segment individual plants, and a membership function was used to quantify leaf color on a continuous scale. Based on these high-throughput phenotypic data, a genome-wide association study was used to identify two candidate genes, BrEMB976 and BrGSH2, on chromosome A06. Subsequent virus-induced gene silencing analysis showed that silencing these genes altered leaf color. In addition, a deep learning-based genomic selection model, BrDeepGS, was developed for leaf color prediction, which achieved a Pearson correlation coefficient of 0.853. These results demonstrate the potential of integrating UAV-based high-throughput phenotyping, candidate gene analysis, and genomic prediction for leaf color evaluation and selection in Chinese cabbage breeding.

Why it matches plant phenotyping methodsUAVマルチスペクトル画像、個体分割、葉色の連続量化による高スループット表現型取得が研究の中心であり、育種への応用も行っている。

abstractan unmanned aerial vehicle (UAV)–based multispectral imaging platform was used to collect phenotypic data from 214 Chinese cabbage inbred lines

Improved YOLOv8n-seg for instance segmentation of mango fruits and peduncles in natural orchard environments ↗

To improve the instance segmentation accuracy of mango fruits and peduncles in complex mountainous orchard scenes and provide visual decision support for robotic harvesting, this study proposes a model-driven perception and picking-point localization method. Specifically, an RGB-D mango dataset was constructed under natural orchard conditions, covering strong illumination, shadows, backlighting, fruit overlap, branch and leaf occlusion, and peduncle crossing. An improved lightweight instance segmentation model named SHS-YOLOv8n-seg was then developed based on YOLOv8n-seg. StarNet_s1 was introduced as the backbone to enhance feature extraction under complex backgrounds. Furthermore, a high-frequency and spatial perception feature pyramid network was adopted to strengthen multi-scale feature fusion and improve the representation of slender peduncles. The SPPF module was used to expand the receptive field, and the parameter-free SimAM attention mechanism was introduced to enhance target responses while suppressing background interference. In the single-run comparison, the proposed model achieved Precision, Recall, mAP@50, and mAP@50:95 values of 89.62%, 88.17%, 90.19%, and 67.94%, respectively. Compared with the baseline YOLOv8n-seg model, these values increased by 2.42, 2.90, 2.75, and 2.57 percentage points, respectively. Moreover, fruit–peduncle matching, geometric constraints, RGB-D depth information, and PCA-based local direction estimation were combined to infer the picking point and recover its 3D coordinates from the segmentation masks. In the evaluation of 57 RGB-D images, the picking point position accuracy reached 98.2%, while the local peduncle direction accuracy reached 91.2%. Overall, the proposed method can accurately segment mango fruits and peduncles in complex natural environments and convert the segmentation results into picking point positions, 3D coordinates, and local direction information, thereby providing theoretical and technical support for intelligent mango harvesting robots.

Why it matches plant phenotyping methodsマンゴー果実・果梗の画像セグメンテーションと3D形状情報の抽出手法を開発・評価しており、単なる収穫対象の位置検出を超えて、再利用可能な植物器官の形態情報を取得する方法が中心である。

abstractfruit–peduncle matching, geometric constraints, RGB-D depth information, and PCA-based local direction estimation were combined to infer the picking point and recover its 3D coordinates from the segmentation masks

Depth4PH: a vision foundation model-based framework for plant height estimation in agricultural scenes ↗

Plant height is a key 3D phenotypic trait for assessing crop growth, biomass accumulation, and lodging resistance. To overcome the practical limitations of conventional plant height measurement methods, this study proposes a novel vision foundation model-based framework named Depth for Plant Height (Depth4PH) for plant height estimation in agricultural scenes using low-cost monocular RGB imaging. As part of our contributions, a synthetic–real coupled multimodal dataset was constructed by integrating Blender virtual agricultural scenes (Blender VAS) with real field images. Building upon the existing Depth Anything V2 foundation model, we developed a novel module called Transfer-based Agricultural Metric Depth Anything V2 (TAM-Depth V2) for absolute metric depth estimation through parameter-efficient fine-tuning, depth decoder reconstruction, and joint loss optimization. Furthermore, we designed a novel multi-source prompt-based segmentation framework, MSP-SAM2, to generate positive and negative prompts for zero-shot crop instance segmentation. Finally, a new inverse physical plant height estimation algorithm, RANSAC-Per, was introduced to estimate plant height by combining truncated percentile statistics with local RANSAC micro-plane fitting, thereby reducing the effects of depth noise and field microtopographic variation. The result showed that TAM-Depth V2 achieved stable absolute depth estimation, with an RMSE of 0.1162 m and an AbsRel of 4.25%. Compared to the original box-prompted SAM 2, MSP-SAM2 achieved a 4.4% improvement in mIoU, reaching 91.6% and a recall of 93.2%. On a 350-plant multi-crop test set, Depth4PH achieved R 2 = 0.948, RMSE = 12.23 cm, and MAE = 8.82 cm, and MAPE =10.15%, with crop-specific RMSEs ranging from 3.99 cm (cucumber) to 20.73 cm (maize), significantly outperforming the traditional Global-MinMax baseline (which had an RMSE of 22.62 cm). These results indicate that Depth4PH provides a promising foundational pathway for high-throughput crop phenotyping. With future optimization for edge deployment, it holds significant potential to support high-throughput monitoring in precision agriculture.

Why it matches plant phenotyping methods植物高の画像取得・深度推定・セグメンテーション・高さ抽出アルゴリズムを一体化した植物表現型計測フレームワークの開発と検証が中心であり、データセット構築と性能評価も含む。

abstractthis study proposes a novel vision foundation model-based framework named Depth for Plant Height (Depth4PH) for plant height estimation in agricultural scenes using low-cost monocular RGB imaging.

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.

HagPF: Hierarchical-annotation-guided phenotypic framework for stem instance segmentation and length measurement in plant point clouds ↗

As a critical structural component that connects almost all other types of plant organs, the stem system not only supports the weight of the total plant, but also serves as a vital channel for nutriment transportation. Accurate phenotypic measurement of stem instances is of practical significance for assessing crop growth dynamics and predicting yield. To address current 3D phenotyping challenges of crops such as the difficulty in separating stem segments from the stem system and the low accuracy in stem length measurement, we propose a Hierarchical-annotation-guided Phenotypic Framework (HagPF) for Stem Instance Segmentation and Length Measurement in plant point clouds. Specifically, a hierarchical leaf-stem organ instance annotation strategy is devised to effectively train a PSegNet network for leaf and stem instance segmentation. The segmentation is then followed by a shape-adaptive measurement algorithm to automatically measure the length of stem segments that are morphologically diverse in space. On a 3D dataset comprising four crop species, the proposed framework achieved an Intersection over Union (IoU) of 95.45% for organ semantic segmentation and a Mean Weighted Coverage (mWCov) of 87.87% for instance segmentation (both stem and leaf). Regarding to the stem length measurement, the method obtained an average Root Mean Square Error (RMSE) of 1.044 cm and a relative error of 11.907%, outperforming 7 mainstream methods. The relevant dataset and source code can be found at: https://github.com/Jinx00/stem-length-measurement .

Why it matches plant phenotyping methods植物点群から茎のインスタンスを分割し、茎長を自動測定する3D表現型解析フレームワークの開発・比較検証が中心である。

abstractwe propose a Hierarchical-annotation-guided Phenotypic Framework (HagPF) for Stem Instance Segmentation and Length Measurement in plant point clouds.

An integrated YOLOv11-based framework for wheat spike phenotyping segmentation and grain yield estimation ↗

Spike count and spatial arrangement are among the strongest determinants of grain yield in wheat, yet reliable spike-level phenotyping under field conditions remains challenging. Field-acquired images are often affected by occlusion, heterogeneous illumination, and dense canopy overlap. In addition to these visual complexities, the effort required to generate large-scale instance-level annotations makes it difficult to build the extensive labeled datasets typically needed for robust segmentation models. This paper addresses both problems. The core methodological contribution is a semi-automated iterative annotation workflow: a YOLOv11x-seg model trained on a small manually annotated set is applied to unlabeled field images, and its predictions, after post-processing to remove duplicated, fragmented, and merged detections, are incorporated back into training. To prevent augmentation from distorting the training distribution, we introduce a distribution-aware augmentation strategy guided by Fréchet Inception Distance (FID), which retains only those augmented samples that remain within an acceptable distance from the original data distribution. Together, these components allowed us to build an effective training set from 3,899 high-resolution RGB images (4000 × 3000 pixels) of durum wheat collected at the CREA Research Centre for Cereal and Industrial Crops, with substantially reduced manual annotation effort. On the independent test set(242 images), the final YOLOv11x-seg model (M5 model) achieved a mask-level precision of 86.73%, recall of 83.02%, F1-score of 84.83%, mAP@50 of 89.42%, and mAP@50:95 of 60.51%. Spike masks were used to derive image-based traits including spike count, spike density, canopy coverage, spike area, spatial distribution, and vegetation indices. Their relationships with measured grain yield were explored through statistical analysis and machine-learning-based yield estimation.Both statistical and machine-learning analyses demonstrated that image-derived spike traits provided meaningful information for grain yield estimation, with canopy coverage showing the strongest positive association with yield. Using repeated nested cross-validation with out-of-fold (OOF) predictions, XGBoost achieved the highest yield estimation performance ( R OOF 2 = 0.312 , RMSE = 106.61 g/plot), supporting the potential of near-image phenotyping for late-stage yield estimation in wheat. These results show that semi-automated iterative annotation can enable practical wheat spike segmentation and image-based phenotyping under realistic open-field conditions. While grain yield estimation should be interpreted within the context of the experimental setting, the proposed framework highlights the value of image-derived spike traits for late-stage phenotyping and yield assessment in breeding experiments rather than for early-season yield forecasting.

Why it matches plant phenotyping methods半自動アノテーション、YOLOv11x-segによる小麦穂の画像セグメンテーション、分布認識型データ拡張、形質抽出と検証が中心的な方法論的貢献である。

abstractThe core methodological contribution is a semi-automated iterative annotation workflow

Smartphone-based high-fidelity 3D semantic segmentation of finger millet panicles using 3D Gaussian splatting for automated phenotyping and yield estimation ↗

Finger millet is an important cereal crop widely cultivated worldwide for food and fodder. Breeding programs aim to select genotypes with desirable architectural traits to develop new varieties with higher yields. In this effort, accurate high-throughput plant phenotyping is essential for accelerating crop improvement. To overcome the time-consuming and labor-intensive process of manual measurements, this study presents a comprehensive 3D imaging pipeline that leverages neural radiance fields (NeRF), 3D gaussian splatting (3DGS), and its advanced extensions (e.g., Feature 3DGS and Gaussian Grouping) to reconstruct, segment, and analyze finger millet yield component traits using multi-view 2D images. First, multiple-view RGB images of a single finger millet plant were captured, and COLMAP was then utilized to estimate the camera poses of the images and reconstruct the sparse point cloud, followed by advanced 3D reconstruction through 3DGS and NeRF. Second, feature 3DGS and gaussian grouping models were used to generate the 3D gaussian representation of finger millet panicles. This single-process framework enabled the generation of high-fidelity 3D point clouds and semantic feature fields without the need for expensive depth sensors or manual annotations. Our results demonstrated the effectiveness of these models in capturing morphological variations across different panicle phenotypes, including compact versus open panicle architectures. In addition, the 3D point clouds of the panicles were utilized to extract structural traits for yield prediction, achieving biologically meaningful correlations with grain productivity. This work highlights the potential of 3DGS-based phenotyping pipelines as a low-cost, near real-time, photorealistic solution for trait quantification, segmentation, and yield estimation in real-world agricultural settings.

Why it matches plant phenotyping methods3D画像再構成・セグメンテーション・形質抽出を統合した植物フェノタイピング手法の開発が中心であり、収量関連形質の定量と予測まで技術的に評価している。

abstractthis study presents a comprehensive 3D imaging pipeline that leverages neural radiance fields (NeRF), 3D gaussian splatting (3DGS), and its advanced extensions (e.g., Feature 3DGS and Gaussian Grouping) to reconstruct, segment, and analyze finger millet yield component traits using multi-view 2D images.

Detecting Callose Deposition in Soybean Lateral Roots During Fungal Infections. ↗

Callose is a β-1,3-glucan polysaccharide deposited at the plant cell wall interface. It is involved in numerous plant physiological processes and responses to both biotic and abiotic stresses. Callose deposition under biotic stress conditions is typically associated with pattern-triggered immunity, which is activated upon recognition of pathogen-associated molecular patterns or damage-associated molecular patterns at the cell wall interface. These depositions reinforce compromised and damaged cell walls caused by pathogen invasion. The standard method for visualizing callose deposition in various plant tissues involves aniline blue staining. Aniline blue fluorochrome preferentially binds to β-1,3-glucans, which enables this staining technique to specifically locate callose deposition. Although multiple protocols for callose detection using aniline blue are available in various model plants, such as Arabidopsis, there is no optimized method for lignified lateral root tissues after fungal infection. Lignification of roots can hinder the clear visualization of callose depositions; therefore, it is essential to remove them for improved callose detection. Here, we have optimized a robust and reliable method for detecting callose deposition in soybean lateral roots during Macrophomina phaseolina infections. M. phaseolina is a filamentous, soil-borne, necrotrophic fungus that causes charcoal rot disease in soybean and other crop plants. Here, we also provide a detailed methodology for soybean root infection with M. phaseolina using the root-dip method of inoculation, followed by aniline blue staining. Furthermore, we provide a detailed workflow for employing open-source Fiji software together with the Trainable Weka Segmentation (TWS) plugin to detect and count callose structures in fungal-infected root tissues. This protocol may be applicable for detecting callose deposition in other crop plants during fungal infections. © 2026 Wiley Periodicals LLC. Basic Protocol 1: Infection assay with M. phaseolina using root dip method of inoculation Basic Protocol 2: Staining of M. phaseolina-infected soybean roots with aniline blue and imaging of stained soybean roots using fluorescence microscopy Support Protocol: Callose quantification using ImageJ software combined with the TWS plugin.

Why it matches plant phenotyping methods感染根のカルロース沈着という植物の病態・生理状態を、染色・蛍光画像・Fiji/TWSで検出および定量する方法を最適化した手法論文であり、表現型取得が中心です。

abstractHere, we have optimized a robust and reliable method for detecting callose deposition in soybean lateral roots during Macrophomina phaseolina infections.

Methodological framework of automatic field-based plot extraction and maize emergence counting using UAV imagery and deep learning ↗

Accurate plant population estimation is critical for crop monitoring, yield prediction, and field management in precision agriculture. However, challenges such as complex backgrounds, overlapping plants, and the need for large-scale coverage make seedling counting from UAV imagery difficult. In this study, we propose a novel automated pipeline for maize seedling counting based on high-resolution UAV orthomosaic images. The pipeline begins with an automatic field-based plot extraction method that isolates individual planting regions without the need for manual intervention. A lightweight object detection model, YOLOv8n-CA, is then employed, incorporating Coordinate Attention to enhance feature localization while maintaining fast inference. To further accelerate the process, we introduce the ‘In-Range Sliding’ strategy, which limits inference to only planting regions, reducing computational overhead. Extensive experiments demonstrate the effectiveness of our approach, achieving a mean absolute error (MAE) of 0.587 and a coefficient of determination ( R 2 ) of 94.19 % at the plot level. Additionally, our system enables spatial feature extraction such as seedling spacing, supporting more refined agronomic analysis. This work provides an efficient and scalable solution for plant counting, offering valuable insights for large-scale, rapid post-processing agricultural monitoring.

Why it matches plant phenotyping methodsUAV画像と深層学習によるトウモロコシ幼苗の計数・圃場区画抽出パイプラインを開発し、計数精度を検証しているため、植物表現型取得法が中心である。

abstractwe propose a novel automated pipeline for maize seedling counting based on high-resolution UAV orthomosaic images.

Field-scale crop growth stage mapping using multispectral images and deep hierarchical segmentation ↗

Accurate, field-scale mapping of crop growth stages is critical for supply-sensitive vegetable production, where timely harvests require detailed phenological information. Consecutive growth stages often involve rapid and subtle morphological changes and are influenced by challenging open-field conditions, which frequently result in misclassification when stages are treated as independent, discrete categories. To address this issue, CropMap is proposed as a growth-stage mapping framework that integrates Hierarchical Semantic Segmentation Networks (HSSN) with multispectral unmanned aerial vehicles (UAVs) imagery. CropMap incorporates the structured biological progression of crop development into the learning objective through tree-based label constraints, allowing the model to recognize phenological continuity and reduce confusion between adjacent stages. The framework is evaluated on the publicly available National Information Society Agency of Korea (NIA) field crop growth-stage dataset, a large-scale, multi-institutional UAV dataset containing 337,665 multispectral patches across six hierarchically related growth stages of Chinese cabbage and radish, curated by the NIA. CropMap achieves a test-set mean Intersection over Union (mIoU) of 0.5382, representing a 5% relative improvement over the best-performing transformer baseline (SegFormer; mIoU = 0.5124). Performance varies across classes: background separation is strong (IoU = 0.9128) and the rosette stage is well distinguished (IoU = 0.6354), while the leaf expansion stage remains the primary challenge (IoU = 0.3541), reflecting the inherent difficulty of mapping this spectrally and morphologically transitional class. These findings indicate that hierarchy-aware learning reduces inter-stage confusion for most phenological classes, but transitional growth stages remain a significant limitation for field-scale deployment. The framework provides a foundation for stage-resolved crop monitoring to support harvest timing and supply forecasting in high-value vegetable systems.

Why it matches plant phenotyping methods作物の生育段階という植物状態を、マルチスペクトルUAV画像と階層型セマンティックセグメンテーションで推定する手法が研究の中心であり、公開データセット上で性能評価も行っている。

abstractCropMap is proposed as a growth-stage mapping framework that integrates Hierarchical Semantic Segmentation Networks (HSSN) with multispectral unmanned aerial vehicles (UAVs) imagery.

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.

Machine Learning-Based Crop Growth Diagnosis System Using Spatiotemporal Relative Analysis of Vegetation Indices via a Quartile-Based Method ↗

Japanese agriculture faces pressing challenges, including a declining and aging farming population and the need to adapt to climate change. To address these issues, Smart Agriculture is being introduced to improve production efficiency. Among these, unmanned aerial vehicles (UAVs) have gained attention for their ability to rapidly monitor entire fields. We proposed a machine learning-based crop growth diagnosis system that generates spatiotemporal data for multiple vegetation indices (VIs) using the quartile method and diagnoses crop growth based on patterns of change in these values. The experimental site consisted of five paddy fields within an 80 m × 50 m plot in Iwate Prefecture, Japan, equipped with weather and water sensors. Ground-truth data (overall length, culm length, panicle number, and stem number) were collected approximately one week before harvest. UAV monitoring was conducted four times using a multispectral camera, and growth analysis was performed with six VIs. Correlation analysis revealed a positive relationship between crop growth and the daily average water level during the drainage period, and a negative relationship with the daily temperature range in mid-June. A combined cluster-label representation, constructed from clustering results of all VIs for each mesh, enabled integrated analysis and visualization of multi-index patterns. Grid size optimization showed no significant differences in correlation trends between 1 m × 1 m and 5 m × 5 m resolutions. For non-crop area removal, a comparison of three image segmentation methods demonstrated that the Otsu Method achieved the highest performance. Finally, to facilitate practical use in the field, we prototyped a report interface for the diagnosis system. Future work will focus on developing a comprehensive field diagnosis system to clarify field environments, with the aim of addressing fragmentation and enclaves in Japanese farms.

Why it matches plant phenotyping methodsUAVマルチスペクトル画像と植生指数、画像分割、クラスタリングを統合した作物生育診断システムの開発・評価が中心であり、作物形質との相関検証や実用インターフェースも扱っている。

abstractWe proposed a machine learning-based crop growth diagnosis system that generates spatiotemporal data for multiple vegetation indices (VIs) using the quartile method and diagnoses crop growth based on patterns of change in these values.

LBD-PointNet++: a point cloud segmentation network for phenotypic trait extraction of broccoli seedlings ↗

Broccoli is a globally significant vegetable, but climate change and soil salinization increasingly threaten its productivity. Precise seedling phenotyping is essential for selecting salt-tolerant germplasm, yet traditional manual methods are labor-intensive and error-prone. This study develops LBD-PointNet++, an optimized 3D point cloud semantic segmentation model for automated phenotypic parameter extraction of broccoli seedlings at the germination and early developmental phase under salt stress. High-fidelity 3D point clouds were reconstructed from a precision three-view imaging system using Structure from Motion (SfM) algorithms. LBD-PointNet++ introduces three core optimizations: (1) a Large Kernel Attention (LKA) mechanism using 3D sparse decomposition to capture long-range global dependencies; (2) a Dual Uncertainty and Shape-Adaptive Sampling (DUSAS) mechanism to preserve high-frequency features of fragile stems and margins; and (3) a joint Boundary-Aware Nested Contrastive and Adaptive Varifocal Joint Loss (BNCV-Loss) to effectively isolate overlapping leaves. Experimental results demonstrate superior performance, achieving an overall mean Intersection over Union (mIoU) of 88.07% across all three categories (Leaf, Stem, and Pot) and a Mean F1-score of 93.48%. Compared to state-of-the-art Transformer architectures like PTv3, LBD-PointNet++ achieves higher accuracy with less than 6% of the parameter volume and over twofold faster inference speed. Furthermore, dynamic monitoring across NaCl gradients (0-250 mmol/L) revealed a potential non-linear threshold effect, identifying 100 mmol/L as a preliminary phenotypic threshold under these conditions. Beyond this threshold, growth inhibition intensified rapidly; At 250 mmol/L, plant height decreased by 54.43% and the 3D entity volume shrank to approximately one-fifth of the control group. In summary, LBD-PointNet++ provides a high-efficiency solution for phenotypic identification and digital breeding of salt-tolerant Brassicaceae crops.

Why it matches plant phenotyping methods3D点群分割ネットワークと三視点SfM撮像を開発し、ブロッコリー幼植物の表現型形質抽出を中心的に評価しているため。

abstractThis study develops LBD-PointNet++, an optimized 3D point cloud semantic segmentation model for automated phenotypic parameter extraction of broccoli seedlings

Automated Physical Quality Assessment of Harvested Seeds: A Critical Review of 2D and 3D Computer Vision Systems ↗

Purpose: This paper investigated automated physical quality assessment of harvested seeds. Design/Methodology/Approach: This study provides an extensive review of computer vision-based two-dimensional (2D) and three-dimensional (3D) deployments for the physical inspection of harvested seeds and grains. For this purpose, a total of 75 peer-reviewed articles published between 2022 and 2025 were identified from scientific databases, including Scopus, Web of Science, IEEE Xplore, and ScienceDirect. These articles were based on seed quality assessment, image processing, and artificial intelligence. The selected articles were systematically analysed according to different stages of the processing pipeline, including data acquisition, preprocessing, segmentation, feature extraction, and classification. Research Limitation: This review is restricted to physical quality assessment of harvested seeds, excluding chemical, biochemical, and nutritional parameters. It references 75 peer-reviewed articles published between 2022 and 2025. Findings: This study identified technical problems related to variations in seed samples, hardware setups, segmentation, feature selection, and classification. These problems significantly affect the performance of automated systems. Based on a critical examination of the present automated systems, this paper highlighted the scope for future research. Practical Implication: An advanced, future-ready system can address the need for integrated imaging methods and effective data processing. Social Implication: The adoption of automated seed inspection systems provides assurance of food security. Originality/ Value: This paper identified critical gaps such as the absence of a unified processing framework, the lack of cross-species generalisation, and the limited adoption of explainable AI.

Why it matches plant phenotyping methods収穫種子の物理品質を画像から評価する2D/3Dコンピュータビジョン手法を体系的にレビューしており、植物形質取得法が中心である。

abstractThis study provides an extensive review of computer vision-based two-dimensional (2D) and three-dimensional (3D) deployments for the physical inspection of harvested seeds and grains.

High-resolution LiDAR and thermal UAV data for 3D analysis of urban vegetation structure and its cooling effect in San Nicolás, Mexico ↗

Abstract. Urban vegetation is essential for mitigating the Urban Heat Island effect, yet its cooling performance depends on its three-dimensional structure. This study combines high-resolution Unmanned Aerial Vehicle - based LiDAR (Zenmuse L2) and thermal imaging (Zenmuse H20) to analyze vegetation structure and surface temperature across 4 urban parks in San Nicolás de los Garza, Mexico. LiDAR data were processed to generate Digital Terrain Model, Digital Surface Model and Canopy Height Model models, enabling the segmentation of individual trees and extraction of structural metrics such as canopy height, crown area and point density. Thermal orthomosaics were co-registered with LiDAR models to quantify temperature contrasts between vegetated and impervious areas. Results reveal consistent cooling effects in all parks, with vegetated zones showing 8–15 °C lower surface temperatures depending on canopy density and maturity. Larger parks with continuous canopies displayed the strongest thermal regulation. This integrated LiDAR–thermal approach provides a precise and scalable framework for assessing microclimatic benefits of urban vegetation, supporting climate-resilient planning in rapidly urbanizing regions.

Why it matches plant phenotyping methodsUAV LiDAR・熱画像を用いて個体樹木の樹冠高や樹冠面積などの植物構造形質を抽出する手法と統合ワークフローが中心であり、単なる環境測定ではない。

abstractLiDAR data were processed to generate Digital Terrain Model, Digital Surface Model and Canopy Height Model models, enabling the segmentation of individual trees and extraction of structural metrics such as canopy height, crown area and point density.

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.

A Segmentation-driven Dual-branch Deep Learning Framework with Attention Fusion for Plant Disease Phenotyping ↗

Plant phenotyping plays a critical role in understanding plant health and improving agricultural productivity by enabling quantitative analysis of disease-related physiological characteristics.Among these, leaf diseases significantly impact crop yield and quality, necessitating accurate and automated phenotyping approaches.Traditional phenotyping methods rely on manual inspection or handcrafted feature extraction, which are time-consuming, prone to human error, and lack scalability under diverse environmental conditions.This study introduces a deep learning (DL)-based approach for image-based plant phenotyping, focusing on the classification of disease-affected traits.The developed method integrates segmentation-based region extraction, dual-branch feature learning, and attention-based feature fusion.Initially, input images are preprocessed and passed through a TransUNet-based segmentation module to isolate phenotypically relevant leaf regions while suppressing background interference.Both the original image and the segmented region are then processed using a RegNet-based feature extraction network to capture global structural information and localized disease-specific characteristics.The extracted features are fused using an attention-based mechanism, followed by fully connected layers for multiclass classification.Experimental results obtained on the controlled PlantVillage grape leaf dataset, which serves as a standardized benchmark for plant disease classification, demonstrate an overall classification accuracy of 97.8%, with precision, recall, and F1-score values of 97.7%, 97.9%, and 97.8%, respectively.In addition, the segmentation module achieves an Intersection over Union (IoU) of 94.1% and a Dice score of 96.8%, confirming its effectiveness in isolating relevant phenotypic regions.

Why it matches plant phenotyping methods植物病害形質の画像取得・領域抽出・分類を中核とする深層学習フェノタイピング手法の開発と性能評価であり、方法が中心的です。

abstractThis study introduces a deep learning (DL)-based approach for image-based plant phenotyping, focusing on the classification of disease-affected traits.

Blue-Green Fluorescence for Downy Mildew Phenotyping in Lettuce: Linking Transcriptional, Metabolic, and Optical Changes. ↗

Abstract Effective plant disease phenotyping is crucial for resistance breeding, but traditional visual assessment is often inaccurate and inefficient. This is particularly challenging when breeding lettuce (Lactuca sativa) for resistance to downy mildew, given the obligate biotrophic lifestyle of the causal pathogen Bremia lactucae. We discovered that B. lactucae-infected lettuce exhibits patches of increased blue-green fluorescence (BGF) under UV-A excitation from 6 d post-inoculation, preceding visible symptoms. Co-localization of BGF with hyphae, visualized with trypan blue, indicates that BGF is induced by downy mildew colonization. We therefore investigated its potential for non-invasive disease detection and quantification, as well as the underlying physiological changes. Using a custom imaging system, we demonstrate that BGF leaf area correlates with downy mildew severity and can be automatically quantified via a U-Net-based convolutional neural network, enabling early, objective disease assessment. Exploring transcriptomic and metabolomic changes associated with BGF, we found that induction of the phenylpropanoid pathway led to accumulation of caffeoylquinic acids, whose fluorescence spectra overlap with that of BGF tissue, supporting the hypothesis that these compounds contribute to the fluorescence signal. BGF imaging offers a powerful tool for phenotyping in lettuce breeding and for identifying quantitative resistance traits that support durable downy mildew resistance.

Why it matches plant phenotyping methods青緑蛍光のカスタム撮像とU-Netによる自動定量を開発し、レタスべと病の重症度を非侵襲・早期に評価する方法が研究の中心である。

abstractUsing a custom imaging system, we demonstrate that BGF leaf area correlates with downy mildew severity and can be automatically quantified via a U-Net-based convolutional neural network, enabling early, objective disease assessment.

A Review of Plant Leaf Disease Identification Using Deep Learning: Recent Advances, Challenges, and Future Directions ↗

Agriculture plays a pivotal role in ensuring global food security, economic stability, and sustainable development. Plant diseases significantly reduce agricultural productivity, resulting in substantial economic losses and threatening food supply worldwide. Early and accurate identification of plant leaf diseases enables timely intervention, minimizes crop damage, and enhances agricultural yield. Traditional disease diagnosis relies heavily on visual inspection by agricultural experts, making the process labor-intensive, subjective, and unsuitable for large-scale deployment. Recent advances in artificial intelligence, particularly deep learning, have transformed plant disease diagnosis by enabling automatic feature extraction and highly accurate image-based classification. This review presents a comprehensive analysis of recent developments in deep learning techniques for plant leaf disease identification. Various convolutional neural network (CNN) architectures, including AlexNet, VGGNet, ResNet, DenseNet, EfficientNet, MobileNet, Inception, and Xception, are critically reviewed along with modern transformer-based models such as Vision Transformer (ViT), Swin Transformer, and hybrid CNN–Transformer frameworks. The paper also examines transfer learning strategies, object detection methods including YOLO and Faster R-CNN, and semantic segmentation approaches such as U-Net and DeepLabV3+. Publicly available benchmark datasets, including PlantVillage, PlantDoc, AI Challenger, Cassava Leaf Disease, and Rice Leaf Disease datasets, are discussed in terms of dataset diversity, annotation quality, and practical applicability. Furthermore, image preprocessing techniques, data augmentation methods, evaluation metrics, and deployment considerations for mobile and edge devices are comprehensively reviewed. The paper identifies current research challenges, including dataset imbalance, environmental variability, model interpretability, computational complexity, and limited real-world generalization. Finally, emerging research directions such as explainable artificial intelligence, federated learning, multimodal learning, self-supervised learning, lightweight architectures, and edge AI are discussed to provide future research opportunities. This review serves as a valuable resource for researchers, practitioners, and agricultural technologists interested in developing robust, scalable, and intelligent plant disease identification systems.

Why it matches plant phenotyping methods植物葉の病害状態を画像から識別する深層学習手法を中心に、モデル、データセット、評価、展開を体系的にレビューしており、植物表現型計測手法のレビューに該当する。

abstractThis review presents a comprehensive analysis of recent developments in deep learning techniques for plant leaf disease identification.

