Plant phenotyping methods.

Cost-Effective Smartphone-Based Computer Vision Pipeline for Actinidia Phenological Stage Mapping →

Abstract Dioecious crops face significant pollination challenges due to the asynchrony in flowering between male and female plants. This asynchrony varies spatially across orchards, requiring targeted interventions in zones where synchrony is lacking. Assisted pollination addresses this deficiency, albeit at a substantial operational cost that could be optimised through spatial phenological mapping. Manual assessment proves economically infeasible at commercial scales, while existing computer vision systems are unable to classify phenological stages and integrate geospatial information. This study presents the Mobile Phenological Mapping (MPM) Framework, which integrates GNSS-synchronised smartphone video with automated phenological detection to generate plant-level phenological distribution maps validated in commercial kiwifruit (Actinidia chinensis) orchards. This modular framework comprises (i) training and validation data acquisition, (ii) model optimisation, (iii) operational pipeline, and (iv) performance evaluation. MPM employs hierarchical deep learning across three stages: structure detection, gender classification, and phenological stage classification. Video frames are georeferenced through timestamp matching with GNSS metadata, enabling spatial phenological mapping. Operational validation across four commercial orchard zones demonstrated mean absolute percentage errors of 17.2% for structure detection and 20.1% for gender classification. The framework reduces monitoring time from 113 to 1.6 hours per hectare, decreasing labour costs from €2 060 (113 hours × 18.20 € per hour) to €29 (1.6 hours × 18.20 € per hour) per hectare based on the Portuguese hourly labour cost for minimum wage workers. When integrated with routine orchard operations, video acquisition incurs negligible additional cost. MPM provides growers with precision phenological maps for targeted pollination interventions. While validated in a kiwifruit orchard, the modular architecture can be adapted to other crops by replacing the training data.

Why it matches plant phenotyping methodsスマートフォン動画とGNSSを用いて植物体レベルの性別・生育段階を自動検出し、フェノロジー分布を作成する手法と、その性能評価・商業園での検証が研究の中心である。

abstractThis study presents the Mobile Phenological Mapping (MPM) Framework, which integrates GNSS-synchronised smartphone video with automated phenological detection to generate plant-level phenological distribution maps validated in commercial kiwifruit (Actinidia chinensis) orchards.

Measuring and modelling the structural dynamics of poricidal anthers: a mechatronic approach. →

The mechanical dynamics of poricidal stamens play a crucial role in buzz pollination, but they have only been studied in a few species showing comparatively less curvature. This paper presents an integrated experimental-computational approach to characterize the dynamic behaviour of the morphologically more complex stamens of Medinilla magnifica. An experimental set-up employing a custom-built shaker and a laser triangulation sensor is developed to measure the stamen motion with high spatial and temporal resolution. The resulting displacement transmissibility reveals three distinct resonances, with the second one falling within the reported frequency range of pollination buzzes. Finite-element and multi-body models are developed and validated against experimental results. The models further reveal how the stamen morphology gives rise to its complex dynamic behaviour. The developed method enables precise parametric modelling of stamens and provides new insight into the mechanical basis of pollen release, thereby offering a framework for studying buzz pollination dynamics across plant taxa.

Why it matches plant phenotyping methods植物の雄しべ運動をレーザー計測し、有限要素・マルチボディモデルで検証する実験計算手法が研究の中心であるため。

abstractAn experimental set-up employing a custom-built shaker and a laser triangulation sensor is developed to measure the stamen motion with high spatial and temporal resolution.

CITRUS FLOWER, FRUIT, AND SHOOT RECOGNITION BASED ON IMPROVED YOLOv10 →

In the process of agricultural intelligence, precise detection of plant organs serves as the foundation for core tasks such as crop phenotyping analysis and yield prediction. However, in complex field environments, small targets such as citrus flowers and shoots face challenges including scale variation, background interference, and dense occlusion, which severely impact detection accuracy. This study improves the YOLOv10 model by introducing the BAM (Bottleneck Attention Module) attention mechanism and GIoU (Generalized Intersection over Union) loss function, constructing a YOLOv10s-BAM-GIoU model suitable for citrus flower, fruit, and shoot recognition. The BAM attention mechanism enhances the model's feature extraction capability for small target organs under complex backgrounds through parallel channel and spatial attention branches; the GIoU loss function improves the localization accuracy of densely occluded targets by optimizing the geometric alignment between predicted and ground-truth boxes. Validation experiments were conducted on a self-constructed dataset. The experimental results show that the improved YOLOv10s achieves significant advantages in comprehensive detection accuracy, with an mAP50 of 89.1%, representing an improvement of 2.9%~9.5% over the original YOLOv10s and other comparative models. In fine-grained category detection, the model achieves mAP50 of 91.2%, 83.6%, and 92.5% for shoots, flowers, and fruits, respectively. Furthermore, while maintaining high detection accuracy, the model achieves a detection speed of 23.6 ms per frame, meeting real-time detection requirements. The research results demonstrate that the improved YOLOv10s model integrating the BAM attention mechanism and GIoU loss function achieves an optimal balance between accuracy and speed in citrus organ detection tasks, providing a preferred solution for field real-time detection systems.

Why it matches plant phenotyping methods柑橘の花・果実・シュートという植物器官を画像から検出する改良モデルを開発し、データセットで精度と速度を検証しており、表現型取得手法が中心である。

abstractThis study improves the YOLOv10 model by introducing the BAM (Bottleneck Attention Module) attention mechanism and GIoU (Generalized Intersection over Union) loss function, constructing a YOLOv10s-BAM-GIoU model suitable for citrus flower, fruit, and shoot recognition.

UAV-Hyp: UAV Dataset for Remote Sensing-Based Phenotyping of Hypericum perforatum →

Quantitative flowering phenotypes are needed to support breeding and harvest management in Hypericum perforatum L. (St. John’s wort), but manual flower assessment is slow and difficult to standardize under field conditions. UAV-Hyp is a multi-temporal UAV RGB dataset containing 12,653 high-resolution images acquired at 26 measurement dates across the complete flowering period of 15 H. perforatum accessions. The images represent variable illumination, soil moisture, weed pressure, and developmental stages. The dataset provides 59,163 plant bounding boxes and 107,054 flower bounding boxes. As an application example, cascaded YOLOv8 plant and flower detectors achieved mAP@0.50:0.95 values of 0.977 and 0.950, respectively. UAV-Hyp supports scalable flower quantification and the development of time-series phenotyping methods for genotype comparison and quality-oriented medicinal-plant breeding.

Why it matches plant phenotyping methods植物の開花形質を定量化するUAV画像データセットを提供し、検出性能も評価しているため、フェノタイピング用データセット・解析手法が中心です。

abstractUAV-Hyp is a multi-temporal UAV RGB dataset containing 12,653 high-resolution images acquired at 26 measurement dates across the complete flowering period of 15 H. perforatum accessions.

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

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

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

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

Association of morphological markers of flower buds and anthers with the pollen developmental stage in Vicia faba L. ( Fabaceae ). →

The precise identification of microspore and pollen at the optimal developmental stages to be induced towards embryogenesis (vacuolated microspores and young pollen) is essential for induction of in vitro androgenesis in plants. Such identification is not always easy, and it is especially difficult in recalcitrant species such as Vicia faba . The present study evaluates the relationship between floral bud and anther morphometric parameters, and microspore/pollen developmental stages in V. faba using various methods including fluorescent staining, differential interference contrast microscopy, and morphometry. We measured flower bud and anther length and width, grouping them at different intervals, and performed a detailed microscopical and anatomical analysis of buds, anthers and microspores/pollen at different stages. Our results demonstrated that flower buds in V. faba exhibit complex and irregular morphologies, with considerable variation in both sepal length and shape. Furthermore, the determination of microspore and pollen developmental stages in this species is constrained by pronounced developmental asynchrony and strong genotype dependence. Although anther length measurements correlate closely with microspore and pollen developmental stages, their practical use can be challenging. Therefore, measuring flower bud length, while excluding sepals, remains the most practical criterion for routine applications. Combining this refined morphometric approach with microscopic validation appears to be the most effective strategy for improving the identification of flower buds containing microspores or pollen at developmental stages suitable for androgenesis induction in this recalcitrant legume species.

Why it matches plant phenotyping methods花蕾・葯の形態計測と顕微鏡検証を用いて、微小胞子・花粉の発達段階を推定する実用的な植物フェノタイピング手法を評価しており、方法開発・検証が中心である。

abstractThe present study evaluates the relationship between floral bud and anther morphometric parameters, and microspore/pollen developmental stages in V. faba using various methods including fluorescent staining, differential interference contrast microscopy, and morphometry.

Can Synthetic Data Overcome the Generalization Limits of AI-Based Flower and Pod Detection Across Cowpea Breeding Genotypes and Environments? →

High-throughput phenotyping requires AI-enabled computer vision models that generalize across genotypes, locations, and growing seasons, yet such models often lose accuracy under new conditions. Annotating real imagery for every genotype-by-environment (G x E) combination a breeding program encounters is prohibitively expensive. We quantify how G x E shifts affect AI-based detection of cowpea flowers and pods across two California locations and two growing seasons. Flower detection mAP@50 fell from 76.3% to as low as 50.6% under unseen shifts, and pod detection was more sensitive. Feature-space and image-quality diagnostics confirmed these losses track measurable distributional shifts. Because closing this gap with real data alone is not practical, we test whether synthetic imagery, rendered from a procedural 3D cowpea model, can substitute for that annotation burden. Synthetic supervision alone improved over pretraining but remained limited by a domain gap driven by camera image formation, not scene content. A domain-gap-aware camera-realism augmentation strategy, optimized against measured real-image statistics via Wasserstein distance, narrowed this gap, and a linear HDR representation converted a smaller measured gap into a larger detection gain than an 8-bit representation. Optimized HDR synthetic data combined with as few as five real images matched or exceeded the real-data baseline for spatial generalization, and pod detection benefited most at the lowest shot counts, with more modest gains under temporal shift. These results show that synthetic data can overcome the generalization limits of AI-based flower and pod detection, but only when the domain gap is measured and optimized rather than assumed away.

Why it matches plant phenotyping methods花・莢という植物器官の画像検出を対象に、異なる遺伝型・環境への一般化、合成画像、カメラリアリズム拡張、HDR表現を技術的に評価しており、植物表現型取得手法が研究の中心である。

abstractHigh-throughput phenotyping requires AI-enabled computer vision models that generalize across genotypes, locations, and growing seasons

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.

A simple hand-sectioning approach for cellular-resolution imaging of anatomy and gene expression in small developing organs and boundary regions in Arabidopsis. →

Background Precise characterization of gene expression patterns across temporal, cellular, and tissue-specific contexts is fundamental to understanding plant development and function. Recent advances in ClearSee-based tissue clearing have enabled high-resolution visualization of internal structures and fluorescent reporter signals in plant tissues. Although hand sectioning can provide optical access to tissues that are not amenable to whole-mount clearing, its application to submillimeter-scale and fragile Arabidopsis organs and tissues, including developing inflorescence apices, flowers, fruits, and organ boundaries, has remained limited. Consequently, analysis of these tissues has largely depended on specialized microdissection techniques and labor-intensive histological workflows, such as wax- or resin-embedded microtomy, which restrict throughput, accessibility, and routine use. Results We developed and optimized a simple hand-sectioning and imaging method that enables routine visualization of anatomical organization and gene expression patterns at cellular resolution in small, fragile Arabidopsis tissues. This method relies only on gentle manual tissue processing under a stereomicroscope and readily available reagents, allowing reproducible preparation of delicate tissues without the need for embedding or specialized equipment. Combined with ClearSee-based clearing and fluorescent reporters, the approach enables high-resolution imaging of internal tissue architecture and gene expression, while preserving tissue integrity and fluorescence signals that are often compromised during conventional embedding and microtomy procedures. Conclusions Our method substantially reduces technical complexity, costs, preparation time, and labor associated with cellular-resolution imaging of small, fragile plant tissues. By providing a simple, scalable, and accessible alternative to conventional histological workflows, this approach facilitates routine analysis of internal developmental processes across diverse plant species.

Why it matches plant phenotyping methods小型・脆弱な植物組織の解剖学的構造と遺伝子発現を細胞解像度で取得する手法を開発・最適化しており、表現型取得法が研究の中心である。

abstractWe developed and optimized a simple hand-sectioning and imaging method that enables routine visualization of anatomical organization and gene expression patterns at cellular resolution in small, fragile Arabidopsis tissues.

PolliCrop: A high-throughput computer vision pipeline for pollinator monitoring in agroecosystems →

Abstract Flower-visiting insect populations are declining since the 1990s, especially because of the decrease of floral resources in agricultural settings. Mass flowering crops can help increase resource availability, and plant breeding can be directed towards selecting varieties attracting more flower-visiting insects. This requires the implementation of an automated high-throughput phenotyping tool for assessing the attractiveness of plant genotypes to flower-visiting insects. In this study, ( i ) we present a procedure to take standardized images of sunflower heads with camera traps continuously at day and night in the field; ( ii ) we trained two versions of a deep learning model, named PolliCrop, to automatically detect and identify the three insect classes visiting the most sunflower (non- Bombus bees, bumble bees, lepidopterans); ( iii ) we assessed and validated the ability of PolliCrop to correctly predict the true visitation frequencies of the insect classes on three sunflower genotypes; ( iv ) we presented two statistical approaches to compare the insect visitation frequencies between plant genotypes, one including weather variables, and the other one without. One PolliCrop version yielded satisfying performance to correctly detect the three insect classes. In particular, it correctly predicted the insect visitation frequencies on two sunflower genotypes in a range of ±10%. The other PolliCrop version can be useful in certain contexts of images and objectives. PolliCrop can be extended in the future to other crop species by training PolliCrop on new images captured in these crops. The field experimental design to set up for comparing the attractiveness between genotypes is also discussed.

Why it matches plant phenotyping methods植物遺伝型の花への訪花昆虫誘引性を推定する画像取得・深層学習パイプラインを開発し、訪花頻度の予測性能も検証しており、表現型取得法が中心である。

abstractwe present a procedure to take standardized images of sunflower heads with camera traps continuously at day and night in the field

Dual-view weakly-supervised learning for apple tree flower counting. →

This paper presents a method to estimate apple tree flower cluster count using image analysis techniques. The main research question is how accurately flower clusters on apple trees can be counted using a camera-based approach and weakly-supervised learning, compared to traditional visual estimation. A camera is used to capture images of blooming apple trees from two sides. These images are processed by a weakly-supervised model based on a ResNet feature extractor and a feature pyramid network serving as the feature aggregator. The model is trained and validated using reference data obtained through manual flower cluster counts in the orchard and from estimations based on camera images. The model was trained using field-validated data and visually-estimated data, enabling a comparative evaluation. The proposed model surpassed conventional image segmentation methods in estimating both manually counted and visually estimated flower clusters. The proposed method achieves a relative error of 10.26% in estimating flower cluster quantities, demonstrating its effectiveness and improved accuracy over traditional approaches. Its reliance on field-validated reference data adds to its robustness and practical relevance.

Why it matches plant phenotyping methodsリンゴ樹の花房数という植物形質を、カメラ画像と弱教師あり学習で推定する手法の開発・検証が研究の中心であるため。

abstractThis paper presents a method to estimate apple tree flower cluster count using image analysis techniques.

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

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

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

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

Lodicule Isolation and Morphometric Analysis During Rice Floret Opening. →

Rice lodicules are specialized floral organs located at the base of the ovary that undergo dynamic morphological changes during the flowering period. Water uptake-driven swelling and subsequent dehydration-induced shrinkage of the lodicules trigger floret opening and closure, respectively. Although lodicules play a central role in floret movement, standardized methods for quantitatively monitoring their temporal morphological changes remain limited. Here, we describe a detailed and reproducible workflow for lodicule sampling, dissection, imaging, and quantitative morphometric analysis. Florets are collected at predefined clock time points during the flowering period, and lodicules are carefully isolated under a stereomicroscope. High-resolution imaging is performed under consistent acquisition settings, followed by precise measurement of lodicule length, width, and thickness using image analysis software. This protocol emphasizes positional consistency in sampling, uniform imaging parameters, and standardized data analysis to enhance reproducibility. This method is suitable for evaluating the effects of genetic background or environmental conditions on lodicule morphology. By providing a standardized analytical framework, this protocol enables accurate and quantitative morphometric analysis of rice lodicules during floret opening. Key features • Standardized time-point sampling minimizes variability caused by diurnal fluctuations and handling during lodicule morphometric analysis. • Enables reproducible isolation and imaging of rice lodicules while preserving native morphology and preventing dehydration-induced artifacts. • Time-resolved workflow enables analysis of rapid morphological changes associated with floret opening and closure. • Applicable for comparing genetic and environmental effects on lodicule morphology under controlled experimental conditions.

Why it matches plant phenotyping methodsイネ小花器官の形態を標準化された採取・撮像・画像解析で定量する再現可能な表現型測定プロトコルが中心である。

abstractwe describe a detailed and reproducible workflow for lodicule sampling, dissection, imaging, and quantitative morphometric analysis.

Development of auxin reporters in oilseed rape (Brassica napus) →

Auxin is a key phytohormone that regulates all aspects of plant growth, development, and environmental responses, making the precise analysis of its distribution and signaling essential for understanding plant adaptation and physiological processes. However, despite the agricultural importance of oilseed rape (Brassica napus), the lack of robust, species-specific molecular tools limits detailed studies of hormone signaling in this crop. Here, we developed and characterized reporter systems for the sensitive visualization and quantification of auxin distribution and signaling in B. napus. The DR5cc auxin signaling reporter and a novel synthetic auxin-responsive reporter, BIP3, assembled from promoter fragments of three oilseed rape IAA genes, were generated to drive GUS expression. In hairy roots, both reporters showed auxin-responsive expression in the root apical meristem that became broader after auxin treatment. In transgenic seedlings, flowers at anthesis, and 12-day-old embryos, DR5cc exhibited a more defined expression pattern than BIP3. To monitor real-time auxin dynamics under abiotic stress, DR5cc fluorescent reporters were employed in hairy roots. Mannitol and NaCl treatments induced a time-dependent increase in fluorescence, peaking at 6-12 h before returning to basal levels after 24 h. Furthermore, dual-reporter assays enabled simultaneous monitoring of auxin and cytokinin signaling, revealing distinct hormone-specific spatial responses in hairy roots. Finally, we established a quantitative DII (qDII) reporter system using degron domains from B. napus Aux/IAA proteins, providing a high-resolution quantitative readout of auxin depletion. Together, these reporter systems enable spatial, temporal, and quantitative analyses of auxin dynamics during development and stress adaptation in oilseed rape.

Why it matches plant phenotyping methodsナタネにおけるオーキシン分布・シグナルを可視化および定量するレポーター系を開発・評価しており、植物の生理状態を取得する方法が研究の中心である。

abstractHere, we developed and characterized reporter systems for the sensitive visualization and quantification of auxin distribution and signaling in B. napus.

Plant Acoustics for Evaluating Vase Life in Chrysanthemums: A Novel and Noninvasive Method →

ABSTRACT Vase life is a key determinant of cut flower quality and market value. Conventional vase life assessment relies on visual inspection and physiological monitoring over several days to weeks, making it labor‐ and time‐intensive. This study introduces a rapid and noninvasive approach using plant acoustics to assess postharvest vase‐life‐related variation in cut chrysanthemum flowers. Six chrysanthemum cultivars were grown under two supplemental lighting treatments (Hybrid and LED) and two planting densities (54 and 74 plants m −2 ). Acoustic monitoring was compared with optical microscopy for the assessment of xylem vessel diameter, while conventional vase‐life testing was performed in parallel. Optical microscopy validated the acoustic measurements, with both methods consistently identifying vessel radii around 10 μm. The acoustic radius (), derived from pulse settling time measurements, showed cultivar‐ and planting‐density‐specific variation. Linear mixed‐effects modelling demonstrated that the relationship between acoustic radius and vase life differed significantly among cultivars, indicating that a universal relationship across cultivars is not supported. These findings show that acoustic monitoring provides a meaningful noninvasive proxy for vase‐life‐associated stem traits and may serve as a useful cultivar‐calibrated tool for evaluating postharvest longevity in cut chrysanthemums.

Why it matches plant phenotyping methods植物の茎の道管径に基づく音響的な非破壊測定法を開発し、光学顕微鏡および花持ち試験で検証しているため、表現型取得法が研究の中心です。

abstractThis study introduces a rapid and noninvasive approach using plant acoustics to assess postharvest vase‐life‐related variation in cut chrysanthemum flowers.

Unveiling the genetic control of repeat flowering in blueberry with a novel continuous quantitative phenotyping approach →

Flowering in perennial crops is a trait influenced by genetics, environmental cues and plant vigor. Here, we studied the genetic and environmental control of repeat flowering (RF) in blueberry ( Vaccinium corymbosum ). RF was measured in a full-sib population from a cross between repeat and non-repeat flowering cultivars (‘Hortblue Petite’ and ‘Nui’, respectively). Longitudinal phenotypes were used to model the area under the curve for the first and second flowering peaks. We found that RF was strongly influenced by bush size and vigor, which we then incorporated into the area under the flowering curve models. Quantitative trait loci linked to both first bloom and RF were detected at three hotspots on chromosomes 4 and 10, and genes of interest known to regulate flowering under both temperature and photoperiod control were discussed. The phenotyping protocol and statistical modelling method reported here are an effective strategy for the investigation of complex interactions between multiple genetic loci and environmental variables on developmental traits, such as flowering. Experimental designs with replicated multi-environment and multi-year measurements are now needed to corroborate our results and further elucidate the determinism of RF in blueberry.

Why it matches plant phenotyping methodsブルーベリーの反復開花を連続的・定量的に測定し、開花曲線のモデリングを組み合わせた新規フェノタイピング手法とプロトコルが明示され、開花形質の遺伝解析における方法論的貢献が中心的です。

titlewith a novel continuous quantitative phenotyping approach

A task-specific architecture with multi-scale attention and shape-aware loss for strawberry phenophase recognition in complex fields. →

To address the challenges of recognizing small strawberry targets and achieving accurate phenological perception in complex field environments, this paper proposes a novel end-to-end lightweight detection architecture named HCMS-Net. The backbone is a Residual Efficient Layer Aggregation Network (R-ELAN) enhanced with a Multi-Scale Convolutional Attention (MSCA) mechanism, which emphasizes subtle color and texture variations to differentiate key phenological phases. For feature fusion, hypergraph convolution (from HyperC2Net) and a Mixed Aggregation Network (MANet) are incorporated, modeling the clustered morphology of strawberries and strengthening the representation of sparse small fruits. The detection head incorporates a lightweight Conv2Former module to capture long-range dependencies and spatial contextual information across growth stages, thereby enhancing the model's capacity to represent continuous phenological changes. A Shape-Normalized Wasserstein Distance (Shape-NWD) loss is introduced to stabilize optimization against minor pixel deviations. Experimental results demonstrated that HCMS-Net achieved a mean average precision (mAP) of 94.9% and an F1-score of 90.0%. Specifically, the average precision (AP) values for the flowering, young fruit, green fruit, veraison, and mature fruit stages reached 99.3%, 88.3%, 90.9%, 97.0%, and 98.2%, respectively. Heatmaps confirmed HCMS-Net's precise attention focus across all five phenological stages, effectively suppressing irrelevant backgrounds. Compared to ten mainstream detectors, HCMS-Net surpassed alternatives such as RT-DETR and the YOLOv5n to v13n by 3.4-8.0 percentage points in mAP. It even surpassed YOLOv12s by 2.7 percentage points, while containing only 32.86% of its parameters. The model offers high accuracy and efficiency for phenological period detection, supporting selective harvesting and intelligent agricultural management.

Why it matches plant phenotyping methodsイチゴの生育フェノフェーズを画像から認識する新規検出モデルを開発し、複数手法との性能比較・検証を行っているため、植物フェノタイピング手法が中心である。

abstractthis paper proposes a novel end-to-end lightweight detection architecture named HCMS-Net

Benchmarking hybrid CNN and transformer backbones with graph convolution networks (GCN) for flower growth-stage classification. →

Accurate recognition of flower growth stages is important for plant phenotyping but remains challenging due to subtle visual differences and limited labeled data. This study proposes a hybrid CNN/Transformer + GCN framework for fine-grained flower growth-stage classification. A new dataset, BD Flower Growth, is introduced with 3,889 original images from eight Bangladeshi flower species, categorized into three stages (early, mid, full), forming 24 classes. The dataset is divided into training and testing sets, with augmentation applied only to the training data. Deep backbone networks are used to extract feature maps, which are transformed into graph representations and refined using Graph Convolutional Networks (GCN). A systematic ablation study is conducted by varying GCN depth (3, 5 layers), node resolution ([Formula: see text], [Formula: see text]), and graph construction methods (4-neighbour, 8-neighbour, and KNN with [Formula: see text]). Experimental results show that performance depends strongly on both backbone and graph configuration. The best performance of 97% accuracy is achieved by EfficientNetV2, DenseNet201-based hybrid models, additionally Swin Transformer model shows the largest improvement, increasing from 84% to 97% after GCN integration. Across different settings, grid-based graphs (4- and 8-neighbour) consistently provide more stable and higher performance compared to KNN graphs, while moderate GCN depth (3-5 layers) offers the best balance accuracy. Cross-dataset evaluation on the Oxford 102 Flower dataset further demonstrates the generalization capability of the proposed approach. These findings highlight the effectiveness of hybrid graph-based learning and the importance of graph configuration in improving fine-grained classification.

Why it matches plant phenotyping methods花の生育段階という植物状態を画像から分類する手法の開発・比較検証が中心で、新規データセットとアブレーションおよびクロスデータセット評価も含むため。

abstractAccurate recognition of flower growth stages is important for plant phenotyping

An innovative screening method for heat stress tolerance in chickpea ( Cicer arietinum L.). →

Reliable field phenotyping for terminal heat stress (THS) tolerance in chickpea is constrained by conventional late-sowing approaches that confound reproductive stress with reduced vegetative growth. We developed and validated a deflowering (DF)-based field screening method that selectively imposes heat stress during the reproductive phase while maintaining normal vegetative vigour. Early flowers were removed to synchronize flowering and delay reproduction by 10-15 days, exposing flowering and pod set to high temperatures (>33 °C). Across two seasons and contrasting genotypes, DF maintained vegetative growth but significantly reduced pollen viability, pod set, and yield, with tolerant genotypes showing markedly lower yield penalties than susceptible ones. The method effectively discriminated reproductive thermotolerance and provides a simple, low-cost, and biologically grounded phenotyping tool for chickpea breeding under warming climates.•A DF-based field method selectively imposes reproductive-stage heat stress without compromising vegetative growth.•The approach reliably distinguishes heat-tolerant and susceptible chickpea genotypes under natural field conditions.

Why it matches plant phenotyping methods生殖期の耐暑性を選択的に評価するDFベースの圃場スクリーニング法を開発・検証しており、遺伝子型の識別に用いるフェノタイピング手法が中心である。

abstractWe developed and validated a deflowering (DF)-based field screening method that selectively imposes heat stress during the reproductive phase while maintaining normal vegetative vigour.

CFPR-YOLO: chili flower pose estimation for robotic pollination in unstructured environments. →

Agricultural engineering informatics is playing an increasingly important role in enabling intelligent perception, decision-making, and automated operations in modern horticultural production systems. Within this context, accurate visual perception of reproductive structures is essential for agricultural informatization tasks such as flowering-stage monitoring, precision pollination, and information-driven fruit-set management in chili cultivation. However, reliable detection and pose-aware recognition of chili flowers remain challenging because of small target size, dense distribution, foliage occlusion, and illumination variability in natural or semi-controlled environments. To address these challenges, this study proposes a lightweight and robust edge vision framework, termed CFPR-YOLO, for chili flower detection and pose-aware perception under complex agricultural conditions. Built upon an improved YOLOv11n architecture, the proposed framework incorporates EfficientFormerV2 to strengthen global-context feature extraction, a C3k2_EMA module to enhance localization of small and occluded targets, and Poly-Scale Convolution (PSConv) to preserve structural details while reducing computational redundancy. In addition, a lightweight attention mechanism is introduced to improve feature discrimination in cluttered backgrounds. Experimental results on both self-constructed and generalization datasets show that the proposed method achieves a precision of 92.6%, a recall of 86.8%, and an mAP50 of 92.1% with only 7.26 M parameters. The framework also demonstrates strong robustness and generalization across different chili varieties. When deployed on an edge computing platform (NVIDIA Jetson AGX Orin), the model achieves real-time inference at 39.5 FPS. Furthermore, validation experiments under controlled indoor conditions show that the proposed framework can effectively support simulated pollination tasks, achieving a success rate of 90.0% for upwardfacing flowers. These results indicate that CFPR-YOLO provides an effective visual perception solution for agricultural engineering informatics-oriented pollination systems and offers practical potential for precision pollination and intelligent fruit-set management in horticultural production.

Why it matches plant phenotyping methodsチリ花の検出・姿勢推定という植物器官の画像計測手法を開発し、データセット、汎化性能、エッジ実装、実環境に近い条件での検証まで行っており、単なる受粉実験の補助計測ではない。

abstractthis study proposes a lightweight and robust edge vision framework, termed CFPR-YOLO, for chili flower detection and pose-aware perception under complex agricultural conditions.

Defining critical drivers of cross-pollination for better hybrid grain set in wheat →

Hybrid wheat breeding offers a promising route to enhance grain yield and yield stability through heterosis, yet hybrid grain production remains constrained by limited cross-pollination efficiency due to high rates of autogamy. To achieve cross-pollination in an autogamous species like wheat, pollen must shed outside the floret. This is typically assessed by scoring visual anther extrusion (VAEX), a key floral trait that sets the foundation for cross-pollination. However, VAEX explains only part of the variation in hybrid grain set. To address this, we analyzed floral structures and reproductive processes underlying cross-pollination efficiency in wheat. From 24 elite winter wheat genotypes, we developed traits describing anther extrusion kinetics, pollen release, and floral bract architecture. These traits showed substantial genotypic variation and high heritability. While VAEX alone explained approximately 49% of the variation in hybrid grain set, combined trait analyses explained up to 77%, demonstrating that hybrid grain production is governed by coordinated floral and reproductive trait interactions. Together, our analyses define a hierarchical trait architecture linking floral bract mechanics, anther extrusion dynamics, and pollen shedding to cross-fertilization success. This establishes a systems-level phenotyping framework for improving male parent selection in hybrid wheat breeding. Highlight High cross-pollination efficiency in wheat is a multi-factorial process that requires lighter floral bract architecture combined with adequate anther extrusion and pollen release for improving hybrid grain production.

Why it matches plant phenotyping methods交雑受粉効率を評価するための葯突出動態、花粉放出、苞葉構造の形質を開発し、統合的なフェノタイピング枠組みとして解析しており、表現型取得・評価法が研究の中心である。

abstractFrom 24 elite winter wheat genotypes, we developed traits describing anther extrusion kinetics, pollen release, and floral bract architecture.

BerryFlowerNet: A Customized Convolutional Neural Network for Blueberry Flower Cluster Detection and Flowering Stage Prediction with a Field Phenotyping Robot →

Blueberry production has rapidly expanded over the past decade, accompanied by growing demand for efficient and accurate methods to monitor the flowering and fruiting phases of blueberry development, which has a direct impact on yield potential. Accurate determination of blueberry phenology enables growers to make data-driven decisions on freeze protection applications and harvest windows. In addition, objective phenology data of blueberry mapping populations will provide high-quality phenotype data for the discovery of genetic mechanisms regulating blueberry flowering and fruiting times. Traditional approaches, such as manual counting and visual ratings, are labor-intensive and subjective in capturing variation across genotypes. Recent progress in computer vision and deep learning has enabled automated flower detection, but most existing studies on blueberries remain restricted to narrow flowering windows or close-up images, limiting their application at the bush level and across the seasonal development. In this study, we developed BerryFlowerNet, a customized YOLO-based model to detect and count blueberry flower clusters from bud to green fruit stages. A comprehensive dataset was collected on three dates using a field phenotyping robot, covering five flowering stages. The integration of CFNet, a custom module fusing shallow spatial features, and PIoU loss improved the detection performance. Additionally, the Slicing Aided Hyper Inference algorithm was employed to address small-object detection in bush-level images. Experimental results demonstrated that BerryFlowerNet outperformed the baseline YOLO model and three additional detectors, achieving an average mAP0.5 of 0.644 across five independent training runs. The model achieved an accuracy of 0.88 when predicting blueberry flowering stages, indicating its effectiveness and accuracy. Additionally, the results of the bush-level image analysis showed the capability of the model to capture genotype-level differences in flowering dynamics. Overall, this approach offers new opportunities for growers and breeders to determine blueberry phenological development that is critical for optimizing on-farm management strategies and advancing precision phenotyping to facilitate the development of climate-resilient blueberries.

Why it matches plant phenotyping methodsブルーベリーの花房検出・計数と開花ステージ推定を行うCNNおよびフィールド表現型ロボットの開発・評価が研究の中心であり、植物の生育状態を直接推定する実質的な表現型手法である。

abstractIn this study, we developed BerryFlowerNet, a customized YOLO-based model to detect and count blueberry flower clusters from bud to green fruit stages.

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.

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.

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

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

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

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

A Simplified Heat-Tolerance Evaluation System at the Pollen Development Stage in Rice ( Oryza sativa L.). →

Heat stress, particularly during the reproductive stage, poses a major challenge to rice production, as pollen development is highly sensitive to elevated temperatures. Accurate assessment of heat tolerance during this period is crucial for improving rice heat-stress tolerance but is hindered by asynchronous panicle development and imprecise staging. In this study, we identified a pair of near-isogenic lines, ZP15 and ZP17, which exhibited contrasting seed-setting rates under heat stress. We demonstrated that this divergence arises from differential tolerance during the pollen developmental stage, corresponding to a critical window (9-16 days before heading). Taking these lines as references, we established a reliable system that synchronizes developmental staging and quantitatively assesses heat-induced fertility loss. Validated using heat-tolerant N22 and heat-sensitive Wushansimiao, this system was applied to assess four conventional varieties and eight hybrids. Huanghuazhan and self-bred hybrids (Yangxianyou 912, Yangxianyou 903, and Yangxian 9A/P119-8) displayed high tolerance comparable to control varieties, whereas Yangdao 6 and multiple hybrids showed pronounced sensitivity. Collectively, this work provides a precise and reproducible framework for evaluating heat tolerance during pollen development, offering a valuable tool for accelerating the breeding of heat-resilient rice varieties.

Why it matches plant phenotyping methodsイネの花粉発育期における高温耐性と受精率低下を定量評価する、再現性のある評価システムを開発・検証しており、植物表現型取得が研究の中心である。

abstractwe established a reliable system that synchronizes developmental staging and quantitatively assesses heat-induced fertility loss.

Identification of self-incompatibility in macadamia (Macadamia SPP.) using field-bagging and fluorescence microscopy →

Self-incompatibility (SI) significantly reduces crop yield, often far below its genetic potential. Developing self-compatible varieties is the most effective strategy for overcoming SI in crops. Most macadamia ( Macadamia SPP.) species exhibit SI or partial self-incompatibility (PSI), so the efficient identification of self-compatible germplasms has emerged as a crucial topic. To characterize self-incompatibility phenotypes in macadamia germplasm resources, we conducted a four-year field study using the field-bagging method and established a standardized classification system of self-incompatibility. That is, the degree of SI was based on the final self-incompatibility index (F_SI), which was calculated based on the open-pollination final nut set per raceme (OP_FNS) and self-pollination final nut set per raceme (SP_FNS) values (strong SI: F_SI ≥ 0.7, medium SI: 0.4 ≤ F_SI 35%). Through comprehensive analysis of the field-bagging and fluorescence-microscopy observations, thirteen varieties with strong SI (816, 778, 842, Special, 812, D, 820, 246, 772, A16, A4, 951, and 695), six varieties with moderate SI (851, 828, 508, 936, O.C, and D4), and four varieties with weak SI (915, HY, 836, and 814) were identified. Our study provides a theoretical foundation and technical support for advancing germplasm resource innovation, and the genetic improvement and breeding of self-compatible macadamia varieties.

Why it matches plant phenotyping methods自家不和合性という植物状態を対象に、圃場袋掛けと蛍光顕微鏡観察を用いた標準化分類体系を確立しており、表現型の取得・評価法が研究の中心である。

abstractTo characterize self-incompatibility phenotypes in macadamia germplasm resources, we conducted a four-year field study using the field-bagging method and established a standardized classification system of self-incompatibility.

Augmenting plant-pollinator interactions to promote biodiversity and global food security →

Global agricultural production is currently limited by ongoing climate change. Approximately 90% of crop species and numerous wild plants are dependent on pollinators for reproduction. The global threat to pollinators posed by climate change has grown considerably, as higher temperatures, shifting rainfall patterns, and more frequent extreme weather events disrupt the fragile relationships between plants and their pollinators. The decline in pollinators is also linked to shifts in land use, the widespread adoption of monocropping, and heavy reliance on agrochemicals. Therefore, the protection of pollinators and the preservation of agrobiodiversity are essential to uphold global food systems. Here, we synthesize the adverse impact of climate change on plant-pollinator interactions; throughput assay for phenotyping floral traits; assessing variability and molecular basis of floral display (flower size, shape, color, attractants etc.) and reward (nectar volume and composition, pollen, and fragrance in case of ornamental plants) traits; crop domestication and inbreeding, ploidy and mating systems differences impacting plant-pollinator interactions; volatiles and metabolites mediating plant-pollinator relationships; trade-offs involving reproductive and pollinator traits; and finally, progress in developing pollinator-friendly crop cultivars through conventional plant breeding and biotechnological interventions. Pollinator-assisted phenotyping and selection platform (DARkWIN) combined with other high-throughput phenotyping assays, has the potential to simultaneously quantify multiple interactions impacting pollinators’ visitation and foraging behaviors, and generate data on other parameters like stress tolerance, yield, and nutrition in the target populations. Assessing and exploiting functional diversity for plant-pollinator interactions, combined with the use of functionally characterized genes and associated markers for floral display ( AT2G31010 , AT4G17080 , CmGEG , CmCYC2c , CmJAZ1-like-CmBPE2 , Cyc2CL-1 , Cyc2CL-2 ) and reward ( SWEET9 , BrCWINV4A , EOBI , EOBII ) traits, can be deployed in breeding programs to develop pollinator-friendly crop cultivars. Numerous candidate genes, reported herein, must be functionally validated before being deployed in crop breeding programs.

Why it matches plant phenotyping methods植物―送粉者相互作用と花形質を対象とするレビューであり、花形質のスループット表現型解析やDARkWINによる送粉者支援型フェノタイピング基盤を主要な方法論として扱っている。

abstractthroughput assay for phenotyping floral traits

High‐throughput phenotyping for the prediction and quantification of flower‐related traits in sugarcane →

Abstract Sugarcane ( Saccharum spp.), a C4 plant, is a vital renewable biofuel and sugar source for industries worldwide. However, synchronizing flowering between parental lines often poses challenges for breeders, hindering effective crossbreeding efforts. This study aimed to develop a high‐throughput phenotyping (HTP) strategy to evaluate flowering‐related traits using vegetation indices (VIs) and other metrics alongside artificial intelligence (AI)‐based prediction methods. A total of 154 genotypes were planted in an augmented block design at the IAC sugarcane breeding station in Serra Grande‐BA, Brazil. Raw RGB (Red, Green, Blue) images were captured using a DJI Mavic 3 Enterprise drone during the plant cane (PC) and first ratoon (FR) crop seasons. These images were processed to create orthomosaics and compute metrics/vegetation index; subsequently, machine learning (ML) and deep learning pipelines for systematic analysis were developed. A convolutional neural network (CNN) model achieved promising results, with an accuracy rate of up to 84% in the flowering detection task. Additionally, flower counts from the CNN model showed a moderate correlation with field data, evidenced by an R 2 value of 0.72 at the onset and an R 2 value of 0.29 at the conclusion of the flowering season for the PC. This resulted in an overall average regression R 2 of 0.46 with a root mean square error (RMSE) of 13.80. Furthermore, an artificial neural network classification model reached a notable accuracy of 0.87 in differentiating genotypes based on their flowering response (early‐flowering vs. late‐flowering), utilizing VIs and digital model‐based metrics as input parameters. The ML regression model demonstrated performance levels of R 2 = 0.51 and RMSE = 8.06 for days to flag leaf emergence in PC and R 2 = 0.52 and RMSE = 7.93 for days to flowering in FR. These results highlight the potential of HTP strategies, utilizing orthomosaics and AI, to accelerate data collection and analysis, offering significant insights for breeding programs in sugarcane.

Why it matches plant phenotyping methodsドローンRGB画像、オルソモザイク、植生指数、AIを組み合わせた開花形質のハイスループット取得・予測手法を開発し、精度検証まで実施しており、フェノタイピング手法が研究の中心である。

abstractThis study aimed to develop a high‐throughput phenotyping (HTP) strategy to evaluate flowering‐related traits using vegetation indices (VIs) and other metrics alongside artificial intelligence (AI)‐based prediction methods.

Early Apple Yield Prediction Based on Flowering Stage Image Thinning Simulation Characteristics. →

The existing fruit tree yield prediction methods mainly rely on fruit period images or long-term meteorological and soil data, which make it difficult to meet the needs of early yield prediction. In addition, the flowering period images contain complex spatial distribution and severe overlap between flowers, which makes it challenging to directly extract stable structural indicators related to yield. Most existing research has focused on simple statistical indicators such as the number of flowers, while the spatial clustering structure of flowers and their relationship with yield have not been fully explored. Therefore, this article proposes an early apple yield prediction based on flowering stage image thinning simulation characteristics. In this study, blossom images and fruit maturity yield data from 100 apple trees were collected, with flower mask images extracted through standardized image processing. First, the traditional DBSCAN clustering algorithm was enhanced by integrating a KDTree acceleration structure and an adaptive multi-scale mechanism, forming the adaptive multi-scale clustering algorithm (AMS-DBSCAN) to achieve efficient identification of flower clusters and individual flowers. Based on this, two flower thinning simulation strategies based on density and spatial uniformity were designed to model artificial thinning rules and construct multi-dimensional, interpretable phenotypic features. Then, the original statistical features were fused with strategy-generated features and optimized using Lasso. We compared multiple models including XGBoost, BPNN, and SVR for yield prediction. The experimental results showed that XGBoost achieved good predictive performance under the hybrid feature set (R 2 = 0.856, RMSE = 3.098), which was further improved to R 2 = 0.900 after feature optimization with Lasso. The results demonstrate that the proposed method enables reliable early yield estimation, providing a new reference for precision management and early decision-making in fruit tree cultivation.

Why it matches plant phenotyping methods花画像から花群・個体を抽出し、間引きシミュレーション由来の解釈可能な表現型特徴を構築する画像解析手法が研究の中心であり、収量推定に技術的に応用・評価されている。

abstractflower mask images extracted through standardized image processing

A Precise Reproductive Calendar of Sexual and Apomictic Genotypes of Eragrostis curvula . →

Eragrostis curvula serves as a valuable model for studying diplosporous apomixis due to its unique reproductive mode, wide ploidy range, and extensive genomic resources. A major limitation for reproductive studies in this species is the difficulty of isolating female tissues at precise developmental stages, for example, for transcriptomics studies, since different floral tissues can introduce expression noise from non-target tissues. To overcome this, we performed a detailed cytoembryological and morphometric characterization of male and female development in seven E. curvula genotypes with different ploidy levels (2X-7X) and reproductive modes (sexual, facultative apomictic, and obligate apomictic). Using differential interference contrast microscopy and methyl salicylate clarification, we described key cytological stages of male and female development. These stages were then correlated with external floral parameters, including pistil, ovary, style, and anther length, to generate genotype-specific developmental calendars. Pistil length showed the strongest association with female developmental stage, particularly during the early phases of ovule development, enabling more precise staging. Synchrony between male and female development was also evaluated, revealing no consistent differences among reproductive modes or ploidy levels. This genotype-informed framework provides a practical tool for stage prediction and tissue selection, supporting future reproductive, developmental, and comparative studies in E. curvula and related grasses.

Why it matches plant phenotyping methods花器官の形態計測を細胞発生段階の推定に体系的に対応付け、遺伝子型別の発達カレンダーと再利用可能なステージ予測手法を構築しており、表現型取得が中心である。

abstractThese stages were then correlated with external floral parameters, including pistil, ovary, style, and anther length, to generate genotype-specific developmental calendars.

