Accurate litchi counting from whole-tree images is essential for yield estimation, orchard management, and plant phenotyping, but remains challenging in real orchards because fruits occur in dense, heavily occluded clusters and vary markedly in scale, illumination, and appearance across ripening stages, particularly when green fruits resemble surrounding foliage. Existing methods have shown promise, but their robustness in complex orchard environments remains limited. To address these challenges, we propose FG-LCNet, a two-stage foreground-guided litchi counting framework. In the first stage, an enhanced fruit-cluster detector improves the localization of small and ambiguous clusters under complex canopy backgrounds. In the second stage, the detected foreground regions are fed into a density-regression network with hybrid attention, while a consistency-based training strategy is introduced to improve robustness to appearance and illumination variations. To support this study, a large-scale litchi counting dataset was established, consisting of 1,126 whole-tree images collected from five orchards and spanning three ripening stages, with approximately 120,000 fruit-level dot annotations and more than 20,000 cluster-level bounding boxes. FG-LCNet achieved the best overall counting performance, with an MAE of 7.44 and an RMSE of 11.01. It showed clear advantages in high-density fruit-cluster scenarios and cross-orchard validation, while maintaining competitive results across orchard-region and maturity-stage subsets. The framework further retained inference efficiency suitable for practical deployment. These results indicate that FG-LCNet provides an effective solution for robust litchi counting and offers potential for other clustered fruit-counting tasks.
Why it matches plant phenotyping methods果実数という植物器官形質を whole-tree 画像から推定する二段階画像解析手法を開発し、データセット構築と交差果樹園検証まで行っており、表現型取得・抽出法が中心である。
abstractwe propose FG-LCNet, a two-stage foreground-guided litchi counting framework.
Reproduction assets foundThe paper's implementation code is explicitly stated as publicly available at the authors' GitHub repository (FG-LCNet). The litchi counting dataset (1,126 whole-tree images with ~120,000 dot annotations and 20,000+ bounding boxes) is not yet fully public: a ~100-image annotated subset is promised upon acceptance, and,Code · publicdustry Technology Research System (CARS-32-21), Hainan Modern Agricul-
655
tural Industry Technology System (HNARS-08-G02).
656
Conflicts of Interest
657
The authors declare that there is no conflict of interest regarding the publication of this article.
658
Data Availability
659
The implementation code is publicly available at https://github.com/johnhamtom/FG-LCNet .
660
Upon acceptance, a representative subset of approximately 100 annotated litchi images will be
661
released to support reproducibility and preliminary benchmarking. The full dataset is being further
662
organized for future release. Before full release, the complete dataset can be obtained from the
663
corresponding authorOpen asset ↗johnhamtom/FG-LCNetpdf-raw-page:28 lines:1-81Code / dataset availability confirmedCrossref · checked 15 Sept 2026
Fruit quality is a critical determinant of economic returns in pear production, and maintaining an appropriate fruit load (FL) is essential for achieving high yield and quality. As a direct indicator of canopy photosynthetic capacity and assimilate supply, leaf number constitutes the key biological basis of reasonable FL determination under the leaf-to-fruit ratio concept. However, accurate and efficient estimation of leaf number in mature pear trees remains technically challenging, limiting its practical use in precision FL regulation. Here, we propose a data-driven framework for leaf number and reasonable FL estimation by integrating 3D point cloud-derived canopy structure with machine learning. A pipeline for extracting 3D architectural traits was developed and implemented in the software tool FTPCT, enabling rapid and standardized trait acquisition. Through correlation analysis, multicollinearity diagnosis, and variance inflation factor screening, five key traits strongly associated with leaf number were identified and incorporated into five machine learning models optimized using Bayesian optimization. Among them, the optimized random forest regression model achieved the highest and most stable performance, with R 2 of 0.85, RMSE of 239.74, and MAE of 149.26 for test dataset. SHAP analysis identified tree crown volume as the dominant contributor to leaf number estimation. Field validation demonstrated that FL regulation guided by the proposed framework significantly improved fruit weight and size without reducing yield compared with conventional practices. Notably, the proposed approach avoids explicit leaf-level reconstruction and relies on less canopy-scale traits, substantially reducing data requirements and computational cost, and thereby offering strong potential for rapid, field-deployable FL regulation in large-scale orchards.
Why it matches plant phenotyping methods3D点群から樹冠構造形質を抽出し、葉数と適正着果量を推定する手法およびソフトウェアを開発・検証しており、植物表現型取得が中心である。
abstractA pipeline for extracting 3D architectural traits was developed and implemented in the software tool FTPCT, enabling rapid and standardized trait acquisition.