A two-stage fine-tuning strategy for 3D object segmentation from multi-view images ↗

Neural Radiance Fields (NeRF) have been widely adopted for reconstructing high-quality 3D scenes from 2D RGB images. However, achieving accurate 3D object segmentation within these reconstructed scenes remains challenging. Existing NeRF-based segmentation methods either rely on post-processing (SA3D), which produces noisy point clouds due to the absence of density field optimization, or employ joint training with additional segmentation heads (FruitNeRF), which can lead to suboptimal performance due to conflicting learning objectives. In this work, we propose InvNeRF-Seg (Input-substitution NeRF for Segmentation), a two-stage fine-tuning strategy for 3D object segmentation that preserves the original NeRF architecture and loss function entirely. We first train a standard NeRF on RGB images and then fine-tune it using 2D segmentation masks formatted as RGB-like inputs, without introducing any architectural modifications or additional loss functions. This input-substitution approach reshapes the density field to align with object regions while suppressing background density. We validate InvNeRF-Seg through comprehensive ablation studies examining the roles of density and color MLPs, loss function choices, and training strategies. Field density analysis reveals consistent semantic refinement: densities of object regions increase while background densities are suppressed. Experiments on synthetic fruit datasets and real-world soybean imagery demonstrate that InvNeRF-Seg produces cleaner 3D segmented point clouds compared to both SA3D and FruitNeRF, enabling more accurate downstream object counting. The method is further validated on a self-collected soybean dataset to demonstrate its applicability in real-world agricultural scenarios. Our code is available at https://github.com/ZJiangsan/InvNeRF-Seg .

Why it matches plant phenotyping methods植物画像から3D物体領域を抽出するNeRFベース手法の開発・比較検証が中心で、果実・ダイズ画像を対象に物体カウントへ応用しているため、植物器官の形態・数量推定に関わるフェノタイピング手法として含める。

abstractIn this work, we propose InvNeRF-Seg (Input-substitution NeRF for Segmentation), a two-stage fine-tuning strategy for 3D object segmentation

Image-based trait extraction of Chenopodium quinoa grown under salinity and drought stress. ↗

Above ground crop traits provide an early indication of a plant's capacity to tolerate stress, and are important for breeding programs aimed at improving stress tolerance. In this work, we present a high-throughput methodology to study morphological and physiological traits of individual quinoa plants over time under control, drought, and saline conditions. We used daily sideview imaging of individual plants, followed by segmentation of the panicle, leaf and stem using the deep learning U-Net++ segmentation model. The resulting segmentations were used in regression models to estimate leaf area, fresh and dry biomass, and leaf dry weight. The regression models showed high predictive accuracy. Using these estimates, we could calculate specific leaf area and leaf weight ratio. In addition, radiation use efficiency for above-ground biomass production was calculated, providing an independent physiological check on the consistency of these predictions. Finally, using automated measurements of plant transpiration we were able to determine daily averages of whole plant stomatal conductance. The results show that image-derived morphological traits can be used to accurately estimate biomass-related traits and to derive physiologically meaningful indicators of plant performance over time. This method provides a framework for non-destructive monitoring of quinoa responses to drought and salinity.

Why it matches plant phenotyping methods画像取得、深層学習セグメンテーション、回帰による植物形質推定を中核とする高スループット表現型解析手法であり、ストレス実験での単なるルーチン測定ではない。

abstractwe present a high-throughput methodology to study morphological and physiological traits of individual quinoa plants over time

DINO-Pheno-Cluster: Integrating few-shot foundation models and UAV time-series for spatiotemporal growth and functional characterization of alfalfa ↗

Precise characterization of alfalfa growth dynamics is essential for breeding accessions with superior regrowth capacity, persistence, and yield stability. However, traditional plot level and coarse scale observations suffer from low signal to noise ratios particularly before canopy closure when phenotypic data are strongly affected by weeds and soil background. Moreover, existing studies rarely capture the dynamic mechanisms of crop development across the entire growth cycle. To address this, the DINO-Pheno-Cluster framework is introduced as a foundation model driven and mechanism decomposed phenotyping approach. This decoupled framework first utilizes DINO-XMem, a few-shot individual plant segmentation network based on DINOv3 and a dual memory mechanism. It subsequently applies parameterized dynamic modeling guided by growth process knowledge. Validation utilized high frequency Unmanned Aerial Vehicle (UAV) imagery from 12 time points across three growing seasons covering 127 alfalfa accessions. DINO-XMem achieved an 89.54% mean Intersection over Union (mIoU) under a 10-shot setting and maintained 86.77% under extreme 1-shot conditions. It successfully resolved dense canopy oversegmentation outperforming fully supervised baselines by 4.08% to 11.97% in mIoU. Crucially, the extracted high purity time series trajectories were parameterized into specific biological indicators including maximum growth rate, comprehensive regeneration index, and seasonal stability index. Gaussian Mixture Model (GMM) clustering based on these mechanistic traits identified four distinct functional ideotypes comprising High yield/High regrowth, Upright/Sparse, High stability/Persistent, and Short/Dense, all validated by ground measured biomass. This workflow establishes a precision screening tool for multi harvest crops advancing crop phenomics toward process level analysis.

Why it matches plant phenotyping methods植物の時系列UAV画像から個体を分割し、成長・再生・安定性などの形質を抽出するフェノタイピング手法の開発と検証が中心である。

abstractthe DINO-Pheno-Cluster framework is introduced as a foundation model driven and mechanism decomposed phenotyping approach

Monitoring Station for Agriculture Image Acquisition and Automatic Information about Plant ↗

Abstract The present work deals with Computer Vision precision in the agriculture domain designed to monitor the height variation of plants (h) and the percentage of Ground Cover (PGC). It brings together electronics and Computer Vision. the electronic part consists of two sensors: the first is the DHT11 sensor, which will monitor environmental parameters (temperature, humidity), and the second sensor is a camera (5 MP Raspberry Pi Camera Module Rev 1.3) which monitors the image acquisition to capture visual information about plants and Raspberry Pi 4 as the central processing unit for environmental data. For the Computer Vision part we have developed an algorithm able to do the acquisition and the segmentation of images acquired using Raspberry Pi 4 in real time.

Why it matches plant phenotyping methods植物の高さと地被率を画像取得・セグメンテーションで推定する監視システムおよびアルゴリズムが中心であり、植物フェノタイピング手法として適格です。

abstractdesigned to monitor the height variation of plants (h) and the percentage of Ground Cover (PGC)

Quantitative morphological analysis of Szechuan pepper oil glands: a framework integrating 3D reconstruction and point cloud segmentation ↗

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

Why it matches plant phenotyping methods3D再構成と点群セグメンテーションを統合した植物器官（油腺）の定量形態解析フレームワークが題名上の中心であり、植物形質の取得・抽出手法に該当する。

titleQuantitative morphological analysis of Szechuan pepper oil glands: a framework integrating 3D reconstruction and point cloud segmentation

Todo Fir Crown Instance Segmentation in Dense Plantation Forest Using Polar-FFT and Treetop Queries ↗

Abstract. Monitoring individual trees from unmanned aerial vehicle (UAV)-derived orthomosaics and digital surface models (DSMs) is important for forest management, but instance segmentation remains difficult in dense planted forests in Japan, where Structure from Motion (SfM)-derived DSMs often exhibit blurred crown boundaries, noise, and substantial variation in quality. Existing approaches can benefit from treetop information, but they are sensitive to threshold selection and may introduce false positives when incorrect treetop candidates are provided. To address this problem, we propose a method based on the polar coordinate transform and the fast Fourier transform (PFFT) that represents the local DSM shape around treetop candidates as compact descriptors and integrates them into Mask2Former. The descriptors are used both to suppress low-reliability candidates and to provide spatially meaningful treetop queries to the decoder, thereby improving the separation of adjacent crowns. We evaluated the method on Abies sachalinensis (Todo fir) plantation data acquired at two sites in Hokkaido, Japan, using Mask R-CNN and Mask2Former as baselines. Compared with standard Mask2Former, the proposed method improved mAP50 from 90.14% to 90.87%, mAP75 from 52.18% to 55.47%, and the F1 score at a confidence threshold of 0.5 from 89.86% to 92.08%. It also reduced the number of false positives by 41% without increasing false negatives. Qualitative results showed fewer over-merged crowns and better crown-boundary delineation. These results indicate that treetop-centered local shape cues are effective for instance segmentation in densely planted forests, although further validation across additional species and regions is needed.

Why it matches plant phenotyping methodsUAV由来データから個体樹冠を分離・ delineate する画像解析手法を開発し、複数ベースラインと定量比較しているため、植物形態計測法が中心である。

abstractwe propose a method based on the polar coordinate transform and the fast Fourier transform (PFFT) that represents the local DSM shape around treetop candidates as compact descriptors and integrates them into Mask2Former.

EcoMorph: Universal morphological trait quantification from natural language prompts for ecological research ↗

1. Morphological traits such as floral area and body size are fundamental to ecological research, serving as inputs for studies of pollinator–plant interactions, habitat quality, and biodiversity monitoring. However, accurately measuring these traits from images remains challenging, particularly in complex field conditions where existing tools exhibit reduced accuracy and limited generalizability across taxa. 2. We present EcoMorph, a modular morphological measurement system that leverages the Segment Anything Model 3 (SAM3) to quantify traits across diverse ecological contexts. Unlike task-specific segmentation models requiring domain-specific training data, SAM3's prompt-based architecture enables segmentation of arbitrary biological structures from natural-language prompts, using the same underlying model across flowers, insects, and other targets without retraining. From the resulting segmentations, EcoMorph extracts three classes of measurement: area, linear dimensions, and object count. 3. We validated EcoMorph across two ecological scales. At the intermediate scale, EcoMorph-derived floral area agreed closely with manual ImageJ measurements (R² = 0.935, n = 74) under simple-background conditions and (R² = 0.928, n = 58) under complex-background conditions, with valid predictions for 95% of images. At the fine scale, EcoMorph-derived insect body area was strongly correlated with hand-measured intertegular distance (r = 0.810, n = 349), capturing body-size variation across species from the small Bombus impatiens to the large Xylocopa virginica. Object counts matched manual counts almost exactly for well-separated insects in an insect box (R² = 1.000, n = 12). 4. By combining prompt-based segmentation with modular measurement, EcoMorph enables high-throughput quantification of area, size, and count from heterogeneous image sources without taxon-specific training. This generality supports a broad range of ecological applications, including pollinator and plant trait research, biodiversity and abundance monitoring, and allometric biomass estimation.

Why it matches plant phenotyping methods植物の花の面積を画像から定量する汎用手法を開発し、手動測定と検証しているため、植物フェノタイピング手法が中心である。

abstractWe present EcoMorph, a modular morphological measurement system that leverages the Segment Anything Model 3 (SAM3) to quantify traits across diverse ecological contexts.

Low-cost monocular RGB-based 3D structural mapping for horticultural plants via semantic scene completion ↗

Precision agriculture increasingly relies on detailed structural information, such as canopy height and canopy volume, to enhance crop health monitoring and operational safety. However, existing methods based on costly LiDAR or RGB-D sensors are often impractical for large-scale deployment in dynamic and unstructured horticultural environments. Furthermore, conventional 2D segmentation and SLAM-based pipelines typically generate sparse, geometrically inconsistent semantic maps which are insufficient for actionable structural analysis in agricultural applications. To overcome these limitations, we propose a monocular 3D structural mapping framework tailored for horticultural plants via semantic scene completion. At inference, the proposed model takes a single RGB image as input and predicts voxel-wise geometry and semantics, from which task-oriented structural maps, including canopy height, canopy volume, and obstacle-aware traversability layers, are derived. Specifically, we first introduce a Depth-Aware Decoder Module that explicitly recovers depth in the spatial domain and fuses 2D-to-3D features, thereby mitigating depth ambiguity and reducing reliance on accurate pose. Second, an NCS-Guided Geometry Encoder is designed to inject normalized depth into voxel positional embeddings, enabling self-attention to perform global relational modeling within a depth-aware geometric coordinate system. In addition, a Global Encoder is utilized to refine local structural details, while an occupancy head produces the final 3D semantic completion outputs. We construct a horticultural 3D semantic scene dataset using an RGB-D sensor, which serves as a benchmark for evaluating our method, while the deployed model remains RGB-only. Extensive quantitative and qualitative experiments are conducted on both the Semantic-KITTI dataset and our dataset. On our dataset, the method achieves 82.31% occupancy IoU, 84.26% mIoU, and 86.25% precision. Beyond voxel-level evaluation, manual field measurements further show canopy height MAE values of 0.019-0.026 m and canopy volume proxy relative errors of 8.4%-11.4%. These results demonstrate the effectiveness of our approach in real-world agricultural scenarios, providing actionable structural insights for crop monitoring and autonomous robotic operations.

Why it matches plant phenotyping methods単眼RGB画像から植物の樹冠高・樹冠体積などの構造形質を推定する3Dフェノタイピング手法を開発し、データセット構築と実測検証も行っているため、方法が研究の中心である。

abstractwe propose a monocular 3D structural mapping framework tailored for horticultural plants via semantic scene completion.

A Multiscale Feature Fusion Framework for Plant Leaf Disease Segmentation ↗

.

Why it matches plant phenotyping methods植物葉の病害領域を画像からセグメンテーションする手法が題名で明示されており、病害状態の画像ベース推定が中心と判断できる。抄録がないため詳細な検証内容は不明だが、手法開発研究として採用する。

titleA Multiscale Feature Fusion Framework for Plant Leaf Disease Segmentation

Privileged-depth modulation for close-range pepper organ segmentation in precision crop spraying ↗

Smartphone-based precision spraying aims to restrict chemical application to target organs, but it also requires an organ-level perception model that operates on RGB alone at deployment, without dedicated depth sensors. Combining with monocular depth foundation models such as Depth Anything V2, RGB images can be enriched with dense pseudo-depth during training, turning close-range crop segmentation into a privileged-depth-guided learning problem where depth is available at training but absent at inference. Based on such close-range handheld capture, intra-foreground depth separability collapses while only the foreground–background depth gap remains partially preserved, exposing an imaging regime that we refer to as Close-Range Depth Degeneracy (CRDD) and that undermines the discriminative value of monocular depth for organ segmentation. Even with the available privileged-depth signal, existing RGB-D fusion and depth-branch hallucination routes still either introduce inference-time depth dependence or fail to retain the depth-conditioned effect inside RGB-side parameters under CRDD. How monocular pseudo-depth can serve as training-only privileged information for RGB-only close-range crop spraying under CRDD remains insufficiently studied. To this end, this paper proposes a privileged-depth modulation framework, MDM-Seg, by converting monocular depth from an inference-time modality into a CRDD-conditioned training signal to remove the inference-time depth dependence. Specifically, we characterize CRDD and propose a four-indicator depth-usability diagnostic that delivers a pre-training verdict on the target dataset, with verdicts validated against post-training segmentation outcomes. Then, we formalize the CRDD-conditioned training intervention as a depth-conditioned affine network (DepAN) that injects depth-gradient cues into decoder features, and define a depth hard-pixel mining loss (DHPM) to reweight per-pixel cross-entropy with depth-value evidence, both operating inside the main segmentation stream. Finally, we deploy MDM-Seg on RGB input alone and derive a lightweight consistency trace between the RGB-only and depth-conditioned heads, producing an image-level reliability cue for targeted-versus-fallback spraying without depth at inference. Extensive experiments on Pepper-Field-3940 demonstrate that our MDM-Seg achieves effective depth-conditioned RGB-only segmentation under CRDD, i.e., depth-conditioned modulation retained inside RGB-side parameters with no inference-time depth dependence, such as mIoU 0.8995 with the ResNet-101 configuration ( + 3.73 pp over the RGB-only DeepLabV3+ baseline), a lightweight training-side DepAN module, and an image-level reliability cue rank-correlated with segmentation quality (Spearman ρ = 0.74 ). On a Jetson Orin NX 16 GB with TensorRT FP16, the complete deployment-oriented MobileNetV2 dual-head prescription pipeline runs at 23.87 ms per image, corresponding to 41.89 FPS, 0.62 GB peak memory, and 0.56 J per image.

Why it matches plant phenotyping methods植物器官の画像セグメンテーション手法を開発・評価し、散布対象器官の状態をRGB画像から推定することが中心であるため。

abstractthis paper proposes a privileged-depth modulation framework, MDM-Seg

Deep learning based groundnut and paddy leaf disease classification using dual attention network. ↗

Plant diseases are crucial for improving crop yield and ensuring sustainable agricultural practices, particularly for staple crops such as groundnut and paddy leaf. However, existing methods often suffer from limited feature discrimination, inadequate attention to disease-affected regions, and reduced performance under real-world conditions. To address these limitations, this research introduces a novel deep learning (DL)-based GOPI-NET framework for precise groundnut and paddy leaf disease classification. Initially, the input leaf images are enhanced using Bilateral Filtering (BF) and Contrast Limited Adaptive Histogram Equalization (CLAHE) to reduce noise and improve contrast. Subsequently, HSV color space segmentation is employed to precisely isolate disease-affected regions. The proposed Dual Attention Network (DuAtNet) integrates channel and spatial attention mechanisms within a ConvNeXt backbone to capture discriminative disease-specific features. An efficient Fuzzy Extreme Learning Machine (FELM) classifier is then utilized for final categorization into Healthy, Leaf Spot, Bacterial Wilt, and Leaf Blight classes. The effectiveness of the GOPI-NET is evaluated using precision, recall, specificity, accuracy, and F1-score. The experimental results demonstrate that GOPI-NET achieves an overall accuracy of 98.32%. The GOPI-NET improves classification accuracy by 1.29%, 1.40%, and 2.23% compared to GLDICCNN, DNN-CSA, and LeafNet respectively.

Why it matches plant phenotyping methods植物葉画像から病斑領域を抽出し、病害状態を分類する深層学習手法が研究の中心であり、植物病害表現型の取得・推定に該当する。

abstractthis research introduces a novel deep learning (DL)-based GOPI-NET framework for precise groundnut and paddy leaf disease classification.

Maturity and size estimation with yield mapping for hydroponic strawberries using machine vision ↗

Strawberry production in hydroponic systems requires precise and spatially explicit information on fruit load, maturity, and size to support harvest planning and quality control. This study presents an integrated computer vision and GNSS RTK framework that detects individual strawberries, estimates their maturity and physical dimensions, assigns fruits to operational size–maturity categories, and generates high-resolution yield maps in an open-field hydroponic system. RGB-D images are processed with YOLOv8-seg and a BoT-SORT-based tracking module to obtain instance-level masks, from which a color-based ripeness index and 3D point clouds are derived. After DBSCAN-based filtering, fruit length and width are computed in metric space and combined with ripeness percentage to assign each strawberry to one of nine operational size–maturity categories using predefined threshold rules. The system was evaluated in a commercial hydroponic crop in Arcabuco, Boyacá, Colombia, achieving accurate segmentation, with median IoU values up to 0.83 for bounding boxes and 0.71 for masks, and mean absolute errors of 2.51 mm in length and 1.85 mm in width with respect to Vernier caliper measurements. Yield maps aggregated in 1 m2 cells and by crop row revealed marked spatial variability in fruit density, maturity state, and size–maturity composition, allowing the identification of zones with a high concentration of fruits ready for harvest versus areas dominated by immature fruits. The proposed framework provides a practical and low-cost decision support tool for hydroponic strawberry management and may be adapted to other high-value horticultural crops after recalibration under different crop architectures, cultivars, and environmental conditions.

Why it matches plant phenotyping methodsRGB-D画像と追跡・3D解析により、イチゴ果実の成熟度、寸法、果実密度および収穫状態を個体レベルで推定し、精度検証も行う中心的なフェノタイピング手法研究である。

abstractThis study presents an integrated computer vision and GNSS RTK framework that detects individual strawberries, estimates their maturity and physical dimensions, assigns fruits to operational size–maturity categories, and generates high-resolution yield maps in an open-field hydroponic system.

Comprehensive plant disease classification and severity estimation for sustainable farming via automatic segmentation and multi-scale feature fusion ↗

Abstract Detecting plant leaf diseases at an early stage is one of the most important requirements for sustainable agriculture, increasing crop productivity, and achieving the global Sustainable Development Goals (SDGs). However, accurately recognizing them in real-world farm fields can still be difficult due to factors such as background complexity, changes in light conditions, and very similar looking classes from a visual standpoint. In order to solve these problems, the authors here present a new Multi-Scale Feature Fusion (MSFF) model that can offer robust and highly accurate performance in identifying plant leaf diseases. Firstly, the brand new hybrid method starts with a U-Net segmentation designed exclusively to separate the diseased parts and thus allow the classification to be more robust. Next, Rank Order Fuzzy (ROF) is implemented to get rid of the background while still maintaining the edges, and the additional data is used for the network to generalize better. The color distribution is then analyzed to determine the variations in color brought about by the infection. In terms of features, EfficientNet is paired with an Attention-based Autoencoder to produce both spatially detailed global features and compact latent representations. The two sets of features are then combined through Canonical Correlation Analysis (CCA) which not only identifies the dependencies between the features but also enhances the discriminative strength. The final fused feature set is fed to module based on YOLO for detection and classification in order to obtain the final result of the plant disease identification system which is both accurate and fast. Among other datasets, the model has been tested on different apple leaf datasets such as FGVC7, AppleLeafSet, PlantVillage Apple, Kaggle Apple Leaves, and ATLDSD, which contain five disease classes. The results of the experiments indicate a classification accuracy of 99.95%, thus the model is superior to several state-of-the-art deep learning and classical machine learning methods. Statistical methods like five-fold cross-validation, paired t-tests ( p

Why it matches plant phenotyping methods植物葉の病変部位を画像から自動抽出し、病害の識別・分類を行う画像ベースのフェノタイピング手法を開発・評価しており、手法が研究の中心である。

abstractthe authors here present a new Multi-Scale Feature Fusion (MSFF) model that can offer robust and highly accurate performance in identifying plant leaf diseases

Plant Leaf Disease Detection Using Machine Learning and Deep Learning: A Review and Experimental Study ↗

India’s economy is primarily based on agriculture. Agriculture has significant contribution in nation’s GDP. Food security and employment significantly influenced by agriculture. However factors like uncertain weather conditions, poor quality of seeds and plant diseases impact on agriculture productivity. Computer vision and DL algorithms are most crucial components of precision agriculture. Early detection can improve decision making, maximize pesticide use, and preserve harvests. Using CNN architectures, segmentation-based approaches, handcrafted feature-based methods, and hybrid approaches incorporating Machine Learning and Deep Learning this study seek to provide review of recent publications from 2020 to 2026. The review was carried out using a variety of publications with different datasets, methodologies, and outcomes. The findings show that DL, especially CNN and transfer learning models, performed better than machine learning techniques. It points out several significant problems, such as dataset imbalance, insufficient generalization, computing inefficiency, and a dearth of real-world data. Future research topics are also suggested which includes IoT-driven real-time solutions, lightweight architecture, domain adaption, and multimodal imaging. This review aims to develop plant disease detection technologies that are more dependable, scalable, and field deployable.

Why it matches plant phenotyping methods植物葉の病徴を画像から検出する機械学習・深層学習手法をレビューおよび実験的に扱っており、植物フェノタイピング手法が中心である。

titlePlant Leaf Disease Detection Using Machine Learning and Deep Learning: A Review and Experimental Study

3D micro–X-ray tomography of lumen space in dried stem, branch, and outer tissues of Moringa oleifera: A structural case study ↗

Abstract Moringa oleifera is widely used in dry tropical and subtropical regions due to its rapid growth and high nutritional value, yet its internal tissue organization has primarily been described using two-dimensional anatomical approaches. Here, we present a three-dimensional micro–X-ray computed tomography (micro-XCT) characterization of lumen space in stem, branch, and outer tissues (bark region) from a single M. oleifera individual. Samples were oven-dried prior to imaging; therefore, the quantified void fraction represents apparent lumen/void space in dried material and should not be interpreted as in vivo porosity. Micro-XCT datasets were segmented to quantify cross-sectional lumen area distributions and apparent void fraction from pooled reconstructed slices. All data originate from a single individual; reported metrics represent structural descriptors of pooled cross-sections and not replicated biological measurements. The stem dataset exhibited a dense arrangement of small lumen features and a high number of segmented objects, consistent with a compact woody tissue organization in the scanned region. The branch dataset showed a larger proportion of void space and a strongly right-skewed size distribution with a minority of large lumen features. The outer tissue dataset displayed heterogeneous void space organization, which likely reflects a mixture of cell lumens, intercellular spaces, and drying-related cracks, and therefore is reported descriptively without assigning xylem-vessel identity. This study provides a conservative 3D structural dataset and an image-analysis workflow for quantifying lumen space in dried M. oleifera tissues, complementing published anatomical descriptions. The results highlight strong within-plant heterogeneity across tissue types and underscore the importance of sample preparation and histological validation when interpreting micro-XCT measurements in woody plants.

Why it matches plant phenotyping methods乾燥植物組織の3D micro-XCT画像から管腔・空隙の構造形質を抽出する画像解析ワークフローとデータセットが研究の中心であり、単なる生物学的測定ではない。

abstractMicro-XCT datasets were segmented to quantify cross-sectional lumen area distributions and apparent void fraction from pooled reconstructed slices.

Quantitative morphological phenotyping of infection structures in cucumber downy mildew and powdery mildew. ↗

Introduction: Cucumber diseases severely affect yield and quality. Deep learning-based analysis of microscopic pathogen images enables high-throughput identification and counting of pathogens, thereby facilitating early disease detection. However, most existing pathogen-recognition methods focus mainly on qualitative identification and cannot quantitatively characterize pathogen morphology, which limits their ability to reveal the developmental characteristics and functional differentiation of different infection structures from the perspective of pathogen morphology-function adaptability. Methods: To address this issue, this study focused on cucumber powdery mildew and downy mildew and achieved precise extraction and characterization of pathogen morphological features based on microscopic image instance segmentation. First, an in situ stained microscopic image dataset of cucumber pathogens was constructed. Second, an instance segmentation model, SWS-YOLO11n, was developed for cucumber pathogen infection structures to accurately identify and segment different infection structures in microscopic images. Finally, morphological analysis methods were used to quantitatively extract and characterize pathogen infection-structure features. Results: values greater than 0.90. In addition, category-wise morphological distribution analysis showed that different infection-structure types exhibited clear differentiation in size, contour complexity, and elongation. Discussion: This study provides an effective tool for high-throughput phenotyping of cucumber pathogen infection structures. The proposed method offers methodological support for disease diagnosis, pathogen morphological phenotyping, and precision disease management in horticultural production.

Why it matches plant phenotyping methods顕微鏡画像のインスタンスセグメンテーションを開発し、キュウリ病原体の感染構造の形態形質を定量抽出する手法が中心である。

abstractan instance segmentation model, SWS-YOLO11n, was developed for cucumber pathogen infection structures to accurately identify and segment different infection structures in microscopic images.

Double Transfer Learning-Based Capsule Network for Multi-Crop Plant Disease Classification Using Heterogeneous Leaf Image Datasets ↗

Abstract Crop disease is a major worldwide problem in agricultural production and food security, adversely affecting yield and quality for a variety of plant species. To overcome these drawbacks, this research provides a Double Transfer Learning-based Capsule Network (DTL-CapsNet) approach for automated plant disease classification with multiple crops. Based on the image pre-processing, segmentation, double transfer learning, and Capsule Networks technologies, the proposed framework extracts discriminative features of the diseases and maintains spatial relations between the leaves symptoms effectively. This double transfer learning approach involves extracting general visual features from pre-trained deep learning models and then fine-tuning these features to classify plant diseases. Capsule Networks then leverage the visual similarity of disease patterns to make the recognition more robust, while simultaneously adding hierarchical part–whole relationships in leaf structures, thereby improving the feature representation. Experiments were performed on a heterogeneous data set consisting of 21,927 leaf images belonging to 17 different healthy and diseased classes of apple, chilli, cotton, corn and potato crops. The experimental results proposed DTL-CapsNet framework is more accurate compared to the traditional CNN-based models and conventional transfer learning models. The proposed method of double transfer learning and Capsule Networks offers an efficient and scalable approach for intelligent plant disease diagnosis, offering significant potential in precision agriculture and real-time crop monitoring systems.

Why it matches plant phenotyping methods葉画像から植物病害状態を分類する画像・計算手法が研究の中心であり、提案手法の開発と既存モデルとの比較検証が行われているため。

abstractBased on the image pre-processing, segmentation, double transfer learning, and Capsule Networks technologies, the proposed framework extracts discriminative features of the diseases and maintains spatial relations between the leaves symptoms effectively.

RootHairAreaFinder: an image processing method for quantifying barley root growth and root hairs simultaneously in a flat rhizotron system. ↗

Root system architecture and root hairs highly influence plant resource uptake, yet their simultaneous quantification at the whole-plant scale remains challenging due to the conflicting requirements of high-resolution imaging and non-destructive, repeated measurements. Here, we present a plant growth and imaging system based on A3 sized flatbed rhizotrons, combined with a non-machine-learning image analysis workflow implemented in R, that enables repeated, in situ quantification of barley root system architecture and accompanied visible projected root hair area (VP root hair area) over three weeks of growth. The system produces integrated outputs highlighting both whole-root architecture and the spatial distribution of surrounding root hairs from single images. Validation of the image analysis algorithm showed good segmentation performance, with average Matthews Correlation Coefficient values of 0.68 for projected root area and 0.65 for VP root hair area. To demonstrate its experimental applicability, the system was used to assess root growth and root hair responses under controlled environmental conditions, combining three irrigation regimes (2, 4, and 6 irrigation events per day) with three dry bulk density levels (1.4, 1.5, and 1.6 g cm -3 ). In addition to whole-system metrics, the approach enables analysis of root hair expansion at individual root tips. This methodology provides a training-free method for integrated analysis of root traits e.g. projected root size, root growth, root diameter and root hairs under controlled physical conditions similar to soil, facilitating studies of root-soil interactions that require both spatial resolution and temporal continuity.

Why it matches plant phenotyping methods根系形態と根毛面積を画像から定量する画像解析ワークフローおよび生育・撮像システムを開発し、アルゴリズム性能も検証しているため、植物フェノタイピング手法が中心である。

abstractwe present a plant growth and imaging system based on A3 sized flatbed rhizotrons, combined with a non-machine-learning image analysis workflow implemented in R

Bayesian optimized color filter: A fast method for segmentation of plant phenotypes from 3D point cloud images ↗

Abstract Multispectral three‐dimensional (3D) imaging offers substantial potential for plant phenotyping, yet manual segmentation of plant organs remains a bottleneck in breeding programs. We developed a color‐based filtering workflow for faba bean ( Vicia faba L.) point clouds that optimizes lower and upper thresholds of spectral indices and broadband brightness via Bayesian optimization. Rather than maximizing geometric segmentation accuracy, thresholds are selected to maximize correlations between retained points and yield‐related traits, outperforming manual filtering, reducing user effort, and standardizing decisions. Across multispectral 3D point clouds, Bayesian optimization recovered index‐specific threshold ranges that yielded strong in‐sample correlations with grain yield ( r = 0.72), bean number ( r = 0.61), pod number ( r = 0.53), and straw biomass ( r = 0.72). Peak associations occurred at harvest for straw biomass, at 41 days before harvest (DBH) for seed yield, 33 DBH for bean number, and 34 DBH for pod number. Across the season, greenness‐based indices and broadband brightness metrics consistently showed stronger links with seed yield than pigment ratio or water status indices. For straw biomass and pod number, pigment ratio indices showed consistently lower correlations. Targeting trait‐relevant canopy signals via Bayesian optimization enables reliable, nondestructive assessment of relationships between spectral signals and yield‐related traits in faba bean. By optimizing thresholds to maximize trait correlations rather than geometric accuracy, the workflow can support earlier, more cost‐efficient identification of high‐performing genotypes under drought stress and contribute to strengthening high‐throughput phenotyping in breeding programs. This enables faster identification of canopy signals most relevant to target traits.

Why it matches plant phenotyping methods植物の3D点群画像から表現型を抽出するセグメンテーション手法を開発し、ベイズ最適化による閾値選択と性能評価を行っており、フェノタイピング手法が研究の中心である。

abstractWe developed a color‐based filtering workflow for faba bean ( Vicia faba L.) point clouds that optimizes lower and upper thresholds of spectral indices and broadband brightness via Bayesian optimization.