CryoFluorSEM – A new approach for fluorescence and EM imaging of cryofractured plant samples →

Abstract Cryo‐scanning electron microscopy (CryoSEM) permits the preparation and detailed imaging of bulky samples while keeping them in a hydrated state. For plant biology, cryofractures give information on cell ultrastructure and tissue organisation within a much larger context that is the whole organ or organism. To date, a method to locate fluorescence reporters on the cryofracture has not been reported. Our approach uses a stereofluorescence microscope with an 80 mm working distance and a high‐zoom ratio to image the fracture through a viewing port of the cryopreparation chamber while the sample is still frozen and under vacuum. We have applied this method to look at fluorescent reporters of auxin transport and signalling in plant shoot apices and seedlings, the expression of a poorly characterised gene in the young floral pedicel and nitrogen‐fixing rhizobial bacteria, expressing GFP, in root nodules. This method is applicable to any cryopreserved bulky sample that has a fluorescent output and paves the way for correlative light‐electron microscopy for cryoSEM‐based imaging.

Why it matches plant phenotyping methods植物試料の蛍光レポーターを凍結破断面上で位置特定・画像化する新規CryoFluorSEM法の開発であり、植物の構造・組織状態を取得する方法が中心である。

abstractTo date, a method to locate fluorescence reporters on the cryofracture has not been reported.

Inspection of pollination transfer and success in coffee flowering detection using intersection over union based cascade RCNN in a vision environment. →

The intricate process of coffee blossoming, pollination transfer, and successful development is crucial for creating every exquisite cup of coffee. During the flowering stage of coffee plants, delicate white flowers with a pleasant fragrance appear briefly, providing a limited opportunity for effective pollination. At this stage, the stigma of the flower, which is the female reproductive organ, becomes receptive and prepared to receive pollen. Existing research found methods such as machine learning and image analysis for monitoring crop pollination. Manual image annotation is conducted on pollen count disregarding spatial component of pollen collection which is essential for successful pollination. However, use of these strategies on coffee flowers by their complex structure and continuous changed in flowering stages. The paper represents novel methodologies by introducing methodological approach “IoU-AI” to monitor pollen transmission and success of pollination in coffee flower. IoU-AI utilize high resolution coffee flower image accurately track and detect floral organs by offering insight to pollen transfer. IoU-AI employs deep learning models to detect and observe floral components like stigma and anthers. Further computes overlap between structures and estimate pollen transmission. The flower detection accuracy was evaluated against ground truth measurements. The accuracy of coffee flower detection ranged from 94.77% to 85.34% for flower stages ranging from 20% to 100% blooming.

Why it matches plant phenotyping methodsコーヒー花の画像から柱頭・葯を検出し、重なりに基づいて花粉伝達と受粉成功を推定する画像解析手法を開発・精度評価しており、植物状態の取得が中心です。

abstractThe paper represents novel methodologies by introducing methodological approach “IoU-AI” to monitor pollen transmission and success of pollination in coffee flower.

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

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

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

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

ADA-Net: A Lightweight Model for Apple Flower Maturity Detection in Horticultural Plant Monitoring →

In modern orchards, the pollination process of apple blossoms plays a crucial role in determining both the quality and yield of the fruit. While most current studies concentrate on identifying individual apple flowers, there is limited research on assessing the developmental stages of apple flowers in dynamic and complex orchard settings. Challenges arise due to the intricate environmental factors and subtle color changes in the anthers following the maturation of the apple flowers, which complicate accurate detection. To overcome these challenges, ADA-Net, an efficient YOLOv8n-based detection model, is proposed to evaluate the maturity stages of apple flowers. First, the adaptive downsampling network module replaces the conventional downsampling convolution, which reduces the size of the convolutional kernels and groups input feature mean average precision (maps). This modification helps reduce the model’s parameter count and computational complexity, while simultaneously improving detection of small targets. In addition, inspired by the task alignment technique of the task-aligned one-stage object detection (TOOD) model, a DAD Head is employed to separate the classification from localization tasks, thus minimizing task interference and improving overall accuracy. A custom apple flower dataset is used to test the model, and the results show detection accuracies of 80.7% for mature flowers and 82.4% for immature flowers, with a total model parameter count of just 1.8 million. These results offer important insights for advancing the development of automated pollination systems in orchards.

Why it matches plant phenotyping methodsリンゴ花の成熟段階という植物状態を画像から推定する軽量検出モデルを開発し、専用データセットで精度検証しているため、フェノタイピング手法が中心である。

abstractADA-Net, an efficient YOLOv8n-based detection model, is proposed to evaluate the maturity stages of apple flowers.

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

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

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

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

BloomNet: Exploring Single vs. Multiple Object Annotation for Flower Recognition Using YOLO Variants →

Precise localization and recognition of flowers are crucial for advancing automated agriculture, particularly in plant phenotyping, crop estimation, and yield monitoring. This paper benchmarks several YOLO architectures such as YOLOv5s, YOLOv8n/s/m, and YOLOv12n for flower object detection under two annotation regimes: single-image single-bounding box (SISBB) and single-image multiple-bounding box (SIMBB). The FloralSix dataset, comprising 2,816 high-resolution photos of six different flower species, is also introduced. It is annotated for both dense (clustered) and sparse (isolated) scenarios. The models were evaluated using Precision, Recall, and Mean Average Precision (mAP) at IoU thresholds of 0.5 (mAP@0.5) and 0.5-0.95 (mAP@0.5:0.95). In SISBB, YOLOv8m (SGD) achieved the best results with Precision 0.956, Recall 0.951, mAP@0.5 0.978, and mAP@0.5:0.95 0.865, illustrating strong accuracy in detecting isolated flowers. With mAP@0.5 0.934 and mAP@0.5:0.95 0.752, YOLOv12n (SGD) outperformed the more complicated SIMBB scenario, proving robustness in dense, multi-object detection. Results show how annotation density, IoU thresholds, and model size interact: recall-optimized models perform better in crowded environments, whereas precision-oriented models perform best in sparse scenarios. In both cases, the Stochastic Gradient Descent (SGD) optimizer consistently performed better than alternatives. These density-sensitive sensors are helpful for non-destructive crop analysis, growth tracking, robotic pollination, and stress evaluation.

Why it matches plant phenotyping methods花の物体検出モデルを比較評価し、注釈付きFloralSixデータセットを導入することが中心で、花の認識・局在化を植物フェノタイピングへ応用する技術研究である。

abstractThis paper benchmarks several YOLO architectures such as YOLOv5s, YOLOv8n/s/m, and YOLOv12n for flower object detection under two annotation regimes: single-image single-bounding box (SISBB) and single-image multiple-bounding box (SIMBB).

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

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

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

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

Hyperspectral imaging and metabolomics reveal color classification and anthocyanin profiles in Hydrangea macrophylla cultivars →

Flower color is a key criterion for evaluating Hydrangea macrophylla germplasm and breeding programs. In this study, 95 accessions were classified into six color groups (white, yellow, pink, red, purple, and blue) using the CIELAB and Munsell color systems. Partial least squares discriminant analysis (PLS-DA) of color space values (L*, a*, b*, C, and h) and pigment contents (anthocyanins, carotenoids, flavonoids, phenols) showed that the C value was crucial for the red group, while the L* value was important for the white group. A total of 83 anthocyanin derivatives were identified, with cyanidins and delphinidins being the most abundant. The proportion of delphinidin-3-O-glucoside (Dp3g) was a key factor in sepal color diversity, accounting for less than 11 % of the variation in the white and yellow groups and more than 83 % in the other groups. Dp3g was upregulated in the red, pink, purple, and blue groups compared to the yellow group, whereas malvidin-3-O-arabinoside was upregulated in the red, pink, and blue groups relative to the purple group. Hyperspectral imaging combined with partial least squares regression (PLSR) accurately predicted pigment contents (R² = 0.767–0.939, RPD = 1.946–2.636), with the best performance for anthocyanins. The spectral models for delphinidin-3,5-O-diglucoside (D3g5g) and Dp3g presented the highest correlations among differentially accumulated metabolites (|r| > 0.7), with the D3g5g model achieving the best performance (R² = 0.944, RMSE = 0.101 μg·g⁻¹ FW, RPD = 3.697). This research provides a comprehensive classification of colors and anthocyanin profiles in H. macrophylla sepals and highlights the potential of hyperspectral imaging in breeding practices.

Why it matches plant phenotyping methodsアジサイ萼片の色および色素含量をハイパースペクトル画像から推定し、PLSRで性能評価しており、植物表現型の取得・推定手法が中心である。

abstractHyperspectral imaging combined with partial least squares regression (PLSR) accurately predicted pigment contents (R² = 0.767–0.939, RPD = 1.946–2.636), with the best performance for anthocyanins.

Anther size quantification in wheat using deep learning under normal and heat stress conditions →

Key message We present an imaging-based deep learning phenotyping pipeline that classifies heat-stressed wheat anthers and quantifies size traits using YOLO, enabling fast, precise, scalable measurements to support breeding heat-resilient wheat varieties. Abstract Terminal heat stress is a major abiotic stress causing significant yield loss in wheat. Anther size, a key trait of terminal heat stress tolerance, is least studied in wheat due to complex and tedious scaling trait, and short live span. To provide user friendly approach to plant breeders, integration of the modern digital imaging and deep learning techniques together is the current need of high-throughput phenomic era. In this study, we introduced a hybrid approach that amalgamates the strengths of deep learning models for both binary classification and precise morphological analysis of anther images of 177 wheat accessions under normal and heat stress environments. ResNet18 with 94% accuracy, outperformed the traditional models like CNN and MobileNetV2, achieving high classification performance. For morphological trait extraction, we employed YOLOv8, a cutting-edge object detection model known for its high speed, accuracy, and computational efficiency. YOLOv8 successfully localized anthers and measured width and length with strong agreement to experimental measurements, as validated by Bland–Altman analysis. Its precise detection capability and lightweight architecture makes it ideal for high-throughput phenotyping using digital imaging approach. To further boost the interpretability of our deep learning models, we utilized Grad-CAM, a powerful technique for visualizing class-specific features in the network’s decision-making process. This facilitated in categorizing the key visual features within the anther images that had the greatest influence on the model’s decision-making process. This cohesive workflow not only sets a new benchmark in image-based classification and morphological measurement but also proposes an accessible tool for rapid, real-time phenotyping, supporting data-driven breeding strategies aimed at improving wheat resilience under terminal heat stress.

Why it matches plant phenotyping methodsコムギ葯の画像取得、深層学習による分類・形態形質抽出、実測値との技術検証を中心とする明確な植物フェノタイピング手法研究。

abstractWe present an imaging-based deep learning phenotyping pipeline that classifies heat-stressed wheat anthers and quantifies size traits using YOLO

Inspecting the differences in mechanical resistance between flowers and leaves by multiple mechanical testing and calibration methods. →

Background and aims Flower petal integrity affects the success of plant reproduction and ecological adaptability. The mechanical resistance of plant organs indicates their capacity to withstand physical damage and preserve structural integrity. However, little is known about the mechanical resistance of flowers and their differences from leaves. Methods To address the aforementioned research gaps, we quantified flower petals from 43 species and leaves from 86 species, employing two forces that characterize mechanical resistance: force to punch and force to tear. For force to punch, three different diameter punch needles were used to measure and three methods were employed for calibration. Additionally, we measured functional traits of petals and leaves. Key results We found that petals have significantly lower mechanical strength than leaves in both punch and tear forces. The force to punch and force to tear of petals and leaves were positively correlated with tissue thickness, cuticle thickness and dry mass per unit area. The vein density of petals was positively correlated with force to punch and force to tear, while force to tear was negatively correlated with floral tissue density after phylogenetic independent contrast correlation analysis. For reticular venation leaf, the vein density had no significant relationship with force to tear, but was positively correlated with tissue density. Conclusions Our results indicated that there were differences in the structural basis of mechanical resistance between flowers and leaves. Regarding the most classical mechanical testing method, force to punch, different needle diameters and calibration methods can affect the results for both the petal and leaf. Our research results provide an important reference for better understanding the ecological adaptability of flowers.

Why it matches plant phenotyping methods花弁・葉の機械的抵抗という植物器官形質を測定し、パンチ試験の針径と校正法が結果に与える影響を比較・評価しており、測定法の検証が中心です。

abstractFor force to punch, three different diameter punch needles were used to measure and three methods were employed for calibration.

Quantification of plant trait data from herbarium scans in the DiSSCo Research Infrastructure →

The Distributed System for Scientific Collections (DiSSCo) is a research infrastructure to integrate European natural science collections (NSCs) digitally. The aim is to facilitate and enhance the access, management and analysis of collection assets in one unified digital collection. The Machine Annotation Services (MAS) are essential components of DiSSCo’s Digital Specimen Architecture (DSArch). These services automate the annotation of digital objects to enable labelling and categorisation of NSC's digital assets. To further advance this, a Machine Learning as a Service (MLaaS) approach was developed which provides researchers with the access to pre-trained machine-learning models for complex tasks, such as instance segmentation and morphological analysis of datasets. MLaaS enhances the DiSSCo’s scalability and flexibility and allows the integration of machine-learning tools in close alignment with the FAIR (Findable, Accessible, Interoperable, Reusable) principles. This study employs DiSSCO's MLaaS framework for the quantitative analysis of herbarium specimens. Machine-learning models, such as Mask R-CNN and YOLO11, are comparatively applied to detect and generate the pixel-level masks of plant organs in herbarium sheets. Subsequently, these models are used to reconstruct the scale in the herbarium sheet and to calculate the surface area of identified plant organs. The determination of quantitative characteristics of plant specimens, such as measuring leaf area or the timestamp of the floral transition, opens up herbarium data for reuse in the large prognosis platforms currently developed in the framework of the Common European Data Spaces. In this way, plant trait data mobilised from natural science collections can improve the predictive capability of the vegetation model components of climate-related data spaces.

Why it matches plant phenotyping methodsハーバリウム画像から植物器官を検出・セグメンテーションし、葉面積などの形質を定量化する機械学習手法と基盤の応用が研究の中心である。

abstractThis study employs DiSSCO's MLaaS framework for the quantitative analysis of herbarium specimens.

Polli-markers: spectral and chemical biomarkers for detecting cryptic early plant pollination responses →

Summary Pollination is essential for plant reproduction, ecosystem resilience and human health. Yet, our capability to map pollination service delivery in real-time across large areas remains poor. Determining where and when flowers are pollinated is vital to mitigate widespread pollination deficits, increase plant health and yield, and support pollinator management. Hence, innovative approaches are urgently needed for establishing scalable predictive bioindicators of plant pollination status with the goal of achieving real-time landscape-scale monitoring. Here we present two parallel controlled pollination assays in which we characterise the post-pollination petal physiology of a world leading flowering crop, Brassica napus , using in-situ close-range hyperspectral reflectance and semi-untargeted metabolomics. This multiomics approach coupled with supervised machine learning and biomarker detection reveals cryptic changes in the UV petal reflectance spectrum which are predictive of pollination status, representing a novel set of candidate pollination bioindicators (‘ polli-markers’ ), and our high-resolution time series enables prediction of when this pollination event occurred. It also reveals an associated set of candidate metabolites, including flavonoids and senescence markers, shedding light on the functional pathways related to our polli-markers. This study provides key insights into floral development, enabling a transformative step towards predicting, mapping and quantifying pollination service delivery at the landscape scale.

Why it matches plant phenotyping methods近接ハイパースペクトル計測と機械学習により、植物花弁の受粉状態および受粉時点を推定する方法を開発しており、表現型取得・推定が研究の中心である。

abstractusing in-situ close-range hyperspectral reflectance and semi-untargeted metabolomics

Enhanced Image Annotation in Wild Blueberry ( Vaccinium angustifolium Ait.) Fields Using Sequential Zero-Shot Detection and Segmentation Models. →

This research addresses the critical need for efficient image annotation in precision agriculture, using the wild blueberry ( Vaccinium angustifolium Ait.) cropping system as a representative application to enable data-driven crop management. Tasks such as automated berry ripeness detection, plant disease identification, plant growth stage monitoring, and weed detection rely on extensive annotated datasets. However, manual annotation is labor-intensive, time-consuming, and impractical for large-scale agricultural systems. To address this challenge, this study evaluates an automated annotation pipeline that integrates zero-shot detection models from two frameworks (Grounding DINO and YOLO-World) with the Segment Anything Model version 2 (SAM2). The models were tested on detecting and segmenting ripe wild blueberries, developmental wild blueberry buds, hair fescue ( Festuca filiformis Pourr.), and red leaf disease ( Exobasidium vaccinii ). Grounding DINO consistently outperformed YOLO-World, with its Swin-T achieving mean Intersection over Union (mIoU) scores of 0.694 ± 0.175 for fescue grass and 0.905 ± 0.114 for red leaf disease when paired with SAM2-Large. For ripe wild blueberry detection, Swin-B with SAM2-Small achieved the highest performance (mIoU of 0.738 ± 0.189). Whereas for wild blueberry buds, Swin-B with SAM2-Large yielded the highest performance (0.751 ± 0.154). Processing times were also evaluated, with SAM2-Tiny, Small, and Base demonstrating the shortest durations when paired with Swin-T (0.30-0.33 s) and Swin-B (0.35-0.38 s). SAM2-Large, despite higher segmentation accuracy, had significantly longer processing times (significance level α = 0.05), making it less practical for real-time applications. This research offers a scalable solution for rapid, accurate annotation of agricultural images, improving targeted crop management. Future research should optimize these models for different cropping systems, such as orchard-based agriculture, row crops, and greenhouse farming, and expand their application to diverse crops to validate their generalizability.

Why it matches plant phenotyping methods植物の果実・芽・病徴を対象に、ゼロショット検出とSAM2による検出・セグメンテーション注釈パイプラインを開発・評価しており、植物表現型の画像取得・抽出手法が研究の中心である。

abstractThe models were tested on detecting and segmenting ripe wild blueberries, developmental wild blueberry buds, hair fescue ( Festuca filiformis Pourr.), and red leaf disease ( Exobasidium vaccinii ).

High-Throughput iNaturalist Image Analysis Reveals Flower Color Divergence in Monarda fistulosa . →

AbstractCharacterizing patterns of trait variation across widespread species is a fundamental goal of natural history. Here we create a pipeline to analyze a large community science dataset and test hypothesized flower color divergence across the range of an abundant wildflower. Monarda fistulosa is a North American perennial that produces showy lavender inflorescences. Although previous literature suggests that the flowers of western M. fistulosa might display a deeper purple color than the eastern varieties, this divergence has not been assessed at scale. We process more than 40,000 community science photographs of M. fistulosa to identify flowers and extract color. We demonstrate that the flowers of the montane western variety have lower lightness and higher chroma, corresponding to a deeper violet color, than those of eastern M. fistulosa . Our approach and validation provides a scalable framework for phenotyping community science images and enables analysis of geographic color variation in other widespread species.

Why it matches plant phenotyping methods市民科学画像から花を識別し、色形質を抽出するスケーラブルな画像解析パイプラインを開発・検証しており、植物表現型の取得方法が研究の中心です。

abstractWe process more than 40,000 community science photographs of M. fistulosa to identify flowers and extract color.

Development and application of two-photon fluorescent probe for visual monitoring of isoprene in plants. →

As the main volatile organic compounds (VOCs), isoprene plays a dual role in plant stress protection and air pollution. However, its spatiotemporal dynamic monitoring in plants is insufficient, which limits environmental risk assessment. In this study, by systematically investigating the effects of the introduction of alkyne groups, maleimide groups and conjugated structures on the performance of probes, a probe (TPCM-π-M), with excellent two-photon properties was prepared. It showed good linear response in 1-240 ppm range with a detection limit of 0.2 ppm, enabling accurate detection of isoprene in various plant samples. In addition, the spatial distribution of endogenous isoprene in deep plant tissues and dynamic visual monitoring of isoprene under abiotic stress were achieved through two-photon imaging, overcoming the shortcomings of traditional single-photon imaging such as insufficient penetration depth. In particular, the dynamic regulation mechanism of plant isoprene metabolism under abiotic stress was revealed through the carotenoid/photorespiration inhibition model, and the correlation between the isoprene content in different flowers and their stress response ability was confirmed. This study provides technical support for analyzing the role of isoprene in plant metabolism and environmental adaptation, and has theoretical and applied value in plant physiology, pollution monitoring and biomedical imaging.

Why it matches plant phenotyping methods植物内イソプレンの定量・空間分布・ストレス応答を可視化する二光子蛍光プローブとイメージング法を開発し、植物試料で検証・応用しているため、表現型取得法が中心である。

abstracta probe (TPCM-π-M), with excellent two-photon properties was prepared

A real-time visualized TRSV-based gene silencing method using trichome as a selected marker in cucumber →

Cucumber (Cucumis sativus. L) is economically valuable vegetable crop worldwide. Although cucumber genomic sequence has been completed, the functions of most genes have not yet been characterized. Virus-induced gene silencing (VIGS) is an efficient system for investigating gene function in plants, however, detection of VIGS efficiency by PCR is a time-consuming method. In this study, a vacuum-agroinfiltrated Tobacco ringspot virus (TRSV)-based gene silencing method was developed in cucumber, and CsGLABROUS3 (CsGL3), which functions in initiation of trichome, was cloned into pTRSV2 vector to develop a TRSV-CsGL3 system. Gene silenced cucumbers were visible using trichome as a selected marker, and their glabrous phenotype exhibited throughout the life cycle in TRSV-CsGL3 system. Thereafter, a flower morphogenesis gene (UNUSUAL FLORAL ORGANS, CsUFO) was selected to silence by the TRSV-CsGL3 system, and CsUFO silenced cucumbers produced the flower defect phenotype as expected. In summary, TRSV-CsGL3 is a real-time visualized VIGS system using trichome as a selected marker, which simplify the VIGS identification procedure, and it can be used to investigate gene function throughout the life cycle in cucumber.

Why it matches plant phenotyping methodsキュウリのVIGS効率をトライコーム形態でリアルタイムに可視化・判定する手法の開発が中心であり、植物表現型の取得方法として適格です。

abstracta vacuum-agroinfiltrated Tobacco ringspot virus (TRSV)-based gene silencing method was developed in cucumber

Identification of morphological and phenological traits for the characterization of cultivated Lycium barbarum L. plants →

The genus Lycium L. (Solanaceae) includes economically important species such as Lycium barbarum, L. chinense, and L. ruthenicum (goji). This study focuses on the morphological characterization of L. barbarum, a recently domesticated species lacking standardized descriptors. We evaluated traits including plant habit, vigor, leaf morphology, floral structure, fruit shape, and ripening stages using both qualitative and quantitative analyses. Growth habits were evenly distributed: 33.3 % were erect, 39.3 % were expanded, and 27.4 % were pendulous. The average leaf area was 166.22 ± 79.66 mm², and discriminant analysis of leaf shape achieved 83 % classification accuracy. Floral traits were consistent, with 94.3 % of plants having five petals and 5.7 % having six petals. Fruit ripened rapidly, completing four stages in ∼11.5 days. These findings highlight key diagnostic traits for developing harmonized descriptors. These traits will support future distinctness, uniformity, and stability (DUS) testing, which is essential for cultivar protection, genebank documentation, and product traceability in the growing global market for functional foods and nutraceuticals.

Why it matches plant phenotyping methodsゴジベリーの形態・生育段階を標準化された記述子として整理し、葉形分類やDUS試験に向けた診断形質を開発することが中心であり、単なる生物学的結果測定ではない。

abstractThis study focuses on the morphological characterization of L. barbarum, a recently domesticated species lacking standardized descriptors.

PlantVillage and PlantDoc dataset mediated plant disease predictions: A perspectives review →

Plant disease analysis is crucial for the better yield of the crops, and correct detection of particular infection on the plant parts provide the basis of better control of the plant disease. The prediction and control of disease in crop plants is essential for the food security. The technological advancements, particularly, in the field of the artificial intelligence and machine learning have provided impetus for newer dimensions of application of technology in different fields including the plant crop disease. The fundamental database of different infections in different crop plants forms the basis of the standard training of the machine learning algorithms which further predicts the disease on the test samples. The more detailed dataset of plant diseases with corresponding large number of sample examples helps in better training of the machine learning (ML) modules. The collections of disease dataset by the PlantVillage and evaluated PlantDoc dataset are being extensively used for the ML training and prediction of disease. This perspective discussion delves in the fundamental different types of plant diseases of the different parts of plant (leaf, fruits, flowers, stem), particularly of the crop plants, with emphasis on PlantVillage and PlantDoc datasets. The evaluation of ML techniques for conclusive detection of the disease possibilities has further been included in the discussion.

Why it matches plant phenotyping methods植物病害の画像データセットと機械学習による植物病害検出を中心に扱うレビューであり、植物の病害状態を観測・推定するフェノタイピング手法に該当する。

abstractThe collections of disease dataset by the PlantVillage and evaluated PlantDoc dataset are being extensively used for the ML training and prediction of disease.

Development of an Integrated System for Forecasting Fruit Crop Yields Based on Multimodal Data and an Ensemble of Machine Learning Models →

The article presents a comprehensive system for forecasting orchard yields based on multimodal remote monitoring data. It combines convolutional neural networks for detecting flowers, ovaries, and fruits with an ensemble of linear and nonlinear models (multivariate regression, MLP, LSTM) for yield estimation. LASSO regression and SHAP analysis are used to interpret the results. The developed Python software enables full data processing, visualization, and saving of forecasts. The model achieves a determination coefficient of R2>0.85 and RMSE

Why it matches plant phenotyping methods果実園の収量予測を目的とするが、花・子房・果実をCNNで検出し、マルチモーダルデータを統合して収量を推定する取得・解析システムとPythonソフトウェアが中心であり、植物器官および収量形質の計測ワークフローに該当する。

abstractIt combines convolutional neural networks for detecting flowers, ovaries, and fruits with an ensemble of linear and nonlinear models (multivariate regression, MLP, LSTM) for yield estimation.

Non-Contact Measurement of Sunflower Flowerhead Morphology Using Mobile-Boosted Lightweight Asymmetric (MBLA)-YOLO and Point Cloud Technology →

The diameter of the sunflower flower head and the thickness of its margins are important crop phenotypic parameters. Traditional, single-dimensional two-dimensional imaging methods often struggle to balance precision with computational efficiency. This paper addresses the limitations of the YOLOv11n-seg model in the instance segmentation of floral disk fine structures by proposing the MBLA-YOLO instance segmentation model, achieving both lightweight efficiency and high accuracy. Building upon this foundation, a non-contact measurement method is proposed that combines an improved model with three-dimensional point cloud analysis to precisely extract key structural parameters of the flower head. First, image annotation is employed to eliminate interference from petals and sepals, whilst instance segmentation models are used to delineate the target region; The segmentation results for the disc surface (front) and edges (sides) are then mapped onto the three-dimensional point cloud space. Target regions are extracted, and following processing, separate models are constructed for the disc surface and edges. Finally, with regard to the differences between the surface and edge structures, targeted methods are employed for their respective calculations. Whilst maintaining lightweight characteristics, the proposed MBLA-YOLO model achieves simultaneous improvements in accuracy and efficiency compared to the baseline YOLOv11n-seg. The introduced CKMB backbone module enhances feature modelling capabilities for complex structural details, whilst the LADH detection head improves small object recognition and boundary segmentation accuracy. Specifically, the CKMB module integrates MBConv and channel attention to strengthen multi-scale feature extraction and representation, while the LADH module adopts a tri-branch design for classification, regression, and IoU prediction, structurally improving detection precision and boundary recognition. This research not only demonstrates superior accuracy and robustness but also significantly reduces computational overhead, thereby achieving an excellent balance between model efficiency and measurement precision. This method avoids the need for three-dimensional reconstruction of the entire plant and multi-view point cloud registration, thereby reducing data redundancy and computational resource expenditure.

Why it matches plant phenotyping methodsヒマワリ花頭の形態形質を、画像セグメンテーションと3D点群で非接触抽出する手法を開発・評価しており、フェノタイピング手法が研究の中心である。

abstractThe diameter of the sunflower flower head and the thickness of its margins are important crop phenotypic parameters.

Implementation of EfficientNet-B0 CNN Model for Web-Based Strawberry Plant Disease Detection →

Strawberry production in Indonesia has high economic value but is often hindered by plant diseases that reduce yield quality and quantity. Manual disease identification requires time, cost, and expertise, making it inefficient for farmers. This study proposes a web-based strawberry disease detection system by applying a Convolutional Neural Network (CNN) model using the EfficientNet-B0 architecture. The dataset consists of leaf, fruit, and flower images of strawberries in both healthy and infected conditions. The research followed the CRISP-DM framework, including business understanding, data preparation, modeling, evaluation, and deployment. The model was trained using transfer learning and fine-tuning techniques, with evaluation conducted through a confusion matrix and K-Fold Cross Validation. Experimental results indicate that the EfficientNet-B0 model achieved an overall accuracy of approximately 95.2% and demonstrated stable performance in classifying various strawberry plant diseases. The model achieved perfect accuracy (100%) in several classes such as Healthy Leaf, Leaf Spot, and Healthy Flower, while maintaining high accuracy in other classes like Fruit (95.2%) and Anthracnose Fruit Rot (94.7%), confirming its effectiveness in capturing essential visual features for accurate disease classification. The deployment of the model into a website using the Streamlit framework enables users to upload strawberry images and obtain automatic, fast, and accurate disease detection results. This system is expected to provide a practical solution to help farmers improve productivity and minimize losses caused by plant diseases.

Why it matches plant phenotyping methodsイチゴの葉・果実・花の画像から健全／感染状態や病害を推定するCNN手法を開発・評価し、Webシステムとして実装しており、植物状態の画像ベース表現型推定が中心である。

abstractThis study proposes a web-based strawberry disease detection system by applying a Convolutional Neural Network (CNN) model using the EfficientNet-B0 architecture.

Three-dimensional characterization of hazelnut (Corylus avellana L.) fruit development based on X-ray micro-computed tomography. →

Hazelnut (Corylus avellana L.) is one of the most appreciated and cultivated nuts in temperate areas. Producers are now facing an increasing demand and industries need to select high-yielding and fine-quality cultivars. In this context, a challenge to take up is the development of a rapid, non-destructive and high-resolution method to study the growth and differentiation dynamics of floral reproductive organs, to limit yield losses especially in response to climate adaptation. In this study, we scanned mixed buds from the hazelnut cultivar Tonda di Giffoni from anthesis to fruit formation by micro-computed tomography (Micro-CT). We reconstructed in three dimensions (3D) the spatial arrangement of flowers within the glomerulus, characterized the position and configuration of ovules, ovaries and funiculus as well as observed the formation of the embryo during the early developmental stages. The proposed approach enables precise volume measurements of ovaries, ovules, and embryos. It helps identify abortive ovules early and track developmental stages, such as embryo formation. Unlike traditional 2D methods, this approach captures growth patterns more accurately, supporting research on fruit development, crop quality, and genetic studies. Overall, it provides a powerful tool for advancing reproductive biology research of hazelnuts and improving hazelnut cultivation.

Why it matches plant phenotyping methodsヘーゼルナッツの生殖器官をMicro-CTで非破壊・高解像度に3D再構成し、器官体積や発達段階を定量化する手法が研究の中心であるため。

abstractthe development of a rapid, non-destructive and high-resolution method to study the growth and differentiation dynamics of floral reproductive organs

Quantifying tree-level peach flowering dynamics using UAV imagery and an optimized instance segmentation model →

A timely and accurate assessment of flowering characteristics is vital for tracking floral phenology in agricultural management and peach breeding. In this study, an unmanned aerial vehicle (UAV) equipped with a high-resolution camera was integrated with deep learning techniques to monitor peach flowering across multiple varieties. An instance segmentation model, PeFloSEG, was proposed for the accurate detection of peach flowers and buds. Based on the YOLOv5-seg framework, PeFloSEG integrates an enhanced detection head for improved feature representation and a modified loss function—Focal Efficient Intersection over Union (Focal-EIoU)—to optimize bounding box regression. To boost model efficiency, a network slimming algorithm was applied, significantly reducing model size while maintaining high accuracy. PeFloSEG achieved strong results, with mean average precision (mAP@0.5) scores of 0.876 for detection and 0.825 for segmentation, outperforming state-of-the-art algorithms by 0.5 %–24.9 % in detection and 5.7 %–28.1 % in segmentation. Three flowering indices derived from PeFloSEG outputs—flowering intensity (FI) indices (FI1 and FI2) and single-tree flowering ratio (SFR)—were evaluated. Linear correlation analysis revealed strong relationships between these indices and ground truth values, with R² values of 0.964 (FI1), 0.961 (FI2), and 0.986 (SFR). These indices were further used to assess flowering dynamics over time and to distinguish phenological stages, achieving an overall classification accuracy of 91.7 %. They also enabled effective variety classification, facilitating the exploration of flowering characteristics across different peach varieties. Overall, the proposed approach offers a scalable and efficient solution for high-throughput phenotyping and provides valuable tools for peach breeding and germplasm resource evaluation.

Why it matches plant phenotyping methodsUAV画像とインスタンスセグメンテーションモデルを開発し、花数・開花強度・単木開花率などの植物表現型を定量化することが研究の中心であるため。

abstractAn instance segmentation model, PeFloSEG, was proposed for the accurate detection of peach flowers and buds.

Optical Coherence Imaging Hybridized Deep Learning Framework for Automated Plant Bud Classification in Emasculation Processes: A Pilot Study →

A vision-based autonomous system for emasculating okra enhances agriculture by enabling precise flower bud identification, overcoming the labor-intensive, error-prone challenges of traditional manual methods with improved accuracy and efficiency. This study presents a framework for an adaptive, automated bud identification method to assist the emasculation process, hybridized optical coherence tomography (OCT). Three YOLOv8 variants were evaluated for accuracy, detection speed, and frame rate to identify the most efficient model. To strengthen the findings, YOLO was hybridized with OCT, enabling non-invasive sub-surface verification and precise quantification of the emasculated depth of both sepal and petal layers of the flower bud. To establish a solid benchmark, gold standard color histograms and a digital imaging-based method under optimal lighting conditions with confidence scoring were also employed. The results demonstrated that the proposed method significantly outperformed these conventional frameworks, providing superior accuracy and layer differentiation during emasculation. Hence, the developed YOLOv8 hybridized OCT method for flower bud identification and emasculation offers a powerful tool to significantly improve both the precision and efficiency of crop breeding practices. This framework sets the stage for implementing scalable, artificial intelligence (AI)-driven strategies that can modernize and optimize traditional crop breeding workflows.

Why it matches plant phenotyping methodsOCTと深層学習を組み合わせ、花蕾の識別に加えて萼片・花弁層の深さを定量化し、複数手法を精度・速度面で比較検証しているため、植物器官の表現型取得法が中心です。

abstractThis study presents a framework for an adaptive, automated bud identification method to assist the emasculation process, hybridized optical coherence tomography (OCT).

Quantifying high-temperature-induced reproductive growth imbalance in citrus at anthesis: Insights from the CF-ASPM model →

Global climate change-induced environmental stress poses critical challenges to the stable development of economic crops such as citrus. High temperatures (HTs) at anthesis may cause poor pollination and excessive flower/fruit drop, seriously affecting fruit yield and quality. To comprehensively analyze the developmental dynamics and morphological responses of citrus to HT stress at anthesis, methods for precise whole-flower phenotypic extraction and stamen state classification were developed. A citrus flower automatic segmentation and phenotypic quantitative model (CF-ASPM) that combines the pre-trained Segment Anything Model (SAM) with a lightweight classification module was constructed to accurately identify and quantify key citrus flower structures. Phenotypic parameter extraction correlation coefficients were 0.90–0.98. A few-shot stamen classification method was also designed using a pre-segmentation strategy and differential features, and its classification accuracy was 96.39%. Experiments with Ehime mandarin were conducted to analyze dynamic citrus floral organ changes at different temperatures and the underlying physiological mechanisms. The results showed that citrus exhibits a distinct reproductive priority strategy under HTs. Floral organ growth is inhibited, blooming is accelerated, and an asynchronous compensation mechanism occurs between male and female organs. HTs accelerated flower aging and caused developmental imbalances in the ovary and nectar disc. This may lead to increased flower and fruit drop and altered fruit shape. This study revealed the reproductive priority strategy and growth imbalance of citrus floral organs under HTs using the CF-ASPM model. It provides important data for further exploring the molecular mechanisms and management strategies of HT stress.

Why it matches plant phenotyping methods柑橘花器官の自動セグメンテーション、形質抽出、雄蕊状態分類法を開発し、精度検証したことが研究の中心であるため。

abstractmethods for precise whole-flower phenotypic extraction and stamen state classification were developed.

Comparing hormone dynamics in cereal crops via transient expression of hormone sensors. →

Although hormone biology is critical for plant breeding, complex phenotypic outputs make it difficult to compare across species. We used transient expression of hormone biosensors and transcriptomics to simplify this output and quantify gibberellic acid (GA) and auxin responses across multiple cereal crop genotypes and tissues. We show the GPS2 biosensor detects exogenous GA in maize, barley, sorghum, and wheat. Measuring across GA dosages, we detect tissue- and genotype-specific differences in GA sensor response with an unexpected drop in GPS2 output in the maize d1 GA biosynthesis mutant after GA treatment, likely reflecting differences in GA response across samples. We used RNA sequencing followed by ortholog prediction and Gene Ontology-term enrichment analysis to measure GA responses in leaves and floral tissues from maize wildtype, d1, and barley Golden Promise. We determine that cross-tissue, cross-genotype, and cross-species GA responses include downregulation of GA-INSENSITIVE DWARF1 and upregulation of α-Expansin1, independent of GA biosynthesis. We identify F-Box proteins, hexokinase, and AMPK/SNF1 protein kinase orthologs as unexpected cross-species GA-responsive genes. We then compared transient expression of DR5, DR5v2, and DII-mDII auxin reporters in barley and maize and find DR5v2 and DII-mDII are functional auxin reporters in both species.

Why it matches plant phenotyping methods植物ホルモン応答を定量するバイオセンサーの種・組織・遺伝子型間での機能検証と比較適用が中心であり、植物の生理状態を取得するフェノタイピング手法に該当する。

abstractWe used transient expression of hormone biosensors and transcriptomics to simplify this output and quantify gibberellic acid (GA) and auxin responses across multiple cereal crop genotypes and tissues.

Partial retention of ancient function increases genetic pleiotropy in grass evolution →

Abstract Changes in form are driven by the differential, context-dependent regulation of pleiotropic genes. How genetic pleiotropy itself emerges, however, remains unclear. The maize genes GRASSY TILLERS1 ( GT1 ) and RAMOSA3 ( RA3 ) are required for axillary meristem suppression, a deeply conserved trait across angiosperms, and for floral organ suppression, a trait which evolved within the grass family. To determine how these pleiotropic functions are regulated, we first established a high-throughput method for quantitative phenotyping of grass flowers. Using this method, we show that distinct environmental mechanisms regulate axillary meristem versus floral organ suppression. In line with these differences, we find upstream regulation of GT1 and RA3 has diverged, consistent with their redeployment in flowers. Our results show that, rather than wholesale adoption of genetic networks, developmental genes can retain ancient functions and be recruited into other programs in the evolution of form, thereby increasing genetic pleiotropy.

Why it matches plant phenotyping methodsイネ科の花を定量的に表現型解析する高スループット手法を新規に確立し、遺伝子機能の解析に中心的に適用しているため、方法論文として収録する。

abstractwe first established a high-throughput method for quantitative phenotyping of grass flowers.

Three-dimensional trajectory extraction and flower structure coupling method for bee-flower interactions →

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

Why it matches plant phenotyping methods花の構造を抽出・連結する手法の開発が題名の中心であり、植物器官の形態特性を取得する方法として該当する。

titleThree-dimensional trajectory extraction and flower structure coupling method for bee-flower interactions

A study on the non-contact measurement of sunflower disk inclination and its application to accurate phenotypic analysis. →

The tilt angle of sunflower flower heads is an important phenotypic characteristic that influences their growth and development, as well as the efficiency of mechanised harvesting in precision agriculture. Addressing the issues of low accuracy, high cost, and the risk of plant damage associated with traditional manual measurement methods, this study proposes a non-contact measurement method combining deep learning and geometric analysis to achieve precise measurement of sunflower flower head tilt angles. The specific method involves optimising the lightweight YOLO11-seg model to enhance instance segmentation performance for sunflower flower heads and stems (compared to the initial YOLO11 model, recall rate improved by 3.7%, mAP50 improved by 1.8%, a reduction of 0.29M parameters, and a decrease in computational load of 0.5 GFLOPs), and extracting the surface contour of the flower head and the centreline contour of the stem based on the mask map output by the model. After achieving precise region segmentation through image processing, the geometric analysis module performs elliptical fitting on the flower head contour to obtain the main axis direction, performs curve fitting on the stem contour, and selects the tangent direction at the intersection point of the flower head. The angle between the two is calculated as the tilt angle of the flower head. In the measurement experiment, 220 images were used for testing, with manual protractor measurement results as the reference. The algorithm achieved a measurement accuracy of RMSE = 2.93°, MAE = 2.43°, and R 2 = 0.94. The results indicate that this method significantly improves measurement efficiency and operational convenience while maintaining accuracy. The system does not require contact with the plant, demonstrating good accuracy, adaptability, and practicality. The tilt angle information obtained is of great significance for path planning of harvesting robots, adjustment of gripping postures, and positioning control of end-effectors, and can serve as a key perception module in the automation process of sunflower flower head placement and drying operations in precision agriculture.

Why it matches plant phenotyping methodsヒマワリ花盤の傾斜角という植物形質を、画像セグメンテーションと幾何解析で非接触測定する手法を開発し、手動測定を基準に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 non-contact measurement method combining deep learning and geometric analysis to achieve precise measurement of sunflower flower head tilt angles.

Deep learning-based approach for extracting inflorescence morphology features in cut chrysanthemum →

Accurate identification of floral morphological traits, such as flower type and the diameters of ligulate and bisexual flowers, is essential for the quality evaluation and varietal improvement of cut chrysanthemums ( Chrysanthemum morifolium Ramat.). Traditional manual or rule-based image processing methods are inefficient and struggle with complex floral structures. To address these limitations, we developed a lightweight deep learning and machine learning pipeline for automated trait extraction in over 30 chrysanthemum cultivars. A ShuffleNet V2 model achieved 95.24% accuracy in flower type classification, with lightweight characteristics (1.26M parameters, 0.15 GFLOPs), fast inference time (14.78 ms per image), and 67.65 FPS. Ligulate and bisexual flowers were segmented using an optimized U-Net achieving a reduction of over 95% in parameters, achieving an average Dice similarity coefficient (DSC) of 0.934. For diameter estimation, mean squared errors (MSE) of 6.605 mm (ligulate) and 2.034 mm (bisexual) were obtained, with coefficients of determination (R2) approaching 0.98. Fine-grained classifications—Single-petals vs. Repeating-petals and Incurve vs. Honeycomb—were achieved using geometric and texture features with F1-scores above 0.87. These results demonstrate a scalable and efficient solution for floral trait analysis, supporting high-throughput phenotyping in ornamental horticulture.

Why it matches plant phenotyping methodsキクの花器官形態を画像から自動抽出・推定する深層学習パイプラインを開発しており、植物表現型取得が研究の中心である。

abstractwe developed a lightweight deep learning and machine learning pipeline for automated trait extraction in over 30 chrysanthemum cultivars.

Investigating pea (Pisum sativum L.) flowering with high throughput field phenotyping and object detection →

Flowering is one of the most important and sensitive processes throughout a plant's life and marks the start of the reproductive phase. Flowering traits largely define yield potential and are therefore crucial for crop breeding. To observe flowering dynamics under field conditions, visual ratings have been a standard method for decades. Today, high-throughput field phenotyping (HTFP) methods provide opportunities for objective and efficient data collection. We developed an object detection approach (based on YOLOv8) that allows to collect detailed data about flower and pod density. RGB-images from 12 pea breeding lines were automatically acquired by the field phenotyping platform (FIP) of ETH Zurich in two years. The trained model reached high accuracy for open flower detection, which allowed to monitor flowering dynamics and flower density over time. Maximal flower density (Max.Fl.Dens) was highly correlated (R 2 = 0.967) to ground truth data taken in the field. Clear differences in timing of flowering and flower density were detected between breeding lines and years. Furthermore, a high correlation was observed between the maximal flower density and yield components. This automated, data-driven method of flower and pod detection proved itself as a reliable tool. Therefore, the results are promising for the use of RGB imaging methods to objectively assess not only flowering dynamics but also flower density and fruiting efficiency. Maximal flower density allows to predict seed amount and therefore has potential as selection trait in breeding programs. Fruiting efficiency could be used to identify stress-tolerant breeding lines.