Reproduction assets foundThe paper's phenotyping analysis assets are the authors' publicly released LeafNumPred source code and trained models, and the FTPCT software for 3D trait extraction from pear tree point clouds. Phenotype/point-cloud datasets are only available on request.Code · public. Supplementary data
The following is the Supplementary data to this article:
Multimedia component 1
mmc1.docx (1.6MB, docx)
Data availability
Data will be made available on request. Anyone who wants to obtain other public data can contact us at taost@njau.edu.cn. The source codes and models have been made publicly available at https://github.com/Zhang-Fanhang/LeafNumPred, and the FTPCT software has been released at https://github.com/Zhang-Fanhang/FTPCT/tree/Installation-package.
References
1.Tao S., Khanizadeh S., Zhang H., Zhang S. Anatomy, ultrastructure and lignin distribution of stone cells in two Pyrus species. Plant Sci. 2009;176:413–419. [Google Scholar]
2.Zhang F., Wang Q., Yuan K.Open asset ↗Zhang-Fanhang/LeafNumPredhtml-lines:284-315Code · publical variations [34,35]. The method for calculating these traits are shown in the Supplementary information 1.
2.5. Software implementation for 3D trait extraction (FTPCT)
To facilitate efficient and standardized extraction of canopy structural traits from point cloud data, we used a standalone software tool, FTPCT (available at: https://github.com/Zhang-Fanhang/FTPCT/tree/Installation-package), which integrates the trait extraction procedures applied in this study. The software provides a graphical user interface, enabling users to process tree-level point cloud data and extract key 3D structural traits without requiring advanced programming skills.
FTPCT implements a series of predefined proOpen asset ↗Zhang-Fanhang/FTPCThtml-lines:138-149Code / dataset availability confirmedOpenAlex · arXiv · checked 5 Sept 2026
Existing conversational plant-phenotyping platforms are difficult for plant scientists to use and lack the reliability scientific research demands: failed analyses are reported as valid measurements rather than flagged as missing, statistical tests run without checking assumptions, predictions carry no uncertainty estimate, and specialised hardware limits accessibility. We present PhenoIntel, a lifecycle-aligned multi-agent web platform that turns the full machine-learning workflow into a reliable, user-friendly phenotyping system. Nine specialised agents divide the analysis into stages, from image collection through model selection, inference, and reporting, rather than handing the whole task to one AI manager. Independent checks separate these stages, and every agent reads from and writes to one shared, fixed-structure record, so an inconsistent output from one stage is caught before it reaches the next. Uncertainty is matched to each model family, conformal prediction, detection-confidence spread, or Monte Carlo Dropout, rather than applied uniformly, and quality thresholds adapt to crop and task instead of one global cutoff. When no suitable model exists, PhenoIntel can propose, validate, and integrate a new one on its own. The model repository spans ten trained models across five crops and four imaging modalities. Classification models reach Macro F1 of 0.78-0.996; object-detection models reach 0.96 mAP@50 with a 54% reduction in counting error over an unoptimised baseline; and a temporal model reaches held-out Macro F1 of 0.7050. PhenoIntel runs in a browser on standard hardware, requiring no GPU, and a 1,200-test automated suite confirms complete pipeline execution. Every result carries calibrated uncertainty, validated statistics, and FAIR-compliant provenance, a combination existing conversational phenotyping tools do not offer.
Why it matches plant phenotyping methods植物フェノタイピングの画像収集から推論・報告までを扱うウェブプラットフォームを開発し、複数モデル、精度、不確実性、検証スイートを評価しており、方法が研究の中心である。
abstractWe present PhenoIntel, a lifecycle-aligned multi-agent web platform that turns the full machine-learning workflow into a reliable, user-friendly phenotyping system.