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

UAV-Derived Multispectral Datasets and Index-Guided Segmentation for Maize Water Stress and Common Rust Detection Under Real Field Conditions ↗

The segmentation model achieved Mean IoU values of 0.7723 for Water Stress 2025, 0.9164 for Common Rust 2025, and 0.9531 on the benchmark dataset. The classifier achieved 99.54% accuracy for the five-class task; however, the improvement over the strongest baselines and the RGB + multispectral configuration was limited. Therefore, the classification component is not presented as a substantially superior classification-only model. Instead, it is interpreted as an exploratory multimodal analysis that quantifies the contribution and limitation of RGB, multispectral, Wavelet, and GLCM branches under the adopted UAV dataset protocol. For classification-only deployment, simpler alternatives such as DenseNet201 or the RGB + multispectral configuration may be more practical because they provide comparable accuracy with lower architectural or preprocessing complexity. Ablation, modality-controlled, and 21-run stability experiments showed reproducible segmentation results and clarified the behavior of the classification branches. RGB and multispectral branches mainly provided the peak classification accuracy, whereas Wavelet and GLCM branches mainly affected offline convergence rather than final accuracy. RGB, NDVI, and NDRE visualizations were also added for qualitative support. Since direct physiological ground measurements were not available for all samples, the masks are interpreted as adaptive index-guided labels rather than direct physiological ground truth. Overall, the main evidence of practical benefit is associated with UAV-based dataset construction, adaptive index-guided segmentation, and field-scale stress/disease mapping, while the classification experiments should be interpreted as modality-contribution and convergence analyses rather than proof of a practically superior complex classifier.

Why it matches plant phenotyping methodsUAVマルチスペクトル画像によるトウモロコシの水ストレス・病害状態のセグメンテーション、データセット構築、再現性評価が研究の中心であり、植物表現型の取得・抽出手法として実質的です。

abstractOverall, the main evidence of practical benefit is associated with UAV-based dataset construction, adaptive index-guided segmentation, and field-scale stress/disease mapping

From Benchmark Accuracy to Field Performance: Hybrid Deep Learning-Based Plant Disease Classification with IoT-Enabled Environmental Monitoring ↗

Accurate detection of plant leaf diseases is essential for enhancing crop productivity and supporting global food security. In addition to disease classification, understanding how environmental and soil conditions affect model performance is important for developing robust real-world agricultural monitoring systems. Although deep learning (DL) models achieve high accuracy on benchmark datasets, their performance in real-world settings is often limited by variations in illumination, background complexity, and environmental conditions. This study proposes a smart DL framework for detecting and classifying multiple leaf diseases in tomato, potato, and pepper plants. The framework combines U2-Net-based leaf segmentation with a Convolutional Neural Network–Bidirectional Gated Recurrent Unit (CNN–Bi-GRU) architecture. MobileNetV2 is employed as the feature extraction backbone to capture spatial characteristics, while Bi-GRU layers model sequential feature dependencies, forming a spatio-temporal network whose architectural design prioritizes parameter efficiency through depthwise separable convolutions and reduced gating complexity. The model was trained and validated using the PlantVillage benchmark dataset and achieved a classification accuracy of 99.8% with a macro-averaged F1-score of 94%, outperforming several state-of-the-art architectures. To assess robustness under real-world conditions, the trained model was further tested on leaf images collected from open-field environments near Eluru, South India. The field evaluation revealed a reduction in classification accuracy to 61.97%, indicating the impact of domain shift and environmental variability. To investigate potential contributing factors, soil parameters, including pH, temperature, moisture, and NPK levels, were monitored using an IoT-based Arduino sensing system over ten consecutive days. Rather than serving as direct inputs to the disease classification model, these environmental measurements were analyzed to assess their potential influence on disease symptom expression and the observed reduction in model performance under field conditions. The results suggest that environmental conditions may influence disease symptom expression and model transferability. This study highlights the importance of integrating DL-based disease recognition with environmental monitoring for reliable field-level agricultural applications. Nevertheless, computational complexity metrics, including inference latency and memory footprint, were not evaluated in the present work and are identified as a priority for future edge deployment studies.

Why it matches plant phenotyping methods植物葉の病徴を画像から分類するセグメンテーション・深層学習手法を開発し、ベンチマークと圃場画像で性能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 proposes a smart DL framework for detecting and classifying multiple leaf diseases in tomato, potato, and pepper plants.

In-Field 3D Wheat Head Instance Segmentation from TLS Point Clouds Using Deep Learning without Manual Labels ↗

Abstract. 3D instance segmentation for laser scanning (LiDAR) point clouds remains a challenge in many remote sensing-related domains. Successful solutions typically rely on supervised deep learning and manual annotations, and consequently focus on objects that can be well delineated through visual inspection and manual labeling of point clouds. However, for tasks with more complex and cluttered scenes, such as in-field plant phenotyping in agriculture, such approaches are often infeasible. In this study, we tackle the task of in-field wheat head instance segmentation directly from terrestrial laser scanning (TLS) point clouds. To address the problem and circumvent the need for manual annotations, we propose a novel two-stage pipeline. To obtain the initial 3D instance proposals, the first stage uses 3D-to-2D multi-view projections, the Grounded SAM pipeline for zero-shot 2D object-centric segmentation, and multi-view label fusion. The second stage uses these initial proposals as noisy pseudo-labels to train a supervised 3D panoptic-style segmentation neural network. Our results demonstrate the feasibility of the proposed approach and show performance improvements relative to Wheat3DGS, a recent alternative solution for in-field wheat head instance segmentation without manual 3D annotations based on multi-view RGB images and 3D Gaussian Splatting, showcasing TLS as a competitive sensing alternative. Moreover, the results show that both stages of the proposed pipeline can deliver usable 3D instance segmentation without manual annotations, indicating promising, low-effort transferability to other comparable TLS-based point cloud segmentation tasks.

Why it matches plant phenotyping methods圃場小麦穂の3D個体セグメンテーションを対象に、TLS点群とゼロショット・マルチビュー融合・擬似ラベル学習を組み合わせた表現型取得手法を開発・評価しており、方法が研究の中心である。

abstractsuch as in-field plant phenotyping in agriculture, such approaches are often infeasible.

Pasture Biomass Monitoring in Queensland Rangelands with UAV and Satellite Cascades ↗

Operational satellite monitoring of pasture biomass demands models that extrapolate beyond the range of properties on which they were calibrated. We show that the dominant failure mode of Sentinel-2 pasture-biomass models in tropical Australian rangelands is the saturation and phenological inversion of greenness-based vegetation indices across sites, and that this failure can be substantially repaired with open climate and topsoil covariates from public archives. The work builds on a hierarchical pipeline that scales clip-and-weigh ground truth (n=1120 tare-corrected samples across eleven sites on five Queensland properties) through UAV digital-surface-model imagery to Sentinel-2 predictions, using TabPFN – a pre-trained transformer foundation model for small tabular data – as the regressor at all three nested spatial scales, and a seven-class deep-learning pasture mask (overall accuracy 98.6 %) to suppress mixed-pixel noise. Under a leave-one-site-out (LOSO) cross-validation protocol on twenty site-date aggregates across nine sites, spectral-only models failed to transfer across sites (R2=−0.21, RMSE=4.79 t ha-1). Appending open climate (Open-Meteo ERA5) and soil (SoilGrids 2.0) covariates, and switching to a gradient-boosted regressor on log-transformed biomass, lifted LOSO R2 to +0.07 and reduced RMSE to 4.19 t ha-1. A leaf-nitrogen growth trajectory, predicted by the TabPFN nitrogen regressor developed in our earlier pasture chemistry work, reduced LOSO error by a further 11 % relative to greenness-only growth features. Three additional covariate classes – BARRA-R2 reanalysis climate, three independent fractional-cover products, and Sentinel-1 C-band SAR backscatter – were tested and rejected, all hitting the same RMSE floor. The symmetric negative results suggest that the residual LOSO ceiling at the current nine-property footprint is a sample-size and sensor-saturation limit rather than a feature-engineering one, and that the most tractable operational path forward is to stratify the production model by climatic zone and Queensland Land Type rather than pursue further covariates within a single global learner. Expanding UAV calibration footprints and integrating open climate, soil and plant-chemistry data are complementary, not competing, investments for operational rangeland remote sensing.

Why it matches plant phenotyping methodsUAV・衛星画像、マスク処理、回帰モデルを組み合わせて牧草バイオマスを推定する測定パイプラインを構築し、サイト外交差検証で性能評価しているため、植物形質取得手法が中心である。

abstractThe work builds on a hierarchical pipeline that scales clip-and-weigh ground truth (n=1120 tare-corrected samples across eleven sites on five Queensland properties) through UAV digital-surface-model imagery to Sentinel-2 predictions

PhenoNEST: A Neuro-Symbolic Framework for Ontology-Aware Multimodal Plant Phenotyping and Trait Discovery ↗

High-throughput plant phenotyping generates valuable data that often remains trapped in unstructured text and isolated RGB images. To bridge this semantic gap, we propose a framework for constructing a multimodal granular Knowledge Graph (KG) to monitor genotype-phenotype interactions across time and experiments. In this work, we focus on wheat Triticum aestivum as a representative target crop to validate our methodology across complex canopy environments. Our pipeline first distills noisy field notes to extract entities and relations, dynamically constructing the KG by converting unique instances into hierarchical class entities via RDF-typing. These graph nodes are then aligned with standardized ontologies (PO, RO, WTO) using PlantDeBERTa. To visually ground the constructed graph, a Vision-Language Model paired with a wheat-segmentation ViT generates attention-based softmaps, linking specific KG entities directly to image pixels. We introduce a central observation node Plant_Obs_Id to connect these multimodal subgraphs temporally. Evaluated on 500 curated WisWheat samples using Pointing Game accuracy, Visual Word Sense Disambiguation (VWSD), and rank-based metrics, our neuro-symbolic approach successfully maps complex field observations to a structured graph. This enables automated field note auditing, temporal stress monitoring, and precise spatial trait localization for wheat breeders.

Why it matches plant phenotyping methods植物のマルチモーダル表現型データを知識グラフと画像に統合し、画像画素への形質局在化を行う中核的な計算フレームワークを提案・評価しているため。

abstractwe propose a framework for constructing a multimodal granular Knowledge Graph (KG) to monitor genotype-phenotype interactions across time and experiments

The Turning Point of 3D Plant Phenotyping: 3D Foundation Models Enable Minute-to-Second Cross-Crop Reconstruction and Beyond ↗

3D plant phenotyping is notoriously known to be procedure-complicated and of low throughput due to the extensive multi-view imaging, the fragile 3D reconstruction pipeline, and the additional cost from reconstructed geometry to phenotypic extraction. These limitations are further amplified in low-cost data acquisition, where smartphone videos or sparsely sampled multi-view images provide limited view overlap and self-occlusion. In this work, we show that the conventional 3D plant phenotyping pipeline could be streamlined and significantly accelerated with 3D Foundation Models (3DFMs), and particularly, present one of the first cross-crop 3D phenotyping frameworks powered by 3DFMs. The framework replaces COLMAP-style sparse initialization with 3DFM-based feed-forward geometric recovery, combines geometry-constrained 3D Gaussian Splatting for dense reconstruction, enables few-view reconstruction through iterative view synthesis and refinement, and converts reconstructed geometry into measurable organs through 2D-to-3D semantic transfer, metric scale recovery, and organ instance separation. We further construct a cross-crop dataset with smartphone-based image acquisition, diverse plant morphologies, and manual annotations for segmentation and phenotypic evaluation. Experiments across 26 plant sequences show that 3D Foundation Models reduce the average reconstruction time from 6.52 minutes to 1.58 seconds while maintaining high reconstruction quality and phenotyping accuracy. These results suggest a fresh technical route for high-throughput 3D plant phenotyping, from low-cost image acquisition to fast reconstruction, perception, scale recovery, and phenotypic measurement.

Why it matches plant phenotyping methods3D画像再構成から器官分離・形質測定までを統合した高速植物フェノタイピング手法を開発し、複数作物・データセットで性能評価しているため。

abstractpresent one of the first cross-crop 3D phenotyping frameworks powered by 3DFMs

Leaf area extraction framework: Transformer-based segmentation and geometric-based completion approaches for accurate extraction of field maize leaf area from point clouds ↗

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

Why it matches plant phenotyping methods圃場トウモロコシの葉面積を点群から抽出するセグメンテーション・幾何学的補完手法の開発が題名の中心であり、植物形質の取得方法に該当する。

titleLeaf area extraction framework: Transformer-based segmentation and geometric-based completion approaches for accurate extraction of field maize leaf area from point clouds

A Review of Fruit Tree Canopy Branch Feature Extraction and 3D Reconstruction Algorithms ↗

Accurate perception and 3D reconstruction of fruit tree branch structures are fundamental to smart orchard development, with broad applications in intelligent harvesting, crop phenotyping, and precision management. However, the slender and highly branched morphology, multi-scale distribution, weak surface texture, and severe occlusion inherent to fruit tree branches pose substantial challenges to high-fidelity modeling. This paper systematically reviews advances in branch feature extraction and 3D reconstruction for fruit tree canopies. A structured literature search was conducted using the Web of Science, Scopus, and Google Scholar databases, with search terms including “fruit tree branch”, “point cloud reconstruction”, “3D canopy modeling”, “branch feature extraction”, and “agricultural robotics”. Studies published between 2000 and 2025 were considered, with inclusion criteria requiring relevance to branch structure perception, reconstruction accuracy, or orchard application; non-peer-reviewed sources and studies lacking quantitative evaluation were excluded. We trace the evolution of feature extraction from classical 2D image processing and geometric fitting, through point cloud segmentation and skeleton extraction, to modern deep learning approaches and multimodal perception techniques. For 3D reconstruction, we compare active and passive sensing strategies alongside both explicit and implicit scene representation methods, discussing their respective strengths and applicable scenarios. A five-dimensional evaluation framework is also proposed, encompassing geometric accuracy, structural consistency, feature stability, computational efficiency, and generalization capability. Finally, we identify key bottlenecks in fine-grained structure recovery, occlusion handling, and cross-scene generalization, and highlight future directions in structural prior integration, multimodal collaborative modeling, and lightweight neural representations—offering a structured reference for advancing 3D perception research in smart orchards.

Why it matches plant phenotyping methods果樹の枝構造の特徴抽出と3D再構成を対象とする、植物形態計測・表現型取得手法のレビューであり、方法論が中心です。

abstractThis paper systematically reviews advances in branch feature extraction and 3D reconstruction for fruit tree canopies.

Field estimation of leaf water potential in poplar trees using UAV-based hyperspectral imagery and deep learning ↗

Abstract Climate-change-driven drought intensification increasingly threatens forest ecosystems, highlighting an urgent need for accurate monitoring of forest water stress. Leaf water potential (Ψleaf) is a key integrative indicator, yet conventional measurements are destructive and unsuitable for large-scale or high-frequency monitoring. Hyperspectral remote sensing offers a promising alternative, but robust canopy-level Ψleaf estimation remains constrained by limited labeled data and heterogeneous environmental conditions. Here, we develop a cross-scale framework integrating supervised contrastive learning with deep transfer learning to translate robust leaf-scale pretraining into canopy-scale Ψleaf estimation from hyperspectral data in a Populus × euramericana ‘I-214’ plantation. Hyperspectral imagery was captured at the leaf scale under controlled laboratory conditions (n = 229) and at the canopy scale using a UAV-based platform (n = 200), together with paired Ψleaf measurements. Reflectance consistently increased with declining Ψleaf at both scales, supporting the feasibility of cross-scale modeling. At the leaf scale, physics-consistent spectral augmentation coupled with contrastive learning enhanced feature discrimination and predictive stability under small-sample conditions (R2 = 0.8030). Transfer learning via progressive fine-tuning enabled efficient scaling of the leaf-level pretrained model to canopy-level prediction despite structural and environmental complexity and restricted field data ranges, achieving R2 = 0.7605 and RMSE = 0.1056 MPa. Coupling with individual-tree crown segmentation further enabled spatially explicit mapping of canopy Ψleaf and plot-level forest water stress dynamics. These results demonstrate that combining contrastive representation learning with cross-scale transfer provides a practical pathway for physiological monitoring and scalable, climate-smart forest phenotyping in data-constrained forested environments.

Why it matches plant phenotyping methodsUAVハイパースペクトル画像と深層学習により、ポプラの葉の水ポテンシャルを推定する手法を開発・評価しており、植物生理形質の取得が研究の中心である。

abstractHere, we develop a cross-scale framework integrating supervised contrastive learning with deep transfer learning to translate robust leaf-scale pretraining into canopy-scale Ψleaf estimation from hyperspectral data

Comparative evaluation of precision planter performance via UAV remote sensing: A workflow for maize emergence monitoring ↗

To overcome the inefficiency and subjectivity of manual seedling surveys, this study presents a unsupervised framework for evaluating maize sowing quality and emergence uniformity via UAV-based remote sensing. Centimeter-level multispectral imagery was captured to reconstruct 3D point clouds using SfM and MVS techniques. At the algorithmic level, an improved unsupervised pipeline was developed: the Otsu method was employed for plant segmentation, followed by a Fourier Transform to extract 2D spatial frequency features for precise crop row identification and automated spacing measurement. Subsequently, the Combined Entropy Uniformity (CEU) index was developed using Shannon entropy, and a proxy for canopy closure (CCP) was derived using a porosity model, thereby enabling the simultaneous relative quantification of seedling height consistency, spatial distribution uniformity, and canopy geometric structure variability. At the application level, the framework was validated through field trials involving 19 precision planters of diverse configurations. Performance was assessed using indices such as qualified spacing, miss-sowing, and the Coefficient of Variation of Plant Spacing (PSCV). Results indicate that: (1) Vacuum-type planters exhibited optimal stability at speeds of 7–9 km/h, achieving an average qualified spacing rate of 76.7% and a PSCV of approximately 24%, whereas finger-pickup planters were more sensitive to seed size variation and mechanical vibration. (2) The results from the Generalized Additive Model (GAM) suggest a possible nonlinear relationship between seeding rate and certain uniformity indices, indicating that appropriately adjusting operational parameters could help balance operational efficiency and seeding quality; however, this trend requires further validation with larger sample sizes and repeated observations. (3) Point cloud CEU metrics and canopy structure proxies based on the Gap Fraction model showed statistical correlations with certain manually collected indicators, indicating that this method has the potential for rapid screening of seeding quality and relative evaluation of seedling population structure at the field scale under the current experimental conditions.

Why it matches plant phenotyping methodsUAV画像・3D点群から作物の出芽、草丈均一性、空間分布、群落構造を抽出する解析ワークフローを開発し、19種のプランターで検証しており、植物表現型取得法が中心である。

abstractthis study presents a unsupervised framework for evaluating maize sowing quality and emergence uniformity via UAV-based remote sensing.

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.

AI-Driven Crop Detection and Plant Disease Prediction ↗

Crop disease identification is still a big problem in agriculture, which results in large yield losses and food lacks, especially in regions dependent on manual monitoring. Traditional methods of identifying plant diseases are often labor intensive, error-prone, and ineffective in early-stage diagnosis. To overcome these limitations, this study proposes a hybrid machine learning model for accurate crop type identification, disease classification, and severity prediction using image data. The methodology utilizes the PlantVillage dataset, encompassing over 50,000 annotated leaf images across 14 crops. After rigorous preprocessing involving image resizing, normalization, and cleaning, Improved Deep Joint Segmentation is applied to localize disease-affected regions. Feature extraction incorporates color, texture (GLCM, LBP), and shape attributes to enhance classification accuracy. A hybrid approach integrating XGBoost for feature selection and Support Vector Machine (SVM) for classification is proposed to capture both overarching trends and intricate details. Experimental results across four major crops—potato, tomato, corn, and grape—demonstrate superior performance, with the hybrid model achieving 98.6% accuracy, 98.3% precision, 99.0% recall, and 99.1% F1-score. The model outperforms existing approaches, offering a robust, scalable, and accurate solution for early crop disease detection in precision agriculture.

Why it matches plant phenotyping methods画像から病変領域を抽出し、植物病害の分類と重症度を推定する機械学習ワークフローが研究の中心であり、植物状態の表現型計測に該当する。

abstractthis study proposes a hybrid machine learning model for accurate crop type identification, disease classification, and severity prediction using image data.

Validation of Machine Learning-Based Segmentation for Automated 3D Reconstruction in Electron Microscopy: Application in Life and Materials Science ↗

In recent years, automation of electron microscopy has enabled high-throughput acquisition of large, high-resolution serial-section image volumes. Three-dimensional reconstruction of these data has become essential for visualizing fine structural details in biological and material samples [1]. However, despite rapid advances in automated data acquisition, image analysis remains a major bottleneck. Conventional image processing methods, such as gray-level thresholding and manual annotation, require extensive labor and suffer from reduced reproducibility due to operator subjectivity [2]. To establish a highly efficient three-dimensional measurement workflow from imaging to quantitative analysis, we applied machine-learning (AI) to the most challenging image-analysis step and benchmarked its effectiveness against conventional methods. We prepared serial sections of Chlamydomonas for this evaluation. Continuous serial-section SEM images were acquired using a Hitachi High-Tech scanning electron microscope equipped with Auto Capture for Array Tomography (ACAT) and a focused ion beam scanning electron microscope (FIB-SEM) [3,4]. We performed appropriate sample pretreatment and optimized imaging conditions to clearly visualize the target chloroplast structures, followed by the automatic acquisition of continuous serial-section SEM image stacks. The obtained images were processed by cropping regions of interest, aligning images, adjusting contrast, and applying filters to facilitate structural identification. For segmentation and three-dimensional reconstruction, both a conventional method combining thresholding and manual correction [2] and a machine-learning-based approach (AIVIA, Leica Microsystems) trained on annotated data were employed [5]. In Figure 1(b), the region selected by the conventional method is shown in blue. Regions with contrast resembling that of the U-shaped chloroplast in Chlamydomonas were also selected. In contrast, the deep-learning-based method automatically extracted multi-scale features, such as intensity (gray-level), edges, and curvature, from the annotated regions and classified pixels individually. This facilitated the extraction of chloroplast regions, even in images containing structures with similar contrast (Figure 1(c)). The three-dimensional images reconstructed from the automatically segmented regions (Figures 2(a) and 2(b)) confirmed the presence of large openings and multiple micropores in the chloroplasts. Only 10 out of 60 annotation slices were required, significantly reducing manual annotation time compared to the conventional method. High reproducibility was also achieved in three-dimensional measurements. Furthermore, we acquired continuous serial-section SEM images of HIPS resin and an aluminum alloy using FIB-SEM and performed three-dimensional reconstruction combined with machine-learning-based segmentation. This presentation shows that integrating automated image acquisition with deep-learning-based segmentation streamlines the workflow from acquisition through three-dimensional reconstruction. It presents quantitative evaluation results and demonstrates the method’s utility for high-throughput three-dimensional analysis [7]. Comparison of chloroplast segmentation in Chlamydomonas. (a)An SEM image acquired using an FE-SEM equipped with ACAT, (b) the regions segmented using a threshold-based method, (c) the regions segmented using AIVIA. Three-Dimensional reconstruction of a Chlamydomonas chloroplast. (a) Three-dimensional reconstruction of the chloroplast obtained through automatic segmentation, (b) The same chloroplast viewed from a different orientation. The large opening and multiple micropores are found at the positions indicated by the white arrows.

Why it matches plant phenotyping methodsChlamydomonasの chloroplast 構造を対象に、機械学習セグメンテーションと3D再構築を従来法と比較・評価しており、植物構造の定量的取得ワークフローが研究の中心である。

abstractTo establish a highly efficient three-dimensional measurement workflow from imaging to quantitative analysis, we applied machine-learning (AI) to the most challenging image-analysis step and benchmarked its effectiveness against conventional methods.

A review: research progress on intelligent technologies for orchard yield monitoring ↗

Accurate yield estimation and crop load monitoring are essential for precision orchard management, supporting targeted fertilization, pruning, thinning, harvest planning, and marketing decisions. However, reliable in-situ monitoring remains challenging because commercial orchards are characterized by severe canopy occlusion, fruit overlap, heterogeneous tree architecture, variable illumination, and complex backgrounds. This review synthesizes advances in multi-modal sensing and deep learning for orchard yield estimation, breaking down the paradigm into intermediate fruit-counting or crop-load monitoring steps and supplementary spectral quality-assessment dimensions. First, yield-related indicators are summarized, including direct phenotypic traits such as fruit number, size, volume, and spatial distribution, as well as indirect structural and physiological proxies such as canopy volume, vegetation indices, flowering intensity, and spectral maturity attributes. Second, representative sensing devices and carrying platforms are reviewed, including red-green-blue (RGB) cameras, red-green-blue-depth (RGB-D) sensors, light detection and ranging (LiDAR), hyperspectral and multispectral systems, unmanned ground vehicles (UGVs), and unmanned aerial vehicles (UAVs). Third, the evolution of estimation methods is discussed, from traditional image processing and machine learning to object detection, instance segmentation, multi-object tracking, point-cloud analysis, remote-sensing regression, and multi-modal fusion. The review shows that no single sensor or algorithm can satisfy all orchard monitoring requirements. Ground-based vision and depth sensing are more suitable for fine-scale fruit counting and sizing, whereas UAV and spectral sensing provide advantages for regional yield mapping and quality-enhanced assessment. Future research should emphasize occlusion-aware perception, robust cross-environment generalization, lightweight edge deployment, standardized benchmarks, and integrated quantity-quality monitoring frameworks for actionable crop load management.

Why it matches plant phenotyping methods果実数・サイズ・体積・空間分布などの植物形質を対象に、センシング機器と画像解析・深層学習による収量推定法を体系的にレビューしており、フェノタイピング手法が中心である。

abstractThis review synthesizes advances in multi-modal sensing and deep learning for orchard yield estimation, breaking down the paradigm into intermediate fruit-counting or crop-load monitoring steps and supplementary spectral quality-assessment dimensions.

An Agentic AI Framework to Accelerate Scientific Discovery in Plant Phenotyping ↗

High-throughput plant phenotyping now generates image derived datasets far faster than scientists can analyze them. At Oak Ridge National Laboratory's Advanced Plant Phenotyping Laboratory (APPL), automated stations image hundreds of plants daily across multiple remote sensing modalities; yet, trait extraction and interpretation remain manual, expert-bound, and strictly post-hoc, making analysis, not acquisition, the binding constraint on discovery. We present an end-to-end agentic AI framework that turns the facility from a data factory into an interactive autonomous, discovery platform, where scientists partner with AI agents to accelerate time to insight. A conversational Co-Scientist Agent translates a scientist's natural-language question into a structured analysis plan, and a headless Compute Agent dispatches Vision Transformer segmentation and trait extraction on the Frontier exascale supercomputer. The two agents run in separate security and resource domains and communicate over a secure, token-authenticated streaming channel, a design that accounts for the federation, data-movement, and provenance realities cloud-native agentic frameworks ignore, ensuring end-to-end provenance is captured for every interaction. The framework turns a days- to weeks-long analysis process into an interactive loop where agents reason over results, recommend next analyses, and respond to follow-up questions in seconds.

Why it matches plant phenotyping methods植物画像からの形質抽出を自動化するエージェント型AIフレームワークの開発であり、解析・抽出手法が研究の中心である。

abstractWe present an end-to-end agentic AI framework that turns the facility from a data factory into an interactive autonomous, discovery platform, where scientists partner with AI agents to accelerate time to insight.

TDAVM-UNet: task-driven attention VM-UNet for crop disease detection from UAV imagery ↗

Crop diseases pose a serious threat to agricultural yield and global food security. Accurate detection using Unmanned Aerial Vehicle (UAV) remote sensing imagery is of great significance for precision agriculture. However, this task remains challenging due to complex field backgrounds, diverse spectral-spatial characteristics of diseased leaf regions, irregular lesion boundaries, and variable texture patterns. To address these issues, this paper proposes a Task-Driven Attention VM-UNet (TDAVM-UNet), a novel deep learning model for crop disease detection from UAV imagery. The model integrates two task-driven attention modules: (1) Disease-Aware Dynamic Attention (DADA), which enhances the representation of diseased regions through disease feature enhancement, multi-scale dynamic channel attention, and texture-guided spatial attention; and (2) Channel-Spatial Visual State Space (CSVSS), which enables efficient long-range dependency modeling and local-global feature fusion while maintaining linear computational complexity. A hybrid loss strategy combining binary cross-entropy (BCE) loss, Dice loss, and cross-entropy (CE) loss with optimized coefficients is employed to address class imbalance and boundary delineation challenges. Extensive experiments are conducted on a self-constructed UAV crop disease unified mix dataset, comprising soybean disease images from Maharashtra, India, and rust disease images from wheat, corn, and other crops in Yangling, China, totaling 6,680 raw collected images, which after deduplication yields 5,000 images for experimentation. The results demonstrate that TDAVM-UNet achieves 26.87M parameters and 31.45 GFLOPs for 256×256 inputs, maintaining O(N) linear complexity (80% lower than TransUNet’s 156.78 GFLOPs), with 82.22% mIoU. This work provides a high-accuracy, robust, and computationally efficient method for UAV-based crop disease detection, offering significant technical support for precision agriculture applications.

Why it matches plant phenotyping methodsUAV画像から作物病害の病変領域・病害状態を推定する深層学習モデルを開発し、データセット上で性能評価しており、植物表現型取得・抽出手法が研究の中心である。

abstractthis paper proposes a Task-Driven Attention VM-UNet (TDAVM-UNet), a novel deep learning model for crop disease detection from UAV imagery.

Three-Dimensional Crop Phenotyping for Crop Protection: Reconstruction Routes, Decision Pathways, and Digital-Twin Maturity ↗

Three-dimensional (3D) crop phenotyping is increasingly used to capture crop structure, but its value for crop protection is conditional rather than automatic. 3D approaches are operationally justified only when reconstructed geometry adds decision-relevant information beyond simpler 2D, spectral, scalar, or conventional baselines. This review examines 3D crop phenotyping through a reconstruction-trait-task-maturity framework for crop protection and synthesizes evidence across disease assessment, pest and stress interpretation, pesticide dose adjustment, spray deposition, weed-target perception, protection-oriented breeding, and digital-twin development. The literature is organized through four connected lenses: reconstruction routes that generate crop geometry, 3D traits that may alter protection reasoning, decision pathways that link traits to intervention variables, and maturity levels that distinguish static 3D models, validated phenotypic traits, process-coupled systems, protection outputs, and outcome-updated decision twins. The strongest decision-facing evidence currently comes from canopy-based dose adjustment, deposition prediction, drift reduction, and related spraying applications in which 3D traits are linked to intervention variables and field-facing comparators. Disease, stress, and architecture-aware modelling provide important but more heterogeneous evidence, while many point-cloud datasets, segmentation pipelines, neural reconstruction methods, and agricultural digital-twin frameworks remain upstream of practical crop-protection decisions because they do not yet connect 3D measurements to validated protection labels, comparator baselines, decision thresholds, intervention outputs, or outcome updating. A central conclusion is that high-fidelity 3D representation should not be conflated with decision-twin maturity. Protection-oriented digital twins require explicit coupling among synchronized crop geometry, functional or epidemiological models, decision rules, and recorded field outcomes. This review therefore identifies the evidence and reporting priorities needed to move 3D crop phenotyping toward validated, deployment-oriented, and feedback-aware crop-protection support.

Why it matches plant phenotyping methods3D作物フェノタイピングの再構成、形質抽出、検証、デジタルツイン成熟度を中心に扱うレビューであり、植物フェノタイピング手法が中核。

abstractThis review examines 3D crop phenotyping through a reconstruction-trait-task-maturity framework for crop protection and synthesizes evidence across disease assessment, pest and stress interpretation, pesticide dose adjustment, spray deposition, weed-target perception, protection-oriented breeding, and digital-twin development.