Why it matches plant phenotyping methods花と莢の密度をRGB画像から自動推定する物体検出法を開発し、精度を地上真値と比較検証しており、植物表現型取得が研究の中心です。

abstractWe developed an object detection approach (based on YOLOv8) that allows to collect detailed data about flower and pod density.

Deriving Early Citrus Fruit Yield Estimation by Combining Multiple Growing Period Data and Improved YOLOv8 Modeling. →

Early crop yield prediction is a major challenge in precision agriculture, and efficient and rapid yield prediction is highly important for sustainable fruit production. The accurate detection of major fruit characteristics, including flowering, green fruiting, and ripening stages, is crucial for early yield estimation. Currently, most crop yield estimation studies based on the YOLO model are only conducted during a single stage of maturity. Combining multi-growth period data for crop analysis is of great significance for crop growth detection and early yield estimation. In this study, a new network model, YOLOv8-RL, was proposed using citrus multigrowth period characteristics as a data source. A citrus yield estimation model was constructed and validated by combining network identification counts with manual field counts. Compared with YOLOv8, the number of parameters of the improved network is reduced by 50.7%, the number of floating-point operations is decreased by 49.4%, and the size of the model is only 3.2 MB. In the test set, the average recognition rate of citrus flowers, green fruits, and orange fruits was 95.6%, the mAP@.5 was 94.6%, the FPS value was 123.1, and the inference time was only 2.3 milliseconds. This provides a reference for the design of lightweight networks and offers the possibility of deployment on embedded devices with limited computational resources. The two estimation models constructed on the basis of the new network had coefficients of determination R 2 values of 0.91992 and 0.95639, respectively, with a prediction error rate of 6.96% for citrus green fruits and an average error rate of 3.71% for orange fruits. Compared with network counting, the yield estimation model had a low error rate and high accuracy, which provided a theoretical basis and technical support for the early prediction of fruit yield in complex environments.

Why it matches plant phenotyping methods柑橘の花・果実を画像認識して収量を推定するYOLOv8改良モデルとワークフローを開発・検証しており、植物形質取得法が中心的です。

abstractIn this study, a new network model, YOLOv8-RL, was proposed using citrus multigrowth period characteristics as a data source.

OrchardQuant ‐ 3D : combining drone and LiDAR to perform scalable 3D phenotyping for characterising key canopy and floral traits in fruit orchards →

Summary Orchard fruits such as pear and apple are important for ensuring global food security and agricultural economy as they not only provide essential nutrients, but also support biodiversity and ecosystem services. Breeders, growers and plant researchers constantly study desirable tree morphological features and floral characteristics to ensure fruit production and quality. Still, traditional orchard phenotyping is often laborious, limited in scale and prone‐to‐error, resulting in many attempts to develop reliable and scalable toolkits to address this challenge. Here, we present OrchardQuant‐3D, an analytic pipeline for automating tree‐level analysis of key canopy and floral traits for different types of fruit orchards. We first built a data fusion algorithm to register 3D point clouds collected by both drones (for colour signals) and Light Detection And Ranging (LiDAR, for precise spatial properties), reconstructing high‐quality 3D orchard models at different growth stages. Then, we utilised precise global navigation satellite system signals to position trees in orchards with millimetre‐level accuracy, enabling tree‐level analysis of key canopy (e.g. crown volume and the number or branches) and floral traits (e.g. blossom clusters and volumes) using 3D computer vision, complex graph theory and feature engineering techniques. Equipped with the OrchardQuant‐3D pipeline, we successfully measured varietal differences of four pear cultivars from a small pear orchard in Nanjing China, followed by a scale‐up study that surveyed 3D tree morphologies, key floral and fruit traits from 1104 apple trees in an orchard in East Malling, United Kingdom. To the best of our knowledge, such a multi‐source, comprehensive and expandable methodology has not yet been introduced to this important research domain. Hence, we believe that our work demonstrates a step change in our ability to conduct scalable 3D orchard phenotyping, which is highly valuable to advance orchard breeding, precise tree management and orchard research greatly to sustain fruit tree production in a rapidly changing climate.

Why it matches plant phenotyping methodsドローンとLiDARのデータ融合、3D再構成、コンピュータビジョンによる樹冠・花形質の自動抽出パイプラインを開発しており、植物フェノタイピング手法が研究の中心である。

abstractHere, we present OrchardQuant‐3D, an analytic pipeline for automating tree‐level analysis of key canopy and floral traits for different types of fruit orchards.

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

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

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

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

Optimized LC-MS method for simultaneous polyamine profiling and ADC/ODC activity quantification and evidence that ADCs are indispensable for flower development in tomato →

ABSTRACT Polyamines (PAs) are essential for plant development and stress responses, requiring tight homeostatic regulation. Many PA enzymes are regulated post-transcriptionally, making traditional transcript-based methods ineffective in determining their abundance, highlighting the need for alternative approaches to study PA homeostasis. Here, we refined a liquid chromatography-mass spectrometry (LC-MS) based method to simultaneously quantify activities of two key PA synthesizing enzymes – arginine decarboxylase (ADC) and ornithine decarboxylase (ODC) – from plant tissues using stable isotope substrates. By optimizing substrate concentrations, we increased assay sensitivity >10-fold in tomato leaf tissue. We further adapted this protocol for Nicotiana benthamiana , a model plant widely used for transient recombinant protein expression. Expression of epitope-tagged ADCs in this system revealed a direct correlation between protein abundance and enzymatic activity, demonstrating that ADC activity can infer its protein abundance in native tissues. Proof-of-principle experiments with the N. benthamiana expression system, confirm substrate specificity of tomato ADC and ODC enzymes and essential catalytic residues of tomato ADCs. Beyond enzymatic activities, our LCMS-based method also permits quantification of 11 PA network metabolite concentrations from the same LCMS sample. Visualizing this data as a heatmap pathway diagram, alongside ADC/ODC activities provides a comprehensive overview of PA metabolism in plant tissues. We also studied tomato CRISPR-Cas9-induced mutants deficient in ADC or ODC, complemented by phenotypic analysis. LC-MS analysis of an adc1/adc2 double mutant – an embryo lethal genotype in Arabidopsis – had no detectable agmatine, the product of ADCs. Additionally, despite a reduction in putrescine, no impact on the downstream PAs, spermidine and spermine, was found. The adc1/adc2 double mutant showed severe developmental abnormalities, including complete flower loss, demonstrating the indispensable role of ADCs in flower development. In summary, our optimized LC-MS approach for simultaneous quantification of ADC/ODC enzyme activity and PA-pathway metabolites, the ability to transiently express and functionally analyze recombinant ADC/ODC proteins in planta , and a collection of tomato CRISPR mutants deficient in these enzymes collectively establish a versatile new experimental toolkit to dissect PA homeostasis and PA-dependent developmental processes in plants.

Why it matches plant phenotyping methods植物組織中の酵素活性と代謝物を同時定量するLC-MS法を改良・検証し、発生異常との関連も評価しており、測定法が研究の中心である。

abstractHere, we refined a liquid chromatography-mass spectrometry (LC-MS) based method to simultaneously quantify activities of two key PA synthesizing enzymes – arginine decarboxylase (ADC) and ornithine decarboxylase (ODC) – from plant tissues using stable isotope substrates.

WCS-YOLOv8s: an improved YOLOv8s model for target identification and localization throughout the strawberry growth process. →

Introduction To enhance the quality and yield of strawberries, it is essential to effectively supervise the entire growing process. Currently, the monitoring of strawberry growth primarily relies on manual identification and positioning methods. This approach presents several challenges, including low efficiency, high labor intensity, time consumption, elevated costs, and a lack of standardized monitoring protocols. On the basis of this, there was an urgent need in the market to automate the whole process of target recognition and localization in strawberry growing. Methods Aiming at the above problems, we innovatively constructed a model for target recognition and localization of strawberries based on the YOLOv8s benchmark model, named the WCS-YOLOv8s model. In this paper, the whole growth process of the strawberry was divided into four stages, namely, the bud, flower, fruit under-ripening, and fruit ripening stages, and a total of 1,957 images of these four stages were captured with a binocular depth camera. Using the constructed WCS-YOLOv8s model to process the images, the target recognition and localization of the whole growth process of the strawberry were accomplished. This model proposes a data enhancement strategy based on the Warmup learning rate to stabilize the initial training process. The self- developed SE-MSDWA module is integrated into the backbone network to improve the model's feature extraction capability while suppressing redundant information, thereby achieving efficient feature extraction. Additionally, the neck network is enhanced by incorporating the CGFM module, which employs a multi-head self-attention mechanism to fuse diverse feature information and improve the network's feature fusion performance. Results and discussion The model's Precision (P), Recall (R), HYPERLINK "mailto:mAP@0.5" mAP@0.5, and mAP@0.5:0.95 of detection were 83.4%, 86.7%, 87.53%, and 60.48%, respectively, and the detection speed was 45.9 FPS(21.8 ms/per image, which significantly improved on the detection accuracy and generalization ability of with the YOLOv8s benchmark model. This model can meet the demand for online real-time target identification and localization of strawberries and provide a new detection method for the automated monitoring and management of the whole growth process of strawberries.

Why it matches plant phenotyping methodsイチゴの生育段階（芽、花、未熟果、成熟果）を画像から認識・定位するYOLOモデルを開発し、検出性能も評価しており、植物状態の取得手法が研究の中心である。

abstractwe innovatively constructed a model for target recognition and localization of strawberries based on the YOLOv8s benchmark model, named the WCS-YOLOv8s model.

A handbook for standardised measurements of regenerative plant functional traits →

A lack of standardised sampling protocols prevents functional traits from expressing their full potential to revolutionise plant ecology, biogeography, and evolutionary biology. Handbooks providing protocols for standardised measurements of plant functional traits allow researchers to tackle large-scale ecological questions but have traditionally focused on vegetative traits such as leaves, stems and roots. This handbook provides standardised protocols for 58 regeneration-related traits of flowers and gametophytes (10 traits), fruits (6 traits), seeds (36 traits) and seedlings (6 traits). It is the first effort to standardise sampling for relevant regeneration traits to understand processes, such as pollination, frugivory, seed dispersal, seed longevity, germination, and seedling establishment. The protocols were designed to embrace the diversity of ecological contexts experienced by flowers, gametophytes, fruits, seeds, and seedlings and incorporate methods for temperate to tropical, dry to moist and fire-prone to fire-sensitive ecosystems. We offer general guidelines for sampling, storing, and processing regenerative traits. Before laying out the protocol, we briefly describe each trait functionality, trade-offs, and sources of variability to give a broad context. Standardised protocols to estimate regenerative plant traits will unlock the full potential of plants to mitigate land use and climate change impacts, and restore destroyed ecosystems.

Why it matches plant phenotyping methods植物の再生関連機能形質58項目について、標準化されたサンプリング・保存・処理・測定プロトコルを体系的に提示するハンドブックであり、形質取得法が中心的な貢献である。

abstractThis handbook provides standardised protocols for 58 regeneration-related traits of flowers and gametophytes (10 traits), fruits (6 traits), seeds (36 traits) and seedlings (6 traits).

Characterizing season‐long floral trajectories in cotton with low‐altitude remote sensing and deep learning →

Societal Impact Statement Plant breeding is a critical tool for increasing the productivity, climate resilience, and sustainability of agriculture, but current phenotyping methods are a bottleneck due to the amount of human labor involved. Here, we demonstrate high‐throughput phenotyping with an unmanned aerial vehicle (UAV) to analyze the season‐long flowering pattern in cotton, subsequently mapping relevant genetic factors underpinning the trait. Season‐long flowering is a complex trait, with implications for adaptation of perennials to specific environments. We believe our approach can improve the speed and efficacy of breeding for a variety of woody perennials. Summary Many perennial plants make important contributions to agroeconomies and agroecosystems but have complex architecture and/or long flowering duration that hinders measurement and selection. Iteratively tracking productivity over a long flowering/fruiting season may permit the identification of genetic factors conferring different reproductive strategies that might be successful in different environments, ranging from rapid early maturation that avoids stresses, to late maturation that utilizes the full seasonal duration to maximize productivity. In cotton, a perennial plant that is generally cultivated as an annual crop, we apply aerial imagery and deep learning methods to novel and stable genetic stocks, identifying genetic factors influencing the duration and rate of fruiting. Our phenotyping method was able to identify 24 QTLs that affect flowering behavior in cotton. A total of five of these corresponded to previously identified QTLs from other studies. While these factors may have different relationships with crop productivity and quality in different environments, their determination adds potentially important information to breeding decisions. With transfer learning of the deep learning models, this approach could be applied widely, potentially improving gains from selection in diverse perennial shrubs and trees essential to sustainable agricultural intensification.

Why it matches plant phenotyping methodsUAV画像と深層学習による綿花の季節的開花・結実形質の高スループット表現型計測が研究の中心であり、遺伝解析にも用いられているため。

abstractHere, we demonstrate high‐throughput phenotyping with an unmanned aerial vehicle (UAV) to analyze the season‐long flowering pattern in cotton

Drone-Based Monitoring of Reproductive Potential in a Foundational Shrub Species →

Restoration and conservation of native plant populations will benefit from identifying individual plants with high reproductive success. While high-fecundity plants are ideal for seed sourcing, locating these plants across heterogeneous landscapes presents a logistical challenge. This challenge is especially significant for big sagebrush (Artemisia tridentata), a foundational species that is the focus of large-scale seed collection for restoration efforts in western rangelands. We evaluated whether cost-effective RGB imagery from unoccupied aerial vehicles (UAVs) could map flower stalk production in big sagebrush plants. Models were trained using three years of data from four sites spanning an elevational gradient that included all three big sagebrush subspecies: A. t. wyomingensis, A. t. vaseyana, and A. t. tridentata. Our model predicted flower stalk production from UAV imagery with a Mean Absolute Error (MAE) of [~]100 stalks, which is relatively low given that some plants produced more than 700 stalks. A hurdle model that explicitly accounted for excess zeroes outperformed simpler negative binomial models, suggesting that reproductive failure is distinct from flower stalk production in reproductive plants. Structural metrics, including height differences between June and September, canopy height, and edge-to-area ratio of plant crowns, had stronger effects in our model for counts of flower stalk production than spectral data. Model performance was consistent across environmentally heterogeneous sites but declined when applied to years excluded from training, indicating that year-specific training data may be necessary for interannual predictions. These results demonstrate that UAVs can monitor reproductive potential in wild plants and help identify high-fecundity individuals for seed collection. Our work underscores the need for future research that can improve predictions of flower production, including integrating multispectral data and increasing model reliability across years to support climate-resilient restoration strategies.

Why it matches plant phenotyping methodsUAV RGB画像から個体の花茎生産数を推定するモデルを開発・評価しており、植物の繁殖形質取得が研究の中心です。

abstractWe evaluated whether cost-effective RGB imagery from unoccupied aerial vehicles (UAVs) could map flower stalk production in big sagebrush plants.

An efficient segmentation using adaptive radial basis function neural network for tomato and mango plant leaf images →

Agriculture has become simply to feed ever-growing populations. The tomato is arguably the most well-known vegetable in agricultural areas and plays a significant role in the growth of vegetables in our daily lives. However, because this tomato has multiple diseases, image segmentation of the diseased leaf shows a key role in classifying the disease by the leaf's symptoms. Therefore, in this paper, an efficient plant disease segmentation using an adaptive radial basis function neural network (ARBFNN) classifier. The proposed radial basis function (RBF) neural network is enhanced by using the flower pollination algorithm (FPA). Firstly, the noise is detached by an adaptive median filter and histogram equalization. Then, from every leaf image, different kind of color features is extracted. After the extraction of features, those are fed to the segmentation phase to section the disease serving from the input image. The efficiency of the suggested method is analyzed based on various metrics and our technique attained a better accuracy of 97.58%.

Why it matches plant phenotyping methods植物葉画像から病徴領域を自動抽出する画像セグメンテーション手法の開発・評価が中心であり、植物病害状態の表現型推定に該当する。

abstractimage segmentation of the diseased leaf shows a key role in classifying the disease by the leaf's symptoms.

PhenoVision : A framework for automating and delivering research‐ready plant phenology data from field images →

Abstract Plant phenology plays a fundamental role in shaping ecosystems, and global change‐induced shifts in phenology have cascading impacts on species interactions and ecosystem structure and function. Detailed, high‐quality observations of when plants undergo seasonal transitions such as leaf‐out, flowering and fruiting are critical for tracking causes and consequences of phenology shifts, but these data are often sparse and biased globally. These data gaps limit broader generalizations and forecasting improvements in the face of continuing disturbance. One solution to closing such gaps is to document phenology on field images taken by public participants. iNaturalist, in particular, provides global‐scale research‐grade data and is expanding rapidly. Here we utilize over 53 million field images of plants and millions of human annotations from iNaturalist—data spanning all angiosperms and drawn from across the globe—to train a computer vision model (PhenoVision) to detect the presence of fruits and flowers. PhenoVision utilizes a vision transformer architecture pretrained with a masked autoencoder to improve classification success, and it achieves high accuracy on held‐out test images for flower (98.5%) and fruit presence (95%), as well as a high level of agreement with an expert annotator (98.6% for flowers and 90.4% for fruits). Key to producing research‐ready phenology data is post‐calibration tuning and validation focused on reducing noise inherent in field photographs, and maximizing the true positive rate. We also develop a standardized set of quality metrics and metadata so that results can be used effectively by the community. Finally, we showcase how this effort vastly increases phenology data coverage, including regions of the globe where data have been limited before. Our end products are tuned models, new data resources and an application streamlining discovery and use of those data for the broader research and management community. We close by discussing next steps, including automating phenology annotations, adding new phenology targets, for example leaf phenology, and further integration with other resources to form a global central database integrating all in situ plant phenology resources.

Why it matches plant phenotyping methods植物の開花・結実状態をフィールド画像から推定する視覚モデルを開発・検証し、校正、品質指標、研究用データ資源まで整備しており、フェノタイピング手法が中心である。

abstractto train a computer vision model (PhenoVision) to detect the presence of fruits and flowers

Semi-automated high content analysis of pollen performance using tubetracker. →

Key message TubeTracker provides a method to partially automate analysis of pollen tube growth using live imaging. Pollen function is critical for successful plant reproduction and crop productivity and it is important to develop accessible methods to quantitatively analyze pollen performance to enhance reproductive resilience. Here we introduce TubeTracker as a method to quantify key parameters of pollen performance such as, time to pollen grain germination, pollen tube tip velocity and maintenance of pollen tube integrity. TubeTracker integrates manual and automatic image processing routines and the graphical interface allows the user to interact with the software to make manual corrections of automated steps. TubeTracker does not depend on training data sets required to implement machine learning approaches and thus can be immediately implemented using readily available imaging systems. Furthermore, TubeTracker is an excellent tool to produce the pollen performance data sets necessary to take advantage of emerging AI-based methods to fully automate analysis. We tested TubeTracker and found it to be accurate in measuring pollen tube germination and pollen tube tip elongation across multiple cultivars of tomato.

Why it matches plant phenotyping methods植物の花粉管成長をライブイメージングから定量するソフトウェア手法の開発・精度評価が中心であり、花粉発芽、伸長速度、完全性という植物形質を抽出している。

abstractTubeTracker provides a method to partially automate analysis of pollen tube growth using live imaging.

Using a Live Analysis System to Study Amyloplast Replication in Arabidopsis Ovule Integuments. →

Amyloplasts, non-photosynthetic plastids specialized for starch synthesis and storage, proliferate in storage tissue cells of plants. To date, studies of amyloplast replication in roots and the ovule nucelli from various plant species have been performed using electron and fluorescence microscopy. However, a complete understanding of amyloplast replication remains unclear due to the absence of experimental systems capable of tracking their morphology and behavior in living cells. Recently, we demonstrated that Arabidopsis ovule integument could provide a platform for live-cell imaging of amyloplast replication. This system enables precise analysis of amyloplast number and shape, including the behavior of stroma-filled tubules (stromules), during proplastid-to-amyloplast development in post-mitotic cells. Here, we provide technical guidelines for observing and quantifying amyloplasts using conventional fluorescence microscopy in wild-type and several plastid-division mutants of Arabidopsis . Key features • Novel approach for investigating amyloplast differentiation and replication in plant cells. • Detection of stroma-labeled amyloplasts in whole-mount ovules using conventional fluorescence microscopy. • Facilitates quantitative and comparative analysis of amyloplast proliferation using various Arabidopsis resources. • Enables high-resolution analysis of changing amyloplast and stromule morphologies in living cells.

Why it matches plant phenotyping methods生細胞蛍光イメージングによりアミロプラストの数・形状・増殖を定量する技術の技術指針を提示しており、植物表現型の取得・解析方法が研究の中心である。

abstractHere, we provide technical guidelines for observing and quantifying amyloplasts using conventional fluorescence microscopy in wild-type and several plastid-division mutants of Arabidopsis .

Detection of Botrytis cinerea severity in rose petals using hyperspectral imaging for plant breeding applications →

Botrytis cinerea is a fungal pathogen that can affect a wide range of plants, including roses. Resistance against Botrytis is quantitative, making breeding for resistance challenging. To enable proper genetic marker development, high-throughput and objective data on Botrytis sensitivity is essential. Rose petal discs of different cultivars were manually infected with Botrytis and were monitored with hyperspectral imaging using a fully automated spectral imaging setup. Predictive modelling analysis involved both detection of Botrytis and explaining the severity of infection by linking the spectral data to visual scoring by human eye. Furthermore, band selection analysis was performed to detect key spectral bands relevant for Botrytis detection and to facilitate development of lower cost multi spectral systems for detection of Botrytis infected areas in roses. The presented approach can help plant breeders to explore and adapt to new plant phenotyping technologies such as hyperspectral imaging for breeding against biotic and abiotic stresses.

Why it matches plant phenotyping methodsバラ花弁におけるBotrytis感染の重症度をハイパースペクトル画像と予測モデルで検出・推定する方法を開発し、育種向けに評価しており、植物表現型取得が中心である。

abstracthigh-throughput and objective data on Botrytis sensitivity is essential

The Quest for the Sli Locus →

Genetic gain in potato breeding is limited by the heterozygous tetraploid genome of cultivated potato. Recent efforts to breed potato at the diploid level promise to improve genetic gain and allow more straightforward genetics and introgression breeding. Diploid F1 hybrid potato breeding relies on the ability to create diploid inbred lines via repeated self-fertilization. However, self-fertilization of diploid potato is hampered by a gametophytic self-incompatibility system encoded by the S-locus that prevents fertilization by self-pollen. Nonetheless, self-compatible diploid potato genotypes exist and have been used to create inbred lines. The S-locus inhibitor (Sli) gene is a dominant gene that provides strong self-compatibility in diploid potato and was previously mapped to Chromosome 12. While the Sli gene has already been identified and characterized, the most tedious challenge was to develop the optimal phenotyping methods and genetic populations preceding the cloning of this gene. To this end, we developed an effective phenotyping protocol to identify suitable parents and create diploid populations segregating for Sli. We show that an accurate phenotyping method is crucial to discriminate between confounding fertility factors and self-compatibility. In addition, we found that the Sli locus shows extreme segregation distortion on Chromosome 12. Finally, we used these insights to develop three F1 populations that segregate for Sli, which we later used for the identification of the Sli gene.

Why it matches plant phenotyping methodsSli遺伝子の識別に向け、自己適合性を評価する表現型判定プロトコルを開発しており、フェノタイピング手法が研究の中心である。

abstractthe most tedious challenge was to develop the optimal phenotyping methods and genetic populations preceding the cloning of this gene.

Detection of Botrytis cinerea severity in rose petals using hyperspectral imaging for plant breeding applications →

• Hyperspectral imaging can detect Botrytis cinerea 1 day after inoculation. • Hyperspectral imaging detects it 1 day earlier than colour imaging. • Chemometric approaches allowed visualisation of disease progression. • Disease severity can be explained with R 2 = 0.84 using near-infrared spectroscopy. Botrytis cinerea is a fungal pathogen that can affect a wide range of plants, including roses. Resistance against Botrytis is quantitative, making breeding for resistance challenging. To enable proper genetic marker development, high-throughput and objective data on Botrytis sensitivity is essential. Rose petal discs of different cultivars were manually infected with Botrytis and were monitored with hyperspectral imaging using a fully automated spectral imaging setup. Predictive modelling analysis involved both detection of Botrytis and explaining the severity of infection by linking the spectral data to visual scoring by human eye. Furthermore, band selection analysis was performed to detect key spectral bands relevant for Botrytis detection and to facilitate development of lower cost multi spectral systems for detection of Botrytis infected areas in roses. The presented approach can help plant breeders to explore and adapt to new plant phenotyping technologies such as hyperspectral imaging for breeding against biotic and abiotic stresses.

Why it matches plant phenotyping methodsバラのBotrytis感染部位と感染重症度を、完全自動化ハイパースペクトル撮像および予測モデルで検出・推定する方法が研究の中心であり、植物表現型計測法として明確に該当する。

abstractRose petal discs of different cultivars were manually infected with Botrytis and were monitored with hyperspectral imaging using a fully automated spectral imaging setup.

Integrated deep learning neural network and hyperspectral imaging for non-destructive prediction of biochemical properties of plant organs →

ABSTRACT The methods used to analyze the medicinal properties of plants are often destructive, time-consuming, expensive and labor-intensive, making them unsuitable for fast and online quality analysis. This context has motivated the development of non-destructive methods for plant analyses. The main objective of this study is to non-destructively determine the biochemical characteristics of plants based on the integration of hyperspectral imaging and nonlinear modeling. Two nonlinear modeling methods, deep learning neural network (DNN) and regression modeling (NRM), were used to predict the active substances of plant organs according to their spectral reflectance. Two datasets, important spectra determined using reconstruction independent components analysis (RICA) and all spectra, were used to train the modeling methods in which the biochemical characteristics of the plants were target. Higher R 2 value, lower RMSE value and higher p-value indicated that the accuracy of DNN model was much higher than that of the NRM. Therefore, the combined HSI and DNN model was proposed as a suitable method for predicting the biochemical and medicinal properties of plant organs. Using the DNN model, the highest accuracy was obtained for carotenoid content estimation, its R 2 = 0.9997 and RMSE= 0.234 for all spectra, and its R 2 = 0.9952 and RMSE= 0.239 for important spectra. Nonlinear regression analysis of the spectra showed that the spectral reflectance at 538 nm was maximized for medicinal plants with higher amounts of total flavonoids, antioxidant activity and total tannin contents. The HSI analysis of plant organs and measurement the biochemical properties showed that the greatest therapeutic effect of plants was obtained for flower and leaf organs. These results concluded that the integration of HSI, RICA and NRM was successful for predicting biochemical and medicinal properties of plant organs according to their spectral reflectance.

Why it matches plant phenotyping methods植物器官の生化学的特性を非破壊推定するためのHSI・DNN統合手法の開発と精度評価が研究の中心であり、単なる生物学的実験のルーチン測定ではない。

abstractThe main objective of this study is to non-destructively determine the biochemical characteristics of plants based on the integration of hyperspectral imaging and nonlinear modeling.

AI-driven time series analysis for predicting strawberry weekly yields integrating fruit monitoring and weather data for optimized harvest planning →

Strawberries, as an indeterminate crop, produce fruit multiple times per season, making fruit monitoring and wave-specific yield prediction essential for optimizing harvest planning. This study developed an AI-driven approach to predict next week’s yield using real-time plant image data collected by a machine vision system and environmental data. YOLOv8n was employed to count flowers, immature fruit, and mature fruit per plant, with manual counts used to evaluate the system’s accuracy. The YOLOv8n-based data, combined with weather features, were used to train several AI models for yield prediction. These models included traditional time series machine learning approaches, such as Multiple Linear Regression (MLR) with time lag features, Vector Autoregression (VAR), Gradient Boosting Machines (GBM), Random Forest, and deep learning time-series models, including Long Short-Term Memory (LSTM) and Temporal Convolutional Networks (TCN). Recursive Feature Elimination (RFE) was employed to identify the most relevant features. The performance of these models was evaluated across three strawberry varieties: Sensation, Brilliance, and Medallion. Results showed that MLR outperformed other models for Sensation and Brilliance, with R² values of 0.633 and 0.908, respectively. For Medallion, GBM achieved the best performance with an R² score of 0.848. LSTM, which outperformed TCN, achieved R² scores of 0.522 (Sensation), 0.839 (Brilliance), and 0.740 (Medallion). This AI-driven system automates yield forecasting, reducing labor costs and enabling more efficient harvest planning. The study highlights the potential of combining machine vision and predictive analytics for precise, scalable yield prediction, offering valuable insights for proactive farm management and supply chain optimization.

Why it matches plant phenotyping methods機械視覚で植物ごとの花・未熟果・成熟果を計数し、手動計数で精度評価する手法が収量予測の中心であるため、植物表現型計測・検証を含む。

abstractYOLOv8n was employed to count flowers, immature fruit, and mature fruit per plant, with manual counts used to evaluate the system’s accuracy.

A Three-Dimensional Phenotype Extraction Method Based on Point Cloud Segmentation for All-Period Cotton Multiple Organs. →

Phenotypic data of cotton can accurately reflect the physiological status of plants and their adaptability to environmental conditions, playing a significant role in the screening of germplasm resources and genetic improvement. Therefore, this study proposes a cotton phenotypic data extraction algorithm that integrates ResDGCNN with an improved region-growing method and constructs a 3D point cloud dataset of cotton covering the entire growth period under real growth conditions. To address the challenge of significant structural variations in cotton organs across different growth stages, we designed an innovative point cloud segmentation algorithm, ResDGCNN, which integrates residual learning with dynamic graph convolution to enhance organ segmentation performance throughout all developmental stages. In addition, to address the challenge of accurately segmenting overlapping regions between different cotton organs, we introduced an optimization strategy that combines point distance mapping with curvature-based normal vectors and developed an improved region-growing algorithm to achieve fine segmentation of multiple cotton organs, including leaves, stems, and flower buds. Experimental data show that, in the task of organ segmentation throughout the entire cotton growth cycle, the ResDGCNN model achieved a segmentation accuracy of 67.55%, with a 4.86% improvement in mIoU compared to the baseline model. In the fine-grained segmentation of overlapping leaves, the model achieved an R 2 of 0.962 and an RMSE of 2.0. The average relative error in stem length estimation was 0.973, providing a reliable solution for acquiring 3D phenotypic data of cotton.

Why it matches plant phenotyping methods綿花の全生育期間にわたる3D点群から器官を分割し、葉・茎・花蕾の表現型データを抽出する手法の開発と評価が研究の中心である。

abstractthis study proposes a cotton phenotypic data extraction algorithm that integrates ResDGCNN with an improved region-growing method

Hazelnut Yield Estimation: A Vision-Based Approach for Automated Counting of Hazelnut Female Flowers. →

Accurate estimation of hazelnut yield is crucial for optimizing resource management and harvest planning. Although the number of female flowers on a flowering plant is a reliable indicator of annual production, counting them remains difficult because of their extremely small size and inconspicuous shape and color. Currently, manual flower counting is the only available method, but it is time-consuming and prone to errors. In this study, a novel vision-based method for automatic flower counting specifically designed for hazelnut plants ( Corylus avellana ) exploiting a commercial high-resolution imaging system and an image-tiling strategy to enhance small-object detection is proposed. The method is designed to be fast and scalable, requiring less than 8 s per plant for processing, in contrast to 30-60 min typically required for manual counting by human operators. A dataset of 2000 labeled frames was used to train and evaluate multiple female hazelnut flower detection models. To improve the detection of small, low-contrast flowers, a modified YOLO11x architecture was introduced by adding a P2 layer, improving the preservation of fine-grained spatial information and resulting in a precision of 0.98 and a Mean Average Precision (mAP@50-95) of 0.89. The proposed method has been validated on images collected from hazelnut groves and compared with manual counting by four experienced operators in the field, demonstrating its ability to detect small, low-contrast flowers despite occlusions and varying lighting conditions. A regression-based bias correction was applied to compensate for systematic counting deviations, further improving accuracy and reducing the mean absolute percentage error to 27.44%, a value comparable to the variability observed in manual counting. The results indicate that the system can provide a scalable and efficient alternative to traditional female flower manual counting methods, offering an automated solution tailored to the unique challenges of hazelnut yield estimation.

Why it matches plant phenotyping methodsハシバミ植物の雌花数という収量関連形質を画像から自動抽出する手法を開発し、データセット、モデル改良、現地検証、手動計数との比較まで行っており、フェノタイピング手法が中心である。

abstractIn this study, a novel vision-based method for automatic flower counting specifically designed for hazelnut plants ( Corylus avellana ) exploiting a commercial high-resolution imaging system and an image-tiling strategy to enhance small-object detection is proposed.

Determination of Optimal Harvest Time in Cannabis sativa L. Based upon Stigma Color Transition. →

Cannabis sativa L. is cultivated for therapeutic and recreational use. Delta-9 tetrahydrocannabinol (THC) and cannabidiol (CBD) are primarily responsible for its psychoactive and medicinal effects. As the global cannabis industry continues to expand, constant review and optimization of horticultural practices are needed to ensure a reliable harvest and improved crop quality. There is currently uncertainty about the optimal harvest time of C. sativa , i.e., when cannabinoid concentrations are at their highest during inflorescence maturation. At present, growers observe the color transition of stigmas from white to amber as an indicator of harvest time. This research investigates the relationship between stigma color and cannabinoid concentration using liquid chromatography-mass spectrometry (LCMS) and digital image analysis. Additionally, early screening prediction models have also been developed for six cannabinoids using near-infrared (NIR) spectroscopy and LCMS to assist in early cannabinoid determination. Among the genotypes grown, 22 of 25 showed cannabinoid concentration peaks between the third (mostly amber) and fourth (fully amber) stages; however, some genotypes peaked within the first (no amber) and second (some amber) stages. We have determined that the current 'rule of thumb' of harvesting when a cannabis plant is mostly amber is still a useful approximation in most cases; however, studies on individual genotypes should be performed to determine their individual optimal harvest time based on the desired cannabinoid profile or total cannabinoid concentration.

Why it matches plant phenotyping methodsデジタル画像解析とNIRによる予測モデルを開発し、花序の色およびカンナビノイド濃度を用いた収穫時期・植物状態の推定を扱っており、表現型取得・推定手法が中心的です。

abstractThis research investigates the relationship between stigma color and cannabinoid concentration using liquid chromatography-mass spectrometry (LCMS) and digital image analysis.

Integrating Dense Genotyping with High-Throughput Phenotyping Empowers the Genetic Dissection of Berry Quality and Resilience Traits in Grapevine. →

Abstract Investigating the genetic architecture of important agronomic traits in grapevine, like berry quality and resilience to abiotic stress, has been hampered by bottlenecks in genotyping and phenotyping. To address these limitations, this study aimed to develop innovative tools to unravel the complex polygenic genomic architecture of these traits. Specifically, a high‐density 200K single nucleotide polymorphism array is developed and validated its effectiveness by genotyping 471 accessions from three F 1 breeding populations. A high‐throughput grape phenotyping tool is developed to accurately capture berry color, shape, and size. By integrating data from the two platforms, associated loci are identified over three growing seasons. Association mapping and haplotype analysis identified novel loci and candidate genes for berry shape ( bHLH017 ), soluble sugars ( ACT ), and organic acids ( ALMT1 and FUSC2 ), as well as vine cold tolerance ( NAC08 ), and fine‐mapped the flower sex determination locus. Furthermore, the functional role of NAC08 is validated, demonstrating that it activates the expression of a raffinose synthase gene, thereby increasing raffinose levels and conferring cold tolerance. Together, these augmented tools, the integrated data, and novel loci establish a better foundation for trait aggregation that will enhance breeding efficiency and boost the development of high‐quality grape varieties.

Why it matches plant phenotyping methodsブドウ果実の色・形・サイズを高精度に取得するハイスループット表現型解析ツールの開発が研究の中心であり、遺伝子型データとの統合応用も行っている。

abstractA high‐throughput grape phenotyping tool is developed to accurately capture berry color, shape, and size.

A Method for Identifying Picking Points in Safflower Point Clouds Based on an Improved PointNet++ Network →

To address the challenge of precise picking point localization in morphologically diverse safflower plants, this study proposes PointSafNet—a novel three-stage 3D point cloud analysis framework with distinct architectural and methodological innovations. In Stage I, we introduce a multi-view reconstruction pipeline integrating Structure from Motion (SfM) and Multi-View Stereo (MVS) to generate high-fidelity 3D plant point clouds. Stage II develops a dual-branch architecture employing Star modules for multi-scale hierarchical geometric feature extraction at the organ level (filaments and frui balls), complemented by a Context-Anchored Attention (CAA) mechanism to capture long-range contextual information. This synergistic feature learning approach addresses morphological variations, achieving 86.83% segmentation accuracy (surpassing PointNet++ by 7.37%) and outperforming conventional point cloud models. Stage III proposes an optimized geometric analysis pipeline combining dual-centroid spatial vectorization with Oriented Bounding Box (OBB)-based proximity analysis, resolving picking coordinate localization across diverse plants with 90% positioning accuracy and 68.82% mean IoU (13.71% improvement). The experiments demonstrate that PointSafNet systematically integrates 3D reconstruction, hierarchical feature learning, and geometric reasoning to provide visual guidance for robotic harvesting systems in complex plant canopies. The framework’s dual emphasis on architectural innovation and geometric modeling offers a generalizable solution for precision agriculture tasks involving morphologically diverse safflowers.

Why it matches plant phenotyping methods3D画像再構成・点群解析・器官セグメンテーションを統合し、植物器官の位置を推定する方法が研究の中心である。

abstractthis study proposes PointSafNet—a novel three-stage 3D point cloud analysis framework

Dense object detection based canopy characteristics encoding for precise spraying in peach orchards →

Accurate and precise spraying in orchards is paramount for optimized agricultural practices, ensuring efficient pesticide utilization, minimized environmental impact, and enhanced crop yield by targeting specific areas with the right amount of treatment. The asymmetrical distribution of foliage and flowers in peach orchards poses a formidable challenge to achieving precise spray accuracy, impeding the uniform application of treatments and compromising the overall efficacy of pest and disease control measures. In response to the prevailing challenges in achieving accurate spray application caused by the asymmetrical distribution of foliage and flowers in peach orchards, this paper introduces a novel deep neural network to map the RGB image and corresponding depth to the density map of peach flowers or foliage. The model consists of components: (1) two backbones based on ResNet-50 that extract contextual features from the RGB image and depth features from depth data at multiple scales and levels; (2) an optimized depth-enhanced module that effectively fuses the distinct features extracted from the two input streams; and (3) a two-stage decoder that aggregates the high-level cross-modal features to regress the coarse density map and subsequently integrates it with the low-level cross-modal features for final density map prediction. To evaluate the performance of our model, we collected 493 frames (206,095 instances) of peach flowers and 475 frames (350,833 instances) of foliage from the peach orchards utilizing our sprayer prototype equipped with stereo cameras. The proposed method outperforms state-of-the-art models on our datasets, demonstrating the superiority and efficacy for encoding canopy characteristics in the form of flower and foliage density maps for blossom and cover sprays. It attains significant computational efficiency, exhibiting a frame rate of 20 FPS, and showcases exceptional accuracy with a WMAPE of 12.11% for peach flowers and a WMAPE of 13.37% for leaves.

Why it matches plant phenotyping methods桃の花・葉の密度という植物器官の形質をRGB-D画像から推定する手法を開発・評価しており、散布制御への応用を超えてフェノタイピング手法自体が中心です。

abstractthis paper introduces a novel deep neural network to map the RGB image and corresponding depth to the density map of peach flowers or foliage

Enhancing entomophilous pollination for sustainable crop production. →

SUMMARY Successful fertilization of insect‐pollinated crops hinges on a delicate interplay of olfactory and visual signals of pollinator attraction, the chemical complexity of nectar and pollen rewards, and the physical interaction between insects and flower anatomy for efficient pollen transfer. These traits, which are controlled genetically and exhibit phenotypic variance even within species, present opportunities for breeding technologies to map and select genotypes with floral traits that actively guide pollinator preferences. Recent technological advancements and automation have enabled high‐throughput metabolic phenotyping of floral chemical traits of pollinator attraction and rewards. These measurements, when integrated with computed tomography (CT) scans of flower shape analysis and video tracking of pollinator behavior, can guide the selection of genotypes with enhanced insect visitation rates and effective cross‐pollination. In this perspective article, we highlight the potential of this strategy for blueberry ( Vaccinium corymbosum L.), a crop heavily reliant on bee pollination for fruit production and with flowers that display considerable variance of chemical and morphological traits and pollinator visitation rates. Leveraging blueberry's genetic diversity can address pollination issues exacerbated by global warming and declining health of managed bees, thus contributing to a more sustainable agricultural production.

Why it matches plant phenotyping methods花の化学・形態・訪花行動を高スループットに測定し、CT解析と動画追跡を統合する植物表現型評価戦略を中心に論じる展望論文であり、方法論的役割が明確。

abstractRecent technological advancements and automation have enabled high‐throughput metabolic phenotyping of floral chemical traits of pollinator attraction and rewards.

DM_CorrMatch: a semi-supervised semantic segmentation framework for rapeseed flower coverage estimation using UAV imagery. →

Rapeseed (Brassica napus L.) inflorescence coverage is a crucial phenotypic parameter for assessing crop growth and estimating yield. Accurate crop cover assessment is typically performed using Unmanned Aerial Vehicles (UAVs) in combination with semantic segmentation methods. However, the irregular and variable morphology of rapeseed inflorescences presents significant challenges in segmentation. To address these challenges, advanced methods that can improve segmentation accuracy, particularly under limited data conditions, are needed. In this study, we propose a cost-effective and high-throughput approach using a semi-supervised learning framework, DM_CorrMatch. This method enhances input images through strong and weak data augmentation techniques, while leveraging the Denoising Diffusion Probabilistic Model (DDPM) to generate additional samples in data-scarce scenarios. We propose an automatic update strategy for labeled data to dilute the proportion of erroneous labels in manual segmentation. Furthermore, a novel network architecture, Mamba-Deeplabv3+, is proposed, combining the strengths of Mamba and Convolutional Neural Networks (CNNs) for both global and local feature extraction. This architecture effectively captures key inflorescence features, even under varying poses, while reducing the influence of complex backgrounds. The proposed method is validated on the Rapeseed Flower Segmentation Dataset (RFSD), which consists of 720 UAV images from the Yangluo experimental station of the Oil Crops Research Institute of the Chinese Academy of Agricultural Sciences (CAAS). The experimental results showed that our method outperforms four traditional segmentation methods and eleven deep learning methods, achieving an Intersection over Union (IoU) of 0.886, Precision of 0.942, and Recall of 0.940. The proposed semi-supervised learning-based method, combined with the Mamba-Deeplabv3+ architecture, demonstrates superior performance in accurately segmenting rapeseed inflorescences under challenging conditions. Our approach effectively handles complex backgrounds and various poses of inflorescences, providing a reliable tool for rapeseed flower cover estimation. This method can aid in the development of high-yield cultivars and improve crop monitoring through UAV-based technologies.

Why it matches plant phenotyping methodsUAV画像からナタネ花序被覆率という植物表現型を推定する半教師ありセグメンテーション手法を開発し、データセット上で既存手法と比較検証しているため、方法が中心的である。

abstractwe propose a cost-effective and high-throughput approach using a semi-supervised learning framework, DM_CorrMatch.

A Comprehensive Review of Deep Learning in Computer Vision for Monitoring Apple Tree Growth and Fruit Production. →

The high nutritional and medicinal value of apples has contributed to their widespread cultivation worldwide. Unfavorable factors in the healthy growth of trees and extensive orchard work are threatening the profitability of apples. This study reviewed deep learning combined with computer vision for monitoring apple tree growth and fruit production processes in the past seven years. Three types of deep learning models were used for real-time target recognition tasks: detection models including You Only Look Once (YOLO) and faster region-based convolutional network (Faster R-CNN); classification models including Alex network (AlexNet) and residual network (ResNet); segmentation models including segmentation network (SegNet), and mask regional convolutional neural network (Mask R-CNN). These models have been successfully applied to detect pests and diseases (located on leaves, fruits, and trunks), organ growth (including fruits, apple blossoms, and branches), yield, and post-harvest fruit defects. This study introduced deep learning and computer vision methods, outlined in the current research on these methods for apple tree growth and fruit production. The advantages and disadvantages of deep learning were discussed, and the difficulties faced and future trends were summarized. It is believed that this research is important for the construction of smart apple orchards.

Why it matches plant phenotyping methodsリンゴ樹の生育、器官、収量、病害を画像・深層学習で評価する方法を中心にレビューしており、植物フェノタイピング手法レビューに該当する。

abstractThis study reviewed deep learning combined with computer vision for monitoring apple tree growth and fruit production processes in the past seven years.

Remote Phenotyping Strategies for Sunflower Flowering Assessments Using Deep Learning Approaches →

ABSTRACT The flowering date of sunflowers is a crucial trait that significantly influences crop management practices and product placement. Traditional ground methods for data collection are labor-intensive and subjective, requiring field scientists to manually estimate and record data in the field. This trait can be measured by counting the number of days from planting until 50% of plants in each research plot have reached flowering at R5 developmental growth stage. However, this method is time-consuming and may overlook valuable information related to flowering rates and duration. Flowering time of sunflower also can be approximated by counting the number of heads (flowers) across multiple dates. We propose a method for rapidly counting sunflower heads to model flower counts over time and estimate flowering time using RGB images acquired by Unmanned Aerial Vehicles (UAVs). The method developed employs a deep learning model trained to detect sunflower heads from UAV imagery and modeling these counts over time using a logistic function to estimate the 50% flowering date. The experimental results obtained from this method enabled estimation of the flowering date with a high correlation to ground measurements ( r > 0.91). Significantly, this approach not only reduces labor but also improves the precision of data collection. Moreover, an increase of 6% in heritability across trials, compared to traditional methods, suggests that our approach contributes to a deeper genetic understanding of flowering dynamics. This includes enhanced insights into the timing and rates of flowering, essential for optimizing breeding strategies and understanding genetic responses to environmental conditions. This innovative approach offers a promising avenue for enhancing the efficiency and accuracy of sunflower phenotyping.

Why it matches plant phenotyping methodsUAV画像からヒマワリ頭花を深層学習で検出し、開花時期という植物形質を推定する手法が研究の中心であり、地上測定との相関による検証も行っている。

abstractWe propose a method for rapidly counting sunflower heads to model flower counts over time and estimate flowering time using RGB images acquired by Unmanned Aerial Vehicles (UAVs).

Vase-Life Monitoring System for Cut Flowers Using Deep Learning and Multiple Cameras. →

Here, we developed a vase-life monitoring system (VMS) to automatically and accurately assess the post-harvest quality and vase life (VL) of cut roses. The VMS integrates camera imaging with the YOLOv8 (You Only Look Once version 8) deep learning algorithm to continuously monitor major physiological parameters including flower opening, fresh weight, water uptake, and gray mold disease incidence. Our results showed that the VMS can automatically measure the main physiological factors of cut roses by obtaining precise and consistent data. The values measured for physiology and disease by the VMS closely correlated with those measured by observation (OBS). Additionally, YOLOv8 achieved a high performance in the model by obtaining an object detection accuracy of 90%. Additionally, the mAP0.5 supported the high accuracy of the model in evaluating the VL of cut roses. Regression analysis revealed a strong correlation between the VL, VMS, and OBS. The VMS incorporating the microscope detected physiological and disease factors in the early stages of development. These results show that the plant monitoring system incorporating a microscope is highly effective for evaluating the post-harvest quality of cut roses. The early detection method using the VMS could also be applied to the flower breeding process, which requires rapid measurements of important characteristics of flower species, such as VL and disease resistance, to develop superior cultivars.

Why it matches plant phenotyping methodsカメラ画像とYOLOv8を統合したシステムを開発・検証し、切り花の開花、鮮重、吸水、灰色かび病、花瓶寿命を自動評価しているため、植物表現型の取得手法が中心です。

abstractwe developed a vase-life monitoring system (VMS) to automatically and accurately assess the post-harvest quality and vase life (VL) of cut roses.

Optimization of resource allocation in field phenotyping of sunflower for components of partial resistance to Sclerotinia sclerotiorum on capitula →

In sunflower breeding, plant phenotyping of white rot (WR) resistance requires a significant amount of resources. Thus the present study aimed to evaluate the possibility to make a more efficient phenotyping of WR resistance in sunflower hybrids per unit of allocated resources. The Degree of Genetic Determination (DGD) estimated from 37 commercial hybrids evaluated by their relative incubation period (RIP) and relative daily lesion growth (RDLG) for 3 years (y) in field experiments designed with 3 replications (r) and 12 plants/plot (pl/p), i.e. 108 plants/hybrid (pl/h), was compared with DGDs estimated using < 108 pl/h. When using fewer resources, DGD values were estimated with less precision in all year-replication-plant/plot combinations. The bias between the DGD averages estimated and the benchmarked DGD values of 0.78 (RIP) and 0.63 (RDLG) and, consequently, the inaccuracies of such estimations increased gradually. The 3y-2r-6pl/p combination was the level of allocated resources showing a still acceptable relative genotypic variability detected for RIP, given that a 100% probability of the DGD estimated was higher than the proposed threshold (DGD = 0.60) value, although the probability for RDLG was quite lower. That combination also resulted in a not-to-be overlooked gain in relative genotypic variability per unit of allocated resources in relation to that with 108 pl/h. So, the cost associated with resources, such as land, seeds, time, and personnel, allocated to assess WR resistance could be reduced without significantly altering the accuracy and precision of the DGD values estimated respect to the benchmarked ones.

Why it matches plant phenotyping methodsヒマワリの菌核病抵抗性という植物病害形質について、圃場フェノタイピングの資源配分・サンプリング設計を比較し、推定精度と再現性を評価しているため、測定方法の技術的検証が中心である。

abstractThe Degree of Genetic Determination (DGD) estimated from 37 commercial hybrids evaluated by their relative incubation period (RIP) and relative daily lesion growth (RDLG) for 3 years (y) in field experiments designed with 3 replications (r) and 12 plants/plot (pl/p)

Data-Fusion Based On Transfer Learning For Plant Disease Recognition →

In this paper, the research focused on wild and introduced cultivated flowers with multiple diseases such as Stephanitis, Sooty Mould, Xanthosis, and Leaf Blight, utilizing transfer learning and and data fusion technology to construct a plant disease detection model employing Faster R-CNN.The self-built data set collected during the flower growth cycle was trained and identified.To solve the problem of disease category imbalance in the actual collected data samples, the data of small category samples is enhanced from the perspective of category balance and label balance, and FocalLoss is used to improve the original classification loss function. Based on this self-built data set, the constructed IFRCNN disease detection model was compared with the SSD (Single Shot multibox Detector), ResNet18 and Yolov3 models. The results showed that for several common plant diseases in the dataset, the mAP of IFRCNN disease detection model was significantly higher than that of the other three models. It can effectively locate plant leaf disease areas, realize the detection of multiple diseases, and provide reference for accurate disease prevention and control.

Why it matches plant phenotyping methods植物葉の病斑領域を画像から検出・分類するモデルの構築、データ拡張、損失関数改良、他モデルとの比較評価が中心であり、病害状態の表現型推定手法に該当する。

abstractconstruct a plant disease detection model employing Faster R-CNN

Robust Flower Cluster Matching Using The Unscented Transform →

Monitoring flowers over time is essential for precision robotic pollination in agriculture. To accomplish this, a continuous spatial-temporal observation of plant growth can be done using stationary RGB-D cameras. However, image registration becomes a serious challenge due to changes in the visual appearance of the plant caused by the pollination process and occlusions from growth and camera angles. Plants flower in a manner that produces distinct clusters on branches. This paper presents a method for matching flower clusters using descriptors generated from RGB-D data and considers allowing for spatial uncertainty within the cluster. The proposed approach leverages the Unscented Transform to efficiently estimate plant descriptor uncertainty tolerances, enabling a robust image-registration process despite temporal changes. The Unscented Transform is used to handle the nonlinear transformations by propagating the uncertainty of flower positions to determine the variations in the descriptor domain. A Monte Carlo simulation is used to validate the Unscented Transform results, confirming our method's effectiveness for flower cluster matching. Therefore, it can facilitate improved robotics pollination in dynamic environments.

Why it matches plant phenotyping methodsRGB-D画像から花房を時系列追跡・マッチングする画像登録手法が研究の中心で、植物成長の観測に直接用いられるため、植物フェノタイピング手法として含める。

abstractThis paper presents a method for matching flower clusters using descriptors generated from RGB-D data and considers allowing for spatial uncertainty within the cluster.

YO-AFD: an improved YOLOv8-based deep learning approach for rapid and accurate apple flower detection. →

The timely and accurate detection of apple flowers is crucial for assessing the growth status of fruit trees, predicting peak blooming dates, and early estimating apple yields. However, challenges such as variable lighting conditions, complex growth environments, occlusion of apple flowers, clustered flowers and significant morphological variations, impede precise detection. To overcome these challenges, an improved YO-AFD method based on YOLOv8 for apple flower detection was proposed. First, to enable adaptive focus on features across different scales, a new attention module, ISAT, which integrated the Inverted Residual Mobile Block (IRMB) with the Spatial and Channel Synergistic Attention (SCSA) module was designed. This module was then incorporated into the C2f module within the network's neck, forming the C2f-IS module, to enhance the model's ability to extract critical features and fuse features across scales. Additionally, to balance attention between simple and challenging targets, a regression loss function based on Focaler Intersection over Union (FIoU) was used for loss function calculation. Experimental results showed that the YO-AFD model accurately detected both simple and challenging apple flowers, including small, occluded, and morphologically diverse flowers. The YO-AFD model achieved an F1 score of 88.6%, mAP50 of 94.1%, and mAP50-95 of 55.3%, with a model size of 6.5 MB and an average detection speed of 5.3 ms per image. The proposed YO-AFD method outperforms five comparative models, demonstrating its effectiveness and accuracy in real-time apple flower detection. With its lightweight design and high accuracy, this method offers a promising solution for developing portable apple flower detection systems.

Why it matches plant phenotyping methodsリンゴ花を対象とするYOLOv8改良型の画像解析手法を開発し、検出性能を比較評価している。花の検出は開花状態や生育・収量推定に関わる植物器官の表現型取得であり、手法が研究の中心である。

abstractan improved YO-AFD method based on YOLOv8 for apple flower detection was proposed.

FloPE: Flower Pose Estimation for Precision Pollination →

This study presents Flower Pose Estimation (FloPE), a real-time flower pose estimation framework for computationally constrained robotic pollination systems. Robotic pollination has been proposed to supplement natural pollination to ensure global food security due to the decreased population of natural pollinators. However, flower pose estimation for pollination is challenging due to natural variability, flower clusters, and high accuracy demands due to the flowers' fragility when pollinating. This method leverages 3D Gaussian Splatting to generate photorealistic synthetic datasets with precise pose annotations, enabling effective knowledge distillation from a high-capacity teacher model to a lightweight student model for efficient inference. The approach was evaluated on both single and multi-arm robotic platforms, achieving a mean pose estimation error of 0.6 cm and 19.14 degrees within a low computational cost. Our experiments validate the effectiveness of FloPE, achieving up to 78.75% pollination success rate and outperforming prior robotic pollination techniques.

Why it matches plant phenotyping methods花の姿勢という植物器官の形態的状態を推定する画像・計算手法を開発し、ロボット実機で性能検証しており、フェノタイピング手法が中心である。

abstractThis study presents Flower Pose Estimation (FloPE), a real-time flower pose estimation framework for computationally constrained robotic pollination systems.

Unveiling Nature’s Architecture: Geometric Morphometrics as an Analytical Tool in Plant Biology →

Geometric morphometrics (GMM) is an advanced morphometric method enabling quantitative analysis of shape and size variations in biological structures. Through high-resolution imaging and mathematical algorithms, GMM provides valuable insights into taxonomy, ecology, and evolution, making it increasingly relevant in plant science. This review synthesizes the existing literature and explores methodological details, research questions, and future directions, establishing a strong foundation for further study in plant biology. Following PRISMA 2020 guidelines, a rigorous literature search finally identified 83 studies for review. The review organized data on plant species, organs studied, GMM objectives, and methodological aspects, such as imaging and landmark positioning. Leaf and flower structures emerged as the most frequently analyzed organs, primarily in studies of shape variations. This review assesses the use of GMM in plant sciences, identifying knowledge gaps and inconsistencies, and suggesting areas for future research. By highlighting unaddressed topics and emerging trends, the review aims to guide researchers towards methodological challenges and innovations necessary for advancing the field.

Why it matches plant phenotyping methods植物器官の形状・サイズを画像と幾何学的形態計測で定量化する手法を中心に、植物科学での利用法と方法論的課題を体系的にレビューしている。

abstractGeometric morphometrics (GMM) is an advanced morphometric method enabling quantitative analysis of shape and size variations in biological structures.

Local Topological Structures and Global Connectivity Patterns in a Trachelospermum jasminoides: a Pilot Study →

Topological approaches to biological systems provide insights into their growth patterns, network connectivity and spatial organization. This perspective explores how biological structures self-organize, maintain stability and adapt to environmental constraints, revealing fundamental principles of efficiency, robustness, resilience and functional optimization. In this pilot study, we analysed the local and global topological properties of a Trachelospermum jasminoides bush (commonly known as star jasmine) using persistent homology, graph theory, spectral analysis and percolation theory. The spatial positions of individual flowers were extracted from an image of the bush and represented as a point cloud to capture their structural distribution and spatial relationships. Using Delaunay triangulation, a connectivity graph revealed a dominant connected component with minimal isolated structures. DBSCAN analysis identified a large number of small, localized clusters, reflecting biological and environmental influences. Most flowers connected to five to six neighbours, forming a uniform network with high clustering. Shortest path analysis showed efficient long-range connectivity, with paths avoiding sparse regions. Spectral analysis indicated smooth percolation without bottlenecks, while percolation analysis simulations revealed resilience up to 18% flower removal, after which connectivity broke down. In sum, we showed that the star jasmine bush topology balances local structural constraints with global connectivity, ensuring efficient resource distribution and structural integrity. By integrating topological data analysis with ecological modeling, we suggested a methodological approach to understanding natural growth networks. These insights can inform broader studies on biological pattern formation, network resilience and plant architecture modeling in ecology, agricultural sciences and biomimetic design.

Why it matches plant phenotyping methods画像から花の空間的位置を抽出し、植物構造・連結性を定量化する計算手法を中心に扱っているため、植物形態・構造のフェノタイピング手法として収載する。

abstractThe spatial positions of individual flowers were extracted from an image of the bush and represented as a point cloud to capture their structural distribution and spatial relationships.

Confocal Live Imaging of Reproductive Organs Development in Arabidopsis . →

Understanding how multicellular organisms are shaped requires high-resolution, quantitative data to unravel how biological structures grow and develop over time. In recent years, confocal live imaging has become an essential tool providing insights into developmental dynamics at cellular resolution in plant organs such as leaves or meristems. In the context of flowers, growth tracking has primarily been limited to sepals, the outermost floral organs, or the post-fertilization gynoecium, which are easily accessible for microscopy. Here, we describe a detailed pipeline for the preparation, dissection, and confocal imaging of the development of internal reproductive floral organs of Arabidopsis thaliana including both the stamen and gynoecium. We also discuss how to acquire high-quality images suitable for efficient 2D and 3D segmentation that allow the quantification of cellular dynamics underlying their development. Key features • Fine dissection of tiny and tightly enclosed floral organs. • Confocal live imaging method allowing long-term observation of plant reproductive morphogenesis. • Assessing the quality of acquired images for efficient segmentation at cellular resolution in 2D and 3D.

Why it matches plant phenotyping methods植物の生殖器官を対象とした共焦点ライブイメージングと、2D/3Dセグメンテーションによる細胞動態定量化の実験・解析パイプラインが中心であり、植物表現型取得法の開発に該当する。

abstractHere, we describe a detailed pipeline for the preparation, dissection, and confocal imaging of the development of internal reproductive floral organs of Arabidopsis thaliana including both the stamen and gynoecium.

Estimating optimal crop-load for individual branches in apple tree canopies using YOLOv8 →

Shortage of labor in fruit crop production has become a significant challenge in recent years. Therefore, mechanized and automated machines have emerged as promising alternatives to labor-intensive orchard operations such as harvesting, pruning, and thinning. One of the key aspects of the automated machines in accomplishing these tasks is their ability to identify tree canopy parts such as trunk and branches and estimate their geometric and topological parameters such as branch diameter, branch length, branch angles, and spacing between branches. By utilizing geometric parameters such as branch diameter, length, and orientation, researchers then can develop automated pruning and thinning systems that make more effective decisions to achieve optimal fruit yield and quality by accurately estimating the desired crop-load. In this study, we propose a machine vision system for estimating one of the canopy parameters in apple orchards: branch diameter. This parameter was used to estimate the optimal number of fruit that individual branches could bear in a commercial orchard, which provides a basis for robotic pruning, flower thinning, and fruitlet thinning so that desired fruit yield and quality could be achieved. Utilizing color and depth information collected with an RGB-D sensor (Azure Kinect DK, Microsoft, Redmond, WA), a YOLOv8-based instance segmentation technique was developed to identify trunks and branches of apple trees in the dormant season. We then applied a Principal Component Analysis (PCA) technique to estimate branch orientation, which was subsequently utilized to estimate branch diameter. The estimated branch diameter was used to calculate the Limb Cross Sectional Area (LCSA), which was then used to estimate optimal crop-load, as a larger LCSA indicates a higher potential fruit-bearing capacity of the branch. With this approach, Root Mean Squared Error (RMSE) for branch diameter estimation was calculated to be 2.06 mm (relative RMSE 10.82%) and the same for crop-load estimation (Number of fruits per branch) to be 3.93 (relative RMSE 22.25%). Our study demonstrated a promising workflow with a high level of performance in identifying and sizing branches of apple trees in a dynamic orchard environment and integrating farm management practices into automated decision-making for optimizing crop-load in apple orchards.

Why it matches plant phenotyping methodsRGB-D画像とYOLOv8・PCAを用いてリンゴ枝径および枝ごとの作物負荷を推定する手法を開発・評価しており、植物形質の取得が中心です。

abstractIn this study, we propose a machine vision system for estimating one of the canopy parameters in apple orchards: branch diameter.

Integrated of Hyperspectral Imaging and Machine Learning Algorithms for Nondestructive Detection of Therapeutic Properties of Plants. →

The approaches used to determine the medicinal properties of the plants are often destructive, labor-intensive, time-consuming, and expensive, making it impossible to analyze their quality analysis online. Performance of hyperspectral imaging (HSI) integrated with intelligent techniques to overcome these problems was investigated in this research. For this purpose, three classification methods-support vector machine, random forest (RF), and extreme gradient boosting-were studied for the classification of plants in three classes of medicinal, edible, and ornamental for the organs of leaf, stem, flower, and root. The medicinal effects of the plant organs were determined by measuring different biochemical properties of the organs. The spectral reflectance of the samples was used to train and test the classification methods in which output targets were the plant types. The results showed that amounts of the biochemical factors except oil content of the medicinal plants were higher than the other types of plants. Further, the biochemical factors of flowers and leaves were higher than the other organs indicating that the most therapeutic effect of the plants is through the flowers and leaves. Using HSI, a similar spectral trend was appeared in each organ, whereas it was different among the organs. Using the RF as the best method (precision and accuracy were higher than 0.95), the lowest misclassification rates were related to the stem and leaf datasets, indicating that these two organs were most suitable to classify the plants aromatically. The most misclassifications of the organs were occurred between medicinal and edible plants related to the spectra having higher correlations with flavonoid, phenol, and antioxidant compounds. Overall, the misclassification rates were negligible, and thus, the methods developed in this study can be used online in postharvest processes of the medicinal plants.

Why it matches plant phenotyping methods植物器官の生化学的・機能的特性を非破壊HSIと機械学習で推定・分類する手法の開発が研究の中心であり、単なる生物学的実験のルーチン測定ではない。

abstractPerformance of hyperspectral imaging (HSI) integrated with intelligent techniques to overcome these problems was investigated in this research.

CottonSense: A High-Throughput Field Phenotyping System for Cotton Fruit Segmentation and Enumeration aon Edge Devices →

High-throughput phenotyping (HTP) has become a powerful tool for gaining insights into the genetic and environmental factors that affect cotton (Gossypium spp.) growth and yield. With the recent advances in the field of computer vision, namely the integration of deep learning algorithms, the accuracy and efficiency of HTP systems have improved dramatically, enabling them to automatically quantify such fundamental phenotypic traits as fruit identification and enumeration. However, there is currently no HTP system available for counting all the reproductive phases of cotton crop that can be deployed in agronomic field conditions throughout the growing season. This study presents CottonSense, an advanced HTP system that overcomes the challenges of deployment across multiple growth periods by effectively segmenting and enumerating cotton fruits at four stages of growth, including square, flower, closed boll, and open boll. Consequently, CottonSense enhances agronomic management through increased opportunities for data collection and analysis. Using RGB-D cameras, it captures and processes both two and three-dimensional data, facilitating a wider range of phenotypic trait extractions such as crop biomass and plant architecture. To segment the cotton fruits, a Mask-RCNN model is trained and optimized for faster inference using TensorRT. The model yields an average AP score of 79% in segmentation across the four fruit categories. Moreover, the model's accuracy in estimating total fruit count per image is validated by a strong agreement with the counts given by ten domain experts, as reflected by an R² value of 0.94. Furthermore, to accurately count the segmented fruits over large populations of plants, an enumeration algorithm based on a tracking strategy is developed that achieves an R² value of 0.93 when compared to hand-counted fruits in the field. The proposed HTP system, which is implemented entirely on an edge computing device, is cost-effective and power-efficient, making it an effective tool for high-yield cotton breeding and crop improvement. The code for CottonSense is publicly available at https://github.com/FeriBolour/CottonSense.

Why it matches plant phenotyping methods綿花の果実を画像から分割・計数する高スループット表現型計測システムを開発し、専門家および手作業計数で検証しているため、方法が研究の中心である。

abstractThis study presents CottonSense, an advanced HTP system that overcomes the challenges of deployment across multiple growth periods by effectively segmenting and enumerating cotton fruits at four stages of growth, including square, flower, closed boll, and open boll.

Differential scanning calorimetry: a novel approach to study spring frost tolerance in pome tree floral tissues →

Spring frosts occur in many pome fruit-producing regions globally. They are highly detrimental to floral tissues and yield, making frost tolerance of the reproductive organs one of the major breeding challenges. Currently, frost tolerance of flowers and floral buds is determined by meticulous observations of frost damage symptoms, or by methods that relate the damage with the accumulation of physiologically-relevant biochemicals. These methods are often inaccurate and are only feasible in instances of severe frost. We propose differential scanning calorimetry (DSC) to assess the frost tolerance of pome fruit floral tissues by measuring the heat flow of tissue samples when passing the freezing transition. DSC was applied to floral organs isolated from recently open king flowers of the apple 'Jonagold' (Malus domestica Borkh.) and the European pear 'Conference' (Pyrus communis L.) to simulate frost and determine freezing temperature as a quantitative indicator of frost tolerance. Freezing, crystallization, and melting points were measured by cooling and heating isolated ovules, stamens, and stigmas of mature king flowers from 20 to −40 °C and back to 20 °C. In pear, tissue-specific effects were observed, with ovules showing the highest (−9.6 °C) and stamens showing the lowest average freezing temperature (−13.1 °C), indicating that stamens are less susceptible to frost. In contrast, no significant differences in frost tolerance were detected among apple organs (freezing temperature of −11.1 °C). This study shows that DSC is an efficient method for monitoring and evaluating frost tolerance in pome fruit floral tissues and could be utilized for high-throughput phenotyping in breeding programs.

Why it matches plant phenotyping methodsDSCによる花器官の凍結温度測定を、霜害耐性の定量的な表現型取得法として提案・評価しており、方法開発と検証が中心である。

abstractWe propose differential scanning calorimetry (DSC) to assess the frost tolerance of pome fruit floral tissues by measuring the heat flow of tissue samples when passing the freezing transition.

A Protocol for Live Imaging of Arabidopsis Gynoecium Development Using Confocal Microscopy. →

During the Arabidopsis reproductive process, the female whorl of the flower, known as the gynoecium, passes seven of the 20 floral stages during its development. In each of these seven stages, specific developmental events occur, ranging from gynoecium primordium establishment to complex tissue and organ differentiation. Studying gynoecium development is important for its role in fruit and seed formation. Currently, there are many Arabidopsis lines with fluorescent proteins that provide relevant information on gynoecium patterning. However, the fluorescence of some proteins is affected during the steps of histological techniques. Furthermore, the complexity of gynoecium development makes live imaging difficult in the early stages and medial tissues. To address these issues at hand, we describe a methodology that facilitates the analysis of the fluorescent signal during gynoecium development, using as an example the pMIR164c::VENUS line.

Why it matches plant phenotyping methodsシロイヌナズナ雌ずいの発生を対象に、蛍光シグナルを生体で取得・解析する共焦点ライブイメージング法そのものを開発・提示しており、植物表現型取得が中心である。

titleA Protocol for Live Imaging of Arabidopsis Gynoecium Development Using Confocal Microscopy.

Staining Methods for Visualization of Cellular Damage During Petal Abscission. →

Petal abscission involves cell death and reactive oxygen species (ROS) accumulation in the cells at the base of petals. Visualizing changes in the properties of these cells is crucial for analyzing and understanding petal abscission, a trait with important implications, especially for ornamental flower crops. This protocol describes the guidelines, experimental setups, and conditions for visualizing cell death by trypan blue staining and ROS accumulation by 3,3'-diaminobenzidine (DAB) staining in petals. Additionally, it provides instructions for staining and sectioning the entire Arabidopsis thaliana flower to give an improved view of the cells crucial for abscission. This protocol can be used to study the mechanism of petal abscission, including temporal changes at the base of petals during abscission and comparisons with mutants. Although Arabidopsis thaliana and cherry (Prunus sp.) blossoms are used as examples here, this protocol can easily be adapted for other plant species.

Why it matches plant phenotyping methods花弁離脱に関連する細胞死とROS蓄積を可視化する染色プロトコルが研究の中心であり、植物の状態を測定する方法として実質的に記述されている。

abstractThis protocol describes the guidelines, experimental setups, and conditions for visualizing cell death by trypan blue staining and ROS accumulation by 3,3'-diaminobenzidine (DAB) staining in petals.

HACDRAN : A Novel Hybrid Atrous Convolution Model With Densenet and Residual Attenuation Network for Multi‐Plant Leaf Disease Classification →

ABSTRACT The beneficiation of the plant is majorly crucial for both the environment and human life. The crops do trouble from disorders like other species. Various plant leaf disorders happen and trouble the general growth of the crop. These crop leaf disorders are troubles the entire plant consisting flower, root, stem, and leaf. The plant leaf disorders are mostly not taken care of by the farmers so that the crop dies or can create the cause of fruits, flowers and leave a drop. Significant detection of these disorders is essential for detecting and takes preventive measures of plant leaf disorders. The research of plant leaf disorders, procedures, and their causes for handling and managing is known as plant pathology. However, the conventional model encloses the involvement of humans in the identification and categorization of crop leaf disorders. This approach is expensive and consumes more time. It is highly essential to design a new multi‐plant leaf disorder categorization model to tackle the above‐mentioned complexities. At first, the multi‐plant leaf pictures are obtained from online sources and they are offered to the abnormality segmentation phase. Here, the abnormality presented in the multi‐plant leaf image is segmented by adaptive TransUNet, where the parameters are optimized by the developed Mean Position of Sheep Flock and Cuckoo Search (MPSFCS). Further, the abnormality segmented images are offered to the multi‐plant leaf disease classification phase. In this phase, the multi‐plant leaf disorders are categorized by utilizing Hybrid Atrous Convolution based Networks of DenseNet and Residual Attenuation Network (HACDRAN), and their parameters are optimized by the developed MPSFCS to offer effective multi‐plant leaf disease classified outcome. Thus, the developed multi‐plant leaf disease classification model provides a better functionality rate than the conventional methods with multiple analyses.

Why it matches plant phenotyping methods植物葉の画像から病変をセグメンテーションし、病害分類する画像解析手法の開発が中心であり、感染植物の病態を直接評価するため採用。

abstractthe abnormality presented in the multi‐plant leaf image is segmented by adaptive TransUNet

Optimizing Visualization of Pollen Tubes in Wheat Pistils. →

Successful pollination and fertilization are crucial for grain setting in cereals. Wheat is an allohexaploid autogamous species. Due to its evolutionary history, the genetic diversity of current bread wheat ( Triticum aestivum ) cultivars is limited. Introducing favorable alleles from related wild and cultivated wheat species is a promising breeding strategy for resolving this issue. However, wide hybridization between bread wheat and its relatives is hampered by the presence of suppressor genes and difficulties in crossing. Optimized methods for observing pollen tubes are essential for understanding the mechanism of crossability between wheat and its relatives. Here, we improved the crossing procedure between bread wheat and rye ( Secale cereale ) and established an optimized protocol for visualizing pollen tube behavior. Crossing via detached spike culture significantly enhanced crossing efficiency and phenotypic stability. A combination of canonical aniline blue staining and optimized clearing and sectioning allowed us to visualize pollen tube behavior. The proportion of rye pollen tubes reaching the micropyle was lower than that for pollen tubes germinated on the stigmatic hair, explaining why the hybrid seed-setting rate was approximately 75% instead of 100%. This method sheds light on wide hybridization through deeper visualization of the insides of pistils.

Why it matches plant phenotyping methodsコムギ雌ずい内の花粉管挙動を可視化する染色・透明化・切片化手法の最適化が研究の中心であり、植物の生殖状態を測定する実質的な表現型取得法に該当する。

abstractOptimized methods for observing pollen tubes are essential for understanding the mechanism of crossability between wheat and its relatives.

Real-Time Multi-View Flower Counting with a Ground Mobile Robot →

Although season-long cotton flower counts have value to breeders and growers, a manual data collection process is too laborious to be practical in most cases. In recent years, several fully automated flower counting approaches have been proposed. However, such approaches are typically designed to run offline and require a significant amount of computation. Furthermore, little thought has gone into developing convenient interfaces and integrations so that a layperson can use such systems without extensive training. The goal of this study is to develop a lightweight flower tracking system that is deployable on a ground robot and can operate in real-time. We modify a previous GCNNMatch++ approach to increase the inference speed. Additionally, we fuse data from multiple cameras in order to avoid canopy occlusions, and extract three-dimensional flower locations by integrating GPS data from the robot. We show that our approach significantly outperforms UAV-based counting and single-camera counting while running at above 40 FPS on an edge device, achieving a counting error of 15% and an average localization error of 19 cm. This level of performance is enough to observe significant differences in flowering behavior between genotypes. Overall, we believe that our highly-integrated, automated, and simplified flower counting solution makes significant strides towards a practical commercial cotton phenotyping platform.

Why it matches plant phenotyping methodsリアルタイムの花数・三次元位置推定を行う画像解析・ロボット統合手法を開発し、精度と処理速度を評価した綿花フェノタイピング研究であり、方法が中心である。

abstractThe goal of this study is to develop a lightweight flower tracking system that is deployable on a ground robot and can operate in real-time.

Persephone’s Flower: Ecology and Development of Lathraea squamaria (Orobanchaceae), an Unusual Root Holoparasitic Plant →

The hidden lifestyle of the holoparasitic perennial Lathraea squamaria L. (common toothwort), which parasitizes the roots of deciduous trees in forests and woodlands, has led to significant knowledge gaps about the mechanisms underlying this plant symbiotic interaction. Here we present the first detailed structural examination of the interface between L. squamaria and its host root belowground using non-destructive micro-computed tomography (micro-CT). To clarify the physiology of seed germination in this elusive species, we demonstrated efficient in vitro germination of L. squamaria seeds. The terminology for the gross morphology and micromorphology of L. squamaria has been revised, and clear microscopic evidence for several previously described structures (e.g., prehaustoria, haustoria, seeds, elaiosomes, nectaries, and pollen) has been provided. Generally, this research aims to deepen our understanding of parasitic interactions, phenology, as well as the ecological significance of L. squamaria and its biotic associates (e.g., feeders and pollinators) within forest ecosystems.

Why it matches plant phenotyping methods非破壊マイクロCTを用いて寄生植物と宿主根の界面構造を詳細に可視化しており、植物の形態・構造状態の取得が研究の中心的手法の一つである。

abstractHere we present the first detailed structural examination of the interface between L. squamaria and its host root belowground using non-destructive micro-computed tomography (micro-CT).

Three-dimensional tracking of organ development in live plants based on plasma membrane dyes at single-cell resolution. →

Plant developmental biology necessitates precise three-dimensional (3D) tracking of dynamic processes in live plants, and the 3D imaging technique in developmental bioimaging requires suitable fluorophores to achieve single-cell resolution imaging. Herein, we have designed a series of plasma membrane fluorescent dyes with a number of excellent properties and established a single-cell resolution imaging tool based on these dyes for three-dimensional imaging of various tissues and organs in living plants. The designed plasma membrane fluorescent dyes not only have the advantages of rapid wash-free staining, highly specific targeting, high brightness and high contrast imaging, ultralong imaging time and low biotoxicity, but also effectively avoid the autofluorescence interference of chlorophyll in cells, allowing for the development of a three-dimensional imaging approach of living plant organs with single-cell resolution. The three-dimensional histological structures of various organs of adult Arabidopsis thaliana, including roots, leaves, flowers, and fruits, were successfully reconstructed with single-cell resolution using this model plant. Furthermore, the 3D imaging method was employed to track the dynamic changes in tissue and organ morphology at the single-cell level during key plant developmental processes, including seed germination, root development, leaf growth, and anther development.

Why it matches plant phenotyping methods植物器官の3D形態を単一細胞解像度で取得・追跡する蛍光イメージング手法と色素を開発し、複数の器官・発生過程で実証しており、表現型取得法が研究の中心です。

abstractestablished a single-cell resolution imaging tool based on these dyes for three-dimensional imaging of various tissues and organs in living plants

Extracting flowering phenology from grassland species mixtures using time-lapse cameras →

Understanding the impacts of climate change on plant phenology is crucial for predicting ecosystem responses. However, accurately tracking the flowering phenology of individual plant species in grassland species mixtures is challenging, hindering our ability to study the impacts of biotic and abiotic factors on plant reproduction and plant-pollinator interactions. Here, we present a workflow for extracting flowering phenology from grassland species mixtures using near-surface time-lapse cameras. We used 89 image series acquired in plots with known species composition at the Jena trait-based experiment (Germany) to develop random forest classifiers, which were used to classify images and compute time series of flower cover for each species. The high temporal resolution of time-lapse cameras allowed to select images in proper light conditions, and to extract vegetation indices and texture metrics to improve discrimination among flowering species. The random forest classifiers showed a high accuracy in predicting the cover of Leucanthemum vulgare, Ranunculus acris, and Knautia arvensis flowers, whereas graminoid flowers were harder to predict due to their green-to-brownish colours. The proposed workflow can be applied in climate change studies, ecosystem functioning, plant community ecology, and biodiversity change research, including the investigation of effects of species richness on individual species' flowering phenology. Our method could be a valuable tool for understanding the impacts of climate change on plant reproduction and ecosystem dynamics.

Why it matches plant phenotyping methods近接タイムラプス画像とランダムフォレストを用いて、種別の花被覆率および開花フェノロジーを抽出するワークフローを開発しており、植物形質取得法が研究の中心である。

abstractHere, we present a workflow for extracting flowering phenology from grassland species mixtures using near-surface time-lapse cameras.

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

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

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

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

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

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

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

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

AgRegNet: A deep regression network for flower and fruit density estimation, localization, and counting in orchards →

One of the major challenges for the agricultural industry today is the uncertainty in manual labor availability and the associated cost. Automated flower and fruit density estimation, localization, and counting could help streamline harvesting, yield estimation, and crop-load management strategies such as flower and fruitlet thinning. This article proposes a deep regression-based network, AgRegNet, to estimate density, count, and location of flower and fruit in tree fruit canopies without explicit detection or polygon annotation. Inspired by popular U-Net architecture, AgRegNet is a U-shaped network with an encoder-to-decoder skip connection and modified ConvNeXt-T as an encoder feature extractor. AgRegNet can be trained based on information from point annotation and leverages segmentation information and attention modules (spatial and channel) to highlight relevant flower and fruit features while suppressing non-relevant background features. Experimental evaluation in apple flower and fruit canopy images under an unstructured orchard environment showed that AgRegNet achieved promising accuracy as measured by Structural Similarity Index (SSIM), percentage Mean Absolute Error (pMAE) and mean Average Precision (mAP) to estimate flower and fruit density, count, and centroid location, respectively. Specifically, the SSIM, pMAE, and mAP values for flower images were 0.938, 13.7%, and 0.81, respectively. For fruit images, the corresponding values were 0.910, 5.6%, and 0.93. Since the proposed approach relies on information from point annotation, it is suitable for sparsely and densely located objects. This simplified technique will be highly applicable for growers to accurately estimate yields and decide on optimal chemical and mechanical flower thinning practices.

Why it matches plant phenotyping methods花および果実の密度・個数・位置を画像から推定する深層学習手法を提案し、実画像で性能評価しており、植物表現型取得法が研究の中心である。

abstractThis article proposes a deep regression-based network, AgRegNet, to estimate density, count, and location of flower and fruit in tree fruit canopies without explicit detection or polygon annotation.

Fast and High-Resolution Imaging of Pollinated Stigmatic Cells by Tabletop Scanning Electron Microscopy. →

In plants, the first interaction between the pollen grain and the epidermal cells of the stigma is crucial for successful reproduction. When the pollen is accepted, it germinates, producing a tube that transports the two sperm cells to the ovules for fertilization. Confocal microscopy has been used to characterize the behavior of stigmatic cells post-pollination [1], but it is time-consuming since it requires the development of a range of fluorescent marker lines. Here, we propose a quick, high-resolution imaging protocol using tabletop scanning electron microscopy. This technique does not require prior sample fixation or fluorescent marker lines. It effectively captures pollen grain behavior from early hydration (a few minutes after pollination) to pollen tube growth within the stigma (1 h after pollination) and is particularly efficient for tracking pollen tube paths. Key features • Analysis of the pollen behavior in stigmatic cells of Arabidopsis thaliana but can be broadly used for other species. • Rapid and high-resolution imaging method. • Allows testing pollen grain hydration states, pollen tube paths on stigmatic cells from various genetic backgrounds, and also pollen tube phenotypes.

Why it matches plant phenotyping methods卓上走査電子顕微鏡を用いて花粉挙動、花粉管経路、花粉管表現型を取得する高速・高解像度イメージングプロトコルが研究の中心であり、植物表現型計測法の開発に該当する。

abstractHere, we propose a quick, high-resolution imaging protocol using tabletop scanning electron microscopy.

Rose Plant Leaf Disease Recognition Using Machine Learning Methodologies →

The most popular flowers in the world are roses, not only cheer people up but also support livelihoods. Diseases, however, can harm these priceless flowers' health and negatively affect both their quality and the growers' livelihoods. The increased occurrence of ailments in rose plants poses a severe danger to the ornamental flower industry and agricultural productivity. In this paper, we describe a novel deep learning-based method for the automated diagnosis of leaf diseases in rose plants. A big dataset containing images of both healthy and damaged rose leaves was carefully picked to illustrate different disease types and stages. To analyze and identify the visual characteristics that correspond to various illnesses, we used a Convolutional Neural Network architecture, Support Vector Machine, and K-Nearest Neighbors architectures specifically intended for picture classification tasks. We address the interpretability and explainability of the model's predictions in addition to performance indicators, offering insights into the decision-making process. This work addresses a fundamental requirement for effective and long-lasting disease management in rose cultivation by bridging the gap between deep learning and plant pathology. CNNs are often the preferred choice due to their ability to automatically learn relevant features from raw pixel values.

Why it matches plant phenotyping methodsバラ葉の画像から病害状態を自動診断する画像解析・機械学習手法が研究の中心であり、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含める。

abstractwe describe a novel deep learning-based method for the automated diagnosis of leaf diseases in rose plants.

Calculation Method Based on Flower Petal Area and Other Plant Leaf Spot Area →

In order to calculate the area of irregular shapes such as plant leaves and diseased spots or flower petals, this paper presents a new method to calculate them by using flood fill algorithm, HSV color space, improved k-means algorithm and morphological operation. First, 501 butterfly petal images and pathological leaf images of Bauhinia and phyllotaxus were collected, and then flood was used Fill algorithm selects the disease-free area and records the selected pixel value. HSV color space conversion is applied to the image to facilitate the segmentation of leaves. Then, the improved k-means algorithm is used to extract the binary image of leaves and record the pixel value of the outer contour with morphological closed operation. Finally, the proportion and truth of the disease spots of plant leaves are obtained by calculating the pixel value and the real value of the rectangle in the sampling area Real area. Compared with the results of artificial labeling, the average accuracy of petal area and lesion area of Phalaenopsis was 96.3% and 96.61%, respectively. It can be seen that the program can calculate the area of irregular shape of plant surface accurately. In conclusion, this method can replace the artificial grid method to calculate the information of plant leaf area and disease proportion, and effectively reduce the work intensity of experimental personnel.

Why it matches plant phenotyping methods植物の葉面積・花弁面積・病斑面積を画像から抽出する手法を開発し、人工ラベリングと比較検証しており、表現型取得手法が研究の中心です。

abstractthis paper presents a new method to calculate them by using flood fill algorithm, HSV color space, improved k-means algorithm and morphological operation.

Detection of color phenotype in strawberry germplasm resources based on field robot and semantic segmentation →

Strawberry holds significant economic value, but the laborious and time-consuming process of evaluating phenotypic traits in numerous germplasm resources during breeding poses a challenge. Prior studies relied on manual image collection within a single laboratory background, making it difficult to achieve automatic image collection and precise segmentation in complex field environments. However, accurate segmentation of plant organs is crucial for reliable phenotyping. In this research, we collected strawberry images at three growth stages (vegetative, flowering, and fruiting) using mobile phones and a high-resolution industrial camera mounted on our self-developed robot. Next, we designed an improved semantic segmentation model specifically tailored for strawberry plants, named Strawberry Segment Model (SSM), based on the Segment Anything Model. To address the uneven sample distribution problem, we enhanced the loss function and introduced a multi-loss approach combined with the class weight, resulting in improved detection performance. The comparative results demonstrated that SSM achieved state-of-the-art segmentation performance on the mobile phone image set, with a mean Intersection over Union (mIoU) of 80.20 %. We updated the model for the industrial camera on the robot, and achieved 75.81 % mIoU with only 10 % of the new data, striking a balance between performance and cost. Additionally, we mitigated uneven illumination using the Contrast Limited Adaptive Histogram Equalization and employed a Support Vector Machine model to classify 90 germplasm resources. The accuracy rates were 100 % for leaves and flowers, and 92.59 % for fruits. Overall, this study introduces novel equipment and methods for automated phenotypic analysis, supporting breeding investigations.

Why it matches plant phenotyping methodsイチゴの生殖質を対象に、ロボット搭載カメラによる画像取得、器官セグメンテーション、色表現型の分類を開発・評価しており、表現型取得手法が研究の中心である。

titleDetection of color phenotype in strawberry germplasm resources based on field robot and semantic segmentation

Shedding light on pollination deficits: Cueing into plant spectral reflectance signatures to monitor pollination delivery across landscapes →

Abstract Pollination underlies plant yield, health and reproductive success in agricultural and natural systems worldwide. It is therefore concerning that declining animal pollinator populations compounded by growing demands for food are leading to rising pollination deficits, with globally significant economic and environmental implications. Despite this urgent issue, accurate and scalable tools to quantify and track pollination across useful spatiotemporal scales are lacking. Here, we propose to shed new light on pollination deficits, looking to remote sensing platforms as a transformative mapping and monitoring tool and a solution for pollinator conservation and crop management. Providing a synthesis of our current understanding of pollination‐triggered floral senescence and underlying ultrastructural and metabolic changes, we propose how spectral reflectance technologies could be applied to accurately detect pollination events in real‐time and at the landscape scale. Synthesis and applications : We highlight where research efforts can be targeted to produce scalable methods for identifying field‐relevant bioindicators of pollination. We provide guidance on how spectral imaging accompanied by machine learning and coupled with autonomous operation technologies will enable applications to detect pollination delivery across complex landscapes. Ultimately, such an ecological application will transform our quantitative understanding of pollination services and, by directly linking plant yields and health, will reveal pollination deficits at high resolution to help mitigate risks to food security and ecosystem functioning.