A Review on Identification of Plant Leaf Image Classification Using Machine Learning Algorithms ↗

Generally, plants possess great medical benefits that are tremendously diverse and complex to identify the species. There are different varieties of plants that are yet to be fully explored. The plants are made up of some essential parts that are needed for their survival, such as roots, flowers, leaves, shoots, and others, which often appear to be alike with each other. This makes manual sorting of plants more difficult for botanists. Concurrently, image processing performs some operations by extracting useful information from the image for human interpretation. The resulting dataset from the image processing method is then classified by ML (Machine Learning) classifiers. The existing methods have focused on several dimensions; this study provides an overall view of the conventional works of plant species identification and its related plant health. This study was initiated with the purpose of giving a precise review of the advancements in image processing, such as segmentation methods, feature extraction techniques and ML-based models for the identification of plant species and diseases with its leaf because that can be available at all times. Hence, this study discusses the current research between (2019–2024) related to the use of image processing and ML and DL techniques for effective image quality enhancement and plant identification performance. Moreover, it discusses unique contributions in the field, such as agriculture and ayurveda. Moreover, a comparative analysis is carried out by considering the conventional ML models and the varied applications of widely used ML models for the effective classification of plant species.

Why it matches plant phenotyping methods葉画像のセグメンテーション、特徴抽出、機械学習・深層学習による植物病害の画像分類を対象とする方法レビューであり、植物の病態推定手法が中心です。種同定も含みますが、病害・植物健康の画像解析手法を体系的に扱っているため採用します。

abstractThis study was initiated with the purpose of giving a precise review of the advancements in image processing, such as segmentation methods, feature extraction techniques and ML-based models for the identification of plant species and diseases with its leaf

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

UAV-Based Multi-Sensor Fusion for Leaf Age Detection in Maize Inbred Line Population Seedlings ↗

Accurate and rapid detection of maize seedling growth is critical in early breeding decisionmaking, smart management, and yield improvement. Traditional leaf age detection still relies heavily on labor-intensive and low-efficiency manual field surveys, underscoring the urgent need for high-throughput phenotyping. Integrating multisource sensor data from unmanned aerial vehicle (UAV) with measured information such as crop height can further enhance the estimation accuracy of crop phenotypic parameters. Accurate field plot segmentation is critical for field-scale phenotypic analysis. However, current approaches remain largely dependent on slow, manual segmentation. Automating this step would greatly reduce the workload of agronomists. This study used UAV RGB and multispectral imagery collected over maize inbred line population plots before the canopy closure stage to perform automatic plot segmentation on field orthophotos and combined measured plant height with relative flight dates to achieve high-throughput detection of leaf age during the maize seedling stage. First, this study proposed a maize plot automatic segmentation method based on orthophotos. Then, it extracted texture features, RGB, and multispectral vegetation indices of each plot. Combined with relative flight date and plant height, four datasets were constructed. Support vector regression (SVR), random forest regression (RFR), and automatic machine learning (AutoML) regression algorithms were used to build the leaf age detection model. The results showed that the orthomosaic from March 23 achieved the best plot-segmentation performance, with minimum intersection over union (IoU), mean IoU, and IoU standard deviation of 14.67%, 96.47%, and 8.65%, respectively. Incorporating relative flight dates and plant-height measurements improved model performance, and the AutoML demonstrated the greatest robustness, achieving a validation R2 of up to 0.862 and an RMSE as low as 0.715. This study proposed a leaf age estimation method that offers practical technical support for field-based maize seedling assessment and reduces manual labor demands.

Why it matches plant phenotyping methodsUAV RGB・マルチスペクトル画像、圃場区画 segmentation、特徴抽出、回帰モデルを統合し、トウモロコシの葉齢という植物形質を推定する方法を開発・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。

abstractThis study used UAV RGB and multispectral imagery collected over maize inbred line population plots before the canopy closure stage to perform automatic plot segmentation on field orthophotos and combined measured plant height with relative flight dates to achieve high-throughput detection of leaf age during the maize seedling stage.

Plant Leaf Disease and Severity Classification with Improved PCNN-Bi-GRU Architecture with SHAP-XAI and Advanced Segmentation Model ↗

Plant diseases have a significant effect on both the amount and quality of agricultural output. The majority of these illnesses have obvious symptoms, and visual examination of the afflicted leaves is the accepted technique for diagnosing plant leaf diseases. New diseases keep emerging as plant structures and agricultural methods change. To prevent the spread of illness and guarantee the healthy growth of crops, these diseases must be identified and classified as soon as possible. Thus, a novel Parallel Convolutional Bidirectional gated recurrent-based framework for Plant Leaf Disease and Severity Classification (PCB-PLDSC) is proposed in this research. In order to balance the dataset by producing more examples for underrepresented classes, image augmentation is done after bilateral filtering for noise reduction. Moreover, sick regions are isolated using a parallel attention-based U-Net (PA-U-Net) model. Adaptive threshold-based local gradient increasing pattern (AT-LGIP), color characteristics, and median binary pattern (MBP) are used to extract features such as texture, color, and spatial patterns. These are categorized using a hybrid parallel convolutional bidirectional gated recurrent (PCB) model, which integrates a bidirectional gated recurrent units (Bi-GRU) model for disease classification with the multi-residual and layer perceptron-based channel attention parallel convolutional neural networks (MRL-CPCNN) model. The impact of each attribute on predictions is shown during the classification phase by SHapley Additive exPlanations (SHAP)-based explainable artificial intelligence (AI). Finally, for detected diseases, the system estimates severity as mild, moderate, or severe to guide effective crop management.

Why it matches plant phenotyping methods植物葉の病害領域を画像から分離し、病害分類と重症度を推定する画像ベースの表現型解析手法が研究の中心であるため。

abstracta novel Parallel Convolutional Bidirectional gated recurrent-based framework for Plant Leaf Disease and Severity Classification (PCB-PLDSC) is proposed in this research.

PlantFormer: a precise plant disease segmentation network with interactive backbone and global-anisotropic context aggregation ↗

Precise plant disease segmentation in real-world agricultural environments presents challenges that general-purpose models often fail to address, primarily due to the anisotropic spread of lesions, blurred biological boundaries, and severe background dominance. To overcome these bottlenecks, this paper proposes PlantFormer, an end-to-end network that effectively integrates and adapts advanced architectural components to address these domain-specific issues. Specifically, PlantFormer employs an InteractSwin Backbone with a Cross-Level Fusion (CLF) module to preserve early pathological details. To model highly directional disease propagation, a GlobalAnisotropic Context Aggregation (GACA) neck utilizing strip pooling is introduced. Furthermore, a Semantic-Guided Fusion (SGF) decoder acts as a feature “boundary purifier” to suppress field noise, while a decoupled boundary-aware loss function explicitly shifts the optimization focus from healthy leaf regions to subtle necrotic transition zones. Comprehensive experiments demonstrate the effectiveness of our approach: PlantFormer achieves 41.78% mIoU on the complex PlantSeg dataset (unstructured field conditions) and 93.54% mIoU on the structured NLB dataset (vein-aligned lesions). It outperforms generalist models such as DeepLabV3+ and Segformer in key metrics like mIoU and mAcc. Despite these promising results, limitations remain, particularly regarding performance in scenarios with high-density, early-stage disease outbreaks, which will be the focus of future work.

Why it matches plant phenotyping methods植物病斑・壊死領域を直接セグメンテーションする画像解析手法の開発とベンチマークであり、植物病害状態の定量化が中心である。

abstractPrecise plant disease segmentation in real-world agricultural environments presents challenges that general-purpose models often fail to address

An automated unmanned aerial vehicle framework for non-destructive soybean leaf morphology extraction using a structure-adaptive deep learning model ↗

Soybean leaf morphology is an important breeding trait that requires large-scale phenotyping in commercial breeding programs. Conventional leaf phenotyping still relies on manual destructive measurements, which are labor-intensive and inefficient. Low-altitude unmanned aerial vehicles (UAVs) have emerged as a high-throughput phenotyping platform, but the retrieval of leaf morphology in densely occluded canopies remains challenging due to complex canopy backgrounds, illumination heterogeneity, and leaf overlap under field conditions. To address this issue, this study developed an integrated UAV framework that couples a YOLOv10-based leaf detection module, a novel structure-adaptive segmentation network (DynamicU), and a regression-based trait prediction model for retrieving a set of leaf morphological parameters across 273 soybean genotypes under field conditions. The YOLOv10 detector reliably localized individual leaves under complex canopy conditions, achieving a mean average precision (mAP@50) of 0.84. Subsequently, the DynamicU network, whose architecture was automatically optimized via Emperor Penguin Optimization, achieved a segmentation accuracy of 97.2% and a mean Intersection over Union of 93.8%, substantially outperforming conventional models. Using random forest regression, the framework retrieved relative leaf shape traits, including length-to-width ratio and dissection index, with markedly higher accuracy (R 2 =0.97), compared to absolute morphological traits, including leaf length, width, perimeter, and area (R 2 : 0.76–0.84). Notably, relative leaf shape traits showed positive associations with oil yield per plant and protein yield per plant, supporting their potential as complementary indicators for screening soybean germplasm with differential industrial product output. This end-to-end framework establishes a reliable bridge between UAV remote sensing and leaf-level morphological quantification, advancing high-throughput phenotyping capabilities to support precision breeding in soybean.

Why it matches plant phenotyping methodsUAV画像、葉検出・セグメンテーション・回帰モデルを統合し、圃場でダイズ葉形態を自動定量するフレームワークの開発と性能評価が研究の中心であるため。

abstractthis study developed an integrated UAV framework that couples a YOLOv10-based leaf detection module, a novel structure-adaptive segmentation network (DynamicU), and a regression-based trait prediction model for retrieving a set of leaf morphological parameters across 273 soybean genotypes under field conditions.

Multi-task Deep Learning Pipeline for Rice Field Classification and Growth Monitoring Using Drone Imagery ↗

A booming population around the world raises the concern of shortages of food resources in this new era. Thus, monitoring and managing crop production is extremely essential, especially rice crops, as they are the fundamental food source for most countries. Several challenges need to be addressed in this case, such as the classification of farmland from various land usages, precise monitoring of rice seedlings, and segmentation of rice growth. By leveraging advanced technologies such as drone imagery and machine learning, this paper proposed a new integrated pipeline for rice field classification and growth monitoring: a combination of convolutional neural networks (CNNs), You Only Look Once (YOLO), and modified U-Net models. These models were used in stages, specifically for paddy field classification, rice seedling detection, and rice growth segmentation. Substantial measurements and analysis have been carried out to verify the performance of the proposed system, including an accuracy of at least 85%, low classification/segmentation loss below 0.35, and high detection recall above 0.9. Thus, the findings highlight how combining different machine learning models with aerial photography can revolutionise conventional farming methods for better efficacy.

Why it matches plant phenotyping methodsドローン画像とCNN・YOLO・改良U-Netを統合し、イネ苗の検出および生育セグメンテーションを行う技術パイプラインが中心で、性能検証も実施している。農地分類は除外対象になり得るが、植物の生育状態を直接抽出する手法部分が十分に実質的である。

abstractThese models were used in stages, specifically for paddy field classification, rice seedling detection, and rice growth segmentation.

New computer vision tools help to assess wheat ear diseases ↗

PHENET's Use Case 1 on plant health is validating sensors and imaging methods for the assessment of wheat ear diseases, with two AI-powered applications now reaching proof-of-concept stage. The first, FUSASEYD, addresses Fusarium Head Blight (FHB), a major fungal disease in winter wheat. Using RGB field images and a deep learning instance segmentation model (YOLOv11), the application detects and quantifies FHB symptoms on wheat ears, offering an automated alternative to time-consuming expert visual scoring. GEVES has developed both a PC interface and a smartphone application to visualise model predictions in the field. Validation in French registration trials is planned for the 2026 campaign. A companion article by V. Cadot et al. is currently under review in the Journal of Experimental Botany special issue on Plant Phenomics & Enviromics Across Scales. The second, COYL (Counting Orange and Yellow Larvae), tackles a practical challenge faced by breeders, and rapidly counting wheat blossom midge larvae, both Sitodiplosis mosellana and Contarinia tritici, to characterise variety susceptibility. Using smartphone RGB images and YOLOv-based object detection, the best-performing model achieved high accuracy and successfully distinguished between the two visually similar species. An online counting application has been developed, currently accessible to Walloon Agricultural Research Centre members. The labelled COYL-1 dataset is publicly available at https://doi.org/10.5281/zenodo.19402333 for community use. A companion article by Antoine Deryck et al. is under submission at Plant Phenomics Journal.

Why it matches plant phenotyping methodsRGB画像と深層学習によるコムギ穂の病徴検出・定量化を開発し、専門家評点の自動化とセンサー／画像法の検証を目的とするため、植物フェノタイピング手法が中心である。

abstractPHENET's Use Case 1 on plant health is validating sensors and imaging methods for the assessment of wheat ear diseases

New computer vision tools help to assess wheat ear diseases ↗

PHENET's Use Case 1 on plant health is validating sensors and imaging methods for the assessment of wheat ear diseases, with two AI-powered applications now reaching proof-of-concept stage. The first, FUSASEYD, addresses Fusarium Head Blight (FHB), a major fungal disease in winter wheat. Using RGB field images and a deep learning instance segmentation model (YOLOv11), the application detects and quantifies FHB symptoms on wheat ears, offering an automated alternative to time-consuming expert visual scoring. GEVES has developed both a PC interface and a smartphone application to visualise model predictions in the field. Validation in French registration trials is planned for the 2026 campaign. A companion article by V. Cadot et al. is currently under review in the Journal of Experimental Botany special issue on Plant Phenomics & Enviromics Across Scales. The second, COYL (Counting Orange and Yellow Larvae), tackles a practical challenge faced by breeders, and rapidly counting wheat blossom midge larvae, both Sitodiplosis mosellana and Contarinia tritici, to characterise variety susceptibility. Using smartphone RGB images and YOLOv-based object detection, the best-performing model achieved high accuracy and successfully distinguished between the two visually similar species. An online counting application has been developed, currently accessible to Walloon Agricultural Research Centre members. The labelled COYL-1 dataset is publicly available at https://doi.org/10.5281/zenodo.19402333 for community use. A companion article by Antoine Deryck et al. is under submission at Plant Phenomics Journal.

Why it matches plant phenotyping methodsRGB画像と深層学習によりコムギ穂の病徴を検出・定量する手法の開発とセンサー／画像手法の検証が中心であり、植物病害表現型の取得に該当する。

abstractPHENET's Use Case 1 on plant health is validating sensors and imaging methods for the assessment of wheat ear diseases

A scalable framework for UAV-based point cloud reconstruction and organ segmentation of field-grown cotton in complex field environments ↗

Accurate characterization of plant 3D architecture and semantic parsing of key cotton organs represent an essential prerequisite for crop phenotyping, precision field management, and cultivar breeding and selection. However, the overall 3D structure of field-grown cotton plants is highly complex in field environments. The morphological traits and spatial distribution of various organs are modulated by multiple factors including genetics, environmental conditions, and cultivation management practices, resulting in pronounced phenotypic variation under field conditions. Thus, this study proposed an integrated technical framework for UAV-based 3D reconstruction and organ semantic segmentation tailored for field-grown cotton. High-fidelity 3D point clouds of the crop canopy are generated by coupling an field-adapted low-altitude unmanned aerial vehicle (UAV) acquisition strategy with neural radiance fields (NeRF). Despite these attractive characteristics, segmenting and analyzing such intricate point clouds can be quite challenging. To effectively parse these complex geometric structures, a novel deep learning architecture named FieldCotSeg-Net is introduced. This model integrates an Anisotropy-aware Local Attention (ALA) module and a Hierarchical Feature Refinement Gate (HFRG) module to capture fine-grained features for precise point cloud segmentation. Experimental results demonstrate that the proposed model achieves outstanding performance on both the Huaxing3Dcot and Crops3D cotton datasets. On the Huaxing3Dcot dataset, the model yields a mean intersection over union (mIoU) of 75.7%, representing a 4.5% improvement over the baseline model. On the Crops3D cotton dataset, after retraining the model on this dataset, it attains an mIoU of 74.5%, showing substantial adaptability and effectiveness in organ segmentation. This technical system provides a scalable and robust solution for field cotton phenotyping analysis in breeding research and commercial production.

Why it matches plant phenotyping methods綿花の圃場表現型解析を目的に、UAVによる3D再構成と器官セグメンテーション手法を開発・評価しており、植物形態の取得が研究の中心である。

abstractThis technical system provides a scalable and robust solution for field cotton phenotyping analysis in breeding research and commercial production.

Integration of remote sensing and artificial intelligence for carbon quantification in macauba palm trees ↗

Accurate measurement of carbon is stored in plants is essential for evaluating strategies to reduce greenhouse gas emissions. The macauba palm (Acrocomia aculeata) is a native species of South America with high potential for oil production, ecological restoration, and carbon sequestration. Traditional methods to estimate carbon stocks, such as cutting down trees and performing laboratory analysis, are destructive, expensive, and impractical on a large scale. This study tested an alternative approach that combines UAV imagery, computer vision, and artificial intelligence to estimate carbon in macauba palms without damaging the plants. High-resolution aerial images were collected at four sites in Brazil, and a deep learning model (YOLOv8s-seg) was trained to automatically detect and measure palm crowns, achieving a mean Average Precision (mAP@50) of 0.956, precision of 0.946, and recall of 0.944. Plant height was estimated from canopy height models derived from photogrammetric processing of the UAV imagery. Crown diameter and height estimates showed strong correlations with field measurements (r = 0.81 and r = 0.82, respectively), with mean absolute errors of 0.26 m for diameter and 0.61 m for height. Both parameters were used in allometric equations to calculate carbon stock. Carbon estimates ranged from less than 1 ton per hectare in young plantations to more than 190 tonnes per hectare in older stands. These results demonstrate that artificial intelligence and UAV imagery provide a fast and scalable approach for estimating structural variables of macauba palms. However, carbon stock estimates remain sensitive to the allometric equations used and should be interpreted with caution, particularly at the individual level. Therefore, the proposed approach should be understood as a non-destructive monitoring framework rather than a fully generalized carbon prediction model, while still offering a valuable tool to support sustainable agriculture, carbon markets, and land-use policies.

Why it matches plant phenotyping methodsUAV画像、コンピュータビジョン、深層学習を用いてヤシの樹冠径・樹高を自動推定し、現地測定と比較検証している。植物の構造形質取得と炭素量推定の技術が研究の中心である。

abstractThis study tested an alternative approach that combines UAV imagery, computer vision, and artificial intelligence to estimate carbon in macauba palms without damaging the plants.

GuavaVision AI: An Explainable Deep Learning Framework for Automated Classification, Lesion Localization, and Segmentation of Guava Diseases ↗

Guava cultivation is considerably influenced by foliar and fruit diseases whose overlapping symptoms and environmental variability make accurate field-level diagnosis challenging. Numerous studies have been conducted to find efficient methods of diagnosing plant diseases, but most focus on image-level classification and do not include lesion localization or pixel-level segmentation of the images within a single framework of analysis. This study proposes a comprehensive framework for utilizing automated image analysis to classify guava leaf and fruit diseases at the image level, locate lesions, and segment lesions at the pixel level from multiple images of the same type of disease collected from various growing conditions. The dataset was enriched through three augmentation strategies including standard preprocessing, structured augmentation, and GAN-based synthetic image generation, expanding the effective training data to approximately 7,000 images, while a 5-fold cross-validation strategy guided model selection and final performance was assessed on a held-out test set. The experimental evaluation of multiple state-of-the-art Convolutional Neural Networks (CNNs) for the classification of guava leaf and fruit diseases indicated that the model generated using the ResNet50+DenseNet121 model fusion achieved the highest classification accuracy of 98.20%. For lesion detection and segmentation, YOLOv8-seg outperformed Mask R-CNN, achieving mAP@0.5 of 0.907 and 0.889, and mAP@0.5:0.95 of 0.783 and 0.769 for detection and segmentation, respectively, with a balanced precision–recall profile. The techniques of Explainable AI (XAI) were used to increase the transparency of this model by identifying areas in the image that are significant to the actual lesion. The framework was further designed with practical web-based deployment in mind, evaluating both lightweight and high-capacity models to balance computational efficiency against predictive accuracy. From this research, it was concluded that using model fusion, data augmentation, and segmentation-aware lesion detection would provide a solution for managing guava diseases effectively.

Why it matches plant phenotyping methodsグアバの葉・果実における病斑の分類、位置特定、画素レベル分割を自動化する画像解析フレームワークを開発・評価しており、植物の病害状態の表現型取得が研究の中心である。

abstractThis study proposes a comprehensive framework for utilizing automated image analysis to classify guava leaf and fruit diseases at the image level, locate lesions, and segment lesions at the pixel level

A three-dimensional reconstruction method for seedlings based on improved DIFIX3D+ ↗

Three-dimensional (3D) reconstruction of seedlings commonly suffers from under-constrained issues in areas with severe occlusion and insufficient observation, leading to false geometry and rendering artifacts. The existing methods primarily rely on pixel-level consistency constraints, resulting in poor stability when reconstructing seedlings with slender branches and complex structures. To address these challenges, this paper proposes a 3D reconstruction method for seedlings which is based on improved DIFIX3D+. By integrating the Stable Diffusion-VAE module into the DIFIX3D+ framework, this approach enhances the reconstruction constraint mechanism at the representation level. Firstly, high-precision segmentation of seedlings was achieved by eliminating background interference using the Florence-2 semantic priors and the SAM2 (Segment Anything Model 2) instance segmentation model. Then, by jointly mapping DIFIX3D+ restored images and their corresponding rendered images into the latent space of Stable Diffusion-VAE, consistency supervision was established within the latent representation domain. It worked in tandem with traditional pixel-level constraints, thereby suppressing the propagation of pixel noise caused by lighting variations, specular reflections, and texture repetitions at the representation level. Experimental results demonstrated that on the self-built dataset, compared to the original 3DGS (3D Gaussian splatting) and DIFIX3D+, the proposed method achieved the peak signal-to-noise ratio (PSNR) improvement of 28.99% and 24.25%, respectively, and the structural similarity index measure (SSIM) improvement of 3.16% and 3.74%, while reducing the learned perceptual image patch similarity (LPIPS) by 9.24% and 41.94%. The average PSNR, SSIM, and LPIPS values reached 31.54 dB, 0.9759, and 0.054, respectively, demonstrating significantly superior reconstruction accuracy compared to mainstream models such as Nerfacto, Plenoxels, and Mip-Splatting. This method combines high visual fidelity with excellent geometric structure representation capabilities, providing a technical reference for high-quality, low-cost 3D reconstruction of seedlings in complex scenes.

Why it matches plant phenotyping methods苗の3D形状・構造を抽出する画像ベース再構成手法の開発が中心であり、植物表現型取得の方法論に該当する。

abstractThis method combines high visual fidelity with excellent geometric structure representation capabilities, providing a technical reference for high-quality, low-cost 3D reconstruction of seedlings in complex scenes.

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.

Estimation of Seaweed Biomass in Shallow Coastal Waters Using UAV Bathymetric LiDAR and Automated 3D Point Cloud Segmentation ↗

Accurate and wide-area estimation of seaweed biomass is essential for evaluating blue carbon. Conventional diver surveys and two-dimensional (2D) aerial imagery analysis face challenges such as intensive labor and biomass underestimation. While Unmanned Aerial Vehicle-based Light Detection and Ranging (UAV-LiDAR) provides dense 3D spatial data, classifying point clouds in extremely shallow coastal waters with dense kelp and artificial structures remains difficult. This study establishes a high-accuracy biomass estimation method using UAV-LiDAR and PointNet. A heuristic hybrid filtering approach combining physical constraints and local statistics was developed to automatically generate high-quality reference data. The trained PointNet successfully segmented complex point clouds into four classes with an overall accuracy of 94.2%. To calculate biomass, we introduced a volume correction model based on point cloud density (coverage) to mitigate overestimation caused by internal canopy gaps. This correction yielded estimated wet weights nearly identical to the in situ measurements (an approximate 3% difference), confirming highly accurate biomass reproduction. Furthermore, while the conventional 2D maximum likelihood method underestimated total biomass, our 3D point cloud analysis successfully quantified the dense, overlapping canopy. This framework significantly improves the efficiency and accuracy of blue carbon monitoring.

Why it matches plant phenotyping methodsUAV-LiDARとPointNetによる海藻の3D点群分割および biomass 推定手法を開発・検証しており、植物体のバイオマスという形質の取得が研究の中心である。

abstractThis study establishes a high-accuracy biomass estimation method using UAV-LiDAR and PointNet.

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.

Weakly Supervised Fine-Grained Discrimination of Wheat Mold Using Local RGB-HSI Fusion. ↗

Wheat is a major staple crop, and storage mold growth poses a severe threat to grain safety and quality stability. Natural mold development in stored wheat exhibits subtle, localized, and highly heterogeneous characteristics. Existing unimodal methods and global fusion approaches generally suffer from insufficient local feature sensitivity, hindering fine-grained mold severity grading. To address this limitation, we propose a Mask-Guided Fine-Grained Fusion Network, a weakly supervised framework based on local RGB-HSI fusion. This framework employs a dynamic parallel A/B experimental design to construct time-matched proxy labels via weakly supervised learning. A standardized preprocessing pipeline including single-kernel extraction, foreground segmentation, and cross-modal registration is established to resolve RGB-HSI spatial misalignment, ensuring physical-level spatial consistency of multimodal features. The model incorporates a Foreground-Aware Spectral Recalibration (FASR) module to suppress background noise, a Mask-Guided Dilated Cross-modal Local Attention (MDCLA) mechanism to establish fine-grained local mappings between RGB visual phenotypes and hyperspectral responses, and a sample-level adaptive fusion strategy to dynamically weight features by modal reliability, enhancing representation of complex samples across all mold stages. Experiments show that the Mask-Guided Fine-Grained Fusion Network achieves 0.9689 classification accuracy, 0.9698 Macro-F1 score, and 0.0593 Mean Absolute Error (MAE), significantly outperforming state-of-the-art unimodal deep models and global attention fusion baselines. This work provides a proof-of-principle framework for fine-grained non-destructive mold risk assessment in stored wheat.

Why it matches plant phenotyping methodsRGB-HSI融合と弱教師あり学習により、保存小麦粒のカビ状態・重症度を推定する手法が研究の中心であり、植物器官の病害状態を直接評価している。

abstractwe propose a Mask-Guided Fine-Grained Fusion Network, a weakly supervised framework based on local RGB-HSI fusion.

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

Deep Learning and Computer Vision for Crop Maturity Assessment ↗

Maturity at harvest is a critical determinant of yield, storability, market value, and nutritional quality, making accurate and objective maturity assessment essential for sustainable crop and fruit production. The agricultural sector is under pressure to satisfy rising global food demand while reducing losses and environmental impacts, yet conventional maturity assessment methods remain largely manual, subjective, and labour-intensive. Against this backdrop, computer vision and deep learning have emerged as powerful tools for non-destructive, high-throughput evaluation of maturity traits in the field and along the supply chain.​ This review consolidates recent advances in deep learning-based maturity assessment across a wide range of crops, with a particular emphasis on citrus fruits, where external colour change, internal quality, and heterogeneous orchard conditions pose distinctive challenges. The paper analyzes state of the art architectures for classification, segmentation and detection, associated datasets and imaging modalities, and the metrics used to benchmark performance. By critically examining their advantages and limitations for real-world deployment, the review outlines key research gaps and future directions toward robust, scalable, and sustainable DL-driven maturity assessment systems for both citrus and other major crops.

Why it matches plant phenotyping methods作物の成熟度という植物形質を対象に、画像・深層学習による評価手法、データセット、画像モダリティ、ベンチマーク指標を体系的にレビューしており、フェノタイピング手法が中心です。

abstractThis review consolidates recent advances in deep learning-based maturity assessment across a wide range of crops

Intelligent framework for automated rice leaf disease diagnosis using a Simplicial Finite-Element-Informed Neural Network optimised by the MCA ↗

Rice, a staple food for more than half of the global population, faces significant yield and quality losses due to various diseases and environmental stresses. This paper presents a new Simplicial Finite-Element-Informed Neural Network based on the Musical Chairs Optimisation Algorithm (SFEINN-MCOA) to detect rice leaf disease precisely and efficiently. The first step involves the acquisition of the RGB image from the Rice Leaf Disease dataset. The Iterative Robust Peak-Aware Guided Filter (IRPAGF) is used to remove noise and enhance contrast, thus improving the image. The Graph-Based Soft-Balanced Fuzzy Clustering (GSBFC) method is used to separate diseased regions and then analyse them. The Self-Distillated Masked Autoencoder (SMA) is used to perform feature extraction and capture important attributes of leaves. The SFEINN classifies data under the category of healthy and diseased leaves, and the MCOA optimises the model parameters to achieve maximum accuracy and minimum error. Experimental findings reveal that the SFEINN-MCOA model has an accuracy of 99.9% and an F1-score of 98.9%, which is better and stronger. This smart system offers a secure, automatic, and effective system for early disease identification of rice and helps farmers to enhance crop health and yield sustainability.

Why it matches plant phenotyping methodsイネ葉の病斑領域を画像から抽出し、健全・罹病状態を自動判定する画像解析フレームワークが研究の中心であり、植物病害状態の表現型推定に該当する。

abstractThis paper presents a new Simplicial Finite-Element-Informed Neural Network based on the Musical Chairs Optimisation Algorithm (SFEINN-MCOA) to detect rice leaf disease precisely and efficiently.

An in situ image-based phenotyping system for hydroponic maize seedling roots based on DB-UNet and customized skeleton-based analysis. ↗

monitoring capabilities, and existing models have limited accuracy in root segmentation. To address these issues, we developed a crop root phenotyping system integrating crop cultivation and data collection. We also proposed a DB-UNet model for hydroponic maize root segmentation. DB-UNet builds a CNN-ViT dual-branch parallel structure during encoder downsampling level. The lightweight ViT branch uses sequential downsampling to achieve global topological dependency modeling while reducing computational costs. An attention fusion module dynamically calibrate dual-branch features weights, achieving complementary fusion of local root edge details and global context information. we constructed a mixed loss function combining Dice loss, Focal loss, and structural consistency KL loss to solve class imbalance, hard sample segmentation, and semantic divergence of dual-branch features. On our custom hydroponic maize root dataset, DB-UNet achieved an mIoU of 91.02%, an FG IoU of 82.78%, and a Centerline-Dice of 97.72%.Compared to classic UNet, mIoU, FG IoU, and Centerline-Dice increased by 0.92%, 1.84%, and 1.99%, respectively. Plant-level five-fold cross-validation further showed that DB-UNet maintained stable segmentation performance across different plant-level partitions. Based on DB-UNet segmentation results, we propose a custom skeleton-based algorithm for multi-trait root phenotyping, enabling the extraction of total root length and root branch points. Root area is calculated from binary mask pixel statistics. Compared to the traditional Zhang-Suen algorithm, the average relative error of root length measurement is reduced to 3.14%, which is 8.42 percentage points lower than the traditional method. Furthermore, we analyzed relationships between segmentation accuracy metrics and phenotypic relative errors. Higher segmentation quality generally led to lower phenotypic relative errors and more reliable trait measurements. In particular, Centerline-Dice was closely associated with root length estimation, whereas pixel-level segmentation consistency was more closely related to root area measurement. Pearson and Spearman correlation analyses showed a strong positive correlation between maize plant height and total root length, with coefficients of 0.8466 and 0.8634, respectively.

Why it matches plant phenotyping methods画像ベースの根セグメンテーションと骨格解析を開発・検証し、根長や分枝点などの形質を抽出するシステムが研究の中心であるため。

abstractwe developed a crop root phenotyping system integrating crop cultivation and data collection.