Why it matches plant phenotyping methods植物の受粉状態をスペクトル反射で検出・定量する方法のレビューおよび応用指針であり、植物状態の取得技術が中心。

abstractWe provide guidance on how spectral imaging accompanied by machine learning and coupled with autonomous operation technologies will enable applications to detect pollination delivery across complex landscapes.

PhenoVision: A framework for automating and delivering research-ready plant phenology data from field images →

Plant phenology plays a fundamental role in shaping ecosystems, and global change-induced shifts in phenology have cascading impacts on species interactions and ecosystem structure and function. Detailed, high-quality observations of when plants undergo seasonal transitions such as leaf-out, flowering, and fruiting are critical for tracking causes and consequences of phenology shifts, but these data are often sparse and biased globally. These data gaps limit broader generalizations and forecasting improvements in the face of continuing disturbance. One solution to closing such gaps is to document phenology on field images taken by public participants. iNaturalist, in particular, provides global scale research-grade data and is expanding rapidly. Here we utilize over 53 million field images of plants and millions of human annotations from iNaturalist – data spanning all angiosperms and drawn from across the globe – to train a computer vision model (PhenoVision) to detect the presence of fruits and flowers. PhenoVision utilizes a vision transformer architecture pretrained with a masked autoencoder to improve classification success, and it achieves high accuracy for flower (98.5%) and fruit presence (95%). Key to producing research-ready phenology data is post-calibration tuning and validation focused on reducing noise inherent in field photographs, and maximizing the true positive rate. We also develop a standardized set of quality metrics and metadata so that results can be used effectively by the community. Finally, we showcase how this effort vastly increases phenology data coverage, including regions of the globe where data have been limited before. Our end products are tuned models, new data resources, and an application streamlining discovery and use of those data for the broader research and management community. We close by discussing next steps, including automating phenology annotations, adding new phenology targets, e.g., leaf phenology, and further integration with other resources to form a global central database integrating all in-situ plant phenology resources.

Why it matches plant phenotyping methods植物の野外画像から開花・結実というフェノロジー形質を推定する画像解析モデルを開発し、校正・検証・品質指標も扱っており、フェノタイピング手法が中心である。

abstractto train a computer vision model (PhenoVision) to detect the presence of fruits and flowers

Improved Multi-Size, Multi-Target and 3D Position Detection Network for Flowering Chinese Cabbage Based on YOLOv8 →

Accurately detecting the maturity and 3D position of flowering Chinese cabbage ( Brassica rapa var. chinensis) in natural environments is vital for autonomous robot harvesting in unstructured farms. The challenge lies in dense planting, small flower buds, similar colors and occlusions. This study proposes a YOLOv8-Improved network integrated with the ByteTrack tracking algorithm to achieve multi-object detection and 3D positioning of flowering Chinese cabbage plants in fields. In this study, C2F-MLCA is created by adding a lightweight Mixed Local Channel Attention (MLCA) with spatial awareness capability to the C2F module of YOLOv8, which improves the extraction of spatial feature information in the backbone network. In addition, a P2 detection layer is added to the neck network, and BiFPN is used instead of PAN to enhance multi-scale feature fusion and small target detection. Wise-IoU in combination with Inner-IoU is adopted as a new loss function to optimize the network for different quality samples and different size bounding boxes. Lastly, ByteTrack is integrated for video tracking, and RGB-D camera depth data are used to estimate cabbage positions. The experimental results show that YOLOv8-Improve achieves a precision ( P ) of 86.5% and a recall ( R ) of 86.0% in detecting the maturity of flowering Chinese cabbage. Among them, mAP50 and mAP75 reach 91.8% and 61.6%, respectively, representing an improvement of 2.9% and 4.7% over the original network. Additionally, the number of parameters is reduced by 25.43%. In summary, the improved YOLOv8 algorithm demonstrates high robustness and real-time detection performance, thereby providing strong technical support for automated harvesting management.

Why it matches plant phenotyping methods開花中国白菜の成熟度という植物状態を画像から検出・推定する改良YOLOv8と3D位置推定手法が研究の中心であり、収穫対象の単なる位置検出を超える。

abstractThis study proposes a YOLOv8-Improved network integrated with the ByteTrack tracking algorithm to achieve multi-object detection and 3D positioning of flowering Chinese cabbage plants in fields.

Integration of Mitoflash and Time-Series Transcriptomics Facilitates Energy Dynamics Tracking and Substrate Supply Analysis of Floral Thermogenesis in Lotus. →

The high biosynthetic and energetic demands of floral thermogenesis render thermogenic plants the ideal systems to characterize energy metabolism in plants, but real-time tracking of energy metabolism in plant cells remains challenging. In this study, a new method was developed for tracking the mitochondrial energy metabolism at the single mitochondria level by real-time imaging of mitochondrial superoxide production (i.e., mitoflash). Using this method, we observed the increased mitoflash frequencies in the receptacles of Nelumbo nucifera Gaertn. at the thermogenic stages. This increase, combined with the higher expression of antioxidant response-related genes identified through time-series transcriptomics at the same stages, shows us a new regulatory mechanism for plant redox balance. Furthermore, we found that the upregulation of respiratory metabolism-related genes during the thermogenic stages not only correlates with changes in mitoflash frequency but also underscores the critical roles of these pathways in ensuring adequate substrate supply for thermogenesis. Metabolite analysis revealed that sugars are likely one of the substrates for thermogenesis and may be transported over long distances by sugar transporters. Taken together, our findings demonstrate that mitoflash is a reliable tool for tracking energy metabolism in thermogenic plants and contributes to our understanding of the regulatory mechanisms underlying floral thermogenesis.

Why it matches plant phenotyping methods植物細胞のミトコンドリアエネルギー代謝をリアルタイム画像化する手法を開発し、熱産生状態の追跡に適用しており、表現型取得法が研究の中心である。

abstracta new method was developed for tracking the mitochondrial energy metabolism at the single mitochondria level by real-time imaging of mitochondrial superoxide production (i.e., mitoflash).

Three-view cotton flower counting through multi-object tracking and RGB-D imagery →

Monitoring the number of cotton flowers can provide important information for breeders to assess the flowering time and the productivity of genotypes because flowering marks the transition from vegetative growth to reproductive growth and impacts the final yield. Traditional manual counting methods are time-consuming and impractical for large-scale fields. To count cotton flowers efficiently and accurately, a multi-view multi-object tracking approach was proposed by using both RGB and depth images collected by three RGB-D cameras fixed on a ground robotic platform. The tracking-by-detection algorithm was employed to track flowers from three views simultaneously and remove duplicated counting from single views. Specifically, an object detection model (YOLOv8) was trained to detect flowers in RGB images and a deep learning-based optical flow model Recurrent All-pairs Field Transforms (RAFT) was used to estimate motion between two adjacent frames. The intersection over union and distance costs were employed to associate flowers in the tracking algorithm. Additionally, tracked flowers were segmented in RGB images and the depth of each flower was obtained from the corresponding depth image. Those flowers tracked with known depth from two side views were then projected onto the middle image coordinate using camera calibration parameters. Finally, a constrained hierarchy clustering algorithm clustered all flowers in the middle image coordinate to remove duplicated counting from three views. The results showed that the mean average precision of trained YOLOv8x was 96.4%. The counting results of the developed method were highly correlated with those counted manually with a coefficient of determination of 0.92. Besides, the mean absolute percentage error of all 25 testing videos was 6.22%. The predicted cumulative flower number of Pima cotton flowers is higher than that of Acala Maxxa, which is consistent with what breeders have observed. Furthermore, the developed method can also obtain the flower number distributions of different genotypes without laborious manual counting in the field. Overall, the three-view approach provides an efficient and effective approach to count cotton flowers from multiple views. By collecting the video data continuously, this method is beneficial for breeders to dissect genetic mechanisms of flowering time with unprecedented spatial and temporal resolution, also providing a means to discern genetic differences in fecundity, the number of flowers that result in harvestable bolls. The code and datasets used in this paper can be accessed on GitHub: https://github.com/UGA-BSAIL/Multi-view_flower_counting.

Why it matches plant phenotyping methodsRGB-Dカメラ、ロボットプラットフォーム、物体追跡、深度投影、重複除去を統合してワタ花数を自動計測する手法を開発・検証しており、植物表現型取得が中心である。

abstractTo count cotton flowers efficiently and accurately, a multi-view multi-object tracking approach was proposed by using both RGB and depth images collected by three RGB-D cameras fixed on a ground robotic platform.

A massive community-science flower color dataset reveals convergent evolution of delayed flowering phenology in North American red-flowering plants →

Summary The radiation of angiosperms is marked by a phenomenal diversity of floral size, shape, color, scent, and reward. Through hundreds of years of documentation and quantification, scientists have sought to make sense of this variation by defining pollination syndromes. These syndromes are the convergent evolution of common suits of floral traits across distantly related species that have evolved by selection to optimize pollination strategies. The availability of community-science datasets provides an opportunity to develop new tools and to examine new traits that may help further characterize broad patterns of flowering plant diversity. Here we test the hypothesis that flowering phenology can also be a pollination syndrome trait. We generate a novel flower color dataset by using GPT-4 with Vision (GPT-4V) to assign flower color to 11,729 North American species. We map these colors to 1,674,908 community-scientist observations of flowering plants to investigate patterns of phenology. We demonstrate constrained flowering time in the eastern United States for plants with red or orange flowers relative to plants with flowers of other colors. Red-and orange-colored flowers are often characteristic of the “hummingbird” pollination syndrome; importantly, the onset of red and orange flowers corresponds to the arrival of migratory hummingbirds. Our results suggest that the hummingbird pollination syndrome can include flowering phenology and reveal an opportunity to expand the suite of traits included in pollination syndromes. Our methods demonstrate an effective pipeline for leveraging enormous amounts of community science data by using artificial intelligence to extract information about patterns of trait variation.

Why it matches plant phenotyping methodsGPT-4Vによる花色という植物形質の大規模抽出と、コミュニティ科学データを用いた再利用可能な解析パイプラインが研究の中心であるため。

abstractWe generate a novel flower color dataset by using GPT-4 with Vision (GPT-4V) to assign flower color to 11,729 North American species.

The Quest for the Sli Locus. →

Genetic gain in potato breeding is limited by the heterozygous tetraploid genome of cultivated potato. Recent efforts to breed potato at the diploid level promise to improve genetic gain and allow more straightforward genetics and introgression breeding. Diploid F1 hybrid potato breeding relies on the ability to create diploid inbred lines via repeated self-fertilization. However, self-fertilization of diploid potato is hampered by a gametophytic self-incompatibility system encoded by the S-locus that prevents fertilization by self-pollen. Nonetheless, self-compatible diploid potato genotypes exist and have been used to create inbred lines. The S-locus inhibitor ( Sli ) gene is a dominant gene that provides strong self-compatibility in diploid potato and was previously mapped to Chromosome 12. While the Sli gene has already been identified and characterized, the most tedious challenge was to develop the optimal phenotyping methods and genetic populations preceding the cloning of this gene. To this end, we developed an effective phenotyping protocol to identify suitable parents and create diploid populations segregating for Sli . We show that an accurate phenotyping method is crucial to discriminate between confounding fertility factors and self-compatibility. In addition, we found that the Sli locus shows extreme segregation distortion on Chromosome 12. Finally, we used these insights to develop three F1 populations that segregate for Sli , which we later used for the identification of the Sli gene. Supplementary information The online version contains supplementary material available at 10.1007/s11540-024-09792-3.

Why it matches plant phenotyping methodsSli遺伝子探索に先立ち、自己適合性を他の稔性要因と識別するための表現型判定プロトコルを開発し、その有効性を集団作製に適用しており、植物表現型取得法が研究の中心である。

abstractthe most tedious challenge was to develop the optimal phenotyping methods and genetic populations preceding the cloning of this gene.

Floral Precision: Investigating Pea (Pisum sativum L.) Flowering with High Throughput Field Phenotyping and Object Detection →

Abstract Background Flowering is one of the most important and sensitive process throughout a plants life as it marks the start of the reproductive phase. Therefore, phenotyping the continuous development of flowering is crucial for crop breeding. For phenotyping, visual ratings have been a standard method for decades, to observe flowering dynamics by determining timepoints, such as start, end or duration. However, high throughput field phenotyping (HTFP) methods have emerged, providing an objective and efficient approach. We developed an approach that allows to collect detailed data not only about pea flowering dynamics, but additionally flower intensity (flowers per area). For this purpose, an object detection model, based on YOLOv8 was trained on RGB-images. The images were automatically acquired by the field phenotyping platform (FIP) of ETH Z¨urich for 12 pea breeding lines over two years. Results The trained model reached high accuracy for open flower detection, which allowed to monitor flower dynamics and intensity over time. Flower intensity throughout the development of the plants was highly correlated (R2= 0.967) to ground truth data taken in the field. Clear differences in timing, intensity of flowering and fruiting efficiency were detected between breeding lines and years. Furthermore, high correlation between maximal flower numbers and yield components such as seed amount were observed. Conclusion This automated, data-driven method of flower detection proved itself as a reliable tool. This is promising for the use of RGB imaging methods to objectively assess not only timing but also flower intensity. Flower intensity allows to predict seed amount and has therefore potential as selection trait in breeding program. In addition, fruiting efficiency could be included in breeding programs.

Why it matches plant phenotyping methodsピー花の開花時期と花数密度をRGB画像および物体検出で推定する手法を開発・検証しており、植物表現型取得が研究の中心である。

abstractWe developed an approach that allows to collect detailed data not only about pea flowering dynamics, but additionally flower intensity (flowers per area).

Deep learning approach for detecting tomato flowers and buds in greenhouses on 3P2R gantry robot. →

In recent years, significant advancements have been made in the field of smart greenhouses, particularly in the application of computer vision and robotics for pollinating flowers. Robotic pollination offers several benefits, including reduced labor requirements and preservation of costly pollen through artificial tomato pollination. However, previous studies have primarily focused on the labeling and detection of tomato flowers alone. Therefore, the objective of this study was to develop a comprehensive methodology for simultaneously labeling, training, and detecting tomato flowers specifically tailored for robotic pollination. To achieve this, transfer learning techniques were employed using well-known models, namely YOLOv5 and the recently introduced YOLOv8, for tomato flower detection. The performance of both models was evaluated using the same image dataset, and a comparison was made based on their Average Precision (AP) scores to determine the superior model. The results indicated that YOLOv8 achieved a higher mean AP (mAP) of 92.6% in tomato flower and bud detection, outperforming YOLOv5 with 91.2%. Notably, YOLOv8 also demonstrated an inference speed of 0.7 ms when considering an image size of 1920 × 1080 pixels resized to 640 × 640 pixels during detection. The image dataset was acquired during both morning and evening periods to minimize the impact of lighting conditions on the detection model. These findings highlight the potential of YOLOv8 for real-time detection of tomato flowers and buds, enabling further estimation of flower blooming peaks and facilitating robotic pollination. In the context of robotic pollination, the study also focuses on the deployment of the proposed detection model on the 3P2R gantry robot. The study introduces a kinematic model and a modified circuit for the gantry robot. The position-based visual servoing method is employed to approach the detected flower during the pollination process. The effectiveness of the proposed visual servoing approach is validated in both un-clustered and clustered plant environments in the laboratory setting. Additionally, this study provides valuable theoretical and practical insights for specialists in the field of greenhouse systems, particularly in the design of flower detection algorithms using computer vision and its deployment in robotic systems used in greenhouses.

Why it matches plant phenotyping methodsトマトの花・蕾という植物器官の状態を画像から検出する手法を開発・比較評価し、ロボットへの実装まで扱っており、単なる生物実験の routine 測定ではなく、表現型取得法が中心である。

abstractThe performance of both models was evaluated using the same image dataset, and a comparison was made based on their Average Precision (AP) scores

Inferring plant community phenology via bee-collected pollen →

ABSTRACT Global climate change is producing novel biospheric conditions, presenting a threat to the stability of ecological systems and the health of the organisms that reside within them. Variation in climatic conditions is expected to facilitate phenological reshuffling within plant communities, impacting the plant-pollinator interface, and the release of allergenic pollen into the atmosphere. Impacts on plant, invertebrate, and human health remain unclear largely due to the variable nature of phenological reshuffling and insufficient monitoring of these trends. Large-scale temporal surveillance of plant community flowering has been difficult in the past due to logistical constraints. To address this, we set out to test if metabarcoding of honey bee collected pollen could be used to infer the phenology of plant communities via comparison to in situ field monitoring. We found that honey bees can accurately indicate the onset of anthesis, but not its duration, in the plant species they selectively forage on. Increasing the number of colonies used to monitor, and employing a multi-locus approach for metabarcoding of pollen, substantially increased the species detection power of our approach. Here, we demonstrate that metabarcoding of honey bee collected pollen can substantively streamline the establishment of long-term phenological monitoring programs to document the on-going consequences of global climate change and its impact on the temporal aspects of plant-pollinator relationships.

Why it matches plant phenotyping methodsハチ採取花粉のメタバーコーディングを用いて植物群集の開花フェノロジーを推定する手法を開発・現地モニタリングと比較検証しており、植物状態の取得方法が研究の中心である。

abstractTo address this, we set out to test if metabarcoding of honey bee collected pollen could be used to infer the phenology of plant communities via comparison to in situ field monitoring.

Field-Based Soybean Flower and Pod Detection Using an Improved YOLOv8-VEW Method →

Changes in soybean flower and pod numbers are important factors affecting soybean yields. Obtaining the number of flowers and pods, as well as fallen flowers and pods, quickly and accurately is crucial for soybean variety breeding and high-quality and high-yielding production. This is especially challenging in the natural field environment. Therefore, this study proposed a field soybean flower- and pod-detection method based on an improved network model (YOLOv8-VEW). VanillaNet is used as the backbone feature-extraction network for YOLOv8, and the EMA attention mechanism module is added to C2f, replacing the CioU function with the WIoU position loss function. The results showed that the F1, mAP, and FPS (frames per second) of the YOLOv8-VEW model were 0.95, 96.9%, and 90 FPS, respectively, which were 0.05, 2.4%, and 24 FPS better than those of the YOLOv8 model. The model was used to compare soybean flower and pod counts with manual counts, and its R2 for flowers and pods was 0.98311 and 0.98926, respectively, achieving rapid detection of soybean flower pods in the field. This study can provide reliable technical support for detecting soybean flowers and pod numbers in the field and selecting high-yielding varieties.

Why it matches plant phenotyping methods圃場画像からダイズの花・莢数を推定するYOLOv8改良法を開発し、手動計数との比較で検証しており、植物形質取得手法が中心である。

abstractTherefore, this study proposed a field soybean flower- and pod-detection method based on an improved network model (YOLOv8-VEW).

Field-level analysis of phenological cycles and dynamics of sunflower (Helianthus annuus L.) and oil seed rape (Brassica napus L.) flowering within various regions of Hungary →

Phenological observations are expensive and demanding in terms of manpower to monitor the vegetation stages. Therefore, satellite products have opened new possibilities for easier and more widespread data collection. Nowadays biomass estimations extensively rely on these tools, given their extensive spatial and temporal coverage, which are defined by indicators such as vegetation indices, which describe the biomass growth, canopy structure, vegetation health and even water management etc. However, the detection of flowering stages through remote sensing is less explored, with fewer established methods available.This study investigates temporal phenological changes during the blooming period of the most widely cultivated oilseed crops in Hungary in 2021, specifically the sunflower (Helianthus annuus L.) and the winter-cultivated oilseed rape (Brassica napus L.). The objective is to characterize the blooming phase and dynamics of these two crop species utilizing various vegetation indexes and satellite-derived products. The investigation is conducted across seven distinct regions, using honey bees as bioindicators of the fields.Methodologies outlined in prior scientific literature, focusing on the analysis of anthesis timing and duration in major nectar-producing crops utilizing Sentinel-1 SAR and Sentinel-2 optical products, serve as the basis for this research. Within each radius study areas, the parcel-averaged and smoothed daily time series were acquired. The estimation of the blooming phases was achieved through parcel smoothing methods using daily non-parametric local regression (loess) approach which showed better performance compared to the Savitzky-Golay (SG) algorithm. In our flowering detection analysis, we also examined the differences in the ascending and descending orbits and their combined results. In the case of oil seed rape, the NDVI index reached its maximum after flowering, while for sunflower it varied. Additionally, we investigated the outcomes of all polarization and method combinations within each crop type.Our study enables the comprehension of temporal flowering patterns in bee pasture crops through the integration of SAR and optical measurements. Additionally, it supports the utilization of beehive scales to provide field-based reference data for estimating anthesis.The research was funded by the National Multidisciplinary Laboratory for Climate Change, RRF-2.3.1-21-2022-00014 project. Project No. 993788 has been implemented with the support provided by the Ministry of Culture and Innovation of Hungary from the National Research, Development and Innovation Fund, financed under the KDP-2020 funding scheme.

Why it matches plant phenotyping methods衛星SAR・光学データから作物の開花時期・期間を推定する手法が中心で、loessとSavitzky–Golay法の性能比較も行っているため、植物フェノタイピング研究に該当する。

abstractThe objective is to characterize the blooming phase and dynamics of these two crop species utilizing various vegetation indexes and satellite-derived products.

Image Processing Analysis of Plant Morphometry with Examples from the Genus Sedum (Crassulaceae). →

The complex systematics of the genus Sedum , the difficulties of its classification and the ambiguity of the concrete identification of the taxa brought about the need to implement a measurement system adaptable to field conditions, so as to facilitate the accuracy of data collection, avoiding the etiolation of samples and, therefore, the deterioration of the morphological structures subject to analysis. Thus, our study describes a digitization of the classic method of making measurements using millimeter paper, thus facilitating the subsequent statistical processing of quantifiable values. Depending on the number of pixels in the photos taken and the pixel/millimeter ratio, a variable measurement scale can be created depending on the size of the analyzed taxomes. The method used adds to the classic taxonomy, which is based on the analysis of morphological characteristics to determine the species of these succulent plants. The applicability of our method is shown by means of the example of an analysis performed on the flowers of the native species of the genus Sedum in the territory of Romania.

Why it matches plant phenotyping methods植物形態計測をデジタル化し、画像のピクセル情報から花の形態を定量化する手法の開発・適用が中心である。

abstractour study describes a digitization of the classic method of making measurements using millimeter paper

Advancing jasmine tea production: YOLOv7-based real-time jasmine flower detection. →

Background To produce jasmine tea of excellent quality, it is crucial to select jasmine flowers at their optimal growth stage during harvesting. However, achieving this goal remains a challenge due to environmental and manual factors. This study addresses this issue by classifying different jasmine flowers based on visual attributes using the YOLOv7 algorithm, one of the most advanced algorithms in convolutional neural networks. Results The mean average precision (mAP value) for detecting jasmine flowers using this model is 0.948, and the accuracy for five different degrees of openness of jasmine flowers, namely small buds, buds, half-open, full-open and wiltered, is 87.7%, 90.3%, 89%, 93.9% and 86.4%, respectively. Meanwhile, other ways of processing the images in the dataset, such as blurring and changing the brightness, also increased the credibility of the algorithm. Conclusion This study shows that it is feasible to use deep learning algorithms for distinguishing jasmine flowers at different growth stages. This study can provide a reference for jasmine production estimation and for the development of intelligent and precise flower-picking applications to reduce flower waste and production costs. © 2024 Society of Chemical Industry.

Why it matches plant phenotyping methodsYOLOv7画像解析を用いてジャスミン花の開花・生育段階を分類する手法が研究の中心であり、花器官の状態という植物形質を直接推定している。

abstractThis study addresses this issue by classifying different jasmine flowers based on visual attributes using the YOLOv7 algorithm

Prediction of cyanidin 3-rutinoside content in Michelia crassipes based on near-infrared spectroscopic techniques. →

Currently the determination of cyanidin 3-rutinoside content in plant petals usually requires chemical assays or high performance liquid chromatography (HPLC), which are time-consuming and laborious. In this study, we aimed to develop a low-cost, high-throughput method to predict cyanidin 3-rutinoside content, and developed a cyanidin 3-rutinoside prediction model using near-infrared (NIR) spectroscopy combined with partial least squares regression (PLSR). We collected spectral data from Michelia crassipes (Magnoliaceae) tepals and used five different preprocessing methods and four variable selection algorithms to calibrate the PLSR model to determine the best prediction model. The results showed that (1) the PLSR model built by combining the blockScale (BS) preprocessing method and the Significance multivariate correlation (sMC) algorithm performed the best; (2) The model has a reliable prediction ability, with a coefficient of determination (R 2 ) of 0.72, a root mean square error (RMSE) of 1.04%, and a residual prediction deviation (RPD) of 2.06. The model can be effectively used to predict the cyanidin 3-rutinoside content of the perianth slices of M. crassipes , providing an efficient method for the rapid determination of cyanidin 3-rutinoside content.

Why it matches plant phenotyping methodsNIR分光とPLSRによる花被片のアントシアニン含量推定法を開発し、前処理・変数選択と予測性能を評価しており、植物形質取得法が研究の中心である。

abstractwe aimed to develop a low-cost, high-throughput method to predict cyanidin 3-rutinoside content

How precisely can x-ray predict the viability of wild flower plant seeds? →

The detection of seed viability is an important step in seed production, as well as in conservation and restoration practice. Due to random natural events, the quality and viability of seeds of wild flowering species vary substantially, and hence a quick and reliable method for seed viability assessment is desirable. X-rays provide information about the internal structures of a seed and therefore show promise for detection of viability and even germination capacity. Seeds of 207 accessions of 176 wild flowering plant species were x-rayed and the viability results were compared with combined germination-TZ test results. Of special interest was whether there are certain plant families for which x-ray is an appropriate method for viability detection, considering correlations with seed internal morphology, seed mass and/or shape. The comparison revealed a strong correspondence between viability determination by combined germination-TZ tests and by x-ray analysis. According to taxonomy and seed type, two main groups could be distinguished, that differed significantly in viability detection by x-ray and combined germination-TZ test. Whereas the evaluation of little/non-endospermic seeds gave approximately identical results, there was greater discrepancy for of endospermic seeds. Seeds of different sizes and shapes were evaluated similarly with both methods. Especially for little/non-endospermic seeds, x-ray can provide a useful and quick tool for viability detection, whereas for endospermic seeds, further research is needed. For the commercial seed industry, viability detection via x-ray should be the first step before further vigour testing is performed.

Why it matches plant phenotyping methods種子の生存性をX線で推定する方法を、207アクセッション・176種で発芽/TZ試験と比較検証しており、植物状態の取得手法が研究の中心である。

abstractSeeds of 207 accessions of 176 wild flowering plant species were x-rayed and the viability results were compared with combined germination-TZ test results.

Pollen Morphology and Variability Among Indian Cultivars of Chrysanthemum morifolium and Comparative Analysis with Genera of the Asteraceae Family →

Abstract This study investigates the pollen morphology of 134 Chrysanthemum morifolium Ramat cultivars through scanning electron microscopy (SEM). Chrysanthemum, a globally significant cut-flower crop, is renowned for its ornamental and medicinal properties. Morphology of a pollen grain, a microscopic flower structure known for being reproductive unit of higher plants was put forth for Scanning Electron Microscopy analysis that revealed diverse Chrysanthemum pollen traits, including shape, size, spine length, spine rows between colpi, ornamentation, and aperture type. Comparative analysis with 14 genera from daisy family, the PalDat database further explains uniqueness of Chrysanthemum in Asteraceae. Statistical analyses, employing cluster and principal component analyses, classify Chrysanthemum cultivars based on their pollen morphological characters. Significant cultivars exhibit distinct outgroups, suggestive of geographic and environmental impacts on evolution. The study suggests the significance of pollen characters, such as length, form index, and equatorial diameter in taxonomy and classification. This study contributes considerations into Chrysanthemum pollen morphology, enhancing knowledge of intrageneric relationships. The conclusions feature the importance of SEM techniques in identifying species based on palynomorphological traits. Future research, encompassing morphological, karyological, and molecular aspects, is recommended for a complete taxonomy of the Chrysanthemum genus.

Why it matches plant phenotyping methodsSEMによる花粉形態の取得と形態形質の定量・分類が研究の中心であり、植物器官の観察可能な形態表現型を扱っている。

abstractthrough scanning electron microscopy (SEM)

Pollinator‐assisted plant phenotyping, selection, and breeding for crop resilience to abiotic stresses →

Food security is threatened by climate change, with heat and drought being the main stresses affecting crop physiology and ecosystem services, such as plant-pollinator interactions. We hypothesize that tracking and ranking pollinators' preferences for flowers under environmental pressure could be used as a marker of plant quality for agricultural breeding to increase crop stress tolerance. Despite increasing relevance of flowers as the most stress sensitive organs, phenotyping platforms aim at identifying traits of resilience by assessing the plant physiological status through remote sensing-assisted vegetative indexes, but find strong bottlenecks in quantifying flower traits and in accurate genotype-to-phenotype prediction. However, as the transport of photoassimilates from leaves (sources) to flowers (sinks) is reduced in low-resilient plants, flowers are better indicators than leaves of plant well-being. Indeed, the chemical composition and amount of pollen and nectar that flowers produce, which ultimately serve as food resources for pollinators, change in response to environmental cues. Therefore, pollinators' preferences could be used as a measure of functional source-to-sink relationships for breeding decisions. To achieve this challenging goal, we propose to develop a pollinator-assisted phenotyping and selection platform for automated quantification of Genotype × Environment × Pollinator interactions through an insect geo-positioning system. Pollinator-assisted selection can be validated by metabolic, transcriptomic, and ionomic traits, and mapping of candidate genes, linking floral and leaf traits, pollinator preferences, plant resilience, and crop productivity. This radical new approach can change the current paradigm of plant phenotyping and find new paths for crop redomestication and breeding assisted by ecological decisions.

Why it matches plant phenotyping methods受粉者の行動を用いて植物の花形質・耐性を定量化する新規フェノタイピング基盤の開発を中心課題としている。

abstractwe propose to develop a pollinator-assisted phenotyping and selection platform for automated quantification of Genotype × Environment × Pollinator interactions through an insect geo-positioning system.

A robust transformer-based pipeline of 3D cell alignment, denoise and instance segmentation on electron microscopy sequence images →

Germline cells are critical for transmitting genetic information to subsequent generations in biological organisms. While their differentiation from somatic cells during embryonic development is well-documented in most animals, the regulatory mechanisms initiating plant germline cells are not well understood. To thoroughly investigate the complex morphological transformations of their ultrastructure over developmental time, nanoscale 3D reconstruction of entire plant tissues is necessary, achievable exclusively through electron microscopy imaging. This paper presents a full-process framework designed for reconstructing large-volume plant tissue from serial electron microscopy images. The framework ensures end-to-end direct output of reconstruction results, including topological networks and morphological analysis. The proposed 3D cell alignment, denoise, and instance segmentation pipeline (3DCADS) leverages deep learning to provide a cell instance segmentation workflow for electron microscopy image series, ensuring accurate and robust 3D cell reconstructions with high computational efficiency. The pipeline involves five stages: the registration of electron microscopy serial images; image enhancement and denoising; semantic segmentation using a Transformer-based neural network; instance segmentation through a supervoxel-based clustering algorithm; and an automated analysis and statistical assessment of the reconstruction results, with the mapping of topological connections. The 3DCADS model's precision was validated on a plant tissue ground-truth dataset, outperforming traditional baseline models and deep learning baselines in overall accuracy. The framework was applied to the reconstruction of early meiosis stages in the anthers of Arabidopsis thaliana, resulting in a topological connectivity network and analysis of morphological parameters and characteristics of cell distribution. The experiment underscores the 3DCADS model's potential for biological tissue identification and its significance in quantitative analysis of plant cell development, crucial for examining samples across different genetic phenotypes and mutations in plant development. Additionally, the paper discusses the regulatory mechanisms of Arabidopsis thaliana's germline cells and the development of stamen cells before meiosis, offering new insights into the transition from somatic to germline cell fate in plants.

Why it matches plant phenotyping methods植物組織の3D画像再構成・細胞インスタンス分割・形態解析を行う手法が研究の中心であり、植物組織データセットで検証されています。

abstractThis paper presents a full-process framework designed for reconstructing large-volume plant tissue from serial electron microscopy images.

Detection of tomato plant phenotyping traits using YOLOv5-based single stage detectors →

Plant phenotyping is the study of complex plant traits to evaluate its status depending on the life-cycle conditions. Often, these evaluations are carried out by human operators, and the accuracy could be biased by their experience and skill, especially when dealing with huge amounts of data produced by high-throughput phenotyping (HTP) platforms. With the rapid development of key enabling technologies, HTP is only made possible by the vast amounts of data made available by computer vision systems. In this scenario, artificial intelligence algorithms play a key role in the automation, standardization, and quantitative analysis of large data. This paper focuses on detecting tomato plants phenotyping traits using single-stage detectors (either stand-alone or ensemble) based on YOLOv5, aiming to effectively identify nodes, fruit, and flowers on a challenging dataset acquired during a stress experiment conducted on multiple tomato genotypes. Results demonstrate that the models achieve relatively high scores, considering the particular challenges of the input images in terms of object size, similarity between objects, and their color.

Why it matches plant phenotyping methodsYOLOv5ベースの画像解析により、トマトの節・果実・花を自動検出する手法を開発・評価しており、植物形質の取得が研究の中心です。

abstractThis paper focuses on detecting tomato plants phenotyping traits using single-stage detectors (either stand-alone or ensemble) based on YOLOv5

Characterisation of cuticle mechanical properties: analysing stiffness in layered living systems to understand surface buckling patterns →

Development of a living organism is a highly regulated process during which biological materials undergo constant change. De novo material synthesis and changes in mechanical properties of materials are key for organ development; however, few studies have attempted to produce quantitative measurements of the mechanical properties of biological materials during growth. Such quantitative analysis is particularly challenging where the material is layered, as is the case for the plant cuticle on top of the plant epidermal cell wall. Here, we focus on Hibiscus trionum flower petals, where buckling of the cuticle forms ridges, producing an iridescent effect. This ridge formation is hypothesised to be due to mechanical instability, which directly depends upon the mechanical properties of the individual layers within the epidermal cells. We present measurements of the mechanical properties of the surface layers of petal epidermal cells through atomic force microscopy (AFM) and the uniaxial tensile tester for ultrathin films (TUTTUT), across growth stages. We found that the wavelength of the surface ridges was set at the ridge formation stage, and this wavelength was preserved during further petal development, most likely because of the plasticity of the material. Our findings suggest that temporal changes in biological material properties are key to understanding the development of biological surface patterns.

Why it matches plant phenotyping methods植物花弁表皮の機械特性をAFMとTUTTUTで定量測定する手法が研究の中心であり、成長段階に伴う植物表面特性を評価している。

abstractWe present measurements of the mechanical properties of the surface layers of petal epidermal cells through atomic force microscopy (AFM) and the uniaxial tensile tester for ultrathin films (TUTTUT), across growth stages.

Deep Learning Approaches for Sunflower Disease Classification: A Study of Convolutional Neural Networks with Squeeze and Excitation Attention Blocks →

Diseases in agricultural plants are one of the most important problems of agricultural production. These diseases cause decreases in production and this poses a serious problem for food safety. One of the agricultural products is sunflower. Helianthus annuus, generally known as sunflower, is an agricultural plant with high economic value grown due to its drought-resistant and oil seeds. In this study, it is aimed to classify the diseases seen in sunflower leaves and flowers by applying deep learning models. First of all, it was classified with ResNet101 and ResNext101, which are pre-trained CNN models, and then it was classified by adding squeeze and excitation blocks to these networks and the results were compared. In the study, a data set containing gray mold, downy mildew, and leaf scars diseases affecting the sunflower crop was used. In our study, original Resnet101, SE-Resnet101, ResNext101, and SE-ResNext101 deep-learning models were used to classify sunflower diseases. For the original images, the classification accuracy of 91.48% with Resnet101, 92.55% with SE-Resnet101, 92.55% with ResNext101, and 94.68% with SE-ResNext101 was achieved. The same models were also suitable for augmented images and classification accuracies of Resnet101 99.20%, SE-Resnet101 99.47%, ResNext101 98.94%, and SE-ResNext101 99.84% were achieved. The study revealed a comparative analysis of deep learning models for the classification of some diseases in the Sunflower plant. In the analysis, it was seen that SE blocks increased the classification performance for this dataset. Application of these models to real-world agricultural scenarios holds promise for early disease detection and response and may help reduce potential crop losses.

Why it matches plant phenotyping methodsヒマワイラ葉・花の画像から病害状態を分類する深層学習手法を比較評価しており、植物病害表現型の取得・推定が研究の中心である。

abstractIn this study, it is aimed to classify the diseases seen in sunflower leaves and flowers by applying deep learning models.

Optimizing tomato plant phenotyping detection: Boosting YOLOv8 architecture to tackle data complexity →

Effective identification of tomato plant traits is crucial for timely monitoring and evaluating their growth and harvest. However, conducting stress experiments on multiple tomato genotypes introduces challenges due to the nature of the data. One of these challenges arises from an imbalanced sample distribution, potentially leading to misclassification between classes and disruptions in model recognition. This paper addresses the effect of these challenges by considering the imbalanced classes of flowers, fruits, and nodes and proposing an improved detection approach through data balancing. A novel data-balancing approach is introduced in this study to overcome the issue of imbalanced data. The proposed solution involves the implementation of a YOLOv8 deep learning model, which effectively detects flowers, fruits, and nodes in tomato plants. This model significantly enhances the ability of the algorithm to detect objects of varying sizes within complex environments. To further bolster the recognition capability of the targeted classes, the proposed model integrates a Squeeze-and-Excitation (SE) block attention module into its head architecture. This module strengthens the model recognition ability by giving increased attention to the studied classes, thereby enhancing overall detection performance. The results demonstrate that the data balancing approach successfully improves the model performance in response to the data challenges. When applying the technique of pre-training the optimal weights obtained from balanced data on imbalanced data, the SE-block module showed significant improvements in outcomes.

Why it matches plant phenotyping methodsトマトの花・果実・節という器官形質を画像から検出するYOLOv8手法を開発・改良し、データ不均衡と複雑環境での性能を評価しており、フェノタイピング手法が中心である。

abstractThis paper addresses the effect of these challenges by considering the imbalanced classes of flowers, fruits, and nodes and proposing an improved detection approach through data balancing.

Using photographs and deep neural networks to understand flowering phenology and diversity in mountain meadows →

Abstract Mountain meadows are an essential part of the alpine–subalpine ecosystem; they provide ecosystem services like pollination and are home to diverse plant communities. Changes in climate affect meadow ecology on multiple levels, for example, by altering growing season dynamics. Tracking the effects of climate change on meadow diversity through the impacts on individual species and overall growing season dynamics is critical to conservation efforts. Here, we explore how to combine crowd‐sourced camera images with machine learning to quantify flowering species richness across a range of elevations in alpine meadows located in Mt. Rainier National Park, Washington, USA. We employed three machine‐learning techniques (Mask R‐CNN, RetinaNet and YOLOv5) to detect wildflower species in images taken during two flowering seasons. We demonstrate that deep learning techniques can detect multiple species, providing information on flowering richness in photographed meadows. The results indicate higher richness just above the tree line for most of the species, which is comparable with patterns found using field studies. We found that the two‐stage detector Mask R‐CNN was more accurate than single‐stage detectors like RetinaNet and YOLO, with the Mask R‐CNN network performing best overall with mean average precision (mAP) of 0.67 followed by RetinaNet (0.5) and YOLO (0.4). We found that across the methods using anchor box variations in multiples of 16 led to enhanced accuracy. We also show that detection is possible even when pictures are interspersed with complex backgrounds and are not in focus. We found differential detection rates depending on species abundance, with additional challenges related to similarity in flower characteristics, labeling errors and occlusion issues. Despite these potential biases and limitations in capturing flowering abundance and location‐specific quantification, accuracy was notable considering the complexity of flower types and picture angles in this dataset. We, therefore, expect that this approach can be used to address many ecological questions that benefit from automated flower detection, including studies of flowering phenology and floral resources, and that this approach can, therefore, complement a wide range of ecological approaches (e.g., field observations, experiments, community science, etc.). In all, our study suggests that ecological metrics like floral richness can be efficiently monitored by combining machine learning with easily accessible publicly curated datasets (e.g., Flickr, iNaturalist).

Why it matches plant phenotyping methods画像と深層学習によって花の種数・開花状態を推定する手法が研究の中心で、複数検出器の比較評価と精度検証も行っているため。

abstractwe explore how to combine crowd‐sourced camera images with machine learning to quantify flowering species richness

Development of a Low-Cost Distributed Computing Pipeline for High-Throughput Cotton Phenotyping. →

In this paper, we present the development of a low-cost distributed computing pipeline for cotton plant phenotyping using Raspberry Pi, Hadoop, and deep learning. Specifically, we use a cluster of several Raspberry Pis in a primary-replica distributed architecture using the Apache Hadoop ecosystem and a pre-trained Tiny-YOLOv4 model for cotton bloom detection from our past work. We feed cotton image data collected from a research field in Tifton, GA, into our cluster's distributed file system for robust file access and distributed, parallel processing. We then submit job requests to our cluster from our client to process cotton image data in a distributed and parallel fashion, from pre-processing to bloom detection and spatio-temporal map creation. Additionally, we present a comparison of our four-node cluster performance with centralized, one-, two-, and three-node clusters. This work is the first to develop a distributed computing pipeline for high-throughput cotton phenotyping in field-based agriculture.

Why it matches plant phenotyping methods綿花の花の検出を対象とする高スループット表現型解析用の分散計算パイプラインを開発し、異なるクラスタ構成の性能比較も行っており、表現型取得・処理手法が中心である。

abstractthe development of a low-cost distributed computing pipeline for cotton plant phenotyping using Raspberry Pi, Hadoop, and deep learning

Fluorescence hybridization chain reaction enables localization of multiple molecular classes combined with plant cell ultrastructure →

ABSTRACT Background Recent developments in hybridization chain reaction (HCR) have enabled robust simultaneous localization of multiple mRNA transcripts using fluorescence in situ hybridization (FISH). Once multiple split initiator oligonucleotide probes bind their target mRNA, HCR uses DNA base-pairing of fluorophore-labeled hairpin sets to self-assemble into large polymers, amplifying the fluorescence signal and reducing non-specific background. Few studies have applied HCR in plants, despite its demonstrated utility in whole mount animal tissues and cell culture. Our aim was to optimize this technique for sectioned plant tissues embedded with paraffin and methacrylate resins, and to test its utility in combination with immunolocalization and subsequent correlation with cell ultrastructure using scanning electron microscopy. Results Application of HCR to 10 µm paraffin sections of 17-day-old Setaria viridis (green millet) inflorescences using confocal microscopy revealed that the transcripts of the transcription factor KNOTTED 1 ( KN1 ) were localized to developing floret meristem and vascular tissue while SHATTERING 1 ( SH1 ) and MYB26 transcripts were co-localized to the breakpoint below the floral structures (the abscission zone). We also used methacrylate de-embedment with 1.5 µm and 0.5 µm sections of 3-day-old Arabidopsis thaliana seedlings to show tissue specific CHLOROPHYLL BINDING FACTOR a/b ( CAB1 ) mRNA highly expressed in photosynthetic tissues and ELONGATION FACTOR 1 ALPHA ( EF1 α ) highly expressed in meristematic tissues of the shoot apex. The housekeeping gene ACTIN7 ( ACT7 ) mRNA was more uniformly distributed with reduced signals using lattice structured-illumination microscopy. HCR using 1.5 µm methacrylate sections was followed by backscattered imaging and scanning electron microscopy thus demonstrating the feasibility of correlating fluorescent localization with ultrastructure. Conclusion HCR was successfully adapted for use with both paraffin and methacrylate de-embedment on diverse plant tissues in two model organisms, allowing for concurrent cellular and subcellular localization of multiple mRNAs, antibodies and other affinity probe classes. The mild hybridization conditions used in HCR made it highly amenable to observe immunofluorescence in the same section. De-embedded semi-thin methacrylate sections with HCR were compatible with correlative electron microscopy approaches. Our protocol provides numerous practical tips for successful HCR and affinity probe labeling in electron microscopy-compatible, sectioned plant material.

Why it matches plant phenotyping methods植物組織で複数mRNAを局在化するHCR法を最適化し、異なる切片材料・モデル植物・顕微鏡法で実証した方法開発研究である。

abstractOur aim was to optimize this technique for sectioned plant tissues embedded with paraffin and methacrylate resins, and to test its utility in combination with immunolocalization and subsequent correlation with cell ultrastructure using scanning electron microscopy.

Optimizing DUS testing for Chimonanthus praecox using feature selection based on a genetic algorithm. →

Chimonanthus praecox is a famous traditional flower in China with high ornamental value. It has numerous varieties, yet its classification is highly disorganized. The distinctness, uniformity, and stability (DUS) test enables the classification and nomenclature of various species; thus, it can be used to classify the Chimonanthus varieties. In this study, flower traits were quantified using an automatic system based on pattern recognition instead of traditional manual measurement to improve the efficiency of DUS testing. A total of 42 features were quantified, including 28 features in the DUS guidelines and 14 new features proposed in this study. Eight algorithms were used to classify wintersweet, and the random forest (RF) algorithm performed the best when all features were used. The classification accuracy of the outer perianth was the highest when the features of the different parts were used for classification. A genetic algorithm was used as the feature selection algorithm to select a set of 22 reduced core features and improve the accuracy and efficiency of the classification. Using the core feature set, the classification accuracy of the RF model improved to 99.13%. Finally, K-means was used to construct a pedigree cluster tree of 23 varieties of wintersweet; evidently, wintersweet was clustered into a single class, which can be the basis for further study of genetic relationships among varieties. This study provides a novel method for DUS detection, variety identification, and pedigree analysis.

Why it matches plant phenotyping methods花形質を自動パターン認識で定量化し、特徴選択と分類によりDUS試験を高効率化する手法が研究の中心であるため、植物フェノタイピング手法として収載する。

abstractflower traits were quantified using an automatic system based on pattern recognition instead of traditional manual measurement to improve the efficiency of DUS testing

Development of a longevity prediction model for cut roses using hyperspectral imaging and a convolutional neural network →

Introduction Hyperspectral imaging (HSI) and deep learning techniques have been widely applied to predict postharvest quality and shelf life in multiple horticultural crops such as vegetables, mushrooms, and fruits; however, few studies show the application of these techniques to evaluate the quality issues of cut flowers. Therefore, in this study, we developed a non-contact and rapid detection technique for the emergence of gray mold disease (GMD) and the potential longevity of cut roses using deep learning techniques based on HSI data. Methods Cut flowers of two rose cultivars ('All For Love' and 'White Beauty') underwent either dry transport (thus impaired cut flower hydration), ethylene exposure, or Botrytis cinerea inoculation, in order to identify the characteristic light wavelengths that are closely correlated with plant physiological states based on HSI. The flower bud of cut roses was selected for HSI measurement and the development of a vase life prediction model utilizing YOLOv5. Results and discussion The HSI results revealed that spectral reflectance between 470 to 680 nm was strongly correlated with gray mold disease (GMD), whereas those between 700 to 900 nm were strongly correlated with flower wilting or vase life. To develop a YOLOv5 prediction model that can be used to anticipate flower longevity, the vase life of cut roses was classed into two categories as over 5 d (+5D) and under 5 d (-5D), based on scoring a grading standard on the flower quality. A total of 3000 images from HSI were forwarded to the YOLOv5 model for training and prediction of GMD and vase life of cut flowers. Validation of the prediction model using independent data confirmed its high predictive accuracy in evaluating the vase life of both 'All For Love' (r 2 = 0.86) and 'White Beauty' (r 2 = 0.83) cut flowers. The YOLOv5 model also accurately detected and classified GMD in the cut rose flowers based on the image data. Our results demonstrate that the combination of HSI and deep learning is a reliable method for detecting early GMD infection and evaluating the longevity of cut roses.

Why it matches plant phenotyping methodsHSIと深層学習を用いて、切り花の灰色かび病と花持ちを非接触推定する手法を開発し、独立データで検証しており、植物状態の取得・推定が研究の中心である。

abstractwe developed a non-contact and rapid detection technique for the emergence of gray mold disease (GMD) and the potential longevity of cut roses using deep learning techniques based on HSI data.

Grassland vertical height heterogeneity predicts flower and bee diversity: an UAV photogrammetric approach →

The ecosystem services offered by pollinators are vital for supporting agriculture and ecosystem functioning, with bees standing out as especially valuable contributors among these insects. Threats such as habitat fragmentation, intensive agriculture, and climate change are contributing to the decline of natural bee populations. Remote sensing could be a useful tool to identify sites of high diversity before investing into more expensive field survey. In this study, the ability of Unoccupied Aerial Vehicles (UAV) images to estimate biodiversity at a local scale has been assessed while testing the concept of the Height Variation Hypothesis (HVH). This hypothesis states that the higher the vegetation height heterogeneity (HH) measured by remote sensing information, the higher the vegetation vertical complexity and the associated species diversity. In this study, the concept has been further developed to understand if vegetation HH can also be considered a proxy for bee diversity and abundance. We tested this approach in 30 grasslands in the South of the Netherlands, where an intensive field data campaign (collection of flower and bee diversity and abundance) was carried out in 2021, along with a UAV campaign (collection of true color-RGB-images at high spatial resolution). Canopy Height Models (CHM) of the grasslands were derived using the photogrammetry technique "Structure from Motion" (SfM) with horizontal resolution (spatial) of 10 cm, 25 cm, and 50 cm. The accuracy of the CHM derived from UAV photogrammetry was assessed by comparing them through linear regression against local CHM LiDAR (Light Detection and Ranging) data derived from an Airborne Laser Scanner campaign completed in 2020/2021, yielding an [Formula: see text] of 0.71. Subsequently, the HH assessed on the CHMs at the three spatial resolutions, using four different heterogeneity indices (Rao's Q, Coefficient of Variation, Berger-Parker index, and Simpson's D index), was correlated with the ground-based flower and bee diversity and bee abundance data. The Rao's Q index was the most effective heterogeneity index, reaching high correlations with the ground-based data (0.44 for flower diversity, 0.47 for bee diversity, and 0.34 for bee abundance). Interestingly, the correlations were not significantly influenced by the spatial resolution of the CHM derived from UAV photogrammetry. Our results suggest that vegetation height heterogeneity can be used as a proxy for large-scale, standardized, and cost-effective inference of flower diversity and habitat quality for bees.

Why it matches plant phenotyping methodsUAV-SfMによる植物群落のCanopy Height Modelと高さ不均一性を構築・検証し、植生構造および花多様性の推定に用いる手法が研究の中心であるため。

abstractCanopy Height Models (CHM) of the grasslands were derived using the photogrammetry technique "Structure from Motion" (SfM)

CottonSense: A high-throughput field phenotyping system for cotton fruit segmentation and enumeration on edge devices →

High-throughput phenotyping (HTP) has become a powerful tool for gaining insights into the genetic and environmental factors that affect cotton ( Gossypium spp.) growth and yield. With the recent advances in the field of computer vision, namely the integration of deep learning algorithms, the accuracy and efficiency of HTP systems have improved dramatically, enabling them to automatically quantify such fundamental phenotypic traits as fruit identification and enumeration. However, there is currently no HTP system available for counting all the reproductive phases of cotton crop that can be deployed in agronomic field conditions throughout the growing season. This study presents CottonSense, an advanced HTP system that overcomes the challenges of deployment across multiple growth periods by effectively segmenting and enumerating cotton fruits at four stages of growth, including square, flower, closed boll, and open boll. Consequently, CottonSense enhances agronomic management through increased opportunities for data collection and analysis. Using RGB-D cameras, it captures and processes both two and three-dimensional data, facilitating a wider range of phenotypic trait extractions such as crop biomass and plant architecture. To segment the cotton fruits, a Mask-RCNN model is trained and optimized for faster inference using TensorRT. The model yields an average AP score of 79% in segmentation across the four fruit categories. Moreover, the model's accuracy in estimating total fruit count per image is validated by a strong agreement with the counts given by ten domain experts, as reflected by an R 2 value of 0.94. Furthermore, to accurately count the segmented fruits over large populations of plants, an enumeration algorithm based on a tracking strategy is developed that achieves an R 2 value of 0.93 when compared to hand-counted fruits in the field. The proposed HTP system, which is implemented entirely on an edge computing device, is cost-effective and power-efficient, making it an effective tool for high-yield cotton breeding and crop improvement. The code for CottonSense is publicly available at https://github.com/FeriBolour/CottonSense .

Why it matches plant phenotyping methods綿花の果実を画像から分割・列挙し、専門家および手作業カウントで検証する高スループット表現型解析システムの開発が中心である。

abstractThis study presents CottonSense, an advanced HTP system that overcomes the challenges of deployment across multiple growth periods by effectively segmenting and enumerating cotton fruits at four stages of growth, including square, flower, closed boll, and open boll.

Effects of sampling methodology on phenology indices: insights from sites across India and modelling →

Plant phenology is the study of timing and extent of leaf, flower, and fruit production. Phenology data are used to study drivers of cyclicity and seasonality of plant life-history stages, interactions with organisms such as pollinators, and effects of global change factors. Indices such as timing of phenological events, proportion of individuals in a particular phenophase, seasonality, and synchrony have often been used to summarise plant phenology data. However, these indices have specific utilities and limitations and may be sensitive to sampling methodology, making cross-site comparisons challenging, particularly when data collection methods vary in terms of sample size, observation frequency, and the resolution at which phenophase intensity scores/values are recorded. We use fruiting phenology data from tropical trees across five sites in India to study the effects of sampling methodology on two indices: an index of population-level synchrony (overlap), and an index of seasonality. We supplement these results with simulations of fast- and slow-changing phenologies to test for the effects of sampling methodology on these indices. We found that the overlap index is sensitive to the phenophase intensity measurement resolution--with coarser intensity measures leading to overestimation of the overlap index. The seasonality index, on the other hand, was not affected by intensity resolution. Simulations indicated that finer intensity resolution is more important than frequency of observation to accurately estimate population synchrony and seasonality for fast- and slow-changing phenophases. Based on our findings, we provide recommendations for study design of future tropical tree phenology research, particularly for long-term or cross-site studies.

Why it matches plant phenotyping methods植物のフェノロジー指標について、観察頻度・サンプルサイズ・フェノフェーズ強度の測定解像度が指標推定に与える影響を実データとシミュレーションで検証しており、表現型データ取得・解析方法が中心である。

abstractWe use fruiting phenology data from tropical trees across five sites in India to study the effects of sampling methodology on two indices: an index of population-level synchrony (overlap), and an index of seasonality.

Early Detection of Botrytis cinerea Infection in Cut Roses Using Thermal Imaging. →

Botrytis cinerea ( B. cinerea ) causes gray mold disease (GMD), which results in physiological disorders in plants that decrease the longevity and economic value of horticultural crops. To prevent the spread of GMD during distribution, a rapid, early detection technique is necessary. Thermal imaging has been used for GMD detection in various plants, including potted roses; however, its application to cut roses, which have a high global demand, has not been established. In this study, we investigated the utility of thermal imaging for the early detection of B. cinerea infection in cut roses by monitoring changes in petal temperature after fungal inoculation. We examined the effects of GMD on the postharvest quality and petal temperature of cut roses treated with different concentrations of fungal conidial suspensions and chemicals. B. cinerea infection decreased the flower opening, disrupted the water balance, and decreased the vase life of cut roses. Additionally, the average temperature of rose petals was higher for infected flowers than for non-inoculated flowers. One day before the appearance of necrotic symptoms (day 1 of the vase period), the petal temperature in infected flowers was significantly higher, by 1.1 °C, than that of non-inoculated flowers. The GMD-induced increase in petal temperature was associated with the mRNA levels of genes related to ethylene, reactive oxygen species, and water transport. Furthermore, the increase in temperature caused by GMD was strongly correlated with symptom severity and fungal biomass. A multiple regression analysis revealed that the disease incidence in the petals was positively related to the petal temperature one day before the appearance of necrotic symptoms. These results show that thermography is an effective technique for evaluating changes in petal temperature and a possible method for early GMD detection in the cut flower industry.

Why it matches plant phenotyping methods熱画像法により感染したバラ花弁の温度という植物状態を測定し、病徴出現前の灰色かび病を検出・評価する方法を中心的に検証しているため。

abstractIn this study, we investigated the utility of thermal imaging for the early detection of B. cinerea infection in cut roses by monitoring changes in petal temperature after fungal inoculation.

Robust statistical analysis to predict and estimate the concentration of the cannabidiolic acid in Cannabis sativa L.: A comparative study →

Growing awareness of the medicinal and therapeutic benefits of cannabis has resulted in extensive research, increasing numbers of commercial growers, and the provision of commercial testing. For commercial production, the importance of monitoring for consistent cannabinoid composition is essential. Gas chromatography and/or liquid chromatography methods are effective methods. Unfortunately, they are not easily scaled up for frequent or large-scale testing. Precision cultivation for medicinal cannabis requires the industry to test large volumes of plants frequently during different stages of the growth cycle. This cannot be achieved with destructive testing alone. A statistical method with ¹H nuclear magnetic resonance (NMR) is proposed and investigated to explore its potential for a cost-effective mass-screening method of plant material samples. In addition, hyperspectral imaging (HSI) is employed for frequent non-destructive measurements. This allows increasing the frequency of observations during the growth of the plant. The cannabidiolic acid (CBDA) concentration is determined by the application of both HSI and NMR spectroscopy and validated against liquid chromatography-mass spectrometry (LCMS). The paper proposes a multivariate statistical regression algorithm that automatically determines the CBDA concentration directly from bucket integration of the NMR spectrum. The algorithm successfully predicted the CBDA concentration of 7 unknown samples from data selected from 4 known samples, with an average R² value of 0.98. The proposed statistical method was applied to the data collected for HSI. It showed that while the hyperspectral dataset can be correlated with CBDA concentration, it was subject to high variance. However, HSI retains the spatial information of the actual plant structure, allowing the CBDA prediction to be mapped back to the original spatial location in the plant while providing visual information on CBDA concentration within a flower or leaf without requiring the plant component to be destroyed in the process.

Why it matches plant phenotyping methods植物試料のCBDA濃度という形質を、NMR統計解析と非破壊ハイパースペクトル画像から推定する手法を開発・検証しており、植物フェノタイピング手法が中心です。

abstractA statistical method with ¹H nuclear magnetic resonance (NMR) is proposed and investigated to explore its potential for a cost-effective mass-screening method of plant material samples.

Comparing hormone dynamics in cereal crops via transient expression of hormone sensors →

ABSTRACT Plant hormones are small molecules which elicit profound physiological responses. Although plant hormone biosynthesis and response genes have been critical for agricultural improvement, it has been difficult to experimentally compare hormone biology across species because of complex phenotypic outputs. We used transient expression of genetic hormone sensors and transcriptomics to quantify tissue-specific gibberellic acid (GA) and auxin responses across tissues and genotypes in cereal crops. We found that the FRET-based GPS2 biosensor detects exogenous GA treatments in maize, barley, sorghum, and wheat, in both vegetative and floral tissues. Measuring GPS2 output across GA dosages revealed tissue- and genotype-specific differences in GA sensor response. We observed marked differences in maize vs barley leaves and floral tissues and an unexpected drop in GPS2 output in the maize d1 GA biosynthesis mutant after GA treatment, likely reflecting differences in bioactive GA content, GA transport, and mechanisms of GA response. We then used RNAseq to measure transcriptional responses to GA treatment in leaves from maize wildtype, d1 , and barley as well as floral tissues from maize and barley for a cross-tissue, cross-genotype, and cross-species GA-response comparison. After orthology prediction and analysis of within- and cross-species GO-term enrichment, we identified core sets of GA-responsive genes in each species as well as maize- barley orthogroups. Our analysis suggests that downregulation of GA-INSENSITIVE DWARF1 ( GID1 ) and upregulation of α -Expansin1 ( EXPA1 ) orthologs comprises a universal GA-response mechanism that is independent of GA biosynthesis, and identifies F-Box proteins, hexokinase, and AMPK/SNF1 protein kinase orthologs as unexpected cross-tissue, cross-genotype, and cross-species GA-responsive genes. We then compared the transient expression of the DR5, DR5v2, and DII-mDII auxin reporters in barley and maize and find that although DR5 did not respond to exogenous auxin in barley, DR5v2 responded to auxin treatment with a similar magnitude as in maize. Both species display auxin-mediated DII degradation that requires the 26S proteasome.

Why it matches plant phenotyping methods遺伝子型・組織・種をまたいでホルモンセンサーの応答を検証・比較し、植物の生理状態を定量化する手法が研究の中心である。

abstractWe used transient expression of genetic hormone sensors and transcriptomics to quantify tissue-specific gibberellic acid (GA) and auxin responses across tissues and genotypes in cereal crops.

Use of an unmanned aerial vehicle for monitoring and prediction of oilseed rape crop performance →

The flowering stage of oilseed rape (Brassica napus L.) is of vital interest in precision agriculture. It has been shown that data describing the flower production of oilseed rape (OSR), at stage 3, in spring can be used to predict seed yield at harvest. Traditional field-based techniques for assessing OSR flowers are based on a visual assessment which is subjective and time consuming. However, a high throughput phenotyping technique, using an unmanned aerial vehicle (UAV) with multispectral image (MSI) camera, was used to investigate the growth stages of OSR (in terms of crop height) and to quantify its flower production. A simplified approach using a normalised difference yellowness index (NDYI) was coupled with an iso-cluster classification method to quantify the number of OSR flower pixels and incorporate the data into an OSR seed yield estimation. The estimated OSR seed yield showed strong correlation with the actual OSR seed yield (R2 = 0.86), as determined using in-situ sensors mounted on the combine harvester. Also, using our approach allowed the variation in crop height to be assessed across all growing stages; the maximum crop height of 1.35 m OSR was observed at the flowering stage. This methodology is proposed for effectively predicting seed yield 3 months prior to harvesting.

Why it matches plant phenotyping methodsUAVマルチスペクトル画像と画像分類により、ナタネの草高・花数を定量化し収量予測へ利用する高スループット表現型計測手法が中心である。

abstracta high throughput phenotyping technique, using an unmanned aerial vehicle (UAV) with multispectral image (MSI) camera, was used to investigate the growth stages of OSR (in terms of crop height) and to quantify its flower production.

Tomato flower pollination features recognition based on binocular gray value-deformation coupled template matching →

It is necessary to recognize the tomato pollination features for the designing demand of intelligent and precise tomato supplementary pollination equipment. Mentioned pollination features include flower opening state and the three-dimensional position and pose of flower anther. Tomato flower pollination features recognition method is designed in this paper based on the deep learning full opened flower recognition model and binocular template matching three-dimensional information recognition method. First of all, a binocular stereo vision system is built to acquire the tomato flower images in greenhouse with natural lighting. Which can help vision system avoid the impact of inconsistent light intensity on image recognition. The acquired images were equalized with three groups parameters to labeled images. And the improved MC-AlexNet deep learning model is established to recognize the full opened tomato flowers in the left image of image pair acquired with binocular vision system. Then, the template is created with the full opened flower recognition result of deep learning model in left image based on gray value and deformation template matching method. And the template matching is established to recognize the corresponding full opened flowers in the right image of image pair. Finally, with the template matching result, the anther segmentation is conducted to calculate three-dimensional position and pose of anther. The experimental results show that the accuracy of full opened tomato flowers recognition model is 96.23%. The average position recognition deviation of anther is 5.94 mm. And the average anther pose recognition deviation in three plane is 6.24° for the images that anthers can be observed. And the average time consuming is about 143.18 ms per image pair. It can be concluded that the method of binocular template matching established in this paper can fulfill the demand of supplementary pollination equipment design, and the research result lays a foundation for designing and improvement of tomato supplementary pollination equipment in greenhouse.

Why it matches plant phenotyping methodsトマト花の開花状態と葯の三次元位置・姿勢という植物器官形質を、深層学習・両眼ステレオ・テンプレートマッチングで取得する方法を開発・評価しており、フェノタイピング手法が中心である。

abstractTomato flower pollination features recognition method is designed in this paper based on the deep learning full opened flower recognition model and binocular template matching three-dimensional information recognition method.

Growth couples temporal and spatial fluctuations of tissue properties during morphogenesis →

Living tissues display fluctuations – random spatial and temporal variations of tissue properties around their reference values – at multiple scales. It is believed that such fluctuations may enable tissues to sense their state or their size. Recent theoretical studies developed specific models of fluctuations in growing tissues and predicted that fluctuations of growth show long-range correlations. Here we elaborated upon these predictions and we tested them using experimental data. We first introduced a minimal model for the fluctuations of any quantity that has some level of temporal persistence or memory, such as concentration of a molecule, local growth rate, or mechanical property. We found that long-range correlations are generic, applying to any such quantity, and that growth couples temporal and spatial fluctuations, through a mechanism that we call ‘fluctuation stretching’ — growth enlarges the lengthscale of variation of this quantity. We then analysed growth data from sepals of the model plant Arabidopsis and we quantified spatial and temporal fluctuations of cell growth using the previously developed Cellular Fourier Transform. Growth appears to have long-range correlations. We compared different genotypes and growth conditions: mutants with lower or higher response to mechanical stress have lower temporal correlations and longer-range spatial correlations than wild-type plants. Finally, we used theoretical predictions to merge experimental data from all conditions and developmental stages into an unifying curve, validating the notion that temporal and spatial fluctuations are coupled by growth. Altogether, our work reveals kinematic constraints on spatiotemporal fluctuations that have an impact on the robustness of morphogenesis. Significance Statement How do organs and organisms grow and achieve robust shapes in the face of subcellular and cellular variability? In order to address this outstanding mystery, we investigated the variability of growth at multiple scales and we analysed experimental data from growing plant tissues. Our results support the prediction that tissue expansion couples temporal memory of growth with spatial variability of growth. Our work reveals a constraint on the spatial and temporal variability of growth that may impact the robustness of morphogenesis.

Why it matches plant phenotyping methodsArabidopsis萼片の細胞成長をCellular Fourier Transformで定量し、時空間変動を解析・理論予測と比較して検証しており、植物成長表現型の抽出・解析が研究の中心です。

abstractFinally, we used theoretical predictions to merge experimental data from all conditions and developmental stages into an unifying curve, validating the notion that temporal and spatial fluctuations are coupled by growth.

Tomato flower pollination features recognition based on binocular gray value-deformation coupled template matching →

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

Why it matches plant phenotyping methodsトマト花の受粉関連特徴を双眼画像とテンプレートマッチングで認識する手法開発であり、植物器官の状態・特徴抽出が中心と判断される。

titleTomato flower pollination features recognition based on binocular gray value-deformation coupled template matching

Hyperspectral imaging for estimating leaf, flower, and fruit macronutrient concentrations and predicting strawberry yields. →

Managing the nutritional status of strawberry plants is critical for optimizing yield. This study evaluated the potential of hyperspectral imaging (400-1,000 nm) to estimate nitrogen (N), phosphorus (P), potassium (K), and calcium (Ca) concentrations in strawberry leaves, flowers, unripe fruit, and ripe fruit and to predict plant yield. Partial least squares regression (PLSR) models were developed to estimate nutrient concentrations. The determination coefficient of prediction (R 2 P ) and ratio of performance to deviation (RPD) were used to evaluate prediction accuracy, which often proved to be greater for leaves, flowers, and unripe fruit than for ripe fruit. The prediction accuracies for N concentration were R 2 P = 0.64, 0.60, 0.81, and 0.30, and RPD = 1.64, 1.59, 2.64, and 1.31, for leaves, flowers, unripe fruit, and ripe fruit, respectively. Prediction accuracies for Ca concentrations were R 2 P = 0.70, 0.62, 0.61, and 0.03, and RPD = 1.77, 1.63, 1.60, and 1.15, for the same respective plant parts. Yield and fruit mass only had significant linear relationships with the Difference Vegetation Index (R 2 = 0.256 and 0.266, respectively) among the eleven vegetation indices tested. Hyperspectral imaging showed potential for estimating nutrient status in strawberry crops. This technology will assist growers to make rapid nutrient-management decisions, allowing for optimal yield and quality.

Why it matches plant phenotyping methodsイチゴの葉・花・果実の栄養状態と収量という植物形質を、ハイパースペクトル画像とPLSRで推定・検証しており、表現型取得法の適用と性能評価が中心である。

abstractThis study evaluated the potential of hyperspectral imaging (400-1,000 nm) to estimate nitrogen (N), phosphorus (P), potassium (K), and calcium (Ca) concentrations in strawberry leaves, flowers, unripe fruit, and ripe fruit and to predict plant yield.

Robust Detection of Plant Features with Overhead Imaging in a Range of Crop and Weed Scenarios →

Overhead imaging from UAVs and UGVs can help detect features of interest for farm scenarios with crop-specific features such as flowers, fruits, and surrounding weeds. These features are important for yield assessment and de-weeding. However, identifying them can be challenging due to their morphological similarity and occlusion. We use deep learning to process high-resolution images of crop fields and classify the features at different complexity levels, for example, to detect green-coloured fruits that are partly concealed beneath leaves. We compare different approaches for multiple seasonal crops and weeds in the Kharif season and discuss their performance and limitations. The feature recognition outputs are illustrated at various complexity levels, which should help pave the way forward in creating holistic insights that drive action on the ground to enhance management efficiency and profitability.

Why it matches plant phenotyping methods作物の花・果実などの植物器官をオーバーヘッド画像と深層学習で検出・分類し、収量評価に利用する画像解析手法が研究の中心であるため。

abstractWe use deep learning to process high-resolution images of crop fields and classify the features at different complexity levels, for example, to detect green-coloured fruits that are partly concealed beneath leaves.

CRISPR/Cas9-induced DNA breaks trigger crossover, chromosomal loss, and chromothripsis-like rearrangements. →

DNA double-stranded breaks (DSBs) generated by the Cas9 nuclease are commonly repaired via nonhomologous end-joining (NHEJ) or homologous recombination (HR). However, little is known about unrepaired DSBs and the type of damage they trigger in plants. We designed an assay that detects loss of heterozygosity (LOH) in somatic cells, enabling the study of a broad range of DSB-induced genomic events. The system relies on a mapped phenotypic marker which produces a light purple color (betalain pigment) in all plant tissues. Plants with sectors lacking the Betalain marker upon DSB induction between the marker and the centromere were tested for LOH events. Using this assay, we detected a tomato (Solanum lycopersicum) flower with a twin yellow and dark purple sector, corresponding to a germinally transmitted somatic crossover event. We also identified instances of small deletions of genomic regions spanning the T-DNA and whole chromosome loss. In addition, we show that major chromosomal rearrangements including loss of large fragments, inversions, and translocations were clearly associated with the CRISPR-induced DSB. Detailed characterization of complex rearrangements by whole-genome sequencing and molecular and cytological analyses supports a model in which a breakage-fusion-bridge cycle followed by chromothripsis-like rearrangements had been induced. Our LOH assay provides a tool for precise breeding via targeted crossover detection. It also uncovers CRISPR-mediated chromothripsis-like events in plants.

Why it matches plant phenotyping methods植物組織の色素マーカーによるセクター表現型を利用して体細胞LOHや染色体イベントを検出するアッセイを開発しており、表現型取得法が研究の中心である。

abstractWe designed an assay that detects loss of heterozygosity (LOH) in somatic cells, enabling the study of a broad range of DSB-induced genomic events.

Detection and Classification of Saffron Plant Diseases using Machine Learning: A Research →

Abstract: Saffron, known as "red gold," is a valuable spice derived from the flower of Crocus sativus. However, saffron cultivation faces challenges due to diseases that can harm crop yield and quality. This thesis proposes a deep learning-based approach using the VGG 16 architecture to detect and classify saffron diseases. The study collects a comprehensive saffron disease dataset, organizes it by disease type, and enhances its quality through analysis and augmentation. The VGG 16 architecture, known for image classification, is adapted for saffron disease detection, utilizing convolutional and fully connected layers for feature extraction and classification. The model is trained using multiple epochs, achieving an impressive 87% accuracy. Comparison with other methods demonstrates the superiority of the proposed approach. The study utilizes highperformance computing systems for efficient evaluation. Overall, this research demonstrates the potential of deep learning in saffron disease management, aiding farmers in effective decision-making for disease control measures.

Why it matches plant phenotyping methodsサフラン植物の画像から病害状態を検出・分類する深層学習手法を開発し、データセット構築、拡張、比較評価まで行っており、植物病害フェノタイピングが中心である。

abstractThis thesis proposes a deep learning-based approach using the VGG 16 architecture to detect and classify saffron diseases.

Object-Detection from Multi-View remote sensing Images: A case study of fruit and flower detection and counting on a central Florida strawberry farm →

Object detection in remote sensing images is one of the most critical computer vision tasks for various earth observation applications. Previous studies applied object detection models to orthomosaic images generated from the SfM (Structure-from-Motion) analysis to perform object detection and counting. However, some small objects that are occluded from the vertical view but observable in raw images from the oblique views cannot be detected in the orthomosaic image, leading to an occlusion issue that cannot be resolved with the traditional orthophoto-based approach. Taking strawberry detection as a case study, the objective of this study is to detect small objects directly from multi-view raw images. Firstly, an object-detection model (Faster R-CNN in this study) was applied to each raw image to identify strawberry fruit and flower objects. Each unique strawberry object on the ground can be detected multiple times in the raw images because images have forward- and side overlap. To find the unique objects from the step one detection results, an improved FaceNet model was proposed to combine the image and position information to calculate the feature distance between those objects, and a clustering algorithm was used to associate the cluster with each unique strawberry using the object distance output from the FaceNet model, from which the final position and number of strawberry fruits and flowers were obtained. Compared with the orthomosaic image alone, this approach using multi-view images effectively solved the occlusion problem and improved overall recognition accuracy of strawberry flowers, unripe fruits, and ripe fruits from 76.28% to 96.98%, 71.64% to 99.09%, and 69.81% to 97.17%, respectively, highlighting the potential of multi-view stereovision (MVS) in small object detection.

Why it matches plant phenotyping methodsイチゴの花・果実をマルチビュー画像から検出・重複排除して位置と個数を推定する手法が研究の中心であり、植物器官の表現型計測に該当する。

abstractthe objective of this study is to detect small objects directly from multi-view raw images

VARIATIONS IN THE ULTRAVIOLET FLORAL PATTERNS AND POLLINATOR PREFERENCE AMONG SELECTED NON-INVASIVE AND INVASIVE PLANTS OF TAMIL NADU, INDIA →

Fossil evidence shows that pollinator-mediated plant reproduction evolved [~]140 million years ago and bee facilitated pollination evolved [~]70 million years ago. Human vision is limited to the visible color range of 400 to 750 nanometres, whereas most pollinators can perceive the ultraviolet (UV) range in addition to visible colors. Bees have been reported to have highest spectral sensitivity in the ultraviolet spectrum. The main objectives of the study were (1) to assess the prevalence of ultraviolet floral patterns, (2) to analyse floral patterns in relation to plant-pollinator interaction among invasive and non-invasive plants, and (3) to test for intraspecific floral pattern variations among plants with different flower color morphs. A study was conducted on 188 plant species (80 invasive and 108 non-invasive) from parts of Western and Eastern Ghats region of Tamil Nadu, India. The flowers of the studied plant species were imaged in ultraviolet (320-380 nm) and visible spectrums. The mode of pollination for the selected species were documented and confirmed with existing literature. The intraspecific variations in the floral patterns among flower color polymorphic plant species (N=10) were documented in ultraviolet and visible spectrums. Among the studied plant species, around 58% had discernible floral patterns when observed in the UV spectrum, whereas the rest were observed to completely absorb or reflect UV radiation. Whereas 46% of the studied plants exhibited no pattern in the visible spectrum. A significant difference was observed in the pollinator relationship among the ultraviolet floral patterns in invasive plants ({chi}2 = 63.98, df = 32, P < 0.001), whereas no significant variation was evidenced in the pollinator relationship among the ultraviolet floral patterns in non-invasive plants ({chi}2 = 19.50, df = 24, P = 0.724). Analysis of pollinator preference revealed that invasive species were mostly pollinated by bee and butterfly mediated pollination, whereas non-invasive species were mostly pollinated by bees and generalist insects. Intraspecific variations in the floral ultraviolet signal were observed among different morphs in a few flower color polymorphic species, especially in Lantana camara. The multispectral analysis of floral patterns revealed that plants utilize both the visible and ultraviolet spectrums to effectively communicate with pollinators. The results from the present study strongly suggest that the variation in the floral ultraviolet signature among invasive species might play a vital role in plant-pollinator interaction and invasion success.

Why it matches plant phenotyping methods花の紫外線・可視画像から花冠のパターンという植物器官形質を取得し、多数種で比較することが研究の中心であるため、画像ベースの植物フェノタイピング応用として採用。

abstractThe flowers of the studied plant species were imaged in ultraviolet (320-380 nm) and visible spectrums.

Identification of Plant Leaf Disease Using a Novel Convolutional Neural Network →

A critical element in preventing a major outbreak is the detection of plant leaves. An important research issue is the automatic detection of plant diseases. For both human life and condition, a plant's dedication is essential. Like humans and other animals, plants do suffer the negative impacts of illnesses. A plant's normal development is influenced by the frequency of plant diseases that occur. The entire plant, including the leaf, stem, organic material, root, and flower, is affected by these diseases. Most of the time, if a plant's ailment is not treated, it dies or may cause leaves, blooms, organic products, and so forth to fall off. For accurate identification and treatment of plant diseases, appropriate determination of these disorders is necessary. Plant pathology is the study of plant infections, their causes, and methods for preventing, managing, and eradicating them. However, the current approach includes human inclusion for structure and identifying disease proof. This tactic is time-consuming and expensive. Instead of using the current method, a programmed division of diseases from plant leaf images utilising a delicate registration methodology may be more beneficial. In this study, we describe a method for identifying and characterising plant leaf diseases naturally called Bacterial Searching Improvement Based Radial Basis Function Neural Network (BRBFNN). We use bacterial search streamlining (BFO), which increases the speed and accuracy of the system to recognise and organise the regions contaminated by diverse illnesses on the plant leaves, to assign Radial Basis Function Neural Network (RBFNN) the proper weight. The location development calculation increases the system's efficiency by searching for and gathering seed focuses on typical traits for the highlighted extraction operation. To make progress against parasite diseases including early curse, leaf twist, leaf spot, late scourge, and basic, cedar apple, and leaf rust. The suggested approach achieves more accuracy in identifying evidence and characterizing infections.

Why it matches plant phenotyping methods植物葉画像から病害領域を自動抽出・識別するCNN系手法が研究の中心であり、植物の病害状態を画像から推定するため、植物フェノタイピング手法に該当する。

abstractwe describe a method for identifying and characterising plant leaf diseases naturally called Bacterial Searching Improvement Based Radial Basis Function Neural Network (BRBFNN).

Development and deployment of a big data pipeline for field-based high-throughput cotton phenotyping data →

In this study, we propose a big data pipeline for cotton bloom detection using a Lambda architecture, which enables real-time and batch processing of data. Our proposed approach leverages Azure resources such as Data Factory, Event Grids, Rest APIs, and Databricks. This work is the first to develop and demonstrate the implementation of such a pipeline for plant phenotyping through Azure's cloud computing service. The proposed pipeline consists of data preprocessing, object detection using a YOLOv5 neural network model trained through Azure AutoML, and visualization of object detection bounding boxes on output images. The trained model achieves a mean Average Precision (mAP) score of 0.96, demonstrating its high performance for cotton bloom classification. We evaluate our Lambda architecture pipeline using 9,000 images yielding an optimized runtime of 34 minutes. The results illustrate the scalability of the proposed pipeline as a solution for deep learning object detection, with the potential for further expansion through additional Azure processing cores. This work advances the scientific research field by providing a new method for cotton bloom detection on a large dataset and demonstrates the potential of utilizing cloud computing resources, specifically Azure, for efficient and accurate big data processing in precision agriculture.

Why it matches plant phenotyping methods綿花の開花を画像から検出するクラウド型高スループット・フェノタイピングパイプラインを開発・評価しており、植物形質の取得手法が研究の中心である。

titleDevelopment and deployment of a big data pipeline for field-based high-throughput cotton phenotyping data

A CRISPR-induced DNA break can trigger crossover, chromosomal loss and chromothripsis-like rearrangements →

The fate of DNA double-strand breaks (DSBs) generated by the Cas9 nuclease has been thoroughly studied. Repair via non-homologous end-joining (NHEJ) or homologous recombination (HR) is the common outcome. However, little is known about unrepaired DSBs and the type of damage they can trigger in plants. In this work, we designed a new assay that detects loss of heterozygosity (LOH) in somatic cells, enabling the study of a broad range of DSB-induced genomic events. The system relies on a mapped phenotypic marker which produces a light purple color (Betalain pigment) in all plant tissues. Plants with sectors lacking the Betalain marker upon DSB induction between the marker and the centromere were tested for LOH events. Using this assay we detected a flower with a twin yellow and dark purple sector, corresponding to a germinally transmitted somatic crossover event. We also identified instances of small deletions of genomic regions spanning the T-DNA and whole chromosome loss. In addition, we show that major chromosomal rearrangements including loss of large fragments, inversions, and translocations were clearly associated with the CRISPR-induced DSB. Detailed characterization of complex rearrangements by whole genome sequencing, molecular, and cytological analyses, supports a model in which breakage-fusion-bridge cycle followed by chromothripsis-like rearrangements had been induced. Our LOH assay provides a new tool for precise breeding via targeted crossover detection. It also uncovers CRISPR mediated chromothripsis-lke events that had not been previously identified in plants.

Why it matches plant phenotyping methods植物組織の色素表現型を利用して体細胞LOHや染色体イベントを検出する新規アッセイを開発しており、表現型に基づく測定法が研究の中心である。

abstractIn this work, we designed a new assay that detects loss of heterozygosity (LOH) in somatic cells, enabling the study of a broad range of DSB-induced genomic events.

How to sample a seizure plant: the role of the visualization spatial distribution analysis of Lophophora williamsii as an example →

Natural compounds in plants are often unevenly distributed, and determining the best sampling locations to obtain the most representative results is technically challenging. Matrix-assisted laser desorption/ionization mass spectrometry imaging (MALDI-MSI) can provide the basis for formulating sampling guideline. For a succulent plant sample, ensuring the authenticity and in situ nature of the spatial distribution analysis results during MSI analysis also needs to be thoroughly considered. In this study, we developed a well-established and reliable MALDI-MSI method based on preservation methods, slice conditions, auxiliary matrices, and MALDI parameters to detect and visualize the spatial distribution of mescaline in situ in Lophophora williamsii . The MALDI-MSI results were validated using liquid chromatography-tandem mass spectrometry. Low-temperature storage at -80°C and drying of "bookmarks" were the appropriate storage methods for succulent plant samples and their flower samples, and cutting into 40 μm thick sections at -20°C using gelatin as the embedding medium is the appropriate sectioning method. The use of DCTB (trans-2-[3-(4-tert-butylphenyl)-2-methyl-2-propenylidene]malononitrile) as an auxiliary matrix and a laser intensity of 45 are favourable MALDI parameter conditions for mescaline analysis. The region of interest semi-quantitative analysis revealed that mescaline is concentrated in the epidermal tissues of L. williamsii as well as in the meristematic tissues of the crown. The study findings not only help to provide a basis for determining the best sampling locations for mescaline in L. williamsii , but they also provide a reference for the optimization of storage and preparation conditions for raw plant organs before MALDI detection. Key points An accurate in situ MSI method for fresh water-rich succulent plants was obtained based on multi-parameter comparative experiments.Spatial imaging analysis of mescaline in Lophophora williamsii was performed using the above method.Based on the above results and previous results, a sampling proposal for forensic medicine practice is tentatively proposed.

Why it matches plant phenotyping methods植物組織内の化合物空間分布を可視化・半定量するMALDI-MSI法の開発とLC-MS/MSによる検証が研究の中心であり、植物器官の状態・分布を測定する方法論的貢献に該当する。

abstractwe developed a well-established and reliable MALDI-MSI method based on preservation methods, slice conditions, auxiliary matrices, and MALDI parameters to detect and visualize the spatial distribution of mescaline in situ in Lophophora williamsii

3D cellular morphometrics of ovule primordium development in Zea mays reveal differential division and growth dynamics specifying megaspore mother cell singleness. →

Introduction Differentiation of spore mother cells marks the somatic-to-reproductive transition in higher plants. Spore mother cells are critical for fitness because they differentiate into gametes, leading to fertilization and seed formation. The female spore mother cell is called the megaspore mother cell (MMC) and is specified in the ovule primordium. The number of MMCs varies by species and genetic background, but in most cases, only a single mature MMC enters meiosis to form the embryo sac. Multiple candidate MMC precursor cells have been identified in both rice and Arabidopsis , so variability in MMC number is likely due to conserved early morphogenetic events. In Arabidopsis , the restriction of a single MMC per ovule, or MMC singleness, is determined by ovule geometry. To look for potential conservation of MMC ontogeny and specification mechanisms, we undertook a morphogenetic description of ovule primordium growth at cellular resolution in the model crop maize. Methods We generated a collection of 48 three-dimensional (3D) ovule primordium images for five developmental stages, annotated for 11 cell types. Quantitative analysis of ovule and cell morphological descriptors allowed the reconstruction of a plausible developmental trajectory of the MMC and its neighbors. Results The MMC is specified within a niche of enlarged, homogenous L2 cells, forming a pool of candidate archesporial (MMC progenitor) cells. A prevalent periclinal division of the uppermost central archesporial cell formed the apical MMC and the underlying cell, a presumptive stack cell. The MMC stopped dividing and expanded, acquiring an anisotropic, trapezoidal shape. By contrast, periclinal divisions continued in L2 neighbor cells, resulting in a single central MMC. Discussion We propose a model where anisotropic ovule growth in maize drives L2 divisions and MMC elongation, coupling ovule geometry with MMC fate.

Why it matches plant phenotyping methods3D画像を細胞単位で注釈し、形態記述子を定量解析する手法が、トウモロコシ胚珠の発生軌跡の再構築における中心的手段です。

abstractWe generated a collection of 48 three-dimensional (3D) ovule primordium images for five developmental stages, annotated for 11 cell types.

High-throughput Cotton Phenotyping Big Data Pipeline Lambda Architecture Computer Vision Deep Neural Networks →

In this study, we propose a big data pipeline for cotton bloom detection using a Lambda architecture, which enables real-time and batch processing of data. Our proposed approach leverages Azure resources such as Data Factory, Event Grids, Rest APIs, and Databricks. This work is the first to develop and demonstrate the implementation of such a pipeline for plant phenotyping through Azure's cloud computing service. The proposed pipeline consists of data preprocessing, object detection using a YOLOv5 neural network model trained through Azure AutoML, and visualization of object detection bounding boxes on output images. The trained model achieves a mean Average Precision (mAP) score of 0.96, demonstrating its high performance for cotton bloom classification. We evaluate our Lambda architecture pipeline using 9000 images yielding an optimized runtime of 34 minutes. The results illustrate the scalability of the proposed pipeline as a solution for deep learning object detection, with the potential for further expansion through additional Azure processing cores. This work advances the scientific research field by providing a new method for cotton bloom detection on a large dataset and demonstrates the potential of utilizing cloud computing resources, specifically Azure, for efficient and accurate big data processing in precision agriculture.

Why it matches plant phenotyping methods綿花の花の検出という植物器官の表現型取得を対象に、クラウド型ビッグデータ処理パイプラインとYOLOv5による画像解析手法を開発・評価しており、方法が研究の中心である。

abstractThis work is the first to develop and demonstrate the implementation of such a pipeline for plant phenotyping through Azure's cloud computing service.