Mapping understorey tree invasion in a drought-affected forest using multi-view UAV imagery and deep learning ↗

Advances in deep learning (DL) and structure from motion (SfM) photogrammetry combined with off-the-shelf unoccupied aerial vehicles (UAVs) and high-resolution cameras enable unprecedented plant species mapping accuracy. While these tools have been mainly applied to flat terrain or upper forest canopies, the forest understorey remains largely unexplored. Here, we present a method combining DL with multi-view UAV imagery to map the invasive tree-of-heaven ( Ailanthus altissima ) in the understorey of a drought-affected Central European forest. The raw UAV photographs were segmented with convolutional neural networks (CNNs). Resulting predictions were projected onto georeferenced point clouds using SfM. This novel approach revealed that more than 40% of the invasion was hidden beneath the canopy and would have been missed by conventional orthomosaic-based methods. To assess CNN generalization abilities, we altered training and prediction domains: lower-processing-level aerial images vs. higher-processing-level orthomosaic, both originating from a small training extent (420 m 2 or 0.25% of the study area). For intra-domain predictions, aerial-trained models (F1=0.880) outperformed ortho-trained models (F1=0.805). When applied cross-domain, aerial models retained superior performance (F1=0.843) over ortho-trained ones (F1=0.750). Expanding the training extent eightfold raised the accuracy of the ortho-trained models to F1=0.836 within-domain and F1=0.846 cross-domain. In summary, integrating photogrammetry with DL is a promising route for utilizing overlapping aerial imagery efficiently and leveraging information that conventional orthomosaic-based analyses discard. The resulting richer 3D information and improved transferability may support decision-making and retrofitting this novel technique to upcoming and existing datasets opens new avenues in vegetation studies and beyond.

Why it matches plant phenotyping methods森林下層の侵入樹木を対象に、UAV多視点画像、SfM、深層学習を統合した植物状態（侵入・分布）の抽出法を開発し、ドメイン間性能も検証しており、方法が中心である。

abstractHere, we present a method combining DL with multi-view UAV imagery to map the invasive tree-of-heaven ( Ailanthus altissima ) in the understorey of a drought-affected Central European forest.

Quantifying Canopy Closure Dynamics Using UAV Imagery and Semantic Segmentation in Rice Breeding Trials. ↗

The canopy closure stage is a critical phase of rice ( Oryza sativa L.) development that influences canopy structure and final grain yield. Accurate and continuous monitoring of canopy closure dynamics is therefore essential for variety screening and cultivation optimization. This study combines unmanned aerial vehicle (UAV) remote sensing technology with deep learning-based semantic segmentation to establish an efficient framework for quantifying rice canopy closure dynamics. UAV RGB images were acquired for 198 hybrid rice varieties during early growth stages and used to build a canopy segmentation dataset. Three semantic segmentation models, i.e., DeepLabv3+, U-Net, and PSPNet, were systematically evaluated. Results show that DeepLabv3+ performed the best and enabled precise extraction of rice canopy features, obtaining a mean intersection over union (mIoU) of 0.86. Based on the extracted canopy coverage, the Gompertz model was utilized to characterize temporal canopy closure trajectories for all varieties, achieving an average R 2 of 0.978. Subsequently, five key dynamic indicators were derived, including canopy closure limit value ( K ), initial growth coefficient ( a ), growth rate coefficient ( b ), maximum instantaneous growth rate ( MGR ), and days to maximum growth rate ( Tm ). K-means clustering analysis was performed on these indicators to categorize all rice varieties into three clusters, disclosing pronounced differences in early-stage canopy development characteristics. Correlation analysis further demonstrated that canopy closure dynamics were closely associated with grain yield. Overall, while acknowledging the limitations of a single-season and single-site dataset, this study provides a scalable and objective framework for quantifying rice canopy closure dynamics, offering valuable support for variety selection, cultivation optimization, and high-yield rice production.

Why it matches plant phenotyping methodsUAV画像と深層学習セマンティックセグメンテーションを用いてイネのキャノピー閉鎖動態を定量化する手法を構築・評価しており、植物形質抽出が研究の中心である。

abstractThis study combines unmanned aerial vehicle (UAV) remote sensing technology with deep learning-based semantic segmentation to establish an efficient framework for quantifying rice canopy closure dynamics.

RootNet: A deep learning framework for automated tomato radicle segmentation and length measurement ↗

Automated phenotyping of crops is a vital component of precision agriculture. As a representative economic crop, the radicle length of tomato seeds is a key phenotypic indicator for assessing seed vigor and seedling health. To reduce labor costs and improve measurement efficiency, we developed an integrated seed germination phenotype acquisition system that combines cultivation and imaging, enabling continuous image acquisition throughout the tomato seed germination process. To achieve automatic measurement of radicle length, we propose a deep learning-based segmentation framework, termed RootNet. The framework incorporates a custom-designed module, MambaNextBlock (MNB), within skip connections to enhance long-range feature modelling, and integrates an Atrous Spatial Pyramid Pooling (ASPP) module at the bottleneck to capture multi-scale contextual information. Post-segmentation, Canny edge detection is employed to extract radicle contours, from which actual lengths are computed based on contour arc length. Experimental results show that RootNet achieved 77.75% Intersection over Union (IOU), 86.03% Precision, 88.72% Recall, and 87.46% F1-Score on the root class. Compared with manual measurements conducted using ImageJ, our method showed high agreement across 1170 radicle measurements, with an R² of 0.9785, an MAE of 0.274 mm, an RMSE of 0.344 mm, and a Bias of −0.008 mm. Bland–Altman analysis further confirmed the absence of systematic bias, with 95% limits of agreement ranging from −0.682 mm to +0.666 mm. Meanwhile, measurement efficiency was improved by approximately 680-fold. Furthermore, the method was applied to evaluate the effects of drought, salinity stress, and different concentrations of Streptomyces albidoflavus (HL4) and Streptomyces virginiae (GZ2) on radicle growth. The results indicated that drought stress, salinity stress, and undiluted HL4 inhibited radicle elongation, whereas diluted HL4, as well as both undiluted and diluted GZ2, significantly promoted radicle growth. This study provides an efficient and cost-effective solution for non-destructive crop phenotyping and intelligent agricultural management in precision farming.

Why it matches plant phenotyping methodsトマト幼根長を画像から自動抽出・測定する深層学習フレームワークを開発し、手動測定との定量的検証も行っており、植物フェノタイピング手法が研究の中心である。

abstractwe developed an integrated seed germination phenotype acquisition system that combines cultivation and imaging, enabling continuous image acquisition throughout the tomato seed germination process.

Multi Class Support Vector Machine Based Plant Leaf Disease Detection from Color Texture And Shape Pictures ↗

Agriculture plays a vital role in the economy of many countries, and crop productivity is highly dependent on plant health.Plant diseases can significantly reduce crop yield and quality if not detected at an early stage.Traditional disease identification methods rely on manual inspection by agricultural experts, which can be time-consuming, expensive, and sometimes inaccurate.Recent advancements in image processing and machine learning have enabled automated systems for plant disease detection.This research presents a plant leaf disease detection system based on a Multi-Class Support Vector Machine (SVM) classifier using color, texture, and shape features extracted from leaf images.The proposed approach captures leaf images, performs preprocessing to remove noise and enhance image quality, segments the infected region, and extracts relevant features.These features are then used to train a Multi-Class SVM model capable of classifying different plant diseases.The combination of color, texture, and shape characteristics improves classification accuracy by providing comprehensive information about disease symptoms present on the leaf surface.Experimental analysis demonstrates that the proposed method can effectively identify multiple plant diseases with high accuracy while reducing the dependency on manual diagnosis.The developed system offers a cost-effective and efficient solution for farmers and agricultural professionals, helping in early disease detection and timely treatment recommendations.The proposed approach contributes to the advancement of smart agriculture and precision farming technologies.

Why it matches plant phenotyping methods葉画像から病斑領域を分割し、色・テクスチャ・形状特徴を抽出して植物病害状態を分類する画像ベースの表現型推定手法が研究の中心であるため。

abstractThis research presents a plant leaf disease detection system based on a Multi-Class Support Vector Machine (SVM) classifier using color, texture, and shape features extracted from leaf images.

Non-destructive and accurate phenotypic detection method for okra seedlings under salt stress based on dual-view feature fusion and lightweight PointNet+. ↗

Soil salinization has become a critical factor limiting global agricultural production. Characterizing the growth and developmental responses of okra to salt stress and developing efficient and accurate salt-stress phenotyping techniques can provide an important methodological reference for okra cultivation in saline lands and future multi-cultivar salt-stress phenotyping studies. Traditional manual measurement of plant phenotypic parameters suffers from low efficiency and insufficient detection accuracy, making it difficult to achieve rapid and non-destructive analysis of plant phenotypic traits under salt stress. Therefore, this study proposes a computational phenotyping parameter extraction method based on the CSP-MSG Net model. Using dual-view feature fusion, we constructed a dedicated dataset. On the basis of PointNet++-MSG, the original MLP layers were replaced with C2F modules, and the SGE attention mechanism was integrated to enhance morphological feature extraction, thereby constructing a lightweight CSP-MSG Net architecture adapted to okra seedling point clouds for semantic segmentation of okra point clouds combined with DBSCAN clustering to complete instance segmentation, phenotypic parameters including plant height, stem diameter and canopy width were further calculated. This scheme enables high-throughput data acquisition, improves measurement accuracy, effectively reduces model parameters and computational overhead, and realizes lightweight operational performance. The results show that okra seedlings can still grow with increasing salt stress concentration, while the growth rates of the three measured traits are all inhibited, indicating that high-concentration salt stress impairs the growth activity of okra seedlings. To verify the calculation accuracy of the model, the phenotypic parameters predicted by the model were compared with manually measured values. The coefficients of determination for stem diameter, canopy width and plant height of okra seedlings reached 0.96, 0.99 and 0.99, respectively. These results strongly demonstrate the excellent reliability and effectiveness of the proposed method, providing methodological support for non-destructive and accurate phenotypic detection of okra seedlings under salt stress.

Why it matches plant phenotyping methodsオクラ幼苗の点群から草丈・茎径・樹冠幅を抽出する計算フェノタイピング手法を開発し、手動測定との比較で精度検証しているため、方法が研究の中心である。

abstractthis study proposes a computational phenotyping parameter extraction method based on the CSP-MSG Net model.

DDCANet for SiO 2 -mediated drought regulation research: high-precision segmentation and phenotypic detection of cucumber point clouds. ↗

Cucumber is a core cultivated facility vegetable in China. Drought stress at the seedling stage severely inhibits its growth and development. The regulatory mechanism and optimal application concentration of SiO 2 nanoparticles in alleviating drought stress in cucumber seedlings remain unclear. Moreover, traditional manual measurement and classic point cloud segmentation models struggle to achieve high-throughput accurate detection of cucumber seedling phenotypes under drought stress. To address these issues, this study focused on phenotypic detection under drought stress and analysis of the regulatory effects of SiO 2 nanoparticles. An improved compact and low-redundancy segmentation model, DDCANet, was proposed based on PointNet++-SSG. Combined with 3D point cloud technology and the Euclidean clustering algorithm, it enables automatic extraction of phenotypic parameters from cucumber seedlings treated with SiO 2 nanoparticles under drought stress. In this study, Trailing cucumber seedlings were used as experimental materials. 3D point cloud data of cucumber seedlings were collected under treatments with different concentrations of SiO 2 nanoparticles and PEG-simulated drought stress. A dataset containing 70 valid samples was constructed and labeled into two categories: Stem and Leaf. The core optimizations of the DDCANet model are as follows: Firstly, an Adaptive Density-Aware Feature Enhancement (ADFE) module is embedded to accurately capture point cloud density heterogeneity induced by SiO 2 ;Secondly, a Channel Attention and Normalization-enhanced SA Layer (CANL) is designed to strengthen the coupling of local and global drought-related phenotypic features. Thirdly, a Drought-Aware Hybrid Loss (DHL) function is constructed to alleviate the class imbalance of seedling stem and leaf point clouds under drought stress. Results show that the DDCANet model achieves a mean Intersection over Union (mIoU) of 89.01 ± 0.32% and a Stem IoU of 83.6 ± 0.45%, representing improvements of 6.55% and 9.6% respectively compared with the baseline PointNet++-SSG model, and a 30.5% improvement in stem segmentation accuracy compared with the classic PointNet model. It thus enables high-throughput, non-destructive detection of drought phenotypes in cucumber seedlings under SiO 2 nanoparticle treatment. Ablation experiments verified the positive contributions of the ADFE, CANL, and DHL modules. Furthermore, instance segmentation and phenotype extraction were completed using the Euclidean clustering algorithm to analyze the drought-alleviating effects of SiO 2 nanoparticles under PEG-simulated drought stress. Results indicate that a low concentration of 20 mg/L exhibits a weak alleviating effect, medium concentrations of 40-60 mg/L show bidirectional regulatory characteristics, and a high concentration of 100 mg/L causes negative physiological effects. The optimal application concentration is 80 mg/L, which comprehensively improves key phenotypes such as seedling height and volume under drought stress and exerts a positive regulatory effect on seedling growth under drought conditions. The DDCANet model constructed in this study provides an efficient technical tool for the accurate phenotypic detection of crop seedlings treated with SiO 2 nanoparticles under drought stress. It clarifies the optimal application concentration of SiO 2 nanoparticles, offers a precise concentration threshold and theoretical support for the scientific application of SiO 2 nanoparticles in drought-stressed cultivation of protected cucumber, and establishes a novel methodological reference for the research on phenotypic regulation of crops under drought stress via nano-agricultural technology.

Why it matches plant phenotyping methods3D点群分割モデルを開発・検証し、キュウリ幼苗の茎葉分離と形質抽出を自動化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論文として採用。

abstracttraditional manual measurement and classic point cloud segmentation models struggle to achieve high-throughput accurate detection of cucumber seedling phenotypes under drought stress.

Accurate detection of full-surface ear rot in maize using hyperspectral imaging and deep learning. ↗

Maize ear rot severely restricts maize yield and quality, making the breeding of disease-resistant varieties the core strategy for disease prevention and control. Due to the highly uneven spatial distribution of lesions on maize ears, precise full-surface detection is essential for objectively quantifying disease severity. However, traditional manual disease grading is highly subjective, and conventional RGB-based detection methods struggle to precisely identify lesion regions associated with maize ear rot. These limitations hinder the precise identification and quantitative analysis of maize ear rot infection regions, thereby limiting the reliability of phenotypic data used for resistance evaluation and subsequent genome-wide association studies (GWAS). To address these challenges, this study developed an integrated full-surface hyperspectral imaging system featuring line-scan imaging and synchronous rotation control. Non-redundant full-surface ear images were then generated using the oriented FAST and rotated BRIEF (ORB) algorithm combined with random sample consensus (RANSAC), hereafter referred to as ORB-RANSAC. Furthermore, after Savitzky-Golay (SG) preprocessing and feature selection using a genetic algorithm (GA), three machine learning models and three deep learning models were established, and their classification performance was compared. The results showed that the convolutional neural network-bidirectional long short-term memory network (CNN-Bi-LSTM) model achieved the best average performance, with an average overall accuracy (OA) of 95.61 ± 0.36%. It also achieved higher overall accuracy than traditional machine learning models such as random forest (RF), indicating that CNN-Bi-LSTM can achieve high-precision pixel-level detection of lesion regions showing Fusarium-associated maize ear rot symptoms. Additionally, this model was deployed in locally developed automatic analysis software, enabling an integrated analysis workflow from raw hyperspectral data input to the quantification of disease-related phenotypic parameters. This study not only fills the technical gap in the non-destructive full-surface detection of maize ear rot but also provides an efficient and reliable automated tool for high-throughput phenomics research, which holds great significance for accelerating the discovery of maize resistance genes and ensuring food security.

Why it matches plant phenotyping methodsトウモロコシ穂の病斑をハイパースペクトル画像と深層学習で定量し、全表面撮像システム、解析モデル、ソフトウェアを開発したため、植物表現型取得法が中心である。

abstractthis study developed an integrated full-surface hyperspectral imaging system featuring line-scan imaging and synchronous rotation control.

Gmunet: a lightweight hybrid architecture based on ghost and mamba for plant leaf disease segmentation ↗

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

Why it matches plant phenotyping methods植物葉の病害領域を画像からセグメンテーションする新規アーキテクチャの開発が主題であり、病徴・病害状態の抽出方法が中心です。

titleGmunet: a lightweight hybrid architecture based on ghost and mamba for plant leaf disease segmentation

External-field optimality of logarithmic coeffcients with applications to geometric image analysis ↗

This paper develops an external-field optimization framework for logarithmic coefficients of multiplier-defined univalent functions and establishes optimality principles with applications to geometric image analysis. Using the Herglotz representation, logarithmic coefficients are expressed as nonlinear moment functionals of probability measures on the unit circle, where multiplier coefficients act as an external field imposing admissibility constraints. A general Euler&ndash;Lagrange condition is derived, yielding a nonlinear equilibrium equation that characterizes extremal solutions. When the external-field potential admits a unique maximizer, the extremal measure collapses to a one-point distribution, leading to explicit optimal special-function solutions. The theoretical framework is applied to a dataset of citrus lesion images. After segmentation and conformal normalization of lesion regions, approximate logarithmic coefficients are computed from boundary harmonic expansions. A distortion index and harmonic separation criterion are introduced, and a coefficient separation theorem is verified numerically, demonstrating that geometric differences in lesion morphology correspond to measurable differences in logarithmic coefficient distributions. The results provide a mathematically rigorous connection between nonlinear external-field optimization, conformal special-function representations, and shape-based image descriptors. This approach offers a theoretically grounded and conformally invariant methodology for analyzing geometric irregularity in biomedical and agricultural imaging.

Why it matches plant phenotyping methods柑橘病斑画像を分割・正規化し、病斑形態を定量化する新しい画像記述子と判定基準を導入・検証しており、植物の病害状態の表現型抽出が中心である。

abstractThe theoretical framework is applied to a dataset of citrus lesion images. After segmentation and conformal normalization of lesion regions, approximate logarithmic coefficients are computed from boundary harmonic expansions.

Non-destructive Spatial Reconstruction of Plant Leaf Starch Using Reduced-Band SWIR Spectroscopy and Chemometric Modeling ↗

1 Abstract Non-structural carbohydrates (NSCs) are central to plant carbon allocation and physiological regulation, yet their quantification typically relies on destructive biochemical assays that lack spatial resolution. Here, we developed a shortwave infrared (SWIR) hyperspectral imaging workflow for non-destructive estimation and spatial reconstruction of starch-associated variation in strawberry leaves. The workflow combined automated hyperspectral segmentation, spectral preprocessing, Partial Least Squares Regression (PLSR), and constrained wavelength selection. Sample-level spectra extracted from 114 strawberry leaf samples grown across three different metabolic conditions were paired with destructive starch measurements and used to train models across the 900–1750 nm spectral range. A constrained greedy band-selection strategy revealed that predictive performance approached a plateau at approximately 12 wavelengths, indicating substantial spectral redundancy within the full hyperspectral dataset. The final reduced-band model achieved a cross-validated coefficient of determination (R 2 ) of 0.771 ± 0.066 and a root mean squared error (RMSE) of 0.743 ± 0.098 mg g −1 fresh weight using repeated stratified 5-fold cross-validation. Pixel-wise application of the final model generated spatial starch-associated maps that preserved pronounced intra-leaf heterogeneity, including vein-associated spatial structure. These results demonstrate that starch-associated spectral information can be reconstructed from a constrained reduced-band SWIR framework while retaining sufficient predictive performance for spatial mapping. The identified wavelength reduction supports the feasibility of deployable multispectral systems for non-destructive carbohydrate sensing in plant phenotyping applications.

Why it matches plant phenotyping methods植物葉のデンプン状態を非破壊推定・空間再構成するSWIR画像計測とケモメトリック解析ワークフローを開発・検証しており、フェノタイピング手法が中心です。

abstractHere, we developed a shortwave infrared (SWIR) hyperspectral imaging workflow for non-destructive estimation and spatial reconstruction of starch-associated variation in strawberry leaves.

3D Quantitative Modeling for Stone Fruit Quality Assessment by LF-NMRI ↗

The core volume ratio (CVR) is a key indicator for evaluating the proportion of edible fraction in stone fruits. Traditionally, CVR is determined through destructive sampling by separately measuring the masses of the core and entire fruit. Recently, low-field nuclear magnetic resonance imaging (LF-NMRI) has been introduced as a non-destructive alternative, but its sparse sampling limits the ability to achieve accurate spatial and volumetric quantification of fruit quality. To address this limitation, we propose a novel method for high-precision three-dimensional (3D) modeling of stone fruits. The method acquires tomographic LF-NMRI sequences along three orthogonal axes. Each sequence is segmented into pulp and core regions using a SwinUNet deep learning model and converted into point clouds for each view. Point clouds from the three orthogonal views are registered via a genetic algorithm to align structural information from complementary perspectives and fused into a unified 3D model through Poisson surface reconstruction. Using prunes as a representative case, the method enables accurate quantification of core and entire fruit volumes, achieving a CVR estimation with a mean absolute error of 0.13% compared to manual measurements. The proposed three-view reconstruction strategy yields a volumetric error of only 0.73%, significantly outperforming single-view (4.57%) and dual-view (3.73%) approaches. This technology provides a robust and accurate non-destructive solution for 3D internal quality analysis of fruits.

Why it matches plant phenotyping methodsLF-NMRI、深層学習セグメンテーション、3D再構成を組み合わせ、果実内部の芯・可食部体積という植物器官形質を非破壊推定する手法を開発・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 novel method for high-precision three-dimensional (3D) modeling of stone fruits.

Integrated UAV-Based Multispectral Scouting and Variable-Rate Aerial Spraying for Enhanced Crop Yield and Input Efficiency: A Field-Validated Study ↗

Precision agriculture demands integrated systems that couple accurate crop stress detection with targeted intervention to mitigate climate volatility and input overuse. Traditional manual scouting and uniform chemical application are spatially imprecise, labour-intensive, and environmentally burdensome. This study field-validates a closed-loop unmanned aerial vehicle (UAV) framework integrating AI-driven multispectral scouting with prescription-mapped variable-rate aerial spraying (VRS). A randomized complete block design with four replications was implemented in maize (Zea mays L.) across a 2.4 ha field in Davangere Karnataka, India. Scouting flights at 25 m altitude (1.8 cm ground sampling distance) utilized a MicaSense RedEdge-P and FLIR thermal sensor, with imagery processed through a radiometrically calibrated YOLOv8-Seg pipeline to detect early-stage disease, nutrient deficiency, and water stress. Prescription maps derived from NDRE and CWSI thresholds directly controlled a DJI Agras T40 centrifugal sprayer calibrated to ASABE S572.1 standards. The integrated system achieved an AI detection F1-score of 0.91, reduced agrochemical volume by 34.2%, and improved spray deposition uniformity (coefficient of variation = 18.4%) relative to conventional blanket spraying. Grain yield increased significantly by 11.7% (p

Why it matches plant phenotyping methodsUAVマルチスペクトル・熱画像とAI解析により、作物の病害、栄養欠乏、水ストレスを検出する方法を開発・現地検証しており、植物状態の取得が統合システムの中心的要素である。

abstractThis study field-validates a closed-loop unmanned aerial vehicle (UAV) framework integrating AI-driven multispectral scouting with prescription-mapped variable-rate aerial spraying (VRS).

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.

High-Precision Instance Segmentation of Tree Saplings by Multimodal Mask R-CNN Integrating RGB and Multispectral Image-Derived Indices Through a Field Phenotyping Platform ↗

The high-precision instance segmentation of tree saplings is a fundamental prerequisite for the high-throughput phenotypic analysis of individual seedlings in intelligent tree breeding and precision silviculture. However, sapling segmentation remains challenging because of blurred boundaries, object adhesion, missed detections, and inaccurate mask delineation in field environments. To improve sapling segmentation performance and address these challenges, this study proposes a multimodal Mask R-CNN framework in which RGB imagery was paired with one multispectral-derived vegetation index at a time to construct separate RGB-VI input combinations, taking ginkgo saplings as a representative case. A dataset of 400 saplings was constructed using a high-throughput field phenotyping platform. The backbone network was extended with an independent vegetation index branch, and three fusion strategies (early, multi-step, and late fusion) were designed within a feature pyramid network to enable multi-scale multimodal feature integration. The results showed that all multimodal models outperformed unimodal baselines in terms of segmentation accuracy and recall. Among them, the multi-step fusion strategy achieved the best performance, while the RGB-EVI multi-step fusion model achieved the highest strict-matching precision (AP@75 = 87.7%) and recall (71.3%), with superior performance in dense sapling delineation and background suppression. These findings indicate that multimodal feature fusion can effectively improve sapling instance segmentation and provide methodological support for high-throughput plant phenotyping.

Why it matches plant phenotyping methodsマルチモーダル画像による樹木苗個体のインスタンスセグメンテーション手法を開発・比較し、高スループット表現型解析を支援することが中心である。

abstractThe high-precision instance segmentation of tree saplings is a fundamental prerequisite for the high-throughput phenotypic analysis of individual seedlings in intelligent tree breeding and precision silviculture.

MCB-SwinUNet: attention-gated skip fusion framework for multi-crop leaf lesion segmentation with cross-domain generalization and boundary accuracy ↗

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

Why it matches plant phenotyping methods葉の病斑を画像からセグメンテーションする手法の開発が題名の中心であり、植物の病害状態を直接推定するため、植物フェノタイピング手法として適格です。

titleMCB-SwinUNet: attention-gated skip fusion framework for multi-crop leaf lesion segmentation with cross-domain generalization and boundary accuracy

Integration of Aerial Photogrammetry, UAV LiDAR and Terrestrial LiDAR Point Clouds for Individual Tree Measurement and Individual Tree Carbon Storage Estimation ↗

Urban forest carbon sequestration is vital for environmental health, climate change mitigation, and enhancing the quality of life in urban areas. This paper presents a framework for high density point clouds production by integrating point data from aerial photogrammetry, UAV-based LiDAR and terrestrial LiDAR for individual tree measurements and carbon storage estimation. The aerial photos, UAV-based LiDAR and terrestrial LiDAR were observed based on common ground control points and combined using Iterative Closest Point (ICP) algorithm. The combined point cloud was iltered to separate ground points and normalized based on Digital Terrain Model (DTM). The normalized point cloud was used for individual tree segmentation from which individual tree measurements such as, tree height, Diameter at Breast Height (DBH) and crown diameter were estimated. The estimated tree parameters were used for individual carbon estimation. The results show that the individual tree segmentation method signi icantly underestimated the number of trees. The estimation of DBH, tree height, and crown diameter achieved the Root Mean Square Error (RMSE) value of 0.107m, 1.385m and 2.650m respectively. However, in general the estimates experience underestimation as shown by Mean Bias Error (MBE) with 0.003m, -0.636m and 0.001m for DBH, tree height and crown diameter respectively. The estimated values for each individual tree were used for individual tree biomass and carbon storage recording the Root Mean Square Error (RMSE) at 1970.236 kg and 886.606 kgC respectively while attaining the Mean Bias Error (MBE) measure of 140.019 kg and 63.009 kgC each. The proposed framework showed promising results for individual tree carbon estimation. Nonetheless, further attention should be given on individual tree delineation process.

Why it matches plant phenotyping methods航空写真、UAV・地上LiDARを統合し、個体樹木の分離と樹高・DBH・樹冠径を推定して精度評価する手法が中心であり、植物形質計測の技術的検証に該当する。

abstractThis paper presents a framework for high density point clouds production by integrating point data from aerial photogrammetry, UAV-based LiDAR and terrestrial LiDAR for individual tree measurements and carbon storage estimation.

Estimation of Ramie Key Phenotypic Traits Based on UAV Remote Sensing ↗

UAV-based phenotyping enables efficient high-throughput measurement of field crops. Phenotypic monitoring of ramie is critical for its cultivation management and variety breeding. However, ramie exhibits characteristics including multiple annual harvests, short growth cycles and rapid dynamic growth change, all of which increase the difficulty of growth monitoring and yield estimation. This study aims to utilize UAV-based multispectral remote sensing to estimate ramie plant height (PH), leaf area index (LAI), and above-ground biomass (AGB) over multiple time series, and to assess the influence of seasonal effects and different data processing strategies on the accuracy of ramie digital phenotyping. Over three ramie growth cycles, a total of 15 UAV flights were conducted over an experimental field consisting of 72 plots. The structure from motion (SfM) algorithm was applied to estimate PH. Remote sensing features derived from UAV imagery were used with background segmentation and machine learning to estimate LAI. The AGB was estimated by combining remote sensing-derived PH, LAI, and climate data. The results showed that the estimated and measured phenotypes were highly correlated, with optimal coefficients of determination of 0.961 for PH and 0.873 for LAI. Background segmentation improved LAI accuracy. Integrating climate data, remote sensing-derived PH and LAI significantly enhanced the accuracy of AGB estimation. In conclusion, this study provides a feasible method for extracting ramie phenotypes from UAV remote sensing imagery, providing methodological support for large-scale management of the crop industry and intelligent, precise monitoring of crop growth.

Why it matches plant phenotyping methodsUAVマルチスペクトル画像、SfM、背景分割、機械学習を用いてラムーの草丈・LAI・地上部バイオマスを推定し、精度評価まで行う手法研究であり、表現型取得・抽出が中心である。

abstractThis study aims to utilize UAV-based multispectral remote sensing to estimate ramie plant height (PH), leaf area index (LAI), and above-ground biomass (AGB) over multiple time series, and to assess the influence of seasonal effects and different data processing strategies on the accuracy of ramie digital phenotyping.

Automated Fruit Disease Detection using Convolutional Neural Networks ↗

This study proposes a convolutional neural network (CNN)-based method for the automated detection of fruit diseases. Using deep learning techniques, the model is trained on a large collection of fruit images to accurately recognize and classify different types of diseases affecting fruits. The system provides a rapid, reliable, and cost-effective approach for early disease identification, which can support better crop management and minimize the excessive use of harmful chemicals. Experimental results demonstrate high classification accuracy, highlighting the significant potential of artificial intelligence in enhancing modern agricultural practices. In the proposed approach, the application first captures an input image from the user. The image then undergoes segmentation to extract the relevant region of interest. The segmented image is subsequently provided as input to the CNN model, which extracts important feature vectors for accurate fruit disease detection and classification. The proposed model attains 95% detection accuracy. Keywords— Fruit disease detection, CNN, Image classification, Agricultural, automation, Disease identification.

Why it matches plant phenotyping methods果実画像から病害状態を直接推定するCNN手法の開発・評価が中心であり、植物の病害表現型を対象とする画像ベースのフェノタイピング研究。

abstractThis study proposes a convolutional neural network (CNN)-based method for the automated detection of fruit diseases.

LeafFocusAI: An ROI-Aware Deep Learning Framework for Automatic Leaf Disease Detection Using FocusNet-LDD ↗

Abstract Plant disease is a silent threat to global food security and agriculture; the only way to manage plant diseases effectively is through accurate and timely diagnosis. State-of-the-art manual inspection methods are Labor-Intensive and prone to error. In contrast, the few existing automated deep-learning methods struggle with reduced accuracy due to the automatic extraction of superfluous background information and a loss of interpretability. Most state-of-the-art models studied complete leaf images, ignoring localized disease regions, making them less robust and practical. In this paper, we present FocusNet-LDD, a ROI-aware deep learning framework designed to narrow the gaps with state-of-the-art Region of Interest (ROI) extraction, attention mechanisms, and sequential feature modelling, thereby improving plant disease detection. The proposed methodology utilizes YOLOv8 and U-Net architectures to target the areas occupied by diseased leaves, thereby minimizing background noise and concentrating on features associated with the symptoms. The classification model utilizes CBAM to enable spatial and channel-wise attention features, followed by a Transformer encoder that learns contextual representations to support the classification of discrete disease classes across various image acquisition settings. FocusNet-LDD leverages a dual-direction dilated convolution framework to enhance the representation ability of image features, incurring only a minor increase in time and space costs. This is demonstrated through extensive experiments on benchmark datasets, which show that it achieves the best overall accuracy (98.79%) compared to the baseline and more recent state-of-the-art models. Ablation studies validate the contribution of each module, and Grad-CAM visualizations also provide explainability by highlighting which disease-relevant regions drive predictions. The high accuracy, interpretability, and robustness of the proposed framework might pave the way for it to become a real-world tool for timely disease diagnosis of crops and appropriate decision-making. Its modular architecture also enhances its integration within precision agriculture systems and mobile platforms that can operate under low-resource conditions, promoting sustainable crop management and mitigating yield losses.

Why it matches plant phenotyping methods植物葉の病害症状を画像から検出・分類する深層学習フレームワークの開発とベンチマーク検証が中心であり、植物の病害状態を直接推定するため。

abstractwe present FocusNet-LDD, a ROI-aware deep learning framework designed to narrow the gaps with state-of-the-art Region of Interest (ROI) extraction, attention mechanisms, and sequential feature modelling, thereby improving plant disease detection.

An Automated Information Processing Framework for UAV-Based Detection and Spatial Mapping of Crop Damage Using Deep Learning ↗

The early detection and spatial characterization of crop damage are critical for improving decision-making in precision agriculture, particularly in regions where traditional monitoring methods are limited in scalability and objectivity. This study presents an integrated information processing framework that couples UAV-based image acquisition, instance segmentation, slicing-aided inference of large orthomosaics, and georeferenced spatial analysis into a single reproducible pipeline for the detection and mapping of crop damage. The framework is applied to maize cultivated under traditional milpa systems in Yucatán, Mexico, a region characterized by intercropping, irregular plant spacing, and complex backgrounds rarely represented in mainstream agricultural deep learning benchmarks. High-resolution RGB images were systematically acquired over maize fields in Yucatán, Mexico, and curated into specialized datasets representing parcels, individual plants, and damaged vegetation. Instance segmentation models based on the YOLOv11 architecture were trained and evaluated to extract visual information related to crop condition, while the Slicing-Aided Hyper Inference (SAHI) method was integrated to enable efficient processing of large orthomosaic images. The proposed framework achieved high performance in detecting maize plants, with a precision of 92.9% and an mAP50 of 94.2%, and demonstrated reliable identification of damage patterns associated with Spodoptera frugiperda, reaching a precision of 79.2% and an mAP50 of 71.7%. The resulting georeferenced outputs provide spatially explicit information that supports quantitative analysis of crop health and damage distribution. The results indicate that the proposed framework constitutes a scalable and reproducible approach for UAV-based visual information extraction, with potential applicability to broader agricultural monitoring and data-driven decision support systems.

Why it matches plant phenotyping methodsUAV画像、インスタンスセグメンテーション、SAHIを統合し、作物の損傷状態を抽出・定量化する再現可能な手法が研究の中心であり、性能評価も実施している。

abstractThis study presents an integrated information processing framework that couples UAV-based image acquisition, instance segmentation, slicing-aided inference of large orthomosaics, and georeferenced spatial analysis into a single reproducible pipeline for the detection and mapping of crop damage.

Hybrid Explainable DeiT-Based Framework for Plant Disease Classification and Severity Estimation ↗

Abstract The detection of plant diseases is essential to the preservation of agricultural productivity and food security, yet the existing technologies are likely to have low interpretability and low generalization in practice. This work suggests a hybrid deep learning model in the form of Data-efficient Image Transformers (DeiT) to detect and classify plant diseases and estimate their severity. The framework takes advantage of DeiT-Base, DeiT-Small, and DeiT-Tiny models to embrace global contextual dependencies of plant leaf images. The proposed hybrid Explainable Artificial Intelligence (XAI) module aims to enhance interpretability by combining Gradient-weighted Class Activation Mapping (Grad-CAM) as a local feature attribution model and Attention Rollout as a global dependency visualization model. In addition, a leaf segmentation method, a HSV-based method, is employed, which isolates disease-relevant regions and minimizes noise to increase the classification accuracy and level of explanation. The damage ratio analysis is combined with attention maps generated by XAI to build a severity estimation module. Experiments on the New Plant Diseases Dataset (Augmented) with large-scale experiments demonstrate that the proposed DeiT-Base model can achieve a maximum accuracy of 99.13, a better result compared to a variety of CNNs, such as ResNet50, DenseNet121, MobileNetV3, EfficientNet, InceptionV3. Also, hybrid XAI framework has better interpretability performance, such as focus score, noise, signal-to-noise ratio (SNR), and entropy, than single explanation procedures. The system proposed is not only capable of improving the accuracy of classification but also has better transparency and meaningful severity estimation which makes it appropriate to the real-world application of precision agriculture.

Why it matches plant phenotyping methods植物葉画像から病害分類と病害重症度を推定する画像解析手法を開発・評価しており、病害状態の表現型取得が中心的な貢献です。

abstractThis work suggests a hybrid deep learning model in the form of Data-efficient Image Transformers (DeiT) to detect and classify plant diseases and estimate their severity.

The Accuracy and Efficiency of YOLO Algorithms in Identifying Plant Leaf Diseases ↗

Plant diseases are one of the biggest challenges of world agriculture, leading to enormous output losses and economic damages. Early and accurate detection of these diseases may help to increase crop yield, improve resource efficiency, decrease costs and environmental impact and assist the production of high-quality food. In recent years, deep learning (especially computer vision approaches) has become a strong tool for a number of tasks such as picture classification, segmentation and object detection. Such techniques include the You Only Look Once (YOLO) family of neural networks, a state-of-the-art technology for accurate object detection. In this work, we use YOLOv5, YOLOv7 and YOLOv8 models for citrus disease detection with the CCL’20 dataset. During training, a number of data augmentation techniques are used to improve the model performance, such as picture translation, scaling, flipping and mosaic augmentation. The model performance was evaluated using the Mean Average Precision (mAP) for Intersection over Union thresholds from 50% to 95% (mAP@50–95). The results showed that the YOLOv8 model performed better than the other variations, with significant improvements compared to the benchmarks reported in previous studies. After hyper-parameter adjustment, the improved model reached a mAP@50-95 of 96.1% on the test set for detection of the citrus diseases. The model attained the mAP@50-95 of 95.3%, 96.0% and 97.0% for Anthracnose, Melanose and Bacterial Brown Spot respectively for each disease. Furthermore, the model could reliably identify both single and many cases of the same and different diseases inside a single image, illustrating the robustness of recent YOLO architectures. Finally, the trained YOLOv8 model has been successfully installed into the Roboflow platform which is ready for practical applications in citrus disease monitoring.

Why it matches plant phenotyping methods柑橘葉の病害状態を画像から検出・分類するYOLO手法の開発と性能比較が中心であり、植物病害フェノタイピング手法に該当する。

abstractIn this work, we use YOLOv5, YOLOv7 and YOLOv8 models for citrus disease detection with the CCL’20 dataset.

Assessing robustness and transferability of image‐based semantic segmentation models for major field crops ↗

Abstract Plant breeding is essential for crop improvement, yet progress is often hindered by slow, laborious, and subjective field phenotyping methods. High‐throughput phenotyping (HTP), particularly image‐based methodologies powered by machine learning, offers a pathway to overcome these limitations. However, achieving robustness and generalization when analyzing diverse genotypes within a crop and across reproductive stages remains challenging and can affect model performance and the accurate extraction of phenotypic features. This study evaluated the performance of semantic segmentation models across a diverse panel of genotypes and distinct crop reproductive stages, using wheat ( Triticum aestivum L.), sorghum ( Sorghum bicolor L.), and corn ( Zea mays L.) as case studies. The primary objectives were to analyze (i) the overall prediction performance on the aggregated dataset for each crop, (ii) the stratified performance by genotype and collection date, and (iii) the temporal and genotypic transferability across growth stages and unseen genotypes. Four distinct smartphone cameras were used to collect images of the reproductive structure across crop growth stages (different collection dates) from 160 corn, 80 sorghum, and 40 wheat genotypes. The total number of images per crop was 2000 for wheat, 4000 for sorghum, and 3840 for corn. Five semantic segmentation models were tested in this study—DeepLabv3+, MaskFormer, SegFormer, SegNet, and U‐Net—using the images and respective binary masks for training and testing. The SegFormer model achieved the highest intersection over union (IoU) values for corn (0.90) and sorghum (0.92), while the U‐Net model performed best for wheat (0.89). A minor performance decline, with IoU differences up to 0.1, was observed when testing the same model across different genotypes. However, the temporal transferability drops up to 0.5 IoU when training and inferring on different crop growth stages. The main reason for those changes may lie in the natural color and organ architecture temporal changes between the trained and tested datasets when transferring the models across growth stages. These results highlight the urgent need to prioritize robustness and transferability when developing reliable in‐field HTP methodologies.

Why it matches plant phenotyping methods植物の生殖器官画像からの表現型抽出に用いるセマンティックセグメンテーション手法を、作物・遺伝子型・生育段階間で性能と転移性の観点から比較検証しており、方法論が研究の中心である。

abstractThis study evaluated the performance of semantic segmentation models across a diverse panel of genotypes and distinct crop reproductive stages

Heliocot: A Field RGB Imaging Approach for Diurnal Canopy Orientation Dynamics in Early-Season Cotton ↗

Understanding diurnal canopy orientation in crops is important for interpreting plant responses to light and environmental conditions, yet field-based quantification remains limited. In this study, we present Heliocot, a field RGB imaging approach that converts time-resolved images into reference-area standardized projected leaf area (PLA) time series to quantify within-day canopy orientation dynamics in early-season cotton. Leaf instance segmentation was performed using YOLOv8m-seg and refined through a 144-combination post-processing optimization. On the held-out early-stage validation/tuning set, the selected workflow showed strong agreement with manual ground truth (R2 = 0.948; NRMSE = 0.082) and destructive leaf area measurements (R2 = 0.836). Derived diurnal metrics, including Daily Orientation Amplitude (DOA) and Peak Orientation Index (POI), consistently revealed a midday maximum (13:15) in canopy projection. Exploratory genotype-level analysis suggested negative associations between orientation indices and selected plant traits, including specific leaf area (SLA) versus DOA (r = −0.71, p = 0.021, R2 = 0.508), destructive leaf area (LA) versus DOA (r = −0.69, p = 0.028, R2 = 0.471), and stem dry weight (SDW) versus POI (r = −0.74, p = 0.014, R2 = 0.554), while plant height was not significantly associated with POI and DOA (p > 0.05). Although currently limited to early-season conditions and two field-imaging dates, this approach provides a practical workflow for field-based monitoring of canopy projection dynamics in cotton, while broader temporal and environmental validation remains necessary.

Why it matches plant phenotyping methods圃場RGB画像から葉面積と日周キャノピー配向動態を推定する手法を開発・検証しており、植物形質取得が研究の中心である。

abstractwe present Heliocot, a field RGB imaging approach that converts time-resolved images into reference-area standardized projected leaf area (PLA) time series to quantify within-day canopy orientation dynamics in early-season cotton.

Deep Learning for Tomato Disease Detection and Severity Assessment: A Systematic Analytical Review of Methods, Datasets, and Challenges ↗

Abstract Tomato diseases significantly affect crop productivity and food security, necessitating accurate and timely detection methods. This paper presents a systematic and analytical review of deep learning approaches for tomato disease detection and severity assessment, based on 76 research studies. Existing methods are categorized into classification, detection, segmentation, and emerging multi-task frameworks. The analysis shows that convolutional neural networks achieve high accuracy on controlled datasets but exhibit limited generalization in real-world conditions. Advanced architectures, including transformer-based and hybrid models, improve performance but increase computational complexity. A key finding is the limited focus on disease severity assessment, which remains underexplored despite its importance for precision agriculture. The review identifies major challenges, including dataset limitations, lack of standardized benchmarks, and deployment constraints. Future directions emphasize multi-task learning, real-world dataset development, lightweight models, and explainable AI. This study provides a foundation for developing robust and practical tomato disease detection systems.

Why it matches plant phenotyping methodsトマト病害の検出・重症度評価という植物状態の画像推定手法を、研究・データセット・課題の観点から体系的にレビューしており、フェノタイピング手法のレビューが中心である。

abstractThis paper presents a systematic and analytical review of deep learning approaches for tomato disease detection and severity assessment, based on 76 research studies.

Multi-Scale Feature Rectification for Crop Leaf Disease Segmentation in Complex Scenarios ↗

Crop leaf disease segmentation in complex natural environments remains challenging because lesion regions often exhibit substantial scale variation, blurred boundaries, and severe background interference. To address these issues, this study proposes a Multi-Scale Feature Rectification Network (MFR-Net) for crop leaf disease segmentation. The proposed network adopts an EfficientNetV2-S-based encoder to extract hierarchical features, incorporates a hybrid attention mechanism to enhance lesion-sensitive spatial and channel representations, introduces a Cross-Window Atrous Spatial Pyramid Pooling (CWASPP) module to strengthen multi-scale contextual modeling, and employs a Feature Rectification Module (FRM) in the decoder to alleviate semantic inconsistency during cross-level feature fusion. Experiments on a Kaggle-derived benchmark constructed from the unaugmented data folder of the public Leaf Disease Segmentation Dataset, containing 588 diseased-leaf images and 588 corresponding binary lesion masks, showed that MFR-Net achieved the highest mIoU of 74.27% and the highest Recall of 87.61% among the compared methods, and maintained competitive Dice performance (84.25%) with 25.10 M parameters and 37.55 G FLOPs. Ablation results further confirmed the effectiveness of the proposed design, with CWASPP providing the most notable individual contribution. Additional experiments were conducted on an independent Apple Leaf Dataset comprising 3197 image–mask pairs, collected under mixed controlled and natural field-like imaging conditions. The results showed competitive performance under a different data distribution, and robustness evaluation further verified stable performance under severe noise, blur, darkness, and contrast variation. All experiments were implemented in PyTorch 2.11.0 (CUDA 12.8) on a workstation equipped with an NVIDIA GeForce RTX 4060 Ti GPU (8 GB). These results indicate that MFR-Net provides an effective and robust solution for crop leaf disease segmentation in complex agricultural scenarios.

Why it matches plant phenotyping methods病斑領域を画像から抽出するセグメンテーション手法を開発し、複数データセット、アブレーション、ノイズ等への頑健性で検証しており、植物病害状態の表現型取得が中心である。

abstractAblation results further confirmed the effectiveness of the proposed design

High-throughput phenotyping for climate-resilient forests: integrating multi-sensor fusion and root-shoot dynamics. ↗

Climate change is increasing the frequency of compound drought and heat events, threatening forest stability worldwide. While genomics has helped identify resilient genotypes, our ability to characterize adaptive traits - phenotyping - has not kept pace. This creates a bottleneck: we can sequence trees faster than we can understand how they physically respond to stress. Moving away from single-sensor monitoring, the field is now embracing multi-sensor data fusion, in which thermal imaging, Solar-Induced Fluorescence (SIF), hyperspectral remote sensing, and LiDAR are combined on platforms ranging from Unmanned Aerial Vehicles (UAVs) to ground-based robotic systems. These integrated approaches are proving effective for detecting physiological stress - such as changes in stomatal conductance - before visible damage appears. Deep learning models, meanwhile, are beginning to outperform traditional vegetation indices for specific tasks such as tree-crown segmentation and stress classification, although their performance remains constrained by overfitting, limited transferability, and domain shift across forest types in analyzing complex forest canopies. A major limitation remains, however: most high-throughput phenotyping (HTP) focuses on the canopy, largely ignoring the root system and the soil-plant-atmosphere continuum (SPAC), which are critical for drought resilience. In this review, we argue that developing climate-resilient forests requires looking below the canopy. We propose a constraint-based framework that couples aerial sensor data with eco-hydrological approaches and process-based modeling to narrow the range of plausible root functional strategies-rather than to directly identify root phenotypes, while critically evaluating the assumptions and validation challenges inherent in this approach. Future research should focus on standardized protocols, open benchmark datasets, and Explainable AI (XAI) to strengthen the link between above-ground signals and below-ground traits.

Why it matches plant phenotyping methods植物フェノタイピング手法を中心に、マルチセンサー融合、深層学習、検証課題、標準化・ベンチマークをレビューしているため。

abstractIn this review, we argue that developing climate-resilient forests requires looking below the canopy.

3D Reconstruction of Mature Arabidopsis Ovules Using FIB-SEM to Study Filiform Apparatus Morphology ↗

Volume electron microscopy based on serial sectioning allows for three-dimensional (3D) visualization and analysis of the internal structures of tissues, cells, and organelles. One such technique, focused ion beam (FIB) scanning electron microscopy (SEM), has the advantages of nanoscale sectioning and high z-resolution, but the disadvantage of limited volume processing. Because of this limitation, targeting localized objects by FIB-SEM is difficult. Here, we developed a FIB-SEM observation workflow that enables the analysis of the filiform apparatus of synergid cells enclosed in the Arabidopsis ovule. In this protocol, plant samples are stained, embedded, trimmed, and carbon-coated while maintaining their orientation within the tissue. Then, sequential observations are performed using Cut & See function of FIB-SEM, followed by image processing for 3D reconstruction. Utilization of multi-scanning and image cropping from high-resolution data helps to identify localized targets within plant tissue. The filiform apparatus, which is an invaginated cell wall structure of the synergid cells, shows distinct contrast in each image, allowing for segmentation using brightness-based binarization. Such segmentation avoids the need to manually trace complex structures and facilitates 3D reconstruction by volume electron microscopy. Key features • Sampling and trimming of the resin block enable directionally loading in FIB-SEM. • Multi-scanning by FIB-SEM and target extraction by image processing software enable 3D reconstruction of local areas within the sample block. • Binarization using distinctive brightness of cellular structures enables segmentation without manual tracing of complex structures such as the filiform apparatus cell wall.

Why it matches plant phenotyping methods植物組織内の構造をFIB-SEMと画像処理で3D再構成・セグメンテーションするワークフローを開発しており、フィリフォーム装置形態という植物器官形質の取得が中心である。

abstractHere, we developed a FIB-SEM observation workflow that enables the analysis of the filiform apparatus of synergid cells enclosed in the Arabidopsis ovule.

Total Fresh Weight Estimation Model for Herbaceous Plant Based on Improved YOLOv5 and 3D Point Clouds ↗

The real-time quantitative estimation of herbaceous plant growth status holds significant potential for investigating fertilization effects, predicting growth curves, and enhancing crop yield. This study constructed a growth quantification model using an improved YOLOv5 architecture integrated with 3D point cloud processing, with pak choi as an exemplar crop. To improve the recognition accuracy while reducing the number of parameters, we employed a lightweight YOLOv5 model enhanced with Atrous Spatial Pyramid Pooling and Ghost convolution modules for individual pak choi plant localization and growth stage classification. We also developed a segmentation method based on the HSV color space to segment leaves. To estimate the total fresh weight of individual plants, we first calculated the leaf surface area by generating a triangular mesh from the corresponding leaf point clouds and predicted the chlorophyll content using a stacking ensemble model. Subsequently, to address the leaf occlusion issues, the leaf pixel ratio in the images, leaf surface area, and mean leaf chlorophyll content were collectively used as independent variables. Finally, a multiple linear regression model was developed to accurately estimate the total fresh weight of individual pak choi plants. Experimental results demonstrate that the modified YOLOv5 architecture achieves a 3.5% improvement in mAP@0.5 (reaching 96%) and a 4.66% increase in F1-score (attaining 90.26%), while significantly reducing the computational complexity compared to the baseline model. Statistical tests verified that the fitted equation could explain 79% of the variation in the total fresh weight, with an average relative error of 12.16%. This enables non-contact and accurate measurement of the pak choi growth status.

Why it matches plant phenotyping methodsYOLOv5、3D点群、葉面積・クロロフィル推定を統合し、個体の生体重という植物形質を非接触推定する手法が研究の中心である。

abstractThe real-time quantitative estimation of herbaceous plant growth status holds significant potential

A Multi-Head UNet++ Framework with Fractional Differential Output Refinement for UAV Multispectral Crop Stress Mapping ↗

This study presents a unified semantic segmentation framework for UAV-based multispectral crop stress mapping, focusing on the integration of water stress and rust disease conditions within a common label space. Unlike conventional approaches that address individual stress factors independently, the proposed framework harmonizes heterogeneous datasets with different annotation schemes into a single multi-class segmentation problem. To achieve this, UAV multispectral orthomosaics are processed using a patch-based strategy and a multi-head UNet++ architecture incorporating segmentation, edge-aware, and Signed Distance Transform (SDT) branches. In addition, a physics-informed output-space refinement module based on fractional partial differential equations (FPDE) is introduced to enhance spatial coherence and boundary preservation in the predicted maps. Experimental results demonstrate the effectiveness of the proposed framework within the evaluated dataset setting, particularly in terms of boundary delineation, spatial consistency, and minority-class detection. The study highlights the feasibility of integrating heterogeneous stress conditions into a unified segmentation framework and provides a foundation for future research on scalable multi-source agricultural monitoring systems.

Why it matches plant phenotyping methodsUAVマルチスペクトル画像から作物の水ストレスおよびさび病状態を推定するセマンティックセグメンテーション手法の開発が中心であり、植物状態の取得・抽出に該当する。

abstracta multi-head UNet++ architecture incorporating segmentation, edge-aware, and Signed Distance Transform (SDT) branches

3D reconstruction and segmentation of grape bunches for robotic berry thinning ↗

• End-to-end pipeline from neural reconstruction to physical grape berry manipulation. • Efficient point clouds generation using NeRF and the metric scale derived directly from robot kinematics. • RANSAC sphere fitting achieves 92.1% berry detection precision without annotated training data. • Stem-aligned 6-DoF pose optimization improves end-to-end grip success by 17.2%. Table grape thinning requires selective removal of 20–40% of berries from dense clusters. In practice, workers decide which berries to remove by considering both the approximate berry count and local 3D spatial characteristics such as crowding and relative positioning. Automating this task is challenging because conventional 2D image-based approaches suffer from occlusion-related counting errors and lack explicit 3D spatial information necessary for reliable manipulation. We propose a robot-integrated vision pipeline that reconstructs grape bunch structure from posed multi-view RGB images. Neural Radiance Fields (NeRF) is used to learn a volumetric scene representation, from which a dense, low-noise point cloud is extracted via depth back-projection, and RANSAC-based geometric fitting models individual berries and stems, enabling berry-level segmentation and orientation estimation for manipulation planning. The perception pipeline uses an eye-in-hand RealSense D405 camera mounted on a Fanuc CRX-5iA collaborative robot. Camera poses are derived from the robot kinematic chain, allowing the reconstructed point cloud and detected berry centers to be expressed directly in the metric robot base frame without external scale recovery. In robot-mounted RealSense D405 experiments on 10 grape bunches, RANSAC sphere fitting achieved a counting MAE of 0.50 berries, RMSE of 0.71 berries, and mean center localization error of 2.71 mm. On a 52-bunch benchmark, RANSAC sphere fitting outperforms the learning-based SoftGroup++ method for 3D berry instance segmentation (92.1% vs 82.8% average precision) without requiring annotated training data. In 35 manipulation trials, the system achieved an 85.7% pre-grasp reachability rate and an 83.3% conditional target success rate demonstrating an end-to-end pipeline from neural reconstruction to manipulation-ready berry poses.

Why it matches plant phenotyping methodsブドウ房の3D再構成、ベリー分割・計数・位置推定を中核とするロボット統合型フェノタイピング手法であり、技術性能も定量評価している。

abstractWe propose a robot-integrated vision pipeline that reconstructs grape bunch structure from posed multi-view RGB images.

AI-Driven Plant Disease and Pest Surveillance: Deep Learning, IoT, and Next-Generation Crop Protection ↗

Plant disease and pest surveillance is undergoing a profound technological transition. Conventional crop protection has historically depended on episodic field scouting, expert visual inspection, and broad-spectrum preventative spraying, all of which are constrained by labour intensity, uneven diagnostic accuracy, and weak temporal resolution. In contrast, recent advances in artificial intelligence, deep learning, the Internet of Things, remote sensing, and edge computing have enabled crop-health monitoring systems that are more continuous, data-rich, and spatially explicit. This review analyses the evolution of AI-driven plant disease and pest surveillance, with particular attention to how image-based deep learning, connected environmental sensing, unmanned aerial vehicle platforms, cloud-edge infrastructures, and multimodal analytics are reshaping next-generation crop protection. The article argues that the central innovation is not merely automated diagnosis, but the emergence of surveillance ecosystems capable of recognising symptoms, estimating risk, localising hotspots, and informing more selective intervention. The review synthesises major developments in convolutional neural networks, object detection, semantic segmentation, transfer learning, domain adaptation, transformer-based computer vision, anomaly detection, environmental time-series modelling, and multimodal analytics. It also evaluates the practical obstacles that still limit real-world deployment, including dataset bias, annotation uncertainty, poor cross-domain generalisation, limited interoperability, energy and connectivity constraints, weak model explainability, and uneven economic accessibility. The article further considers how AI-based surveillance may strengthen integrated pest management by supporting earlier warning, more precise treatment timing, reduced blanket pesticide use, and stronger alignment between biological risk and management action. It concludes that the future of crop protection will depend less on isolated improvements in benchmark accuracy and more on the development of trustworthy, scalable, and biologically meaningful surveillance systems that can support sustainable decisions under real agricultural conditions.

Why it matches plant phenotyping methods植物病害の症状認識・リスク推定・ホットスポット局在化を行う画像解析、センサー、UAV、マルチモーダル手法を中心にレビューしており、植物の病害状態を推定するフェノタイピング手法レビューに該当する。

abstractThis review analyses the evolution of AI-driven plant disease and pest surveillance, with particular attention to how image-based deep learning, connected environmental sensing, unmanned aerial vehicle platforms, cloud-edge infrastructures, and multimodal analytics are reshaping next-generation crop protection.

A Root Foundation Model for Zero-Shot Segmentation ↗

Foundation models pre-trained on massive datasets have demonstrated impressive performance, but in some specialised domains have been found to have lower accuracy. Domain-specific foundation models target a particular domain such as retinal or plant images. These domain-specific models have shown inconsistent results and the benefit to root segmentation is unknown. We train and evaluate the first domainspecific foundation model for root segmentation. Evaluation uses a leave-one-dataset-out design across nine diverse root datasets with two architectures. Applied zero-shot to unseen datasets, the root foundation model achieves 92% of fine-tuned Dice on average (0.636 versus 0.698), with 5 of 9 datasets above 90%. With 10 patches of few-shot fine-tuning, the root foundation model recovers 95% of its full-data Dice on average, versus 69% for a general pre-trained model. At low patch counts the general pre-trained model often failed to converge, with 5 of 9 datasets giving Dice below 0.05 at 3 patches, while the root foundation model produced Dice above 0.47 on every dataset and patch count. With full target-data fine-tuning, the two perform comparably, with mean improvements of +0.011 Dice for MobileSAM and +0.022 for M2F Swin-S, neither significant (Wilcoxon p = 0.150 and 0.064). We release our pre-trained MobileSAM root foundation model for use with RootPainter, enabling fully automatic root segmentation on new datasets with an ordinary laptop or desktop computer, with no need for annotation or training.

Why it matches plant phenotyping methods根の画像セグメンテーションを行う基盤モデルを開発し、9データセットでゼロショット性能を評価する研究であり、植物形質取得手法が中心です。

abstractWe train and evaluate the first domainspecific foundation model for root segmentation.

EpiReasoner: An Integrated Artificial Intelligence Framework for Phenotype-to-Genotype Reasoning in Plant Epidermal Development ↗

Achieving high-throughput and precise phenotypic quantification and imaging modalities of stomatal and epidermal cells across diverse species remains a primary bottleneck in elucidating the mechanisms of stomatal dynamics, epidermal patterning, and environmental adaptation of plants. Here, we developed EpiReasoner, an artificial intelligence framework comprising a vision module, EpiVision, and a knowledge-based reasoning module, EpiBrain, for the quantitative phenotypic analysis and domain-specific knowledge reasoning of stomatal complexes and pavement cells in plants. Operating across bright-field, scanning electron microscopy, and differential interference contrast modalities, EpiVision achieves precise instance segmentation in various monocotyledonous, dicotyledonous, and fern species. Its performance significantly surpasses current state-of-the-art models. Moreover, we defined 23 quantitative indices describing stomatal cell morphology and spatial distribution. For domain-specific tasks such as phenotype prediction, genotype deduction, and molecular mechanism reasoning, EpiBrain demonstrates a human preference rate significantly higher than that of general-purpose large language models, including GPT-5 and Claude Sonnet 4. The application of EpiReasoner to phenotypic data of stomatal density derived from a tomato natural population of 170 accessions successfully identified a major quantitative trait locus on chromosome 8. The candidate gene, SKP1-interaction partner 19L ( SKIP19L ), encoding an F-box family protein, exhibited severe allele frequency drift during tomato domestication, which is highly consistent with the adaptive trend of reduced stomatal density under artificial selection. EpiReasoner provides a novel paradigm that unifies visual phenomics and knowledge-driven reasoning for the biology of stomata and pavement cells, thereby significantly accelerating scientific discovery in plant science.

Why it matches plant phenotyping methods植物の気孔・表皮細胞を対象に、画像解析と知識推論を統合したフェノタイピング手法を開発しており、形態・空間分布の定量化が中心的な貢献である。

abstractwe developed EpiReasoner, an artificial intelligence framework comprising a vision module, EpiVision, and a knowledge-based reasoning module, EpiBrain, for the quantitative phenotypic analysis and domain-specific knowledge reasoning of stomatal complexes and pavement cells in plants.

Deep Learning for Field-Based Cereal Phenomics ↗

PhD thesis investigating deep learning methods for non-destructive, high-throughput phenotyping in cereal crops, covering NIRS, hyperspectral imaging, UAV-based plot segmentation, image-based disease assessment, and cross-platform deployment of phenomics pipelines.

Why it matches plant phenotyping methods穀類の非破壊・高スループット表現型解析を中心に、深層学習、NIRS、ハイパースペクトル画像、UAV画像分割、病害評価、フェノミクス基盤展開を扱う方法研究である。

abstractPhD thesis investigating deep learning methods for non-destructive, high-throughput phenotyping in cereal crops, covering NIRS, hyperspectral imaging, UAV-based plot segmentation, image-based disease assessment, and cross-platform deployment of phenomics pipelines.

A descriptive analysis of plant leaf disease detection using machine learning and deep learning models: a systematic review ↗

Plant leaf disease detection (PLDD) is a growing active research area with burgeoning practical applications across various sectors such as agricultural monitoring, food security, and environmental conservation. Accurate segmentation and classification of plant leaf diseases remains a key challenge in the field of plant leaf disease prediction. The challenge demands automated methods for the plant disease identification because it needs to develop better crop management systems, which will boost agricultural production. In this article, we provide a systematic review of various machine learning (ML) and deep learning (DL) methods extensively used for PLDD. The review strategy follows a formal protocol, involving structured search, screening, and analysis of studies published between 2020 and 2024. We have proposed a taxonomy of PLDD methods that will be useful for experts and researchers working in this exciting research area. The review thoroughly examines techniques for both segmentation and classification of the PLDD workflow. In addition, we examine several public and private datasets that are accessible to study plant diseases and highlight their significance in developing accurate diagnostic models. The paper also presented multiple performance assessment criteria that researchers can use to evaluate PLDD methods at present and in the future. The study also discusses the current challenges in plant leaf disease classification and offers essential insights about upcoming developments and potential enhancements. The research findings from this study provide essential knowledge that helps experts and researchers to develop automated systems to detect and classify plant leaf diseases effectively.