Machine Vision-Based Crop-Load Estimation Using YOLOv8 →

Labor shortages in fruit crop production have prompted the development of mechanized and automated machines as alternatives to labor-intensive orchard operations such as harvesting, pruning, and thinning. Agricultural robots capable of identifying tree canopy parts and estimating geometric and topological parameters, such as branch diameter, length, and angles, can optimize crop yields through automated pruning and thinning platforms. In this study, we proposed a machine vision system to estimate canopy parameters in apple orchards and determine an optimal number of fruit for individual branches, providing a foundation for robotic pruning, flower thinning, and fruitlet thinning to achieve desired yield and quality.Using color and depth information from an RGB-D sensor (Microsoft Azure Kinect DK), a YOLOv8-based instance segmentation technique was developed to identify trunks and branches of apple trees during the dormant season. Principal Component Analysis was applied to estimate branch diameter (used to calculate limb cross-sectional area, or LCSA) and orientation. The estimated branch diameter was utilized to calculate LCSA, which served as an input for crop-load estimation, with larger LCSA values indicating a higher potential fruit-bearing capacity.RMSE for branch diameter estimation was 2.08 mm, and for crop-load estimation, 3.95. Based on commercial apple orchard management practices, the target crop-load (number of fruit) for each segmented branch was estimated with a mean absolute error (MAE) of 2.99 (ground truth crop-load was 6 apples per LCSA). This study demonstrated a promising workflow with high performance in identifying trunks and branches of apple trees in dynamic commercial orchard environments and integrating farm management practices into automated decision-making.

Why it matches plant phenotyping methodsRGB-D画像とYOLOv8を用いてリンゴ樹の枝形態（直径・方向）を抽出し、樹体の作物負荷を推定する手法を開発・評価しており、表現型取得が研究の中心である。

abstractIn this study, we proposed a machine vision system to estimate canopy parameters in apple orchards and determine an optimal number of fruit for individual branches

A Wearable Flower-Shaped Sensor Based on Fiber Bragg Grating Technology for In-Vivo Plant Growth Monitoring →

One of the biggest challenges facing the world agriculture is feeding a growing population in a sustainable way. Therefore, global food availability is under a severe strain exacerbated by climate changes and biological stresses. Moreover, the content of macro- and micronutrients obtained from in plant-food sources strongly depends on the plant development. An attractive strategy to increase agricultural productivity is the growth monitoring of plants and edible parts by using wearable systems. However, most of these tools measure dimensional changes uniaxially, while an accurate representation of the growth distribution requires multipoint strain measurement especially for plants that show an anisotropic development. Here, we present a stretchable multisensor wearable system highly adaptable to the curvilinear surface of leaves and fruits for multidirectional dimensional monitoring. The proposed sensor consists of six fiber Bragg gratings (FBGs) within a biomimetic flexible substrate with a flower design. FBGs with their miniaturized size, high metrological properties, and multiplexing capacities are well suited to this purpose. A finite-element model (FEM) guides the optimal design and sensors positioning within the flower-shaped matrix to exhibit an adequate strain sensitivity and negligible crosstalk effects among the six sensing elements with a reduced encumbrance. A metrological characterization is first performed followed by the application of the proposed system for in-vivo detection of dimensional changes of a leaf and fruit in both indoor and outdoor scenarios.

Why it matches plant phenotyping methods植物の葉・果実の多方向な寸法変化を測定するウェアラブルセンサを開発し、測定学的特性評価と生体内適用を行っており、植物表現型取得手法が中心である。

abstractHere, we present a stretchable multisensor wearable system highly adaptable to the curvilinear surface of leaves and fruits for multidirectional dimensional monitoring.

CherryPicker: Semantic Skeletonization and Topological Reconstruction of Cherry Trees →

In plant phenotyping, accurate trait extraction from 3D point clouds of trees is still an open problem. For automatic modeling and trait extraction of tree organs such as blossoms and fruits, the semantically segmented point cloud of a tree and the tree skeleton are necessary. Therefore, we present CherryPicker, an automatic pipeline that reconstructs photo-metric point clouds of trees, performs semantic segmentation and extracts their topological structure in form of a skeleton. Our system combines several state-of-the-art algorithms to enable automatic processing for further usage in 3D-plant phenotyping applications. Within this pipeline, we present a method to automatically estimate the scale factor of a monocular reconstruction to overcome scale ambiguity and obtain metrically correct point clouds. Furthermore, we propose a semantic skeletonization algorithm build up on Laplacian-based contraction. We also show by weighting different tree organs semantically, our approach can effectively remove artifacts induced by occlusion and structural size variations. CherryPicker obtains high-quality topology reconstructions of cherry trees with precise details.

Why it matches plant phenotyping methodsサクランボ樹木の3D点群から器官の形態・トポロジーを抽出する自動フェノタイピング手法の開発が中心である。

abstractIn plant phenotyping, accurate trait extraction from 3D point clouds of trees is still an open problem.

Using photographs and deep neural networks to understand flowering phenology and diversity in mountain meadows →

Mountain meadows are an essential part of the alpine-subalpine ecosystem; they provide ecosystem services like pollination and are home to diverse plant communities. Changes in climate affect meadow ecology on multiple levels, for example by altering growing season dynamics. Tracking the effects of climate change on meadow diversity through the impacts on individual species and overall growing season dynamics is critical to conservation efforts. Here, we explore how to combine crowd sourced camera images with machine learning to quantify flowering species richness across a range of elevations in alpine meadows located in Mt Rainier National Park, Washington, USA. We employed three machine learning techniques (Mask R-CNN, RetinaNet and YOLOv5) to detect wildflower species in images taken during two flowering seasons. We demonstrate that deep learning techniques can detect multiple species, providing information on flowering richness in photographed meadows. The results indicate higher richness just above the tree line for most of the species, which is comparable with patterns found using field studies. We found that the two-stage detector Mask R-CNN was more accurate than single-stage detectors like RetinaNet and YOLO, with the Mask R-CNN network performing best overall with mean average precision (mAP) of 0.67 followed by RetinaNet (0.5) and YOLO (0.4). We found that across the methods using anchor box variations in multiples of 16 led to enhanced accuracy. We also show that detection is possible even when pictures are interspersed with complex backgrounds and are not in focus. We found differential detection rates depending on species abundance, with additional challenges related to similarity in flower characteristics, labeling errors, and occlusion issues. Despite these potential biases and limitations in capturing flowering abundance and location-specific quantification, accuracy was notable considering the complexity of flower types and picture angles in this data set. We therefore expect that this approach can be used to address many ecological questions that benefit from automated flower detection, including studies of flowering phenology and floral resources, and that this approach can therefore complement a wide range of ecological approaches (e.g., field observations, experiments, community science, etc.). In all, our study suggests that ecological metrics like floral richness can be efficiently monitored by combining machine learning with easily accessible publicly curated datasets (e.g., Flickr, iNaturalist).

Why it matches plant phenotyping methods画像と深層学習によって植物種の検出および開花種 richness という植物群集形質を定量化し、複数手法の精度比較・検証を行っているため、方法が研究の中心です。

abstractwe explore how to combine crowd sourced camera images with machine learning to quantify flowering species richness across a range of elevations in alpine meadows

Drone-Based Identification and Monitoring of Two Invasive Alien Plant Species in Open Sand Grasslands by Six RGB Vegetation Indices →

Today, invasive alien species cause serious trouble for biodiversity and ecosystem services, which are essential for human survival. In order to effectively manage invasive species, it is important to know their current distribution and the dynamics of their spread. Unmanned aerial vehicle (UAV) monitoring is one of the best tools for gathering this information from large areas. Vegetation indices for multispectral camera images are often used for this, but RGB colour-based vegetation indices can provide a simpler and less expensive solution. The goal was to examine whether six RGB indices are suitable for identifying invasive plant species in the QGIS environment on UAV images. To examine this, we determined the shoot area and number of common milkweed (Asclepias syriaca) and the inflorescence area and number of blanket flowers (Gaillardia pulchella) as two typical invasive species in open sandy grasslands. According to the results, the cover area of common milkweed was best identified with the TGI and SSI indices. The producers’ accuracy was 76.38% (TGI) and 67.02% (SSI), while the user’s accuracy was 75.42% (TGI) and 75.12% (SSI), respectively. For the cover area of blanket flower, the IF index proved to be the most suitable index. In spite of this, it gave a low producer’s accuracy of 43.74% and user’s accuracy of 51.4%. The used methods were not suitable for the determination of milkweed shoot and the blanket flower inflorescence number, due to significant overestimation. With the methods presented here, the data of large populations of invasive species can be processed in a simple, fast, and cost-effective manner, which can ensure the precise planning of treatments for nature conservation practitioners.

Why it matches plant phenotyping methodsUAV RGB画像と6種の植生指数を用いて、侵入植物のシュート面積・花序面積・個体数を抽出し、適合性と精度を評価している。単なる分布把握ではなく、植物形質の画像計測法の検証・適用が中心である。

abstractThe goal was to examine whether six RGB indices are suitable for identifying invasive plant species in the QGIS environment on UAV images.

Detection of tomato plant phenotyping traits using YOLOv5-based single stage detectors →

Plant phenotyping is the study of complex plant traits to evaluate its status depending on the life-cycle conditions. Often, these evaluations are carried out by human operators, and the accuracy could be biased by their experience and skill, especially when dealing with huge amounts of data produced by high-throughput phenotyping (HTP) platforms. With the rapid development of key enabling technologies, HTP is only made possible by the vast amounts of data made available by computer vision systems. In this scenario, artificial intelligence algorithms play a key role in the automation, standardization, and quantitative analysis of large data. This paper focuses on detecting tomato plants phenotyping traits using single-stage detectors (either stand-alone or ensemble) based on YOLOv5, aiming to effectively identify nodes, fruit, and flowers on a challenging dataset acquired during a stress experiment conducted on multiple tomato genotypes. Results demonstrate that the models achieve relatively high scores, considering the particular challenges of the input images in terms of object size, similarity between objects, and their color.

Why it matches plant phenotyping methodsYOLOv5ベースの画像解析手法を開発・評価し、トマトの節・果実・花という表現型形質を自動検出することが研究の中心である。

abstractThis paper focuses on detecting tomato plants phenotyping traits using single-stage detectors (either stand-alone or ensemble) based on YOLOv5

Synchrotron micro-computed tomography unveils the three-dimensional structure and origin of staminodes in the Plains Prickly Pear Cactus Opuntia polyacantha Haw. (Cactaceae). →

Floral appendages display an array of shapes and sizes. Among these organs, staminodes are morphologically diverse structures that have lost the ability to produce pollen, but in some instances, they produce fertile pollen grains. In the family Cactaceae staminodes are uncommon and range from simple linear to flat to spatulate structures, but studies describing their structural attributes are scanty. This study highlights the advantages of synchrotron radiation for sample preparation and as a research tool for plant biology. It describes the internal morphology of floral parts, particularly stamen, tepal, and staminode in the Plains Prickly Pear Cactus, Opuntia polyacantha, using synchrotron radiation micro-computed tomography (SR-μCT). It also shows the different anatomical features in reconstructed three-dimensional imaging of reproductive parts and discuss the advantages of the segmentation method to detect and characterize the configuration and intricate patterns of vascular networks and associated structures of tepal and androecial parts applying SR-μCT. This powerful technology led to substantial improvements in terms of resolution allowing a more comprehensive understanding of the anatomical organization underlying the vasculature of floral parts and inception of staminodes in O. polyacantha. Tepal and androecial parts have uniseriate epidermis enclosing loose mesophyll with mucilage secretory ducts, lumen, and scattered vascular bundles. Cryptic underlying structural attributes provide evidence of a vascularized pseudo-anther conjoint with tepals. The undefined contours of staminodial appendages (pseudo-anther) amalgamated to the tepals' blurred boundaries suggest that staminodes originate from tepals, a developmental pattern supporting the fading border model of floral organ identity for angiosperms.

Why it matches plant phenotyping methodsSR-μCTと3次元再構成・セグメンテーションを中心に、花器官の内部形態と維管束構造を取得・可視化しており、植物形態計測法の実質的な適用研究である。

abstractThis study highlights the advantages of synchrotron radiation for sample preparation and as a research tool for plant biology.

Live Imaging of Arabidopsis Pollen Tube Reception and Double Fertilization Using the Semi-In Vitro Cum Septum Method. →

In flowering plants, the growth and guidance of the pollen tube (male gametophyte) within the pistil and the reception of the pollen tube by the female gametophyte are essential for double fertilization and subsequent seed development. The interactions between male and female gametophytes during pollen tube reception culminate in pollen tube rupture and the release of two sperm cells to effect double fertilization. As pollen tube growth and double fertilization are deeply hidden within the tissues of the flower, this process is difficult to observe in vivo. A semi-in vitro (SIV) method for the live-cell imaging of fertilization in the model plant Arabidopsis thaliana has been developed and implemented in several investigations. These studies have helped to elucidate the fundamental features of how the fertilization process occurs in flowering plants and which cellular and molecular changes occur during the interaction of the male and female gametophytes. However, because these live cell imaging experiments involve the excision of individual ovules, they are limited to a low number of observations per imaging session, making this approach tedious and very time-consuming. Among other technical difficulties, a failure of the pollen tubes to fertilize the ovules in vitro is often reported, which severely confounds such analyses. Here, a detailed video protocol for the imaging of pollen tube reception and fertilization in an automated and high-throughput manner is provided, allowing for up to 40 observations of pollen tube reception and rupture per imaging session. Coupled with the use of genetically encoded biosensors and marker lines, this method enables the generation of large sample sizes with a reduced time investment. Nuances and critical points of the technique, including flower staging, dissection, medium preparation, and imaging, are clearly detailed in video format to facilitate future research on the dynamics of pollen tube guidance, reception, and double fertilization.

Why it matches plant phenotyping methods植物の受精過程を観察するライブイメージング法を自動化・高スループット化したビデオプロトコルであり、画像取得法そのものが中心的な技術貢献です。

abstractHere, a detailed video protocol for the imaging of pollen tube reception and fertilization in an automated and high-throughput manner is provided, allowing for up to 40 observations of pollen tube reception and rupture per imaging session.

Modeling temporal and spatial effects on plant reproduction using observational data →

Background and Aims The persistence of a plant species at local sites depend on species ability to survive and reproduce under local conditions. Estimating environmental influence on reproduction is difficult because climatic and soil conditions have synergistic effects on flower and fruit production, and estimating these synergistic effects require tracking a large number of marked individuals. Here, we develop a statistical method that allows investigating the environmental influence on reproduction using observational data only (no marking required). Methods We surveyed 30 standardized permanent plots on central Amazonia for six herbaceous families of Zingiberales and Poales. The plots were surveyed for twelve consecutive months. Using the newly developed method, we estimated the effect of climatic (temporal) and edaphic (spatial) covariates on flower and fruit production. Key results We demonstrate that plant reproduction can be estimated from observational data only when enough temporal and spatial data are available. By using the proposed statistical method, we show that the conversion of flowers into fruits in Amazonian monocots is highest in sandy soils, and the difference in conversion rates between sandy and clayey soils is more pronounced in wetter months. Conclusions By comparing the production of flowers and fruits with previously published data on species occurrence, our results suggesting that species distribution is limited primarily by species capacity to produce fruits (e.g. limited pollination) and not by the capacity to produce flowers. Due to the association of fruit production to climatic and edaphic variables, our results point to potential changes in species reproduction and distribution under future climatic regimes.

Why it matches plant phenotyping methods花・果実生産という植物の生殖形質を、標識なしの観測データから推定する新しい統計手法の開発が研究の中心であり、単なる生物学的応用ではない。

abstractwe develop a statistical method that allows investigating the environmental influence on reproduction using observational data only (no marking required).

UAV Photogrammetry-Based Apple Orchard Blossom Density Estimation and Mapping →

Thinning is an important routine for apple growers to manage crop load and improve fruit quality, which can be accomplished through manual, chemical, or mechanical manipulation of flowers and fruitlets. Traditionally, blossom thinning relies on human experts’ visual evaluation of the flower load, a leading indicator of crop load, which can be imprecise and prone to errors. This study aimed to develop an apple blossom density mapping algorithm utilizing point clouds reconstructed through unmanned aerial vehicle (UAV)-based red-green-blue (RGB) imagery and photogrammetry. The algorithm was based on grid average downsampling and white color thresholding, and it was able to generate top-view blossom density maps of user-defined tree height regions. A preliminary field experiment was carried out to evaluate the algorithm’s accuracy using manual blossom counts of apple tree row sections as ground truths, and a coefficient of determination (R2) of 0.85, a root mean square error (RMSE) of 1307, and a normalized RMSE (NRMSE) of 9.02% were achieved. The algorithm was utilized to monitor the blooming of the apple tree rows and was demonstrated to effectively show blossom density variations between different tree rows and dates. The study results suggested the potential of UAVs as a convenient tool to assist precise blossom thinning in apple orchards, while future research should further investigate the reliability of photogrammetry techniques under different image qualities and flight settings as well as the influence of blossom distribution on algorithm accuracy.

Why it matches plant phenotyping methodsUAV RGB画像とフォトグラメトリからリンゴ樹の開花密度を推定・マッピングするアルゴリズムを開発し、手作業カウントで精度検証しており、植物形質取得法が中心である。

abstractThis study aimed to develop an apple blossom density mapping algorithm utilizing point clouds reconstructed through unmanned aerial vehicle (UAV)-based red-green-blue (RGB) imagery and photogrammetry.

Shape classification technology of pollinated tomato flowers for robotic implementation. →

Three pollination methods are commonly used in the greenhouse cultivation of tomato. These are pollination using insects, artificial pollination (by manually vibrating flowers), and plant growth regulators. Insect pollination is the preferred natural technique. We propose a new pollination method, using flower classification technology with Artificial Intelligence (AI) administered by drones or robots. To pollinate tomato flowers, drones or robots must recognize and classify flowers that are ready to be pollinated. Therefore, we created an AI image classification system using a machine learning convolutional neural network (CNN). A challenge is to successfully classify flowers while the drone or robot is constantly moving. For example, when the plant is shaking due to wind or vibration caused by the drones or robots. The AI classifier was based on an image analysis algorithm for pollination flower shape. The experiment was performed in a tomato greenhouse and aimed for an accuracy rate of at least 70% for sufficient pollination. The most suitable flower shape was confirmed by the fruiting rate. Tomato fruit with the best shape were formed by this method. Although we targeted tomatoes, the AI image classification technology is adaptable for cultivating other species for a smart agricultural future.

Why it matches plant phenotyping methodsトマト花の受粉適期を画像形状から分類するCNNシステムの開発と、結実率による検証が研究の中心であり、植物状態を抽出するフェノタイピング手法に該当する。

abstractwe created an AI image classification system using a machine learning convolutional neural network (CNN).

Characterisation of Banana Plant Growth Using High-Spatiotemporal-Resolution Multispectral UAV Imagery →

The determination of key phenological growth stages of banana plantations, such as flower emergence and plant establishment, is difficult due to the asynchronous growth habit of banana plants. Identifying phenological events assists growers in determining plant maturity, and harvest timing and guides the application of time-specific crop inputs. Currently, phenological monitoring requires repeated manual observations of individual plants’ growth stages, which is highly laborious, time-inefficient, and requires the handling and integration of large field-based data sets. The ability of growers to accurately forecast yield is also compounded by the asynchronous growth of banana plants. Satellite remote sensing has proved effective in monitoring spatial and temporal crop phenology in many broadacre crops. However, for banana crops, very high spatial and temporal resolution imagery is required to enable individual plant level monitoring. Unoccupied aerial vehicle (UAV)-based sensing technologies provide a cost-effective solution, with the potential to derive information on health, yield, and growth in a timely, consistent, and quantifiable manner. Our research explores the ability of UAV-derived data to track temporal phenological changes of individual banana plants from follower establishment to harvest. Individual plant crowns were delineated using object-based image analysis, with calculations of canopy height and canopy area producing strong correlations against corresponding ground-based measures of these parameters (R2 of 0.77 and 0.69 respectively). A temporal profile of canopy reflectance and plant morphology for 15 selected banana plants were derived from UAV-captured multispectral data over 21 UAV campaigns. The temporal profile was validated against ground-based determinations of key phenological growth stages. Derived measures of minimum plant height provided the strongest correlations to plant establishment and harvest, whilst interpolated maxima of normalised difference vegetation index (NDVI) best indicated flower emergence. For pre-harvest yield forecasting, the Enhanced Vegetation Index 2 provided the strongest relationship (R2 = 0.77) from imagery captured near flower emergence. These findings demonstrate that UAV-based multitemporal crop monitoring of individual banana plants can be used to determine key growing stages of banana plants and offer pre-harvest yield forecasts.

Why it matches plant phenotyping methodsUAVマルチスペクトル画像から個体別の樹冠形状・反射特性・生育段階・収量関連形質を抽出し、地上測定で検証する方法の開発・実証が中心である。

abstractIndividual plant crowns were delineated using object-based image analysis, with calculations of canopy height and canopy area producing strong correlations against corresponding ground-based measures of these parameters

Real-time determination of flowering period for field wheat based on improved YOLOv5s model →

The flowering period is one of the important indexes of wheat breeding. The early or late flowering affects the final yield and character stability of wheat. In order to solve the problem that it is difficult to accurately and quickly detect the flowering period of a large number of wheat breeding materials, a determination method of flowering period for field wheat based on the improved You Only Look Once (YOLO) v5s model was proposed. Firstly, a feature fusion (FF) method combing RGB images and corresponding comprehensive color features was proposed to highlight more texture features and reduce the distortion caused by light on the extracted feature images. Second, the YOLOv5s model was selected as a base version of the improved model and the convolutional block attention model (CBAM) was adopted into the feature fusion layer of YOLOV5s model. Florets and spikelets were given greater weight along the channel and spatial dimensions to further refine their effective feature information. At the same time, an integrated Transformer small-target detection head (TSDH) was added to solve the high miss rate of small targets in wheat population images. The accurate and rapid detection of florets and spikelets was realized, and the flowering period was determined according to the proportion of florets and spikelets. The experimental results showed that the average computing time of the proposed method was 11.5ms, and the average recognition accuracy of florets and spikelets was 88.9% and 96.8%, respectively. The average difference between the estimated flowering rate and the actual flowering rate was within 5%, and the determination accuracy of the flowering period reached 100%, which met the basic requirements of the flowering period determination of wheat population in the field.

Why it matches plant phenotyping methods小麦の開花期という植物状態を、画像と改良YOLOv5sで小花・小穂から推定する手法を開発・評価しており、表現型取得が研究の中心である。

abstracta determination method of flowering period for field wheat based on the improved You Only Look Once (YOLO) v5s model was proposed

Cell Biological Analyses of Anther Morphogenesis and Pollen Viability in Arabidopsis and Rice. →

Major advances have been made in our understanding of anther developmental processes in flowering plants through a combination of genetic studies, cell biological technologies, biochemical analyses, microarray and high-throughput sequencing-based approaches. In this chapter, we summarize widely used protocols for pollen viability staining, investigation of anther morphogenesis by scanning electron microscopy (SEM), light microscopy of semi-thin sections, ultrathin section-based transmission electron microscopy (TEM), TUNEL (terminal deoxynucleotidyl transferase-mediated 2'-deoxyuridine 5'-triphosphate (dUTP) nick end labeling) assay for tapetum programmed cell death, and laser microdissection procedures to obtain specific cells or cell layers for transcriptome analysis.

Why it matches plant phenotyping methods花粉生存性や葯の形態を観察・評価する複数の植物表現型取得プロトコルを体系的に扱う方法論的章であり、測定手法が中心である。

abstractIn this chapter, we summarize widely used protocols for pollen viability staining, investigation of anther morphogenesis by scanning electron microscopy (SEM), light microscopy of semi-thin sections, ultrathin section-based transmission electron microscopy (TEM)

MASPC_Transform: A Plant Point Cloud Segmentation Network Based on Multi-Head Attention Separation and Position Code →

Plant point cloud segmentation is an important step in 3D plant phenotype research. Because the stems, leaves, flowers, and other organs of plants are often intertwined and small in size, this makes plant point cloud segmentation more challenging than other segmentation tasks. In this paper, we propose MASPC_Transform, a novel plant point cloud segmentation network base on multi-head attention separation and position code. The proposed MASPC_Transform establishes connections for similar point clouds scattered in different areas of the point cloud space through multiple attention heads. In order to avoid the aggregation of multiple attention heads, we propose a multi-head attention separation loss based on spatial similarity, so that the attention positions of different attention heads can be dispersed as much as possible. In order to reduce the impact of point cloud disorder and irregularity on feature extraction, we propose a new point cloud position coding method, and use the position coding network based on this method in the local and global feature extraction modules of MASPC_Transform. We evaluate our MASPC_Transform on the ROSE_X dataset. Compared with the state-of-the-art approaches, the proposed MASPC_Transform achieved better segmentation results.

Why it matches plant phenotyping methods植物点群から器官を分割する新規ネットワークを開発・評価しており、3D植物表現型研究のための形態・構造形質抽出手法が中心である。

abstractPlant point cloud segmentation is an important step in 3D plant phenotype research.

Studying flowers in 3D using photogrammetry →

Flowers are intricate and integrated three-dimensional (3D) structures predominantly studied in 2D due to the difficulty in quantitatively characterising their morphology in 3D. Given the recent development of analytical methods for high-dimensional data, the reconstruction of flower models in three dimensions represents the limiting factor to studying flowers in 3D. We developed a floral photogrammetry protocol to reconstruct 3D models of flowers based on images taken with a digital single-lens reflex camera, a turntable and a portable lightbox. We demonstrate that photogrammetry allows a rapid and accurate reconstruction of 3D models of flowers from 2D images. It can reconstruct all visible parts of flowers and has the advantage of keeping colour information. We illustrated its use by studying the shape and colour of 18 Gesneriaceae species. Photogrammetry is an affordable alternative to micro-computed tomography (micro-CT) that requires minimal investment and equipment, allowing it to be used directly in the field. It has the potential to stimulate research on the evolution and ecology of flowers by providing a simple way to access 3D morphological data from a variety of flower types.

Why it matches plant phenotyping methods花の3D形態と色を画像から再構成するフォトグラメトリ法を開発し、精度評価と実例適用を行っており、植物形質取得が研究の中心である。

abstractWe developed a floral photogrammetry protocol to reconstruct 3D models of flowers based on images taken with a digital single-lens reflex camera, a turntable and a portable lightbox.

A Neural Network Structure with Attention Mechanism and Additional Feature Fusion Layer for Tomato Flowering Phase Detection in Pollination Robots →

In recent years, convolutional neural networks have made many advances in the field of computer vision. In smart greenhouses, using robots based on computer vision technology to pollinate flowers is one of the main methods of pollination. However, due to the complex lighting environment and the influence of leaf shadow in the greenhouse, it is difficult for the existing object detection algorithms to have high recall rate and accuracy. Based on this problem, from the perspective of application, we proposed a Yolov5s-based tomato flowering stage detection method named FlowerYolov5, which can well identify the bud phase, blooming phase and first fruit phase of tomato flowers. Firstly, in order to reduce the loss of tomato flower feature information in convolution and to strengthen the feature extraction of the target, FlowerYolov5 adds a new feature fusion layer. Then, in order to highlight the information of the object, the Convolutional Block Attention module (CBAM) is added to the backbone layer of FlowerYolov5. In the constructed tomato flower dataset, compared with YOLOv5s, the mAP of FlowerYolov5 increased by 7.8% (94.2%), and the F1 score of FlowerYolov5 increased by 6.6% (89.9%). It was found that the overall parameter of FlowerYolov5 was 23.9 Mbyte, thus achieving a good balance between model parameter size and recognition accuracy. The experimental results show that the FlowerYolov5 has good robustness and more accurate precision. At the same time, the recall rate has also been greatly improved. The prediction results of the proposed algorithm can provide more accurate flower positioning for the pollination robot and improve its economic benefits.

Why it matches plant phenotyping methodsトマト花の発育段階を画像から検出するニューラルネットワークを開発・評価しており、植物器官の状態（蕾・開花・初期果実）を抽出する方法が中心である。

abstractwe proposed a Yolov5s-based tomato flowering stage detection method named FlowerYolov5, which can well identify the bud phase, blooming phase and first fruit phase of tomato flowers.

Prediction of apple first flowering date using daily land surface temperature spatio-temporal reconstruction and machine learning →

The first flowering date (FFD) is a critical phenological parameter closely related to the apple yield, so the accurate prediction of the FFD is important for precise orchard production management. Existing methods to predict the FFD are mostly based on air temperature (Ta) measured at meteorological stations, but to great differences in meteorological variations and the ecological conditions, these methods cannot present the differences of FFD under complex meteorological conditions and provide spatially continuous FFD information at the level of a region. Therefore, we propose a method to predict spatially continuous apple FFD from remote sensing land surface temperature (LST) based on flowering prediction model. Firstly, the missing LST data were reconstructed by using spatio-temporal reconstruction (STR) approach developed. Next, new air temperature (NAT) data were generated by using the daily Ta estimation (DTE) model and the reconstructed LST. Finally, apple FFD was predicted by the NAT data and the apple flowering prediction model established based on random forest (RF) algorithm and the phenology sequential model, and the prediction accuracy was verified by comparison with the independently measured apple FFD. The LST reconstructed by using the STR approach has mean absolute error (MAE) ranging from 0.51 to 0.68 °C, and root mean square error (RMSE) ranging from 1.07 to 1.21 °C. The MAE between the NAT data and the High-Resolution Land Surface Data Assimilation System (HR-CLDAS) meteorological data ranges from 2.15 to 3.23 °C, and the RMSE ranges from 2.81 to 4.27 °C. In addition, the determination coefficient (R²) and RMSE between the predicted and measured FFD is 0.72 and 2.96 days, respectively. These results demonstrate that the developed method maximizes the potential of MODIS LST in predicting spatially continuous apple FFD, which is valuable for flower and fruit thinning, to defend against frost disasters, and in general for refined orchard production management.

Why it matches plant phenotyping methodsリモートセンシングLSTの再構成、気温推定、開花予測モデルを組み合わせてリンゴの初開花日という植物フェノタイプを空間的に推定し、独立測定値で精度検証しているため、手法が研究の中心である。

abstractTherefore, we propose a method to predict spatially continuous apple FFD from remote sensing land surface temperature (LST) based on flowering prediction model.

Hyperspectral imaging with chemometrics for non-destructive determination of cannabinoids in floral and leaf materials of industrial hemp (Cannabis sativa L.) →

With the passage of the 2018 Farm Bill, industrial hemp (Cannabis sativa L.) has become a legal and economically promising crop commodity for U.S. farmers. There has been a surge of interest in growing industrial hemp for producing cannabinoids, such as cannabidiol (CBD), because of their medical potential. Quantitative determination of cannabinoids in harvested materials (primarily floral tissues) is critical for cannabinoid production and compliance testing. The concentrations of cannabinoids in hemp materials are conventionally determined using wet-chemistry chromatographic methods, which require destructive sampling, and are time-consuming, costly, and thus not suitable for on-site rapid testing. This study presents a novel effort to utilize hyperspectral imaging technology for non-destructive quantification of major cannabinoids, including CBD, THC (tetrahydrocannabinol), CBG (cannabigerol) and their acid forms in fresh floral and leaf materials of industrial hemp on a dry weight basis. Hyperspectral images in the wavelength range of 400–1000 nm were acquired from floral and leaf tissues immediately after harvest from a total of 100 industrial hemp plants of five cultivars at varied growth stages. Linear discriminant analysis showed hyperspectral imaging could identify CBD-rich/poor and THC-legal/illegal flower samples with accuracies of 99% and 97%, respectively. Quantitative models based on full-spectrum PLS (partial least squares) achieved prediction accuracies of RPD (ratio of prediction to deviation) = 2.5 (corresponding R² = 0.84) for CBD and THC in floral tissues. Similar accuracies were obtained for their acid forms in flower samples. The predictions for CBG and its acid form in floral tissues and all six cannabinoids in leaf tissues were unsatisfactory with noticeably lower RPD values. Consistently improved accuracies were obtained by parsimonious PLS models based on a wavelength selection procedure for minimized variable collinearity. The best RPD values of approximately 2.6 (corresponding R² = 0.85) were obtained for CBD and THC in floral materials. This study demonstrates the utility of hyperspectral imaging as a potential valuable tool for rapid quantification of cannabinoids in industrial hemp.

Why it matches plant phenotyping methodsヘンプの花・葉組織に含まれるカンナビノイド量を、ハイパースペクトル画像とケモメトリクスで非破壊推定する手法が研究の中心であり、植物組織の化学的形質を直接定量するため。

abstractThis study presents a novel effort to utilize hyperspectral imaging technology for non-destructive quantification of major cannabinoids

FlowerPhenoNet: Automated Flower Detection from Multi-view Image Sequences using Deep Neural Networks for Temporal Plant Phenotyping Analysis →

A phenotype is the composite of an observable expression of a genome for traits in a given environment. The trajectories of phenotypes computed from an image sequence and timing of important events in a plant’s life cycle can be viewed as temporal phenotypes and indicative of the plant’s growth pattern and vigor. In this paper, we introduce a novel method called FlowerPhenoNet which uses deep neural networks for detecting flowers from multiview image sequences for high throughput temporal plant phenotyping analysis. Following flower detection, a set of novel flower-based phenotypes are computed, e.g., the day of emergence of the first flower in a plant’s life cycle, the total number of flowers present in the plant at a given time, the highest number of flowers bloomed in the plant, growth trajectory of a flower and the blooming trajectory of a plant. To develop a new algorithm and facilitate performance evaluation based on experimental analysis, a benchmark dataset is indispensable. Thus, we introduce a benchmark dataset called FlowerPheno which comprises image sequences of three flowering plant species, e.g., sunflower, coleus, and canna, captured by a visible light camera in a high throughput plant phenotyping platform from multiple view angles. The experimental analyses on the FlowerPheno dataset demonstrate the efficacy of the FlowerPhenoNet.

Why it matches plant phenotyping methods花の検出から開花時期・花数・成長軌跡などの植物表現型を抽出する手法を開発し、ベンチマークデータセットと性能評価も提示しており、フェノタイピング手法が研究の中心である。

abstractwe introduce a novel method called FlowerPhenoNet which uses deep neural networks for detecting flowers from multiview image sequences for high throughput temporal plant phenotyping analysis.

Quantifying the reproductive progression of sunflower using FIJI (Image J). →

Sunflower ( Helianthus annuus L.) is today the third leading oilseed crop in the world and seed yield is a valuable trait for breeders and researchers. The sunflower capitulum is composed of 700 to 3000 individual flowers on a flattered receptacle. Most reproductive stages (R5 to R6) have at least two disc flower phenophase's coexisting in the same receptacle (E1 to E4). Today, researchers in agroecology and breeders manually quantify the number of disc flowers that achieve the anthesis at different developmental stages of the receptacle. The presented method applies a bioinformatic tool to estimate: (1) the number of disc flowers of each phenophase that are constituting the sunflower´s capitula at different reproductive stages and, (2) the number of developing seeds of each sunflower capitulum. The ImageJ software was used as an image-analysis tool on sunflower capitula photographs. A use case and method validation for each presented protocol is provided. This method will contribute to correlation analysis in agroecological studies and also would be useful for the early prediction of seed yield in breeding programs.•This is a simple method for the estimation of the number of disc flowers at each phenophase in the sunflower receptacle.•It is based on integrating the knowledge of sunflower reproductive development with an open-source image analysis platform applied in single workflows.•This is a precise, non-destructive, rapid, and low-cost method; thus, it has the potential to be adopted as a phenotyping tool for sunflower breeding and research in agroecology.

Why it matches plant phenotyping methodsヒマワリ頭花の小花フェノフェーズと発達種子数をImageJ画像解析で推定する方法を開発・検証しており、植物表現型取得が中心である。

abstractThe presented method applies a bioinformatic tool to estimate: (1) the number of disc flowers of each phenophase that are constituting the sunflower´s capitula at different reproductive stages and, (2) the number of developing seeds of each sunflower capitulum.

Evaluation of rapeseed flowering dynamics for different genotypes with UAV platform and machine learning algorithm →

Rapeseed (Brassica napus L.) is an important oil-bearing cash crop. Effective identification of the rapeseed flowering date is important for yield estimation and disease control. Traditional field measurements of rapeseed flowering are time-consuming, labour-intensive and strongly subjective. In this study, red, green and blue (RGB) images of rapeseed flowering derived from unmanned aerial vehicles (UAVs) were acquired with a total of seventeen available orthomosaic images, covering the whole flowering period for 299 rapeseed varieties. Five different machine learning methods were employed to identify and to extract the flowering areas in each plot. The results suggested that the accuracy of flowering area extraction by the decision tree-based segmentation model (DTSM) was higher than that of naive Bayes, K-nearest neighbours (KNN), random forest (RF) and support vector machine (SVM) in all varieties and flowering dates, with R² = 0.97 and root mean square error (RMSE) = 0.051 pixels/pixels. Data on the proportion of flowering area and its dynamics showed differences in the time and duration of each flowering date among varieties. All varieties were classified into four clusters based on k-means clustering analysis. There were significant differences in eight phenotypic parameters among the four clusters, especially in the time of maximum flowering ratio and the time entering the early and medium flowering dates. The results from this study could provide a basis for rapeseed breeding based on flowering dynamics.

Why it matches plant phenotyping methodsUAV画像と機械学習による rapeseed の開花面積・開花動態の抽出と精度比較が研究の中心であり、植物形質の取得手法を評価している。

abstractTraditional field measurements of rapeseed flowering are time-consuming, labour-intensive and strongly subjective.

Comparing the efficiency of six clearing methods in developing seeds of Arabidopsis thaliana →

Tissue clearing methods eliminate the need for sectioning, thereby helping better understand the 3D organization of tissues and organs. In the past fifteen years, clearing methods have been developed to preserve endogenous fluorescent protein tags. Some of these methods (ClearSee, TDE, PEA-Clarity, etc.) were adapted to clear various plant species, with the focus on roots, leaves, shoot apical meristems, and floral parts. However, these methods have not been used in developing seeds beyond the early globular stage. Tissue clearing is problematic in post-globular seeds due to various apoplastic barriers and secondary metabolites. In this study, we compared six methods for their efficiency in clearing Arabidopsis thaliana seeds at post-globular embryonic stages. Three methods (TDE, ClearSee, and ClearSee alpha) have been already reported in plants whereas the others (fsDISCO, FAST9, and CHAPS clear) are used in this context for the first time. These methods were assessed for seed morphological changes, clearing capacity, removal of tannins, and spectral properties. We tested each method in seeds from globular to mature stages. The pros and cons of each method are listed herein. ClearSee alpha appears to be the method of choice as it preserves seed morphology and prevents tannin oxidation. However, FAST9 with 60% iohexol as a mounting medium is faster, clears better, and appears suitable for embryonic shape imaging. Our results may guide plant researchers to choose a suitable method for imaging fluorescent protein-labeled embryos in intact Arabidopsis seeds. Key messageClearSee alpha and FAST9 were optimized for imaging Arabidopsis seeds up to the torpedo stages. The methods preserve the fluorescence of reporter proteins and seed shape, allowing phenotyping embryos in intact seeds.

Why it matches plant phenotyping methods発生種子を透明化して無傷胚の形態を画像化・表現型解析するための手法を6種類比較・最適化しており、表現型取得法が研究の中心である。

abstractIn this study, we compared six methods for their efficiency in clearing Arabidopsis thaliana seeds at post-globular embryonic stages.

Automatic flower cluster estimation in apple orchards using aerial and ground based point clouds →

Chemical and mechanical thinning processes have long been used in stone and pome fruit production. During the thinning of apple flowers, growers use chemicals to regulate the tree load. Hand thinning is applied after the June drop to prune trees with excess crop load. The process of thinning can be unpredictable especially in biennial bearing cultivars. Thus, incentives to optimise chemical usage and to reduce expensive manual labour is ever increasing. Ground based machine vision systems have grown in popularity in orchard management due to the level of detail as well as plant coverage they can inspect with. Additionally, unmanned aerial vehicles (UAV) -based remote sensing technology is becoming a popular non-invasive quality inspection solution. This work proposes a framework for combining UAV and ground based RGB image data to detect flowering intensity in a Dutch Elstar apple orchard. The framework, based on point cloud reconstruction, presents automatic point cloud handling techniques as well as automated unsupervised flowering intensity estimation methods. Two linear regression models based on unsupervised machine learning methods were trained and validated from the framework that estimate flowering intensity in the orchard with both models having R² > 0.65, RRMSE < 20% and p-stat < 0.005 for the correlation between the image derived flower index and the flower cluster number counted in field. The proposed methods provide a novel strategy for guiding flower thinning using simple RGB images and location data only. Moreover, the proposed methods also reveal the flexibility of intra-tree inspection by checking its sub-volumes.

Why it matches plant phenotyping methodsUAV・地上RGB画像と点群からリンゴ樹の開花強度を自動推定する手法を開発し、現地計数で検証しており、植物表現型取得が中心である。

abstractThis work proposes a framework for combining UAV and ground based RGB image data to detect flowering intensity in a Dutch Elstar apple orchard.

RoseSegNet: An attention-based deep learning architecture for organ segmentation of plants →

An important component for the advancement of plant breeding, genetics, and genomics research is the rapid and accurate measurement of phenotypic traits of large plant populations. The phenotypic data that are of interest can be at multiple levels of plant organization including organ-level geometric characteristics as well as the spatial organization of the organs. 3D computer vision enabling 3D geometry acquisition and processing promises to supply fast, automated phenotypic data collection. One important component of the processing pipeline is the segmentation of the plant into its structural components, such as leaves, stems, and flowers. In this paper, a novel 3D point-based deep learning network, namely RoseSegnet, is proposed for segmentation of point clouds of rosebush plants to their organs. The network is equipped with two attention-based modules, one for extracting contextual features at the encoder phase, another for feature propagation at the decoder phase. The network processes regions of points in a hierarchical manner, where at each level, point features are aggregated using attention-based operators. The aggregation is performed by incorporating point relations both within and between the receptive fields, defined by the hierarchical organization of points. RoseSegNet outperforms the widely-used architecture PointNet++ by 4% in terms of MIoU on the publicly available ROSE-X data set. Also, it is demonstrated that introducing local surface features together with the spatial coordinates of each 3D point at the input level boosts the segmentation performance of both networks by 9% in terms of MIoU.

Why it matches plant phenotyping methods植物器官の3D点群を自動分割する深層学習手法を開発し、既存手法と定量比較しており、植物表現型取得パイプラインの中核手法である。

abstractIn this paper, a novel 3D point-based deep learning network, namely RoseSegnet, is proposed for segmentation of point clouds of rosebush plants to their organs.

A novel plant leaf disease detection by adaptive fuzzy C-Means clustering with deep neural network →

The contribution of a plant is most significant for both human life and nature. The plant diseases affect whole plants, including leaves, stems, fruit, root, and flower. However, conventional approaches enclosed human involvement in classifying and identifying diseases. This process takes more time to complete a task. The main intention of this paper is to effectively develop a deep structured architecture for the detection of plant leaf diseases by introducing intelligent techniques, which have several processing steps. As a major contribution, Adaptive Fuzzy C-Means Clustering (FCM) is adopted for the abnormality segmentation. Moreover, the Improved Deep Neural Network (I-DNN) has achieved the greatest strength in enhancing the performance of plant leaf disease recognition. Here, Newly Updated Moth-Flame Optimization (NU-MFO) is utilised for enhancing the classification efficiency through a valuable objective function. The recommended method achieves higher accuracy rate in the recognition of diseases when compared to the baseline approaches. The precision of the NU-MFO-I-DNN at 85% learning rate is 0.01%, 0.26%, 0.07%, and 0.28% higher than MFO-I-DNN, GWO-I-DNN, SSO-I-DNN, and PSO-I-DNN, respectively.

Why it matches plant phenotyping methods植物葉の病徴を画像から分割・認識する手法の開発が主題であり、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。

abstractThe main intention of this paper is to effectively develop a deep structured architecture for the detection of plant leaf diseases by introducing intelligent techniques, which have several processing steps.