Why it matches plant phenotyping methods植物葉の病徴を画像から検出・分類する手法を対象とした系統的レビューであり、セグメンテーション、分類、データセット、評価指標を中心に扱うため、植物フェノタイピング手法レビューに該当する。

abstractIn this article, we provide a systematic review of various machine learning (ML) and deep learning (DL) methods extensively used for PLDD.

Gaussian Kernel Fuzzy C-Means (GKFCM) and Correlation Weight Bayesian SqueezeNet (CWBSN) Classifier for Banana Leaf Diseases Diagnosis Using Electrochemical Sensor-Based Image Segmentation and AI Techniques ↗

Bananas are among the most widely cultivated fruits worldwide and constitute a major staple crop in many developing regions. Banana production is highly vulnerable to foliar diseases, which significantly reduce yield and economic sustainability. Early and accurate disease diagnosis plays a central role in mitigating crop losses. This study presents an image-based artificial intelligence framework for banana leaf disease diagnosis using advanced segmentation and deep learning techniques. Gaussian Kernel Fuzzy C-Means (GKFCM) clustering is employed for pixel-level segmentation, enabling precise isolation of diseased regions by preserving nonlinear boundary characteristics and minimizing intra-cluster variance. For disease classification, a Correlation Weight Bayesian SqueezeNet (CWBSN) model is introduced, integrating Bayesian optimization and correlation-aware feature weighting to enhance discriminative representation and classification robustness. The framework is evaluated using RGB images obtained from the BananaLSD dataset and field-acquired imagery collected at Bangabandhu Sheikh MujiburRahman Agricultural University (BSMRAU), Bangladesh. Performance is assessed using accuracy, precision, recall, F1-score, Matthews Correlation Coefficient (MCC), and Receiver Operating Characteristic (ROC) analysis. Experimental results demonstrate that the proposed GKFCM–CWBSN framework achieves reliable and consistent disease recognition based solely on visual symptom analysis. The study establishes a computational foundation for image-driven plant disease diagnosis, with potential adaptability to future multimodal agricultural sensing systems.

Why it matches plant phenotyping methodsバナナ葉の病斑領域を画像から抽出・分類する手法の開発が研究の中心であり、植物病害状態の表現型推定に該当する。

abstractThis study presents an image-based artificial intelligence framework for banana leaf disease diagnosis using advanced segmentation and deep learning techniques.

LOCOPOTS: a low-cost high-throughput screening platform for in vitro potato phenotyping under abiotic stress ↗

Potato crop is highly vulnerable to abiotic stresses like salinity and low nutrient availability. Rapid identification of stress-resilient genotypes is therefore essential for breeding, yet conventional phenotyping is often slow, space-demanding and expensive. We present LOCOPOTS — a LOw-COst high-throughput screening platform for in vitro POTatoes under abiotic Stress — which combines individual in vitro plant culture, low-cost RGB imaging and machine-learning-based automatic segmentation using a trained model of a convolutional neural network, based on U-Net architecture. LOCOPOTS enabled the automated extraction of growth, colour, and vegetation-index traits and demonstrated robust performance across independent phenotyping rounds. We screened 30 potato varieties under control, low-nutrient and saltinity conditions, identifying contrasting growth and physiological responses. Integrated traits such as final area and height, Area_AUC and height_AUC, together with GLI, Ch ol , cive and chlorophyll fluorescence parameters, discriminated genotype performance under stress. Metabolic profiling further revealed genotype-specific reprogramming in carbon and nitrogen metabolism under low nutrition and salt stress, including changes in fructose, myo-inositol, β-aminobutyric acid, γ-aminobutyric acid, proline, and certain polyamines, identifying them as specific chemical biomarkers of plant stress responses. LOCOPOTS provides a scalable, affordable and space-efficient platform for early screening of potato genetic diversity and identification of candidate traits associated with stress resilience.

Why it matches plant phenotyping methods低コストRGB撮像とU-Netによる自動セグメンテーションを中核とする、ジャガイモ表現型取得プラットフォームの開発・検証であり、形態・色・植生指数形質を自動抽出している。

abstractWe present LOCOPOTS — a LOw-COst high-throughput screening platform for in vitro POTatoes under abiotic Stress — which combines individual in vitro plant culture, low-cost RGB imaging and machine-learning-based automatic segmentation using a trained model of a convolutional neural network, based on U-Net architecture.

High-throughput phenotypic analysis of plant and curd growth dynamics during the whole growth period of cauliflower based on instance segmentation ↗

Efficient phenotyping monitoring of cauliflower is crucial for its breeding and production. However, traditional manual measurement methods are time-consuming and labor-intensive, and existing deep learning (DL) methods mostly focus on the seedling stage, lacking systematic research covering the entire growth period. In this study, RGB images of cauliflower from seedling to harvest were collected. Through systematic screening and evaluation of instance segmentation models, accurate segmentation of plants and curds was achieved, and plant canopy width, leaf area, and curd traits were automatically extracted to track their dynamic changes. Evaluation results showed that YOLO12s-seg was the optimal model. It can achieved a segmentation mask mAP 50 of 99.4% for plants and curds in sparsely planted images and showed an advantage in identifying partially occluded early curds beneath inner leaves. Traits such as plant canopy width and curd diameter automatically extracted from segmentation results were highly consistent with manual measurements (R 2 > 0.90). Furthermore, the Richards model and Sine model were used to accurately fit the growth dynamics of leaf area and curd area, respectively. Based on growth kinetics, curds were classified into three types: mature and compact type, peak-burst type, and steady-increase type. Cluster analysis of 47 germplasms based on high-throughput phenotyping data revealed four groups and their growth characteristics: comprehensively coordinated type, mid-maturity compact type, large high-yield type, and curd-dominant type. Integrating the above functions, a platform for cauliflower growth monitoring and phenotypic analysis was developed. It provided full-process support from automatic image processing to growth dynamic analysis. This work provides an effective automated solution for high-throughput phenotyping analysis and growth dynamic monitoring of cauliflower, and offers a referable analytical framework for crop growth pattern research and intelligent breeding decision-making.

Why it matches plant phenotyping methods植物のインスタンスセグメンテーションから葉面積・草冠幅・花蕾形質を自動抽出し、手動測定との技術検証と成長動態解析、統合プラットフォーム開発を行っており、フェノタイピング手法が研究の中心である。

abstractThrough systematic screening and evaluation of instance segmentation models, accurate segmentation of plants and curds was achieved, and plant canopy width, leaf area, and curd traits were automatically extracted to track their dynamic changes.

An Enhanced Hybrid Deep Learning Framework using EfficientNetV2, ResNet, and U-Net for Plant Leaf Disease Classification and Segmentation ↗

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

Why it matches plant phenotyping methods植物葉の病害を画像から分類・セグメンテーションする深層学習手法が題名で明示されており、病徴・病害状態の表現型抽出が研究の中心です。

titleAn Enhanced Hybrid Deep Learning Framework using EfficientNetV2, ResNet, and U-Net for Plant Leaf Disease Classification and Segmentation

Rapid Forest Fuel Load Estimation via Virtual Remote Sensing and Metric-Scale Feed-Forward 3D Reconstruction ↗

Accurate quantification of forest coverage and combustible biomass (fuel load) is critical for wildfire risk assessment and ecosystem management. However, traditional methods relying on airborne LiDAR or field surveys are cost-prohibitive and time-intensive, while satellite imagery often lacks the vertical resolution required for canopy volume analysis. This paper proposes a novel, automated pipeline for rapid forest inventory using virtual remote sensing data derived from Google Earth Studio (GES). Our approach first generates low-altitude orbital imagery and camera poses for a target region. For dense 3D reconstruction, we employ Pi-Long, developed within the VGGT-Long framework. This model serves as a scalable extension of the Pi-3 feed-forward Transformer architecture. To address the inherent scale ambiguity in monocular reconstruction, we introduce a metric recovery module that aligns the reconstructed trajectory with GES ground truth poses via Sim(3) Umeyama optimization. The metric-scale point cloud is then orthogonally projected into Bird's-Eye-View (BEV) height and density maps. Finally, we employ a watershed-based segmentation algorithm combined with height variance analysis to classify tree species (conifer vs. broadleaf), calculate Leaf Area Index (LAI), and estimate total fuel load. Experimental results demonstrate that this pipeline offers a scalable, cost-effective alternative to physical scanning, enabling near-real-time estimation of forest biomass with high geometric consistency.

Why it matches plant phenotyping methods森林の3D再構成、BEVマップ、分割・高さ分散解析を組み合わせ、LAIと燃料量という植物・群落形質を推定するパイプライン自体が中心的な技術貢献であるため。

abstractThis paper proposes a novel, automated pipeline for rapid forest inventory using virtual remote sensing data derived from Google Earth Studio (GES).

Research on Branch Recognition and Pruning Method for Dormant Apple Trees Based on Neural Radiance Fields and PointNeXt ↗

Abstract To address the problem of fine branch identification and pruning decision for dormant apple trees, this study proposes a 3D point cloud branch recognition method integrating Neural Radiance Fields (NeRF) and the PointNeXt network. This method employs the neural radiance field theory to construct a point cloud model of apple trees, achieving fine detail representation and providing a high-precision, high-standard dataset for subsequent branch pruning experiments. First, a panoramic video is captured by circling the fruit tree, and a multi-view image sequence is obtained through frame sampling. Subsequently, the Structure from Motion (SfM) algorithm is employed for sparse reconstruction to recover the pose information of the images. On this basis, a neural radiance field model is trained. Hierarchical sampling is performed using ray casting, and the sampled points, combined with positional encoding, are fed into a multi-layer perceptron (MLP). The radiance field is then generated via volume rendering, from which a high-fidelity 3D point cloud model of the fruit tree is derived. Finally, the point cloud is processed using the PointNeXt semantic segmentation network to achieve the identification and segmentation of branches to be pruned and branches to be retained. To verify the effectiveness of the method, this study reconstructed point cloud models of dormant apple trees and selected 10 of them for experimental analysis. The algorithm achieved an average overall recognition accuracy of 75.15% and an average false negative rate (FNR) of 24.85%. The experimental results demonstrate that the proposed method constructs a 3D point cloud model with multi-scale, multi-modal, and high-precision phenotypic information at a relatively low cost. It not only overcomes the limitations of traditional 3D reconstruction methods, such as insufficient point cloud accuracy and difficulty in accurately identifying thin branches, but also effectively mitigates the high misrecognition rate observed in conventional branch recognition approaches. This provides technical support for unmanned agricultural machinery pruning in orchards and holds significant implications for achieving precision agriculture and sustainable development.

Why it matches plant phenotyping methodsNeRFとPointNeXtを用いてリンゴ樹の3D点群を構築し、剪定対象枝を認識・分割する手法が研究の中心であり、植物の形態・構造状態を直接推定して性能評価している。

abstractthis study proposes a 3D point cloud branch recognition method integrating Neural Radiance Fields (NeRF) and the PointNeXt network.

LIME: a fully automated pipeline for high-throughput quantification of leaf lesions ↗

Abstract Accurate quantification of leaf lesion severity is essential for plant disease research and phenotyping but is often limited by subjective visual scoring and time-intensive manual image analysis. We present LIME, a fully automated, open-source image analysis pipeline for high-throughput quantification of leaf lesions from disease assay images. LIME integrates zero-shot leaf segmentation using the Segment Anything Model with a convolutional neural network for lesion area estimation. Applied to Arabidopsis thaliana leaves infected with Sclerotinia sclerotiorum , the proposed approach achieved a mean absolute percentage error of 12.9%, comparable to observed intrarater variability in manual scoring. Stratified evaluation across lesion-size groups demonstrated consistent prediction accuracy for small, intermediate, and large lesions, and comparative analysis showed that the deep learning–based model substantially outperformed color-based baseline methods. Under GPU-accelerated execution, LIME processed complete assays containing approximately 200 leaves in 15 minutes, representing an approximate 13-fold reduction in processing time relative to manual annotation. Together, these results indicate that LIME enables objective, reproducible, and scalable quantification of leaf lesion severity in standardized plant pathology assays. The pipeline is released as an open-source tool to support quantitative phenotyping studies.

Why it matches plant phenotyping methods植物病斑重症度を画像から定量するオープンソース解析パイプラインを開発・比較評価しており、植物フェノタイピング手法が研究の中心です。

abstractWe present LIME, a fully automated, open-source image analysis pipeline for high-throughput quantification of leaf lesions from disease assay images.

Stem Modeling for Savanna Tree Characterization with Close-Range Photogrammetry: Comparison of the Performance of Automatic Algorithms ↗

Sudanian savannas remain underexplored in terms of utilizing close-range photogrammetry (CRP) for assessing tree characteristics, leaving a gap in ecological research. This study evaluates the performance of automatic stem modeling techniques using CRP-generated point clouds for 30 trees from five savanna species. Two labeling methods, a machine learning-based approach (StemML) and a flatness/vertical structure-based method (StemFlat), were used to extract stem points. We applied three diameter estimation techniques: convex-hull line fitting (CHM), least squares circle fitting (LSM), and Ransac circle fitting (RANSAC), comparing their results against field measurements using root mean square error (RMSE), bias and the coefficient of determination R2. The combination of StemML and CHM yielded the best performance, with an RMSE of 2.1 cm (5.8%), R2 of 0.983 and a bias of −0.30 cm, accurately identifying 93% of stem segments. Diameter estimation accuracy varied with height, with optimal alignment between CRP-derived profiles and manual measurements occurring between 0.5 and 2.5 m. These findings demonstrate CRP’s potential for modeling savanna tree stems and highlight the importance of method selection in ensuring reliable measurements.

Why it matches plant phenotyping methods近距離写真測量による樹幹点群の抽出・モデル化と直径推定手法を開発・比較し、野外測定で性能検証しているため、植物形質計測手法が研究の中心である。

abstractThis study evaluates the performance of automatic stem modeling techniques using CRP-generated point clouds for 30 trees from five savanna species.

PAT: An Image Analysis Tool for Automated Scoring of Pollen in Alexander-Stained Anthers ↗

Quantitative pollen viability analysis is a critical but labor-intensive step in plant reproductive biology. Existing deep-learning Segment Anything Models (SAM) fail to reliably segment viable pollen in Alexander-stained anthers. To address this, we fine-tuned an existing Cellpose-SAM model for pollen segmentation. We integrated it into PAT (Pollen Analysis Tool), a cross-platform desktop application. PAT features instance segmentation with interactive quality control, an in-app model retraining module, and publication-ready statistical outputs. We deployed PAT in an EMS suppressor screen of semi-sterile Arabidopsis smg7-6 mutants, enabling efficient candidate prioritization for whole genome sequencing and mapping candidate mutation. This screen led to the identification of a point mutation in CAP-D2 ( capd2-2 ), a Condensin I subunit, that rescues the smg7-6 meiotic phenotype. Notably, mutation in a Condensin II subunits (CAP-D3 and CAP-H2) does not confer rescue. Further characterization suggests the capd2-2 allele is hypomorphic, showing no defects in vegetative growth, chromocenter compaction, or transposable element silencing. Collectively, we demonstrate that accessible AI tools have the potential to bridge gaps in plant phenotyping and accelerate the pace of biological discovery. Highlight We combined AI-powered image analysis with an easy-to-use desktop app to automate plant pollen counting, then used it to identify a new genetic suppressor of meiotic defects.

Why it matches plant phenotyping methods花粉の生存性を画像から自動定量するセグメンテーション手法とソフトウェアPATの開発が中心であり、植物表現型の取得・抽出手法に該当する。

abstractWe integrated it into PAT (Pollen Analysis Tool), a cross-platform desktop application.

LASH-SegNet: A Lightweight Deep Learning Network for Multi-Trait Segmentation of Early-Stage Soybean Plants ↗

Accurate segmentation of multiple phenotypic traits in early-stage soybean plants is essential for automated phenotyping and early-stage breeding analysis. However, the morphological diversity and heterogeneous visual characteristics of key traits, including hypocotyls, flowers, pubescence, and leaves, make unified segmentation challenging under complex backgrounds. To address this problem, this study proposes LASH-SegNet, a lightweight deep learning network for multi-trait segmentation of early-stage soybean plants. The network integrates dynamic snake convolution to model elongated and non-rigid structures and incorporates a SegNeXt-Attention module to enhance multi-scale feature representation and boundary awareness. In addition, the WIoUv3 loss function is adopted to improve localization accuracy and boundary alignment, particularly for slender targets. Experimental results show that LASH-SegNet achieves a precision of 88.82%, recall of 89.78%, and an F1-score of 89.30%, with an mAP50 of 91.24%, while maintaining a compact model size of 5.9 M parameters and 11.3 MB. These results demonstrate that LASH-SegNet provides an accurate and efficient solution for high-throughput multi-trait early-stage soybean plant phenotyping.

Why it matches plant phenotyping methods大豆幼苗の複数形質を自動抽出する画像セグメンテーション手法を開発しており、植物フェノタイピング手法が研究の中心である。

abstractthis study proposes LASH-SegNet, a lightweight deep learning network for multi-trait segmentation of early-stage soybean plants.

Phenotypic analysis method for 3D reconstruction of eggplant seedlings fused with background purification — based on the improved EggplantPointNet++ model and DBSCAN clustering ↗

Eggplant (Solanum melongena L.) is a widely cultivated vegetable crop worldwide, occupying an important position in the agricultural industries of Asia, the Middle East, and Southern Europe. Its significance extends beyond agricultural economics to diverse dimensions such as dietary nutrition, rendering it of considerable research and application value. Traditional crop phenotyping methods suffer from low efficiency, substantial manual errors, and a tendency to damage tender seedlings, while existing three-dimensional phenotyping techniques face challenges including strong background interference and large data volumes. These dual constraints limit the accuracy and application feasibility of seedling phenotyping. To address these issues, this study proposes a non-destructive phenotyping method for eggplant seedlings, with the improvement of the PointNet++ architecture as its core and point cloud background purification as a key preprocessing step, aiming to enhance eggplant breeding efficiency and seedling screening accuracy. The raw point clouds first undergo background purification to actively remove seedling tray points, thereby improving point cloud purity and reducing data size. Concurrently, based on the PointNet++ model, we develop an improved point cloud segmentation model, EggplantPointNet++, by introducing multi-scale residual blocks, integrating channel attention mechanisms, incorporating a global context module, and refining the feature propagation layer. In conjunction with the DBSCAN clustering algorithm, this approach achieves semantic and instance segmentation of eggplant seedling point clouds, with certain improvements in segmentation accuracy and model efficiency under small-scale and occluded scenarios. To validate the technical effectiveness, multiple comparative experiments and ablation studies were conducted. The results demonstrate that EggplantPointNet++ outperforms the original model, background purification preprocessing provides positive gains, and each improved module contributes positively. The final model achieves improvements in core metrics including Recall and F1-score. Based on the segmented point cloud data, this study calculates core phenotypic parameters including plant height, stem diameter, cotyledon angle, and cotyledon area. Using the technical system established in this study, we completed the time-series measurement of three-dimensional morphological changes in eggplant seedlings during the cotyledon stage, providing quantitative references for seedling growth assessment and superior plant selection.

Why it matches plant phenotyping methodsナス幼苗の3D点群から形質を抽出する非破壊フェノタイピング手法を開発し、比較実験・アブレーションで技術性能を検証しているため、方法が中心的である。

abstractthis study proposes a non-destructive phenotyping method for eggplant seedlings

Construction of a Precision Thinning Framework for Cunninghamia Lanceolata Plantations Driven by Point Cloud Fusion and Multi-Criteria Weighting ↗

Thinning is a cornerstone of sustainable forest management (SFM), yet decisions are often constrained by subjective experience and a lack of quantitative spatial data. To address this, we developed a precision thinning framework for Cunninghamia lanceolata plantations by fusing terrestrial and aerial LiDAR data. Instead of relying on manual selection, this study established a quantitative mechanism for identifying harvesting targets. We employed a layer-stacking seed-point algorithm to accurately segment individual trees and extracted key parameters (tree height, DBH, and crown width) with high precision (Overall R2 ≥ 0.85). Furthermore, an objective multi-criteria weighting method (AHP – CRITIC) was constructed to prioritize thinning targets based on stand stability and growth status. Results indicated that the proposed framework achieved an individual tree segmentation F1-score of 89.24%. Simulated thinning based on the calculated weights significantly optimized the stand spatial structure: canopy openness increased by 11.8%, and spatial indices converged toward optimal ranges. Compared with conventional practices, the proposed approach effectively reduced growth dispersion and enhanced population coordination. These findings demonstrate that integrating multi-platform LiDAR with objective weighting algorithms offers a scientifically rigorous pathway for precision forestry, promoting both productivity and the long-term sustainability of plantation ecosystems.

Why it matches plant phenotyping methodsLiDAR融合による個体木セグメンテーションと樹高・DBH・樹冠幅の抽出、および精度評価が枯間伐フレームワークの中心的な技術要素であるため、植物表現型計測手法として採用する。

abstractWe employed a layer-stacking seed-point algorithm to accurately segment individual trees and extracted key parameters (tree height, DBH, and crown width) with high precision (Overall R2 ≥ 0.85).

Mapping California's Urban Forest at Scale: An Error-Adjusted Canopy Time Series for Monitoring Change ↗

Statewide tracking of urban tree canopy change is essential for evaluating progress toward policy targets, but detecting real change requires both high-resolution mapping and rigorous uncertainty estimation. We produced a four-year canopy cover time series for all California census-designated places using 60-cm NAIP aerial imagery and a U-Net deep learning model trained with semi-automated LiDAR-derived labels and manually annotated tiles. Canopy cover and change were estimated using stratified, error-adjusted area estimation, enabling comparisons across years. Statewide canopy cover showed a modest negative trend from 2016 to 2022 (Sens slope: -0.60% per year), but confidence intervals included zero across all groups and climate zones, indicating that trends were not statistically distinguishable from no change. Urban canopy cover was consistently lower than non-urban canopy by approximately six percentage points, and canopy cover was highest in the Northern California Coast and lowest in the Southwest Desert. Residential parcels accounted for 55-56% of canopy within incorporated urban areas across all years, indicating that statewide canopy increase goals will require engagement with private landowners. Error adjustment substantially altered canopy estimates relative to raw pixel-count totals, with direct implications for AB 2251 canopy tracking where baselines and targets drawn from unadjusted maps may not reflect true canopy extent. This open-source workflow is transferable to future NAIP acquisition years and other U.S. states, providing a scalable framework for long-term urban forest monitoring.

Why it matches plant phenotyping methods航空画像とU-Netにより都市樹冠被覆率を推定し、誤差調整と不確実性評価を行う再利用可能なワークフローを中心に扱っているため、植物状態の測定手法として採用。

abstractWe produced a four-year canopy cover time series for all California census-designated places using 60-cm NAIP aerial imagery and a U-Net deep learning model trained with semi-automated LiDAR-derived labels and manually annotated tiles.

Dual-Path Deep Learning and Hierarchical Spectral Clustering: A Versatile Framework for Semantic and Instance Segmentation of Plant Point Clouds ↗

Accurate plant organ segmentation is essential for high-throughput phenotyping and ideotype selection. However, current methods struggle with plants of complex morphology, particularly small organ categories with sparse point distributions. In addition, severe leaf adhesion in dense canopies often hinders reliable leaf instance segmentation using conventional clustering methods. To address these challenges, we propose a dual-path fusion network (DPFuseNet) for semantic segmentation and a hierarchical multi-scale spectral clustering algorithm (HMSC) for instance segmentation of plant point clouds. DPFuseNet introduces three innovations: a high-frequency information embedding strategy, a dual-path feature extraction module integrating CNN and Transformer branches, and a cross-attention–based dual-granularity feature fusion block. Evaluated on tomato, cabbage, and soybean datasets, DPFuseNet achieved superior performance over state-of-the-art baselines such as Stratified Transformer and Point Transformer v3, reaching average precision, recall, F1-score, and IoU of 96.51%, 96.27%, 96.38%, and 93.32%, respectively. Compared with the current leading single-branch model Point Transformer v3, DPFuseNet improves these metrics by 1.19%, 1.20%, 1.21%, and 2.05%, and by 0.89%, 1.14%, 1.02%, and 1.70% over the dual-branch model PVDST. For instance segmentation, the proposed HMSC algorithm, combined with region growing, achieved mPrec 89.65%, mRec 78.70%, mCov 76.88%, and mWCov 85.11% on multi-stage tomato, cabbage, and soybean datasets, consistently outperforming conventional spectral clustering. Overall, the proposed framework demonstrates robustness and efficiency in both semantic and instance segmentation, offering a novel pathway for advancing plant point cloud analysis and smart agriculture.

Why it matches plant phenotyping methods植物点群から器官の意味・個体分割を行う深層学習およびクラスタリング手法の開発と評価が研究の中心であり、植物表現型解析への直接的な応用を示している。

abstractAccurate plant organ segmentation is essential for high-throughput phenotyping and ideotype selection.

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.

RCTUnet: a deep learning model for crop-residue-soil image segmentation and crop residue cover extraction. ↗

Accurate quantification of crop residue cover (CRC) is crucial for monitoring and evaluating conservation tillage practices, yet it poses a significant image segmentation challenge. The subtle visual distinctions between fragmented residue and soil, compounded by variable illumination and shadows in field imagery, often lead to poor segmentation performance. To overcome these limitations, we introduce RCTUnet, a novel deep learning architecture designed for robust crop-residue-soil segmentation and precise CRC estimation. RCTUnet's architecture synergistically integrates three key components: (1) a ResNet50 backbone for deep, multi-scale feature extraction; (2) a convolutional block attention module (CBAM) to adaptively focus on salient residue features across both channel and spatial dimensions; and (3) a transformer-based global context fusion module (GCFM) to model long-range spatial dependencies, which is critical for interpreting heterogeneous residue patterns. We evaluated RCTUnet on a dataset of 1220 field-acquired images spanning four typical crop rotations. Experimental results show that, compared to traditional models: (1) RCTUnet achieves significantly higher crop-residue-soil segmentation accuracy than classic models including Unet, Unet++, DeepLabV3, segmentation network (SegNet), and fully convolutional network (FCN), with improvements of 3.24%, 3.42%, 4.88%, 8.28%, and 6.05% in overall accuracy, respectively; (2) RCTUnet yields superior residue-soil segmentation performance, with increases in residue recall of 7.67%, 7.37%, 14.09%, 27.05%, and 16.91%, respectively; (3) RCTUnet shows enhanced CRC estimation accuracy, achieving a root mean square error (RMSE) of 4.875, representing a 45.5% improvement over Unet (RMSE=8.941). These results demonstrate the efficacy of our hybrid approach, which combines deep hierarchical features, dual-domain attention, and global context modeling. RCTUnet provides a robust and reliable tool for automated CRC assessment, advancing the capabilities of in-field agricultural monitoring.

Why it matches plant phenotyping methods作物残渣被覆率という植物・圃場状態の画像計測を目的に、セグメンテーション手法を開発し、既存モデルと比較検証しているため、方法が研究の中心である。

abstractwe introduce RCTUnet, a novel deep learning architecture designed for robust crop-residue-soil segmentation and precise CRC estimation.

Quantitative Imaging of RNA in Plants Using Hybridization Chain Reaction-RNA Fluorescence in Situ Hybridization (HCR RNA-FISH). ↗

Quantitative RNA imaging in large plant tissues has historically been challenging because of limited spatial resolution, low signal-to-noise ratios, and the largely qualitative nature of traditional RNA in situ hybridization methods. Hybridization chain reaction-RNA fluorescence in situ hybridization (HCR RNA-FISH) coupled with high-resolution microscopy enables sensitive detection of RNA molecules at cellular resolution. However, quantitative approaches that combine improved tissue accessibility with robust computational pipelines for single-cell transcript quantification in plants remain limited. Here, we present a quantitative HCR RNA-FISH protocol for the developing maize inflorescence. We describe a 4-day workflow that includes fixation, agarose immobilization, vibratome sectioning, probe hybridization, amplification, and mounting and enables multiplexed detection of transcripts at the cellular level in maize ear and tassel primordia. In addition, we provide a Python-based image analysis pipeline for (i) cell segmentation, (ii) RNA spot quantification, (iii) assignment of spots to cells, and (iv) data representation. The scripts can be easily run on Jupyter notebooks and are available on GitHub. Overall, this protocol highlights the importance of integrating robust imaging strategies with quantitative and reproducible data analysis frameworks to extract biologically meaningful insights from imaging data. © 2026 Wiley Periodicals LLC. Basic Protocol: Quantitative RNA imaging in sections of maize ear and tassel primordia using HCR RNA-FISH.

Why it matches plant phenotyping methods植物組織内RNAの細胞レベル画像化と、細胞分割・RNAスポット定量を行う再現可能な解析パイプラインを中心としたプロトコルであり、植物状態の定量的表現型取得法が主題である。

abstractHere, we present a quantitative HCR RNA-FISH protocol for the developing maize inflorescence.

Hyperspectral Imaging-Based Evaluation of Seasonal Growth Characteristics in Turfgrass. ↗

Efficient phenotyping is essential for accelerating genetic improvement in turfgrass breeding, where manual measurements are labor-intensive. This study evaluated hyperspectral imaging (HSI) as a high-throughput tool for assessing Zoysia spp. breeding populations consisting of 464 genotypes. HSI data (400-1000 nm) were processed through a user-in-the-loop hybrid segmentation pipeline integrating UMAP dimensionality reduction, DBSCAN clustering, Random Forest classification, and pseudo-RGB refinement. To independently assess vegetation classification performance, 10,000 manually annotated reference points from 50 pseudo-RGB images were compared with the automated module, yielding an overall accuracy of 0.9697, a precision of 0.8830, a recall of 0.9240, a specificity of 0.9779, an F1-score of 0.9030, and Cohen's kappa of 0.8851. A Combined Ranking Score (CRS) integrating five vegetation indices and vegetation pixel count was significantly associated with aerial shoot count ( r = -0.445, p r = -0.207, p < 0.001). The highest-ranked genotype showed a 9370.3-pixel increase in vegetation area between 6 and 16 weeks after transplanting, compared with 1417.7 pixels for the lowest-ranked genotype. Classification performance declined under high-coverage conditions, indicating increased mixed-pixel ambiguity in dense canopies. These results suggest that HSI-based CRS can support rapid, objective, and non-destructive relative ranking of density-related vegetative growth in turfgrass breeding. Because the study was conducted at a single location and season and correlations with manual traits were moderate, the framework is best interpreted as a screening and ranking tool rather than a direct predictive model.

Why it matches plant phenotyping methodsHSI画像と解析パイプラインを用いて、芝草の植生面積・密度関連成長形質を高スループットに推定・検証することが研究の中心であり、育種集団の表現型スクリーニング手法に該当する。

abstractThis study evaluated hyperspectral imaging (HSI) as a high-throughput tool for assessing Zoysia spp. breeding populations consisting of 464 genotypes.

Application of computer vision and deep learning for automated monitoring of garden strawberry plant growth ↗

The article presents the developed algorithm and software for automated monitoring of strawberry plant growth using neural network technologies. The YOLO11x and YOLOx-seg models, pre-trained by transfer learning, are adapted to recognize and classify plants (plant class), leaves (leaf class), and a reference marker (ref_obj class) of a known size. Segmentation of strawberry leaves using the YOLO11x-seg model makes it possible to analyze the morphometric parameters of individual leaf plates (area, perimeter, roundness, aspect ratio). A set of RGB images (2000 pieces) obtained using a GoPro HERO11 camera under controlled laboratory conditions was formed and annotated, followed by augmentation to increase the model's resistance to variations in shooting conditions. The developed algorithm converts the coordinates of the bounding boxes and segmentation masks of recognized objects into metric units using calibration coefficients calculated from a marker of known size (100×100 mm). The software implemented using PyQt5, TensorFlow, Keras, and OpenCV libraries provides not only visualization of results but also data storage in a local SQLite database with the ability to export to JSON and Excel formats. Validation of the model showed high accuracy in detecting plant bounding boxes (mAP50 = 0.906) and leaf segmentation (mAP50 -mask = 0.625). The average processing speed was 20.3 ms/frame for detection and 34.5 ms/frame for segmentation. The measurement error was less than 3.5 % for the overall parameters of the plant and 5.2 % for the morphometric parameters of the leaves, confirming the effectiveness of the method for assessing the height, width and area of plants, as well as the analysis of the leaf apparatus. The research results show the promise of an approach for automating plant phenotyping in real time.

Why it matches plant phenotyping methods植物の成長・葉形態を画像から自動抽出するアルゴリズム、ソフトウェア、データセットを開発し、精度・処理速度・測定誤差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。

abstractThe article presents the developed algorithm and software for automated monitoring of strawberry plant growth using neural network technologies.

"Fertile islands from above": Utilising UAS imagery to map argan forest patches in a UNESCO biosphere reserve in Morocco ↗

Abstract. Vegetation in dryland ecosystems often exhibits spatial patterning that leads to the formation of fertile islands. Discrete patches accumulate nutrients, organic litter, seeds and water, slow down geomorphodynamic dispersion processes and contrast with rather barren interpatch areas. While this fragmentation shapes surface dynamics in dryland environments across the globe, their spatial arrangement remains difficult to quantify at fine scales. In this study, we utilised data collected by an uncrewed aircraft system (UAS) together with field data to study surface patterns in degraded Argania spinosa forests in South Morocco that show fertile island dynamics. Point clouds generated from UAS imagery using a Structure-from-Motion photogrammetric workflow were classified into vegetation and ground points, allowing the derivation of digital terrain and digital surface models as well as conventional orthophotos and artificial ground-only orthophotos. This high-resolution geospatial data was used to map tree-influenced soil surface areas and crown areas. Their size and spatial relationships were compared and complemented by a detailed assessment of tree morphologies and terrain characteristics based on both field observations and UAS-based geodata. Spatial and statistical analyses were conducted to study the effects of tree morphology, hillslope wash, shading and wind on emerging surface patterns beneath Argania spinosa trees. Across the 496 evaluated tree-influenced areas, the surface influence extended on average to 1.69 times the size of the crown covered area. The extent of this influence beyond the canopy cover is strongly controlled by tree size and morphology, indicating that browsing-induced degradation influences not only tree conditions but also the spatial extent of positive surface effects in the interpatch area. The tree-influenced areas exhibit a consistent north-east displacement, a pattern that surprisingly appears largely decoupled from hillslope wash and is most reasonably explained by a combined influence of shading and wind effects. The results of this study demonstrate the potential of UAS imagery to complement fertile island research by providing spatial insight beyond conventional field-based assessments. At the same time, the impact of browsing on surface dynamics in a UNESCO biosphere reserve is highlighted as a factor contributing to degradation in this silvopastoral land-use system.

Why it matches plant phenotyping methodsUAS-SfM画像から樹冠面積、樹体形態、樹木影響域を抽出するワークフローが研究の中心で、個体レベルの植物形態・状態を定量化しているため。

abstractPoint clouds generated from UAS imagery using a Structure-from-Motion photogrammetric workflow were classified into vegetation and ground points, allowing the derivation of digital terrain and digital surface models as well as conventional orthophotos and artificial ground-only orthophotos.

A Multi-Perspective Recursive Slice Framework with Cross-Slice Attention for Plant Point Cloud Instance Segmentation ↗

Instance segmentation of plant point clouds is challenging due to intricate structures, non-uniform density, and large intra-class variation. Conventional methods often suffer from blurred boundaries, instance adhesion, and insufficient coupling of semantic and instance features. To address these issues, this paper proposes MPRSF-CSA, a novel network integrating recursive slice-based feature extraction with an attention-embedding mechanism. The method first transforms disordered point clouds into ordered sequences via a multi-directional recursive slicing strategy and models inter-slice dependencies using BiLSTM. Parallel decoding branches for semantic and instance segmentation are constructed, and a core attention-embedding module facilitates bidirectional fusion of semantic and instance features. Instance segmentation is achieved via clustering and semantic-aware optimization. Experiments on two public datasets demonstrate that MPRSF-CSA outperforms existing approaches in segmentation accuracy, boundary preservation, and adaptability to complex plant scenes.

Why it matches plant phenotyping methods植物点云のインスタンスセグメンテーション手法を開発し、公開データセットで性能評価しているため、植物形態の取得・抽出を担う方法論が中心である。

abstractInstance segmentation of plant point clouds is challenging due to intricate structures, non-uniform density, and large intra-class variation.

Deep learning and computer vision for image‐based high‐throughput phenotyping of canning quality traits in dry beans ↗

Abstract Canning color retention is a key quality trait in dry bean ( Phaseolus vulgaris L.) breeding, influencing consumer acceptance and commercial value. Public breeding programs maintain canning quality as a selection trait of importance, but existing color evaluation methods such as visual rating are subjective, while instrument colorimetry is costly, provides limited throughput, and often struggles to accurately detect differences between genotypes. To address these challenges, we developed a high‐throughput phenotyping pipeline that integrates computer vision and deep learning to improve canning color quality assessment in dry beans. This pipeline combines the YOLOv8n (“You Only Look Once” version 8, nano variant) object detection model with the Segment Anything Model for precise bean segmentation. 525 black dry bean genotypes from Michigan State University preliminary and advanced yield trials over multiple years were evaluated using this pipeline. The final model was trained with over 1200 images of canned dry bean samples. The YOLOv8n model achieved near‐perfect detection performance, with precision reaching 0.99 and recall reaching 1 after 44 epochs of training. Comparative analysis showed that the image‐derived D ‐score (euclidean distance–based image‐derived color score) consistently outperformed visual ratings and colorimetry methods, with lower prediction error in regression models. The D ‐score metric offered high resolution in color assessment, enabling the distinction of subtle, genotype‐level differences. Additionally, the D ‐score provides a ranking criterion that enables breeders to make informed decisions and select superior genotypes. This pipeline was deployed to Michigan State University high‐performance computing center and can process 200 high‐resolution images in under 5 min, making it practical for large‐scale breeding applications while eliminating subjective bias and reducing costs.

Why it matches plant phenotyping methods乾燥インゲンの缶詰色保持という植物品質形質を対象に、画像認識・深層学習・セグメンテーションによる高スループット表現型取得パイプラインを開発・評価しており、方法が研究の中心です。

abstractwe developed a high‐throughput phenotyping pipeline that integrates computer vision and deep learning to improve canning color quality assessment in dry beans.

SAB-DeepLabV3+: A Semantic Segmentation Framework for Mapping Maize Waterlogging from Single-Date Multispectral Imagery ↗

Rapid identification of maize waterlogging is essential for post-disaster agricultural assessment, but most existing methods rely on multi-temporal imagery that is often unavailable immediately after extreme rainfall events. This study proposes SAB-DeepLabV3+, a semantic segmentation model for mapping waterlogged maize from single-date multispectral imagery within pre-extracted maize planting areas. Built on DeepLabV3+, the model integrates three task-specific modules: a Spectral-Spatial Information Enhancement Module to improve feature discrimination under spectral mixing, an Adaptive Multi-Scale Pooling Module to capture heterogeneous patch sizes, and a Boundary Enhancement Module to refine transition zones. A pixel-level dataset containing 12,198 image patches was constructed from 62 multispectral scenes collected across five major maize-producing cities in Heilongjiang Province, China, during 2022–2024. On the test set, SAB-DeepLabV3+ achieved a waterlogged-class IoU of 68.30%, mIoU of 80.37%, mF1 of 88.62%, and OA of 93.49%, outperforming DeepLabV3+. Leave-one-city-out evaluation further produced an average mIoU of 76.56% and a waterlogged-class IoU of 63.45%. These results indicate that single-date high-resolution multispectral imagery can support rapid and reliable maize waterlogging mapping.

Why it matches plant phenotyping methodsマルチスペクトル画像からトウモロコシの水害状態を抽出するセマンティックセグメンテーション手法を開発し、データセットと都市間評価で検証しているため、植物フェノタイピング手法が中心である。

abstractThis study proposes SAB-DeepLabV3+, a semantic segmentation model for mapping waterlogged maize from single-date multispectral imagery within pre-extracted maize planting areas.

PrivAgriVolt: Privacy-Preserving Shadow-Aware Vision for Crop Stress Diagnosis in Agrivoltaic Photovoltaic Systems ↗

Agrivoltaic systems co-locate photovoltaic (PV) arrays and crops, offering land-use efficiency and potential microclimate benefits, yet they introduce new challenges for computer-vision-based crop monitoring. PV structures produce strong, spatially varying shadows, specular reflections, and periodic occlusions that confound visual cues for diagnosing crop diseases and abiotic stresses. Meanwhile, agrivoltaic deployments are often distributed across farms and operators, making centralized data collection impractical due to privacy, ownership, and regulatory concerns. This paper proposes PrivAgriVolt, a novel privacy-preserving learning framework for agrivoltaic crop issue recognition that explicitly models PV-induced illumination and enables collaborative training without sharing raw images. The core algorithm integrates (i) a PV-geometry-conditioned shadow normalization module that fuses estimated array layout and sun-angle priors into a shadow-aware appearance canonization network, reducing illumination-induced domain shift across times and sites; (ii) a federated contrastive stress learner that aligns stress semantics across farms via prototype-based contrastive objectives while remaining robust to heterogeneous sensors and crop stages; and (iii) an adaptive privacy layer that combines secure aggregation with budget-aware gradient perturbation and client-level clipping to provide formal privacy guarantees while preserving fine-grained diagnostic performance. Extensive experiments on real agricultural vision benchmarks and agrivoltaic shadow variants demonstrate that PrivAgriVolt improves stress recognition and segmentation under PV shading while maintaining strong privacy–utility trade-offs.

Why it matches plant phenotyping methods作物の病害・非生物的ストレス状態を画像から認識・セグメンテーションする手法を開発し、農業用ベンチマークで評価しており、植物表現型取得が中心である。

abstractThis paper proposes PrivAgriVolt, a novel privacy-preserving learning framework for agrivoltaic crop issue recognition

Data-driven estimation of lettuce biophysical traits using multidimensional sensing ↗

• Multisensor platform integrates RGB, depth, IR, and RTK-GPS data streams • Automated plant segmentation and 3D reconstruction extract plant traits in field conditions • System validation shows high correlation with manual and lab measurements • Public RGB-D lettuce dataset released to support reproducible AI research Accurate monitoring of leafy vegetable crops is essential to evaluate plant health, growth, yield, and quality, yet conventional methods based on manual measurements are labor-intensive and error-prone. This study proposes a data-driven framework for automated in-field monitoring of a lettuce crop based on multidimensional data acquired by a ground platform under various field conditions. Specifically, an advanced perception system is developed, including imaging and localization sensors to capture high-resolution visual, structural, and georeferenced information on the crop. An image processing pipeline is then proposed using zero-shot learning for plant segmentation, followed by 3D phenotyping techniques based upon computational geometry to automatically estimate plant biophysical traits, thus minimizing human input. An experimental trial conducted in a test field in Bari, Italy, between April and May 2025 validated the approach against manual and laboratory estimations. The results demonstrate strong correspondence between automated and reference measurements with a Pearson correlation coefficient r > 0.9 for key traits, confirming the potential of the framework. The influence of different nitrogen levels on the growing cycle is also evaluated, showing that the proposed system may provide a useful tool for decision support in lettuce crop monitoring and management.

Why it matches plant phenotyping methodsRGB・深度・IR等を統合したセンシング、植物セグメンテーション、3D形状解析による形質推定を開発し、手測定・実験室測定で検証しているため、フェノタイピング手法が中心である。

abstractAn image processing pipeline is then proposed using zero-shot learning for plant segmentation, followed by 3D phenotyping techniques based upon computational geometry to automatically estimate plant biophysical traits

Integrating mobile RGB-D imaging and digital odometry for trunk diameter mapping in tart cherry orchards ↗

• Depth informed trunk detection performed reliably under field conditions. • Trunk diameter estimates aligned closely with ground truth. • Transmission-based digital odometer provided reliable along-row positioning. • Full-block mapping demonstrated large-scale applicability. Trunk diameter is an important structural trait used to assess tree size, vigor, and long-term growth in orchard systems, but it remains difficult to measure efficiently at orchard scale. This study developed and validated a low-cost mobile imaging system for automated trunk diameter estimation and spatial mapping in tart cherry (Prunus cerasus) orchards. The system integrated RGB-D cameras, deep learning-based trunk detection and segmentation, three-dimensional depth reconstruction, and driveline-based digital odometry for spatial positioning under canopy conditions where GNSS performance was unreliable. Trunks were detected using a YOLO-based model, segmented using a Segment Anything Model (SAM)-based approach, and reconstructed in 3D from depth data to estimate real-world trunk diameter at 40 cm above the trunk base. The system was evaluated in a 15-year-old, 1 ha experimental orchard in Utah, USA, and then applied in a 14-year-old, 9.5 ha commercial orchard. Under unobstructed viewing conditions, trunk diameter estimates showed strong agreement with manual measurements, with a mean absolute error (MAE) of 0.95 cm, a root mean square error (RMSE) of 1.16 cm, and R 2 of 0.79. Across all 462 trees, automated per-tree averaging produced an MAE of 1.40 cm. In the commercial orchard, mapped trunk diameter patterns aligned with UAV-derived canopy height, reflecting underlying zones of tree vigor. These results show that mobile RGB-D imaging combined with driveline-based odometry can provide practical, cost-effective orchard-scale trunk diameter mapping under commercial field conditions.

Why it matches plant phenotyping methodsRGB-D画像、深度再構成、物体検出・セグメンテーション、オドメトリを統合し、樹幹径という植物構造形質を自動推定・空間マッピングする手法を開発・検証しているため。

abstractThis study developed and validated a low-cost mobile imaging system for automated trunk diameter estimation and spatial mapping in tart cherry (Prunus cerasus) orchards.

Climate gradients drive the evolution of seed morphology and life history with impacts to seedling fitness in Fraxinus nigra ↗

Background and AimsClimate gradients influence seed morphology, emergence, and early life-history traits with cumulative impacts to individual fitness. For ex situ seed collections, which represent an invaluable repository of potential trait information for species management and conservation, climate data can guide preservation of adaptive variation and inform deployment strategies for restoration. Here we leverage a range-wide ex situ seed collection of critically endangered black ash seeds (Fraxinus nigra) to evaluate how climatic gradients shape variation in morphology and early life-history. MethodsTo test how climate of origin, seed morphology, and early life-history interact to impact first year fitness, high-throughput X-ray imaging and neural network-based segmentation were used to quantify variation in seed morphology for 701 maternal lineages spanning 76 populations across the range of F. nigra. Following this, a subset of seeds were used to establish a common garden experiment and quantify variation in emergence, early life-history transitions, and their cumulative impact to first-year survival and growth. ResultsOn average, differences within-population explained [~]43% of the variability in seed morphology, while among-population differences explained [~]14%. This suggests that substantial genetic variation exists within populations for natural selection to act upon and differences have evolved among populations. Climate associations indicated warmer and drier environments predicted heavier seeds with faster developmental transitions and increased first-year height. Together, climate of origin, seed mass, and timing of developmental transitions best predicted cumulative fitness, with populations from more continental environments exhibiting greater survival and first-year height accumulation on average. ConclusionsOverall, these results highlight the importance of climate of origin, seed traits, and early developmental transitions to first-year fitness in a perennial tree species. This work demonstrates how ex situ collections can be used to identify climatically structured trait variation and guide conservation strategies aimed at maintaining adaptive potential under environmental change.

Why it matches plant phenotyping methods701系統の種子形態を高スループットX線画像とニューラルネットワーク分割で定量しており、形態表現型の取得・抽出が研究の主要な技術基盤である。

abstracthigh-throughput X-ray imaging and neural network-based segmentation were used to quantify variation in seed morphology for 701 maternal lineages spanning 76 populations across the range of F. nigra

Lightweight Deep Learning-Based Plant Leaf Disease Assisted Diagnosis System ↗

Plant diseases pose a significant threat to agricultural productivity and global food security, making accurate and timely diagnosis essential. Although deep learning has shown promising performance in plant disease recognition, most existing methods focus on single-task classification and lack interpretability and deployability. To address these limitations, this paper proposes a lightweight deep learning-based plant leaf disease assisted diagnosis system. The proposed framework integrates EfficientNet-B3 for disease classification and Small U-Net for leaf and lesion segmentation, enabling precise localization and quantitative analysis. Disease severity is further estimated based on the lesion-to-leaf area ratio, providing interpretable results for end users. Experimental results demonstrate that the proposed method achieves high accuracy and robust performance while maintaining low computational cost. The system also supports mobile-friendly deployment and generates practical recommendations, forming a complete closed-loop diagnostic pipeline suitable for real-world agricultural applications.

Why it matches plant phenotyping methods葉の病変セグメンテーションと病変面積比による病害重症度推定を開発しており、植物状態の画像ベース表現型取得が中心です。

abstractThe proposed framework integrates EfficientNet-B3 for disease classification and Small U-Net for leaf and lesion segmentation, enabling precise localization and quantitative analysis.

Deep learning based instance segmentation of mandarin fruit slices for precision assessment and morphological quantification. ↗

Accurate instance segmentation of mandarin fruit slices is essential for quantifying segment morphology and central core structure, which are key traits in cultivar evaluation, fruit quality assessment, and postharvest application. Manual measurement of these anatomical features, however, is time-consuming and prone to inconsistency. In this study, we developed an automated segmentation framework based on YOLOv8 to detect and semantic segment the fruit segments and the central core in high-resolution mandarin transversely cut images. The model was trained on a curated datasetderived from 58 original high-resolution cross-sectional images (5100 × 7019 pixels), which were systematically partitioned into 280 cropped sub-images (1712 × 1778 pixels), each containing a single complete citrus slice, and demonstrated excellent performance. YOLOv8 achieved near-perfect detection metrics, with bounding box metrics precision ~ 0.997, recall ~ 1.00, mAP50 ~ 0.995, and mAP50-95 ~ 0.922. Semantic segmentation accuracy was similarly strong, with precision = 0.997, Recall ~ 1.00, mAP50 ~ 0.995, and mAP50-95 = 0.965. Training and validation losses converged steadily, indicating stable learning without overfitting. The nonsignificant differences between YOLOv8-predicted measurements and ground truth data, together with low mean absolute error (MAE) values, demonstrate that the model not only performs well in semantic segmentation metrics but also maintains high accuracy in quantitative measurements, which is critical for cultivar discrimination and genetic studies. Our work provides a robust, high-precision, and reproducible framework for mandarin fruit slice phenotyping, offering significant potential for applications in agricultural research, breeding programs, and automated fruit quality evaluation.

Why it matches plant phenotyping methodsマンダリン果実スライスの形態・中心部構造を画像分割で定量する手法を開発し、精度検証と実測値比較を行っており、植物フェノタイピング手法が中心である。

abstractwe developed an automated segmentation framework based on YOLOv8 to detect and semantic segment the fruit segments and the central core

DSH_YOLO enables factory farming production: a method for detecting and grading the cumulative internode length of tomato seedlings. ↗

Introduction The industrial cultivation of tomato seedlings requires a high degree ofuniformity and consistency in grading. However, traditional grading methods based on phenotypictraits such as leaf area and canopy width are susceptible to environmental conditions, therebylimiting the accuracy and efficiency of grading. Since cumulative internode length is relativelystable and closely correlated with seedling vigor, this study aims to develop an accurate methodfor measuring and grading the cumulative internode length of tomato seedlings. Methods A tomato seedling cumulative internode length detection method, termedDSH_YOLO (Deformable Convolution-SIoU-Haar Wavelet Downsampling YOLO), wasproposed based on the YOLOv8-seg framework. First, deformable convolution was introducedinto the backbone to enhance feature extraction for curved stems and occluded regions. Second,the original loss function was replaced with SIoU to improve the alignment between predictedregions and the actual stem structure. Third, a Haar wavelet downsampling module was embeddedinto the backbone to preserve high-frequency detail information and reduce information loss underocclusion conditions. An intelligent grading system was further developed to verify the practicalapplicability of the proposed method. Results Experimental results showed that DSH_YOLO achieved a Precision of 96.1%, aRecall of 94.3%, and an mAP@0.5 of 92.1%. Compared with the baseline YOLOv8 model, theproposed method substantially improved segmentation performance for cumulative internoderegions in tomato seedlings. In prototype validation, the intelligent grading system achieved anaverage grading success rate of 87.50%, with an average cumulative internode length error of 8.0mm. Discussion The results indicate that DSH_YOLO and the grading system can meet therequirements for large-scale grading and detection of tomato seedlings, demonstrating highdetection accuracy and success rates. This approach can provide insights for grading other types ofseedlings during their growth stages and offer support for seedling production and thedevelopment of intelligent agricultural equipment.

Why it matches plant phenotyping methodsトマト苗の累積節間長という植物形態形質を画像分割・検出し、実用的な等級判定まで検証する手法開発が研究の中心であるため。

abstractA tomato seedling cumulative internode length detection method, termedDSH_YOLO (Deformable Convolution-SIoU-Haar Wavelet Downsampling YOLO), wasproposed based on the YOLOv8-seg framework.

Climate-Induced Variations in Plant Leaf Diseases: Optimized Detection Using Honey Badger Algorithm ↗

Climate fluctuation can have positive, negative, or neutral effects on plant leaf diseases depending on the location and period. It can also increase, decrease, or have no influence at all. These impacts will also be observed on other organisms, plant leaves, and other components of the agro-ecosystem. However, identifying these consequences is challenging, thus specialists from other disciplines need to look outside their own academic purview and consider the effects of climate fluctuation in a broader context. The principal application of this research is the detection of numerous factors related to how plant diseases are affected by climate change. Using data from prediction techniques of the future climate associated with disease, new research used to estimate the distribution in future climatic scenarios are outlined. A historical overview of the temporal and geographical distribution of diseases is provided. Major aspects of the development of illnesses under various atmospheric gas conditions are addressed in terms of the effects of increasing gas concentrations. The Plant Village data,where the data are first collected. To offer a reliable technique for background removal and integration of additional data sets, like geography, illness incidence history, and meteorological conditions, bilateral filtering is employed. The SURF method is employed to obtain attributes from images. Additionally, segmentation is done by K-means clustering method. IFFBPNN operates a realistic plant disease detection system that may be used in a range of climates and geographical locations. To identify the best accuracy, IFFBPNN uses a well-performing nature-inspired optimization technique called HBA to optimize its parameters. The outcomes of the simulations show that the suggested strategy is excellent compared to other modern techniques.

Why it matches plant phenotyping methods植物葉の病害状態を画像から検出するため、背景除去、SURF特徴抽出、K-means分割、最適化分類器を組み合わせた技術が中心であり、病害フェノタイピング手法に該当する。

abstractTo offer a reliable technique for background removal and integration of additional data sets, like geography, illness incidence history, and meteorological conditions, bilateral filtering is employed.

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

Label-Free Deep Learning with Feature Adaptation for Crop Anomaly Detection on Small Datasets ↗

Efficient crop health monitoring is crucial for global food security. Supervised deep learning approaches are often impractical due to the scarcity of large, labeled datasets. To address this limitation, this study adapts EfficientAD, an unsupervised, label-free anomaly detection framework originally designed for industrial inspection, for agricultural imagery on small datasets. The method utilizes a Patch Description Network (PDN) for localized feature extraction, a student network for local anomalies, and an autoencoder for global structural constraints. Benchmarked against AnoGAN, Pix2Pix, InTra, and Teacher–Student models, the framework demonstrated superior performance on the MVTec AD, PlantVillage, Coffee Leaf, and a custom real-world Sweet Potato dataset. The model achieved perfect area under the receiver operating characteristic curve (AUROC) scores of up to 100% in categories like “Pongamia”, “Potato”, and “Coffee Leaf”. While image-level classification was exceptionally robust, pixel-level localization (AUPRO) proved sensitive to complex agricultural backgrounds. To overcome this, a background interference analysis was conducted using Background Removed (BGRM) and out-of-distribution Background Replaced-Green (BGRP-G) strategies on the custom dataset. Notably, the BGRP-G strategy remarkably improved the image-level AUROC from 88.9% to 99.5% and substantially boosted the pixel-level AUPRO from 47.1% to 61.9%, successfully preserving the boundary integrity of severe structural defects. Achieving millisecond-level latency without complex data augmentation, this adapted label-free framework offers a versatile, highly efficient solution for real-time crop health diagnostics on resource-constrained Edge AI devices.

Why it matches plant phenotyping methods農作物画像から異常・健康状態を抽出する深層学習手法を開発し、複数データセットで性能比較・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 adapts EfficientAD, an unsupervised, label-free anomaly detection framework originally designed for industrial inspection, for agricultural imagery on small datasets.

Cotton field population phenotyping analysis based on 3D Gaussian reconstruction and dynamic spatial constraints ↗

Introduction High-throughput field phenotyping (HTFP) holds great potential for elucidating the relationship between genomes and phenotypes. However, obtaining high-quality three-dimensional point cloud data of field populations and achieving single-plant phenotypic analysis remain challenging. Methods This study develops an integrated framework for field crop reconstruction based on 3D Gaussian splatting, incorporating a geometry-aware dynamic constraint algorithm to achieve instance segmentation and extract key phenotypic traits of individual plants. Using 3D Gaussian splatting technology, field-scale cotton population modeling is accomplished, generating dense 3D point clouds for regions of interest. Furthermore, the concept of a crop localization domain is proposed, establishing a longitudinal mapping that associates plant positional coordinates with long-term phenotypic attributes. Finally, through a dynamic spatial constraint mechanism, the accuracy and computational efficiency of instance segmentation for crop population point clouds are significantly improved, enabling rapid extraction of individual plant traits such as cotyledon node height, plant height, and leaf area. Results The results demonstrate that PhenotypeAI successfully reconstructed nine cotton populations with PSNR exceeding 30.0 dB. It successfully extracted regions of interest from 403 cotton plants, achieving an average F-score of 91.32% for instance segmentation and an average accuracy of 91.35%. The extracted traits—cotyledon node height, plant height, and leaf area—exhibited strong correlations with manual measurements, with coefficients of determination ( R 2 ) of 0.90, 0.91, and 0.91, respectively. Discussion The proposed method provides a low-cost solution for high-throughput field phenotypic analysis of field cotton and improves the efficiency of cotton breeding.

Why it matches plant phenotyping methods3D再構成と動的空間制約による個体セグメンテーションおよび形質抽出が研究の中心で、綿花の草丈・葉面積などを検証しているため。

abstractThis study develops an integrated framework for field crop reconstruction based on 3D Gaussian splatting, incorporating a geometry-aware dynamic constraint algorithm to achieve instance segmentation and extract key phenotypic traits of individual plants.

Research on acquiring maize aboveground structure data using NeRF-Based 3D reconstruction and point cloud segmentation ↗

Abstract Maize（Zea mays L.） is an important crop, and improving its productivity is required even under challenging conditions such as labor shortages and uncertain climate fluctuations. One approach to enhancing yield is utilizing crop data for cultivation management and yield prediction. However, efficient acquisition of such data remains constrained by various limitations. In this study, we developed a non-contact and labor-efficient method for crop data acquisition by generating 3D models of maize at the ripening stage using Neural Radiance Fields (NeRF). Segmentation was performed on the obtained point clouds to estimate plant height, leaf area, and leaf angle. The coefficients of determination (R2) were 0.903, 0.954, and -0.521, respectively, demonstrating high accuracy for plant height and leaf area even at the ripening stage, while reducing the time required for data acquisition by 93% compared to manual measurements. Nevertheless, some manual operations−such as removing kernels and separating overlapping leaves−were still necessary, and full automation was not achieved. The main sources of error were identified as reconstruction errors in the base during scale adjustment, excessive removal of leaf sheaths, and the curvature of individual plants. Furthermore, we examined how measurement accuracy was influenced by factors such as the time of day and cultivar. The proposed method is expected to contribute to the practical implementation of a labor -saving 3D measurement technique that supports yield prediction and growth diagnosis in maize.

Why it matches plant phenotyping methodsNeRFによる3D再構成と点群セグメンテーションを開発し、トウモロコシの草丈・葉面積・葉角度を推定して精度と誤差要因を検証しており、表現型取得法が研究の中心である。

abstractwe developed a non-contact and labor-efficient method for crop data acquisition by generating 3D models of maize at the ripening stage using Neural Radiance Fields (NeRF).

A terrestrial laser scanning‐based workflow for component‐wise estimation of individual tree above‐ground biomass ↗

Abstract Accurate estimation of individual tree above‐ground biomass (AGB) and its component‐wise allocation is crucial for advancing ecological research and forest management. However, current biomass estimation methods, such as destructive sampling and allometric equation–based approaches, face limitations in both operational efficiency and cost‐effectiveness, and only destructive sampling can provide component‐wise biomass measurements, which is impractical for large‐scale studies or repeated measurements. In this study, we present a terrestrial laser scanning (TLS)‐based workflow integrating wood–leaf separation, voxel‐based foliage estimation and detailed 3D reconstruction of tree architecture to achieve accurate estimation of individual tree AGB and its component‐wise allocation. A total of 68 trees were scanned to obtain high‐resolution TLS data and subsequently destructively harvested to acquire field reference measurements for validation. The results demonstrate that the workflow achieved high accuracy in predicting AGB at the individual tree level (coefficient of determination/ R 2 = 0.88, root mean squared error/RMSE = 16.83 kg, mean absolute error/MAE = 12.18 kg), significantly outperforming estimates derived from locally calibrated allometric equations ( R 2 = 0.61, RMSE = 29.86 kg, MAE = 24.52 kg). Furthermore, this study provides evidence of the strong capability of TLS in estimating branch‐level biomass, with high accuracy achieved across branch orders ( R 2 ranging from 0.66 to 0.91, RMSE from 3.55 to 380 g and MAE from 2.97 to 290 g). By providing precise, non‐destructive estimates of biomass distribution across branches and leaves, this workflow demonstrates strong potential for improving the accuracy of tree biomass quantification, supporting investigations of resource allocation strategies, and enhancing forest carbon monitoring.

Why it matches plant phenotyping methodsTLSによる樹木の地上部・器官別バイオマスを推定するワークフローを開発し、破壊的実測で精度検証しており、植物形質取得法が研究の中心である。

abstractwe present a terrestrial laser scanning (TLS)‐based workflow integrating wood–leaf separation, voxel‐based foliage estimation and detailed 3D reconstruction of tree architecture to achieve accurate estimation of individual tree AGB and its component‐wise allocation.

Segmentation-Aware Hybrid CNN-ViT for Plant Leaf Disease Classification ↗

Diseases that affect plant leaves have a big effect on food supply and agricultural output. This makes it very important to find accurate and automatic ways to diagnose these diseases. This paper presents a segmentation-aware hybrid deep learning (DL) approach that integrates both Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) for the effective classification of plant leaf diseases. An unsupervised K-means clustering method is used first to make rough segmentation masks that don’t need manual labels. Then, a U-Net model is used to make them better. The combination of CNN and ViT is used to get at the segmented leaf images and get both main disease-related features and a broader context. Gradient-weighted Class Activation Mapping is used to show which parts of the leaf affect the diagnosis. This makes it easier to understand the model’s decisions. We test the framework on the PlantVillage dataset to see how well it works and then again on the Plant Disease Detection dataset to see how it works with different types of this data. The results show that the disease classification is better, that the system works better when the data sources change, and that the visual insights are very clear. These results show that the suggested approach is a dependable and comprehensible solution for the automated plant disease identification and can facilitate precision agriculture.

Why it matches plant phenotyping methods植物葉の病徴を画像から分類する手法の開発が中心であり、葉の病害状態を直接推定する画像ベースの表現型解析に該当する。

abstractThis paper presents a segmentation-aware hybrid deep learning (DL) approach that integrates both Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) for the effective classification of plant leaf diseases.

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