Multiple disease detection method for greenhouse-cultivated strawberry based on multiscale feature fusion Faster R_CNN →

Disease has a significant impact on strawberry quality and yield, and deep learning has become an important approach for the detection of crop disease. To address the problems of complex backgrounds and small disease spots in strawberry disease images from natural environments, we propose a new Faster R_CNN architecture. The multiscale feature fusion network is composed of ResNet, FPN, and CBAM blocks, and it can effectively extract rich strawberry disease features. We built a dataset for strawberry leaves, flowers and fruits, and the experimental results showed that the model was able to effectively detect healthy strawberries and seven strawberry diseases under natural conditions, with an mAP of 92.18% and an average detection time of only 229 ms. The model is compared with Mask R_CNN and YOLO-v3, and we find that our model can guarantee high accuracy and fast detection operational requirements. Our method provides an effective solution for crop disease detection and can improve farmers' management of the strawberry growing process.

Why it matches plant phenotyping methodsイチゴの葉・花・果実画像から病害状態を検出する深層学習手法を開発し、データセット構築、比較評価、精度・速度検証を行っており、植物フェノタイピング手法が研究の中心である。

abstractwe propose a new Faster R_CNN architecture.

Deep learning-based accurate grapevine inflorescence and flower quantification in unstructured vineyard images acquired using a mobile sensing platform →

Early grapevine yield forecasting at satisfactory accuracy is among the major trends in precision viticulture research. Conventionally, yield is estimated manually through extrapolation right before harvest, which is mostly inaccurate, requires considerable labor as well as resources, and is often destructive. The number of flowers per vine is one of the main determinants of grapevine yield and can be used as an early indicator for viticulture yield forecasting. In the present study, a non-invasive, automated image analysis framework was proposed for quantifying flowers in unstructured RGB images of grapevine canopies. Images were automatically acquired under field conditions at night, using a mobile sensing platform equipped with artificial illumination. Due to the small shape and dense distribution of individual flowers (a few hundred per inflorescence) and the similar hue of all plant organs in the fore- and background, efficient flower quantification in images is challenging. To overcome this, we adopted a two-step segmentation approach in our algorithm. First, image regions containing inflorescences were recognized and extracted by segmenting each instance of inflorescences in the image using a mask region-based convolutional neural network (Mask R-CNN), followed by test-time augmentation post-processing to achieve high accuracy. Finally, individual flowers in the extracted inflorescences were detected and quantified using another Mask R-CNN model preceded by a contrast enhancement pre-processing operation. For efficient segmentation and quantification of individual flowers, a high-resolution full image was split down into smaller patches and processed in multiple iterations during inference. The algorithm yielded significant performances, with F1 score values of 0.943 and 0.903 for inflorescence segmentation and single flower detection tasks, respectively, against a test set of 75 images from three different cultivars. A determination coefficient (R²) of 0.98 and a normalized root mean square error of 12.24% were obtained in the test set between the automatic flower number quantification and manual counts. In conclusion, the proposed algorithm constitutes a promising approach for automatically predicting yield potential in the early stages of grapevine development, and it can be used for objective monitoring and optimal management of commercial vineyards.

Why it matches plant phenotyping methodsブドウの花序および花数という植物形質を、移動センシングプラットフォームと深層学習画像解析で自動抽出・定量する手法が研究の中心であり、複数品種で性能検証も行っている。

abstracta non-invasive, automated image analysis framework was proposed for quantifying flowers in unstructured RGB images of grapevine canopies.

Multi-Information Model for Large-Flowered Chrysanthemum Cultivar Recognition and Classification. →

The traditional Chinese large-flowered chrysanthemum is one of the cultivar groups of chrysanthemum ( Chrysanthemum × morifolium Ramat.) with great morphological variation based on many cultivars. Some experts have established several large-flowered chrysanthemum classification systems by using the method of comparative morphology. However, for many cultivars, accurate recognition and classification are still a problem. Combined with the comparative morphological traits of selected samples, we proposed a multi-information model based on deep learning to recognize and classify large-flowered chrysanthemum. In this study, we collected the images of 213 large-flowered chrysanthemum cultivars in two consecutive years, 2018 and 2019. Based on the 2018 dataset, we constructed a multi-information classification model using non-pre-trained ResNet18 as the backbone network. The model achieves 70.62% top-5 test accuracy for the 2019 dataset. We explored the ability of image features to represent the characteristics of large-flowered chrysanthemum. The affinity propagation (AP) clustering shows that the features are sufficient to discriminate flower colors. The principal component analysis (PCA) shows the petal type has a better interpretation than the flower type. The training sample processing, model training scheme, and learning rate adjustment method affected the convergence and generalization of the model. The non-pre-trained model overcomes the problem of focusing on texture by ignoring colors with the ImageNet pre-trained model. These results lay a foundation for the automated recognition and classification of large-flowered chrysanthemum cultivars based on image classification.

Why it matches plant phenotyping methods画像と比較形態情報を用いてキク品種を認識・分類する深層学習モデルを開発し、別年データで性能評価している。花色や花弁型など観察可能な植物形態の抽出・表現も検討されており、手法が研究の中心である。

abstractwe proposed a multi-information model based on deep learning to recognize and classify large-flowered chrysanthemum

Application of Convolutional Neural Network-Based Detection Methods in Fresh Fruit Production: A Comprehensive Review →

As one of the representative algorithms of deep learning, a convolutional neural network (CNN) with the advantage of local perception and parameter sharing has been rapidly developed. CNN-based detection technology has been widely used in computer vision, natural language processing, and other fields. Fresh fruit production is an important socioeconomic activity, where CNN-based deep learning detection technology has been successfully applied to its important links. To the best of our knowledge, this review is the first on the whole production process of fresh fruit. We first introduced the network architecture and implementation principle of CNN and described the training process of a CNN-based deep learning model in detail. A large number of articles were investigated, which have made breakthroughs in response to challenges using CNN-based deep learning detection technology in important links of fresh fruit production including fruit flower detection, fruit detection, fruit harvesting, and fruit grading. Object detection based on CNN deep learning was elaborated from data acquisition to model training, and different detection methods based on CNN deep learning were compared in each link of the fresh fruit production. The investigation results of this review show that improved CNN deep learning models can give full play to detection potential by combining with the characteristics of each link of fruit production. The investigation results also imply that CNN-based detection may penetrate the challenges created by environmental issues, new area exploration, and multiple task execution of fresh fruit production in the future.

Why it matches plant phenotyping methods果実生産におけるCNN検出法を、データ取得からモデル訓練、各工程の手法比較まで体系的に扱うレビューであり、果実・花など植物器官の観測・検出手法が中心である。

titleApplication of Convolutional Neural Network-Based Detection Methods in Fresh Fruit Production: A Comprehensive Review

Stem and Calyx Identification of 3D Apples Using Multi-Threshold Segmentation and 2D Convex Hull →

Traditional machine vision is widely used to identify apple quality, but this method finds it difficult to distinguish the apple stem and calyx from defects. To address this, we designed a new method to identify the stem and calyx of apples based on their concave shape. This method applies a fringe projection in a computer vision system of 3D reconstruction, followed by multi-threshold segmentation and a 2D convex hull technique to identify the stem and calyx. A camera and projector were used to reconstruct the 3D surface of the front half of an inspected apple. The height information for each pixel was reconstructed by a fringe projection and mathematical transformation. The 3D-reconstructed result was subjected to a multi-threshold segmentation technique and the segmentation results contained a concave feature in the curved line, representing the concave stem and calyx. The segmentation results were then subjected to a 2D convex hull technique, allowing for the identification of the stem and calyx. This method was evaluated using four groups of apples, and the proposed method is able to identify the stem and calyx with 98.93% accuracy.

Why it matches plant phenotyping methods3D画像再構成、マルチ閾値分割、凸包によってリンゴの茎・がくという器官形状を抽出する手法を開発・評価しており、植物表現型取得が中心である。

abstractwe designed a new method to identify the stem and calyx of apples based on their concave shape.

Fast anther dehiscence status recognition system established by deep learning to screen heat tolerant cotton. →

Background From an economic perspective, cotton is one of the most important crops in the world. The fertility of male reproductive organs is a key determinant of cotton yield. Anther dehiscence or indehiscence directly determines the probability of fertilization in cotton. Thus, rapid and accurate identification of cotton anther dehiscence status is important for judging anther growth status and promoting genetic breeding research. The development of computer vision technology and the advent of big data have prompted the application of deep learning techniques to agricultural phenotype research. Therefore, two deep learning models (Faster R-CNN and YOLOv5) were proposed to detect the number and dehiscence status of anthers. Result The single-stage model based on YOLOv5 has higher recognition speed and the ability to deploy to the mobile end. Breeding researchers can apply this model to terminals to achieve a more intuitive understanding of cotton anther dehiscence status. Moreover, three improvement strategies are proposed for the Faster R-CNN model, where the improved model has higher detection accuracy than the YOLOv5 model. We have made three improvements to the Faster R-CNN model and after the ensemble of the three models and original Faster R-CNN model, R 2 of "open" reaches to 0.8765, R 2 of "close" reaches to 0.8539, R 2 of "all" reaches to 0.8481, higher than the prediction results of either model alone, which are completely able to replace the manual counting results. We can use this model to quickly extract the dehiscence rate of cotton anthers under high temperature (HT) conditions. In addition, the percentage of dehiscent anthers of 30 randomly selected cotton varieties were observed from the cotton population under normal conditions and HT conditions through the ensemble of the Faster R-CNN model and manual counting. The results show that HT decreased the percentage of dehiscent anthers in different cotton lines, consistent with the manual method. Conclusions Deep learning technology have been applied to cotton anther dehiscence status recognition instead of manual methods for the first time to quickly screen HT-tolerant cotton varieties. Deep learning can help to explore the key genetic improvement genes in the future, promoting cotton breeding and improvement.

Why it matches plant phenotyping methods綿花の葯の開裂状態という植物形質を、深層学習による画像認識で自動抽出・計数する手法を開発し、手動計数と比較検証しているため、フェノタイピング手法が中心である。

abstractTherefore, two deep learning models (Faster R-CNN and YOLOv5) were proposed to detect the number and dehiscence status of anthers.

An Automated, Clip-Type, Small Internet of Things Camera-Based Tomato Flower and Fruit Monitoring and Harvest Prediction System. →

Automated crop monitoring using image analysis is commonly used in horticulture. Image-processing technologies have been used in several studies to monitor growth, determine harvest time, and estimate yield. However, accurate monitoring of flowers and fruits in addition to tracking their movements is difficult because of their location on an individual plant among a cluster of plants. In this study, an automated clip-type Internet of Things (IoT) camera-based growth monitoring and harvest date prediction system was proposed and designed for tomato cultivation. Multiple clip-type IoT cameras were installed on trusses inside a greenhouse, and the growth of tomato flowers and fruits was monitored using deep learning-based blooming flower and immature fruit detection. In addition, the harvest date was calculated using these data and temperatures inside the greenhouse. Our system was tested over three months. Harvest dates measured using our system were comparable with the data manually recorded. These results suggest that the system could accurately detect anthesis, number of immature fruits, and predict the harvest date within an error range of ±2.03 days in tomato plants. This system can be used to support crop growth management in greenhouses.

Why it matches plant phenotyping methodsトマトの花・果実の検出、開花時期と未熟果数の推定、収穫日の予測を行うカメラ型フェノタイピングシステムの設計・検証が研究の中心である。

abstractan automated clip-type Internet of Things (IoT) camera-based growth monitoring and harvest date prediction system was proposed and designed for tomato cultivation

Morphological analysis and stage determination of anther development in Sorghum [Sorghum bicolor (L.) Moench]. →

Main conclusion The characteristics of sorghum anthers at 18 classified developmental stages provide an important reference for future studies on sorghum reproductive biology and abiotic stress tolerance of sorghum pollen. Sorghum (Sorghum bicolor L. Moench) is the fifth-most important cereal crop in the world. It has relatively high resilience to drought and high temperature stresses during vegetative growing stages comparing to other major cereal crops. However, like other cereal crops, the sensitivity of male organ to heat and drought can severely depress sorghum yield due to reduced fertility and pollination efficiency if the stress occurs at the reproductive stage. Identification of the most vulnerable stages and the genes and genetic networks that differentially regulate the abiotic stress responses during anther development are two critical prerequisites for targeted molecular trait selection and for enhanced environmentally resilient sorghum in breeding using a variety of genetic modification strategies. However, in sorghum, anther developmental stages have not been determined. The distinctive cellular characteristics associated with anther development have not been well examined. Lack of such critical information is a major obstacle in the studies of anther and pollen development in sorghum. In this study, we examined the morphological changes of sorghum anthers at cellular level during entire male organ development processes using a modified high-throughput imaging variable pressure scanning electron microscopy and traditional light microscopy methods. We divided sorghum anther development into 18 distinctive stages and provided detailed description of the morphological changes in sorghum anthers for each stage. The findings of this study will serve as an important reference for future studies focusing on sorghum physiology, reproductive biology, genetics, and genomics.

Why it matches plant phenotyping methodsソルガム葯の発達段階を分類するため、高スループット画像法と光学顕微鏡を用いた形態計測・解析が研究の中心であり、植物器官の状態を抽出するフェノタイピング手法に該当する。

abstractwe examined the morphological changes of sorghum anthers at cellular level during entire male organ development processes using a modified high-throughput imaging variable pressure scanning electron microscopy and traditional light microscopy methods.

A set of sampling, preparation, and staining techniques for studying meiosis in cucumber. →

The development of genetic and genomic resources for biological studies in cucumber has experienced an unprecedented boom in recent years. To investigate the function of putative meiotic genes and germplasm in breeding programs, an accurate cytogenetic characterization is required. Cytological methods and reference to investigate meiosis in cucumber are limited at present. Here we provide a set of cytological techniques that have been adapted for the study of meiosis in cucumber. The meiotic stages can be identified with high precision using hierarchical criteria from developing buds, undisturbed meiocytes, and freshly stained chromosomes. A meiotic cytological atlas of all stages is presented as a reference for identifying particular stages and for comparison of meiosis between normal and mutant plants. We performed a comparative analysis of the distribution of cytoplasmic organelles between cucumber and Arabidopsis, and we described a highly nonsynchronous condensation of chromosome parts during diplotene. A simplified fluorescence in situ hybridization (FISH) protocol, using robustly spread chromosomes, were developed. In addition, we designed a single oligonucleotide probe for 5S rDNA to use in karyotyping and monitoring of homologous chromosome pairing, which will make FISH analysis of 5S rDNA easier and more economical.

Why it matches plant phenotyping methodsキュウリの減数分裂段階・染色体構造・相同染色体対合を観察するための細胞学的手法とFISHプロトコルの開発が中心であり、植物の細胞遺伝学的状態を測定する方法論研究である。

abstractHere we provide a set of cytological techniques that have been adapted for the study of meiosis in cucumber.

Weakly-supervised learning to automatically count cotton flowers from aerial imagery →

Counting plant flowers is a common task with applications for estimating crop yields and selecting favorable genotypes. Typically, this requires a laborious manual process, rendering it impractical to obtain accurate flower counts throughout the growing season. The model proposed in this study uses weak supervision, based on Convolutional Neural Networks (CNNs), which automates such a counting task for cotton flowers using imagery collected from an unmanned aerial vehicle (UAV). Furthermore, the model is trained using Multiple Instance Learning (MIL) in order to reduce the required amount of annotated data. MIL is a binary classification task in which any image with at least one flower falls into the positive class, and all others are negative. In the process, a novel loss function was developed that is designed to improve the performance of image-processing models that use MIL. The model is trained on a large dataset of cotton plant imagery which was collected over several years and will be made publicly available. Additionally, an active-learning-based approach is employed in order to generate the annotations for the dataset while minimizing the required amount of human intervention. Despite having minimal supervision, the model still demonstrates good performance on the testing dataset. Multiple models were tested with different numbers of parameters and input sizes, achieving a minimum average absolute count error of 2.43. Overall, this study demonstrates that a weakly-supervised model is a promising method for solving the flower counting problem while minimizing the human labeling effort.

Why it matches plant phenotyping methodsUAV画像からワタの花数という植物器官形質を自動推定する弱教師あり画像解析法を開発し、損失関数・MIL・能動学習・データセットを評価しており、フェノタイピング手法が中心である。

abstractThe model proposed in this study uses weak supervision, based on Convolutional Neural Networks (CNNs), which automates such a counting task for cotton flowers using imagery collected from an unmanned aerial vehicle (UAV).

Synergy of optical and synthetic aperture radar data for early-stage crop yield estimation: a case study over a state of Germany →

Traditional crop cutting experiment-based yield estimation method captures the regional yield variability but lacks field-level information. Satellite images hold enormous crop information at finer spatial resolution. Crop yield mapping with optical images is particularly challenging if cloud-free images are unavailable during the crucial crop developmental stages. All-weather availability and sensitivity to crop structure, dielectric properties make synthetic aperture radar (SAR) images an excellent resource for yield estimation. Both types of data provide complementary information about crop conditions. A random forest regression model with genetic algorithm-based feature selection is developed to exploit the Sentinel-2 optical and Sentinel-1 SAR images for yield estimation. We utilized the crop harvest and quality survey (BEE) yield data set collected by the Hessisches Statistisches Landesamt (HSL), Wiesbaden, Germany, over 490 fields. We prepared 20 m resolution yield maps for winter wheat, winter barley, winter rye and winter rapeseed. Input features for the yield estimation model are selected based on the prior knowledge of remote sensing of vegetation. Baseline random forest regression models are developed for all the four crop types with optical and SAR input features. An optimized random forest regression model with genetic algorithm-based feature selection results in performance improvement. Dissimilarity in genetic algorithm selected image features highlights the significance of crop-specific feature selection for yield estimation. The optimized models reliably estimate yield by achieving correlation coefficient (r) of 0.65–0.86, mean absolute error 0.93–1.16 t ha–1 and root mean square error 1.12–1.56 t ha–1 with BEE yield on testing data set. The proposed models could estimate the intra-field yield variation when winter wheat, winter barley, winter rye were in the shooting phase to the beginning of ear-shifting, and winter rapeseed began to flower or was already flowering. These results demonstrate the merits of our model for early-stage crop yield estimation at the field level with mono-temporal image and adaptability for the cropping season with high cloud cover.

Why it matches plant phenotyping methods衛星光学・SAR画像から圃場内の作物収量を推定するモデルを開発・検証しており、植物の収量という形質の取得・推定手法が研究の中心である。

abstractA random forest regression model with genetic algorithm-based feature selection is developed to exploit the Sentinel-2 optical and Sentinel-1 SAR images for yield estimation.

Flower Mapping in Grasslands With Drones and Deep Learning. →

Manual assessment of flower abundance of different flowering plant species in grasslands is a time-consuming process. We present an automated approach to determine the flower abundance in grasslands from drone-based aerial images by using deep learning (Faster R-CNN) object detection approach, which was trained and evaluated on data from five flights at two sites. Our deep learning network was able to identify and classify individual flowers. The novel method allowed generating spatially explicit maps of flower abundance that met or exceeded the accuracy of the manual-count-data extrapolation method while being less labor intensive. The results were very good for some types of flowers, with precision and recall being close to or higher than 90%. Other flowers were detected poorly due to reasons such as lack of enough training data, appearance changes due to phenology, or flowers being too small to be reliably distinguishable on the aerial images. The method was able to give precise estimates of the abundance of many flowering plant species. In the future, the collection of more training data will allow better predictions for the flowers that are not well predicted yet. The developed pipeline can be applied to any sort of aerial object detection problem.

Why it matches plant phenotyping methodsドローン画像と深層学習により植物種ごとの花量を自動推定する手法の開発・評価が研究の中心であり、植物形質の取得方法を直接扱っている。

abstractWe present an automated approach to determine the flower abundance in grasslands from drone-based aerial images by using deep learning (Faster R-CNN) object detection approach, which was trained and evaluated on data from five flights at two sites.

Hyperspectral Imaging With Machine Learning to Differentiate Cultivars, Growth Stages, Flowers, and Leaves of Industrial Hemp ( Cannabis sativa L.). →

L.) grown for cannabidiol (CBD) has spurred a surge of interest in the United States. Cultivar selection and harvest timing are important to produce CBD hemp profitably and avoid economic loss resulting from the tetrahydrocannabinol (THC) concentration in the crop exceeding regulatory limits. Hence there is a need for differentiating CBD hemp cultivars and growth stages to aid in cultivar and genotype selection and optimization of harvest timing. Current methods that rely on visual assessment of plant phenotypes and chemical procedures are limited because of its subjective and destructive nature. In this study, hyperspectral imaging was proposed as a novel, objective, and non-destructive method for differentiating hemp cultivars, growth stages as well as plant organs (leaves and flowers). Five cultivars of CBD hemp were grown greenhouse conditions and leaves and flowers were sampled at five growth stages 2-10 weeks in 2-week intervals after flower initiation and scanned by a benchtop hyperspectral imaging system in the spectral range of 400-1000 nm. The acquired images were subjected to image processing procedures to extract the spectra of hemp samples. The spectral profiles and scatter plots of principal component analysis of the spectral data revealed a certain degree of separation between hemp cultivars, growth stages, and plant organs. Machine learning based on regularized linear discriminant analysis achieved the accuracy of up to 99.6% in differentiating the five hemp cultivars. Plant organ and growth stage need to be factored into model development for hemp cultivar classification. The classification models achieved 100% accuracy in differentiating the five growth stages and two plant organs. This study demonstrates the effectiveness of hyperspectral imaging for differentiating cultivars, growth stages and plant organs of CBD hemp, which is a potentially useful tool for growers and breeders of CBD hemp.

Why it matches plant phenotyping methods植物の品種、成長段階、器官を非破壊的に識別するハイパースペクトル画像法と機械学習ワークフローが中心的に開発・評価されているため。

abstracthyperspectral imaging was proposed as a novel, objective, and non-destructive method for differentiating hemp cultivars, growth stages as well as plant organs (leaves and flowers).

Live-imaging provides an atlas of cellular growth dynamics in the stamen. →

Development of multicellular organisms is a complex process involving precise coordination of growth among individual cells. Understanding organogenesis requires measurements of cellular behaviors over space and time. In plants, such a quantitative approach has been successfully used to dissect organ development in both leaves and external floral organs, such as sepals. However, the observation of floral reproductive organs is hampered as they develop inside tightly closed floral buds, and are therefore difficult to access for imaging. We developed a confocal time-lapse imaging method, applied here to Arabidopsis (Arabidopsis thaliana), which allows full quantitative characterization of the development of stamens, the male reproductive organs. Our lineage tracing reveals the early specification of the filament and the anther. Formation of the anther lobes is associated with a temporal increase of growth at the lobe surface that correlates with intensive growth of the developing locule. Filament development is very dynamic and passes through three distinct phases: (1) initial intense, anisotropic growth, and high cell proliferation; (2) restriction of growth and proliferation to the filament proximal region; and (3) resumption of intense and anisotropic growth, displaced to the distal portion of the filament, without cell proliferation. This quantitative atlas of cellular growth dynamics provides a solid framework for future studies into stamen development.

Why it matches plant phenotyping methods花蕾内部の雄蕊を対象に、共焦点タイムラプス画像法を開発し、細胞成長を定量化する手法が研究の中心であるため。

abstractWe developed a confocal time-lapse imaging method, applied here to Arabidopsis (Arabidopsis thaliana), which allows full quantitative characterization of the development of stamens, the male reproductive organs.

A semi in vivo pollination technique to assess the level of gametophytic self-incompatibility and pollen tube growth in pear (Pyrus communis L.). →

Key message We describe a semi in vivo pollination technique to determine the compatibility relation between different pear cultivars. This assay provides a valuable addition to existing tools in GSI research. The gametophytic self-incompatibility (GSI) system in Pyrus inhibits fertilization by pollen that shares one of the two S-alleles of the style. Depending on their S-locus genotype, two pear cultivars therefore either show a cross-compatible, semi-compatible or incompatible interaction. Because GSI greatly influences seed and fruit set, accurate knowledge of the compatibility type of a cultivar is key for both pear fruit production and breeding. Currently, compatibility relations between different pear cultivars are generally assessed via S-genotyping. However, this approach is restricted to the currently known S-alleles in pear, and does not provide functional assessment of the level of (self-)incompatibility. We here present an optimized semi in vivo pollination assay, that enables quantitative analysis of (self-)incompatibility in pear, and that can also serve useful for more fundamental studies on pollen tube development and pollen-style interactions. This assay involves in vitro incubation of cut pollinated styles followed by microscopic counting of emerging pollen tubes at a specific time interval. The validity and selectivity of this method to determine compatibility interactions in pear is demonstrated in the cultivars "Celina" and "Packham's Triumph." Overall, this technique constitutes a valuable tool for quantitatively determining in vivo pollen tube growth and (cross-)compatibility in pear.

Why it matches plant phenotyping methodsナシの受粉後の花粉管成長と交雑適合性を定量化する半生体測定法を開発・最適化し、品種で妥当性を実証しているため、植物表現型取得法が中心である。

abstractWe here present an optimized semi in vivo pollination assay, that enables quantitative analysis of (self-)incompatibility in pear

Optical Clearing of Plant Tissues for Fluorescence Imaging. →

It is challenging to directly observe the internal structure of multi-layered and opaque plant specimens, without dissection, under a microscope. In addition, autofluorescence attributed to chlorophyll hampers the observation of fluorescent proteins in plants. For a long time, various clearing reagents have been used to make plants transparent. However, conventional clearing reagents diminish fluorescent signals; therefore, it has not been possible to observe the cellular and intracellular structures with fluorescent proteins. Reagents were developed that can clear plant tissues by removing chlorophyll while maintaining fluorescent protein stability. A detailed protocol is provided here for the optical clearing of plant tissues using clearing reagents, ClearSee (CS) or ClearSeeAlpha (CSA). The preparation of cleared plant tissues involves three steps: fixation, washing, and clearing. Fixation is a crucial step in maintaining the cellular structures and intracellular stability of fluorescent proteins. The incubation time for clearing depends on the tissue type and species. In Arabidopsis thaliana, the time required for clearing with CS was 4 days for leaves and roots, 7 days for seedlings, and 1 month for pistils. CS also required a relatively short time of 4 days to make the gametophytic leaves of Physcomitrium patens transparent. In contrast, pistils in tobacco and torenia produced brown pigment due to oxidation during CS treatment. CSA reduced the brown pigment by preventing oxidation and could make tobacco and torenia pistils transparent, although it took a relatively long time (1 or 2 months). CS and CSA were also compatible with staining using chemical dyes, such as DAPI (4',6-diamidino-2-phenylindole) and Hoechst 33342 for DNA and Calcofluor White, SR2200, and Direct Red 23 for the cell wall. This method can be useful for whole-plant imaging to reveal intact morphology, developmental processes, plant-microbe interactions, and nematode infections.

Why it matches plant phenotyping methods植物組織を透明化し、蛍光シグナルを維持したまま細胞構造・形態・発達過程を観察するための具体的なイメージングプロトコルを開発・提示しており、植物表現型取得法が中心である。

abstractReagents were developed that can clear plant tissues by removing chlorophyll while maintaining fluorescent protein stability.

High-Throughput Fluorescent Pollen Tetrad Analysis Using DeepTetrad. →

Meiotic recombination initiates from ~100-200 s of programmed DNA double stranded breaks (DSBs) in plants. Meiotic DSBs can be repaired using homologous chromosomes to generate a crossover . Meiotic crossover is critical for chromosomal segregation and increasing genetic variation. The number of crossovers is limited to one and three per chromosome pair in most plant species. Genetic, epigenetic, and environmental factors control crossover frequency and distribution. Due to the limited number of crossovers it is challenging to measure crossover frequency along chromosomes. We adapted fluorescence-tagged lines (FTLs ) that contain quartet1 mutations and linked transgenes expressing dsRed, eYFP, and eCFP in pollen tetrads into the deep learning-based image analysis tool, DeepTetrad. DeepTetrad enables the measurement of crossover frequency and interference by classifying 12 types of tetrads from three-color FTLs in a high-throughput manner, using conventional microscope instruments and a Linux machine. Here, we provide detailed procedures for preparing tetrad samples, tetrad imaging, running DeepTetrad, and analysis of DeepTetrad outputs. DeepTetrad-based measurements of crossover frequency and interference ratio will accelerate the genetic dissection of meiotic crossover control.

Why it matches plant phenotyping methods植物の花粉四分子画像から交差頻度と干渉を高スループットに抽出するDeepTetradの手法開発・プロトコル提示が中心であり、植物状態の測定法に該当する。

abstractWe adapted fluorescence-tagged lines (FTLs ) that contain quartet1 mutations and linked transgenes expressing dsRed, eYFP, and eCFP in pollen tetrads into the deep learning-based image analysis tool, DeepTetrad.

How to measure flower ultraviolet reflectance using digital photography →

AIMS: Flower ultraviolet (UV) reflectance strongly influences insects’ ability to detect flowers and locate pollen/nectar sources. Although included in the TRY database, the lack of a cost‐effective standardised method of measurement hampers the availability of information on this key floral trait. Digital photography and image processing allow for a novel approach to flower UV reflectance measurement that is both accessible and accurate. LOCATION: European semi‐natural grasslands. METHODS: We used a UV‐LED light and a mirrorless camera with a filter, which represents a low‐cost equipment for narrow emission/reflection photography (350–380 nm). Flowers were photographed with two standards of known reflection, and UV reflectance values were obtained using open‐source image processing software. We measured UV reflectance for 57 plant species typical of European semi‐natural grasslands. RESULTS: Our values substantially matched the categorical classes obtained by analogue photography available in TRY and showed a highly significant relationship with spectrophotometric measures. CONCLUSIONS: The method proposed here overcomes the one based on analogue photography and subjective visual estimates, and represents an easy and low‐cost alternative to spectrophotometry. It may promote the standardised measurement of flower UV reflectance and broaden the information of this trait globally, meeting the needs of functional ecology and trait‐based community assembly studies.

Why it matches plant phenotyping methods花のUV反射率という植物形質をデジタル撮影・画像処理で測定する低コスト手法を開発し、分光測定等と検証しており、フェノタイピング手法が中心である。

abstractDigital photography and image processing allow for a novel approach to flower UV reflectance measurement that is both accessible and accurate.

Dimensionality Reduction of High-throughput Phenotyping Data in Cotton Fields →

In this paper, we implement data reduction methods to reduce the size of image datasets from cotton fields for use in a high-throughput phenotyping (HTP) pipeline in order to allow for data transfer more quickly over poor internet connections. We investigate dimensionality reduction methods to accomplish this goal. Specifically, we utilize Principal Component Analysis (PCA) to compress image data into a smaller dimension space, which when uncompressed retains significant variability from the original image. To demonstrate the ability of PCA to produce quality reconstructions, we consider the example use case of detecting cotton bloom flowering patterns with reconstructed images. We employ Open Source Computer Vision (OpenCV) to generate pixel-wise masks which both further reduces the byte size of data and successfully identifies cotton bloom flowering. The results indicate a high amount of data reduction from the original to the reconstructed images; byte sizes reduce 93% through PCA while preserving around 98% variance when using a much smaller number of components. Bitwise masking with OpenCV yields a 99% reduction in file size. The results demonstrate great potential in employing machine learning techniques for the data reduction pre-processing step prior to performing subsequent analysis. This data reduction is a crucial step in developing a field-based HTP big data pipeline.

Why it matches plant phenotyping methods綿花の高スループット画像データを圧縮し、再構成画像から開花パターンを検出する前処理・画像解析手法が中心であり、植物形質の取得に直接関係する。

abstractwe implement data reduction methods to reduce the size of image datasets from cotton fields for use in a high-throughput phenotyping (HTP) pipeline

Plant-Pollinator Specialization: Origin and Measurement of Curvature. →

AbstractA feature of biodiversity is the abundance of curves displayed by organs and organisms. Curvature is a widespread, convergent trait that has important ecological and evolutionary implications. In pollination ecology, the curvature of flowers and pollinator mouthparts (e.g., hummingbird bills) along the dorsiventral plane has been associated with specialization, competition, and species coexistence. Six differing methods have historically been used to measure curvature in pollination systems; we provide a solution to this inconsistency by defining curvature using well-established concepts from differential geometry. Intuitively, curvature is the degree to which a line is not straight, but more formally it is the rate at which the tangent of a curve changes direction with respect to arc length. Here, we establish a protocol wherein a line is fitted against landmarks placed on an image of a curved organ or organism, then curvature is computed at many points along the fitted line and the sum taken. The protocol is demonstrated by studying the development of nectar spur curvature in the flowering plant genus Epimedium (Berberidaceae). By clarifying the definition of curvature, our aim is to make the language of comparative morphology more precise and broadly applicable to capture other curved structures in nature.

Why it matches plant phenotyping methods植物器官の曲率を画像上のランドマークと曲線フィッティングから定量するプロトコルを定義・実証しており、表現型取得法が研究の中心である。

abstractwe provide a solution to this inconsistency by defining curvature using well-established concepts from differential geometry.

Fast Anther Dehiscence Status Recognition System Establishing by Deep Learning to Screen Heat Tolerant Cotton →

Abstract Background Cotton is one of the most economically important crops in the world. The fertility of male reproductive organs is a key determinant of cotton yield. The anther dehiscence or indehiscence directly determine the probability of fertilization in cotton. Thus, the rapid and accurate identification of cotton anther dehiscence status is important for judging anther growth status and promoting genetic breeding research. The development of computer vision technology and the advent of big data have prompted the application of deep learning techniques to agricultural phenotype research. Therefore, two deep learning models (Faster R-CNN and YOLOv5) were proposed to detect the number and dehiscence status of anthers. Result The single-stage model based on YOLOv5 has higher recognition efficiency and the ability to deploy to the mobile end. Breeding researchers can apply this model to terminals to achieve a more intuitive understanding of cotton anther dehiscence status. Moreover, three improvement strategies of Faster R-CNN model were proposed, the improved model has higher detection accuracy than YOLOv5 model. We have made four improvements to the Faster R-CNN model and after the ensemble of the four models, R2 of “open” reaches 0.8765, R2 of “close” reaches 0.8539, R2 of “all” reaches 0.8481, higher than the prediction result of either model alone, and can completely replace the manual counting method. We can use this model to quickly extract the dehiscence rate of cotton anther under high temperature (HT) condition. In addition, the percentage of dehiscent anther of randomly selected 30 cotton varieties were observed from cotton population under normal conditions and HT conditions through the ensemble of Faster R-CNN model and manual observation. The result showed HT varying decreased the percentage of dehiscent anther in different cotton lines, consistent with the manual method. Conclusions The deep learning technology first time been applied to cotton anther dehiscence status recognition instead of manual method to quickly screen the HT tolerant cotton varieties and can help to explore the key genetic improvement genes in the future, promote cotton breeding and improvement.

Why it matches plant phenotyping methods綿花葯の開裂状態という植物生殖形質を対象に、深層学習による検出・計数モデルを開発し、精度比較と手動法との検証、耐暑性スクリーニングへの適用を行っており、表現型取得法が研究の中心である。

abstracttwo deep learning models (Faster R-CNN and YOLOv5) were proposed to detect the number and dehiscence status of anthers.

Reliability of a commercial platform for estimating flower cluster and fruit number, yield, tree geometry and light interception in apple trees under different rootstocks and row orientations →

Modern horticulture is undergoing a rapid change with the introduction of new predictive technologies that help maximise the automation of orchard management practices. This study aimed to calibrate and validate a commercial sensorised mobile platform for the prediction of flower cluster number, fruit number and yield, tree geometry in ‘ANABP-01′ apples. In addition, this work (i) modelled the relationships between tree geometry and light interception, and (ii) determined the effects of light interception, rootstock and row orientation on flower cluster number, crop load, yield and tree geometry. Results showed that predictions were very accurate after initial calibration. Flower cluster detections had an error (RMSE) of ∼ 5 clusters / image. Fruit number and yield predictions needed independent calibration across rootstocks but errors after validation on a separate dataset were small (RMSE = 5 fruit / tree, and RMSE = 1 kg / fruit, for fruit number and yield, respectively). Orchard errors for fruit number and yield estimations were lower than 5 %. Canopy area, canopy density and canopy cross-sectional leaf area (CSLA) were all linearly related with effective area of shade (EAS, integrated daily canopy light interception) but CSLA had the most robust and stable relationship with intercepted light. Increasing CSLA led to higher flower cluster number, fruit number and yield. Row orientations and rootstocks significantly affected productive performance, tree size and geometry and light interception. The orchard heatmaps generated after data validation proved very useful to support orchard management decisions. Overall, the predictive technology demonstrated to be a valid tool to combine accurate estimates of several important fruit crop parameters (i.e. flower cluster number, fruit number, yield, tree size and geometry, and light interception) in a single platform.

Why it matches plant phenotyping methodsリンゴ樹の花房数、果実数、収量、樹体形状、光 interception を推定する商用センサー搭載移動プラットフォームを較正・検証しており、表現型取得手法が研究の中心である。

abstractThis study aimed to calibrate and validate a commercial sensorised mobile platform for the prediction of flower cluster number, fruit number and yield, tree geometry in ‘ANABP-01′ apples.

Visual classification of apple bud-types via attention-guided data enrichment network →

The number of flower buds on the apple tree is the crucial factor for fruit load determining, thus the essence of apple tree pruning is bud removal. Most horticulture activities in apple orchards at present primarily rely on skilled farmers. However, distinguishing between different types of apple buds is still hard work for many planters due to their similar appearances. The most recent published works have proven the superiority of computer vision and deep learning in image recognition tasks. Deep convolutional neural network (DCNN) is an efficient type of network in deep learning architecture for visual features analysis. To categorize types of apple bud at the fine-grained level, a DCNN-based visual classification model denoting the attention-guided data enrichment network (ADEN) is proposed. Specifically, in ADEN, the ResNeSt50 network is used as the feature extractor module for characterizing the apple bud trait from each input image. Based on attention maps, the attention-guide data enrichment module, containing attention-guided CutMix and attention-guided erasing, is designed for the task of enriching training samples via dropout and fusing local features of images, which further improves the training efficiency and discriminative ability of the classifier. All the experiments are conducted on the orchard-shot image dataset contained two classes of apple buds, include the flower bud and the leaf bud. The proposed method conveys a consistent and significant improvement in performance and achieves testing accuracy of 92.39% with satisfying precision, recall and f1-score, which outperformed the comparative models. The proposed method can readily realize accurate identification for bud-types of apples and is helping to promote the advancement of pruning and training robotization in orchards.

Why it matches plant phenotyping methodsリンゴの花芽・葉芽という植物器官の状態を画像から分類する深層学習手法を提案し、データ拡張と比較実験で性能を評価しているため、植物フェノタイピング手法が中心である。

abstractTo categorize types of apple bud at the fine-grained level, a DCNN-based visual classification model denoting the attention-guided data enrichment network (ADEN) is proposed.

Predicting sensitivity of recently harvested tomatoes and tomato sepals to future fungal infections. →

Tomato is an important commercial product which is perishable by nature and highly susceptible to fungal incidence once it is harvested. Not all tomatoes are equally vulnerable to pathogenic fungi, and an early detection of the vulnerable ones can help in taking timely preventive actions, ranging from isolating tomato batches to adjusting storage conditions, but also in making right business decisions like dynamic pricing based on quality or better shelf life estimate. More importantly, early detection of vulnerable produce can help in taking timely actions to minimize potential post-harvest losses. This paper investigates Near-infrared (NIR) hyperspectral imaging (1000-1700 nm) and machine learning to build models to automatically predict the susceptibility of sepals of recently harvested tomatoes to future fungal infections. Hyperspectral images of newly harvested tomatoes (cultivar Brioso) from 5 different growers were acquired before the onset of any visible fungal infection. After imaging, the tomatoes were placed under controlled conditions suited for fungal germination and growth for a 4-day period, and then imaged using normal color cameras. All sepals in the color images were ranked for fungal severity using crowdsourcing, and the final severity of each sepal was fused using principal component analysis. A novel hyperspectral data processing pipeline is presented which was used to automatically segment the tomato sepals from spectral images with multiple tomatoes connected via a truss. The key modelling question addressed in this research is whether there is a correlation between the hyperspectral data captured at harvest and the fungal infection observed 4 days later. Using 10-fold and group k-fold cross-validation, XG-Boost and Random Forest based regression models were trained on the features derived from the hyperspectral data corresponding to each sepal in the training set and tested on hold out test set. The best model found a Pearson correlation of 0.837, showing that there is strong linear correlation between the NIR spectra and the future fungal severity of the sepal. The sepal specific predictions were aggregated to predict the susceptibility of individual tomatoes, and a correlation of 0.92 was found. Besides modelling, focus is also on model interpretation, particularly to understand which spectral features are most relevant to model prediction. Two approaches to model interpretation were explored, feature importance and SHAP (SHapley Additive exPlanations), resulting in similar conclusions that the NIR range between 1390-1420 nm contributes most to the model's final decision.

Why it matches plant phenotyping methodsNIRハイパースペクトル画像と機械学習により、トマト萼の将来の真菌感染重症度を予測する手法を開発・評価しており、植物病害状態の取得・推定が研究の中心である。

abstractThis paper investigates Near-infrared (NIR) hyperspectral imaging (1000-1700 nm) and machine learning to build models to automatically predict the susceptibility of sepals of recently harvested tomatoes to future fungal infections.

Fast anther dehiscence state recognition system establishing by deep learning to screen heat tolerant cotton →

Cotton is one of the most economically important crops in the world. The fertility of male reproductive organs is a key determinant of cotton yield. The anther dehiscence or indehiscence directly determine the probability of fertilization in cotton. Thus, the rapid and accurate identification of cotton anther dehiscence status is important for judging anther growth status and promoting genetic breeding research. The development of computer vision technology and the advent of big data have prompted the application of deep learning techniques to agricultural phenotype research. Therefore, two deep learning models (Faster R-CNN and YOLOv5) were proposed to detect the number and dehiscence status of anthers. The single-stage model based on YOLOv5 has higher recognition efficiency and the ability to deploy to the mobile end. Breeding researchers can apply this model to terminals to achieve a more intuitive understanding of cotton anther dehiscence status. Moreover, three improvement strategies of Faster R-CNN model were proposed, the improved model has higher detection accuracy than YOLOv5 model. In addition, the percentage of dehiscent anther of randomly selected 30 cotton varieties were observed from cotton population under normal temperature and high temperature (HT) conditions through the integrated Faster R-CNN model and manual observation. The result showed HT varying decreased the percentage of dehiscent anther in different cotton lines, consistent with the manual method. Thus, this system can help us to rapid and accurate identification of HT-tolerant cotton. One sentence summary The deep learning technique was applied to identify the anther dehiscence state for the first time to quickly screen heat tolerant cotton varieties and help to explore key genetic improvement genes.

Why it matches plant phenotyping methods綿花の葯の開裂状態という植物形質を、深層学習画像認識で検出・定量する手法を開発し、手動観察との比較検証および品種スクリーニングに適用しており、表現型取得法が中心である。

abstractTherefore, two deep learning models (Faster R-CNN and YOLOv5) were proposed to detect the number and dehiscence status of anthers.

Quantitative live-imaging of Aquilegia floral meristems reveals distinct patterns of floral organ initiation and cell-level dynamics of floral meristem termination →

In-depth investigation of any developmental process in plants requires knowledge of both the underpinning molecular networks and how they directly determine patterns of cell division and expansion over time. Floral meristems (FM) produce floral organs, after which they undergo floral meristem termination (FMT), and precise control of organ initiation and FMT is crucial to reproductive success of any flowering plant. Using a live confocal imaging, we characterized developmental dynamics during floral organ primordia initiation and FMT in Aquilegia coerulea (Ranunculaceae). Our results have uncovered distinct patterns of primordium initiation between stamens and staminodes compared to carpels, and provided insight into the process of FMT, which is discernable based on cell division dynamics preceding carpel initiation. To our knowledge, this is the first quantitative live imaging of meristem development in a system with numerous whorls of floral organs as well as an apocarpous gynoecium. This study provides crucial information for our understanding of how the spatial-temporal regulation of floral meristem behavior is achieved in both an evolutionary and developmental context.

Why it matches plant phenotyping methods定量的なライブ共焦点イメージングを中核として、花器官原基の開始と花 meristem 終結の細胞動態を抽出・解析しており、単なる生物学的結果測定ではなく植物形態・発達状態の画像計測に重点がある。

titleQuantitative live-imaging of Aquilegia floral meristems reveals distinct patterns of floral organ initiation and cell-level dynamics of floral meristem termination

Plant-pollinator Specialization: Origin and measurement of curvature →