Reproduction assets found論文固有の解析コードとモデル資産を公開するGitHubリポジトリを本文中の根拠とともに確認しました。Code · publiccode, model checkpoints, and the 1,200-test automated suite referenced
throughout this paper are maintained in a version-controlled
repository, available at
https://github.com/Naren1704/PhenoIntel-InternshipOpen asset ↗Naren1704/PhenoIntel-Internshiplines:2047-2163Code / dataset availability confirmedOpenAlex · Europe PMC · checked 15 Sept 2026
Boll-opening concentration is critical for mechanical cotton harvesting, yet it is still assessed mainly by manual records and single time-point indicators that miss temporal dynamics. To bridge the lack of a unified workflow linking vision foundation models, multi-temporal boll-opening monitoring, and harvest decision-making, we developed a cross-scale UAV high-throughput phenotyping framework centered on DINO-BollGX. DINO-BollGX couples a DINO v3 backbone, a RetinaNet detection head, and an adaptive refinement-and-suppression module for robust open-boll detection under complex field conditions. Using multi-temporal UAV imagery collected over two years for 383 cultivars, we reconstructed plot-scale time series of open-boll counts, derived dynamic features describing progression and intensity changes, and proposed a Cotton Boll-Opening Temporal Stability Index (CTSI) to quantify boll-opening rhythm and concentration; CTSI was further integrated with a time-based risk function to generate harvest decision curves. Under unified data and training settings, DINO-BollGX achieved precision = 0.91, F1 = 0.88, and AP@0.50 = 0.80, and provided accurate boll-count estimation (R 2 =0.98; MAE=3.10), outperforming YOLOv11, YOLOv12, YOLOv13, and RT-DETR. On an independent cross-year dataset acquired at 5 m altitude, it obtained precision = 0.98 and F1 = 0.87. An internal consistency analysis showed that CTSI had the expected negative association with Window_days (r = −0.83) and positive associations with Max_count (r = 0.78) and the boll-opening efficiency index (r = 0.92), reflecting the co-occurrence of temporal compactness and main-phase opening intensity in the cultivar population. CTSI ranged from −2.72 to 4.69 across cultivars, enabling identification of highly synchronized boll-opening. Harvest decision curves indicated that the relative net income index peaked at day 67 after the first observation and a compact optimal harvest window near the end of monitoring; on a fixed harvest date, Kuche 130292 (CTSI=4.69) produced 486 open bolls versus 182 for Xinluzao 36 (CTSI=0.53) and 90 for Andizhan-60 (CTSI=-2.72). Overall, the framework integrates dynamic boll-opening phenotyping with harvest timing optimization, supporting scalable cultivar screening and mechanization-ready deployment, with potential extension to harvest decision scenarios in other crops.
Why it matches plant phenotyping methodsUAV画像と基盤モデルを用いて綿花の開絮を検出・定量し、時系列表現型指標を構築・検証する方法が研究の中心であるため。
abstractwe developed a cross-scale UAV high-throughput phenotyping framework centered on DINO-BollGX.
Reproduction assets foundThe paper publicly releases its cotton boll-opening UAV image dataset (3638 patches, 94,774 YOLO-format bounding-box annotations) on GitHub, directly supporting the paper's phenotyping analysis. No author analysis code or trained model checkpoints are explicitly deposited.Dataset · publicentary information for evaluating cross-scale detection performance and characterizing macroscopic spatial patterns. The 5 m imagery acquired on 18 Sept 2024 is used exclusively for cross-year generalization assessment. All cropped images and the corresponding YOLO-format annotation files have been publicly released on GitHub ( https://github.com/mianchen0529/cotton-boll-dataset/tree/main ) to facilitate further research on cotton phenotyping, agricultural remote sensing, and intelligent analytics.
2.3.
Model construction
2.3.1.
Overall architecture of the DINO-BollGX network
The proposed DINO-BollGX network consists of four stages: image preprocessing, feature extraction, object prediction,Open asset ↗mianchen0529/cotton-boll-datasetlines:63-74Code / dataset availability confirmedEurope PMC · checked 5 Sept 2026
Stomatal traits are key microscopic phenotypes for evaluating plant physiology, stress responses, and crop breeding potential. However, in vivo high-magnification microscopy often suffers from a shallow depth of field, causing noticeable defocus blur across different spatial locations and making it difficult to capture clear and complete stomatal structures in a single image. Multi-focus image fusion offers a practical solution, yet existing methods typically rely on supervised training, paired data, or hand-crafted rules, limiting their use in real agricultural microscopy scenarios. In this study, we propose an unsupervised multi-focus fusion framework for reconstructing fully focused stomatal microscopic images. The method integrates two-dimensional feature extraction with three-dimensional cross-focal-plane modeling to capture both spatial details and complementary information across focal planes. A max-response-guided spatial gating module is introduced to enhance focused regions while suppressing defocused responses. Additionally, dual sharpness priors based on perceptual features and wavelet high-frequency information enable pixel-wise pseudo-supervised learning without requiring all-in-focus ground-truth images. The model also predicts a probabilistic focal-plane volume for interpretable all-in-focus reconstruction. Experiments on a maize multi-focus image dataset demonstrate that the proposed method achieves superior or competitive performance across multiple fusion metrics, with entropy (EN), edge information preservation ( Q AB∕F ), Chen-Blum contrast metric ( Q CB ), and visual information fidelity for fusion (VIFF) reaching 7.43, 0.21, 0.41, and 1.01, respectively. Ablation studies confirm the effectiveness of the 3D modeling, spatial gating, and dual-prior sharpness supervision. More importantly, when the fused images serve as input to a YOLO-based stomatal instance segmentation model, the proposed method yields the best segmentation accuracy, with mAP50 and mAP50-95 reaching 0.9937 and 0.9121, respectively. Phenotypic measurements derived from the segmentation masks show high consistency with manual annotations, with the highest coefficient of determination R 2 = 0.97 achieved for stomatal count. These results indicate that the framework can act as an effective front-end module for automated microscopic stomatal phenotyping in agriculture.
Why it matches plant phenotyping methods植物の気孔表現型を対象に、マルチフォーカス画像融合、セグメンテーション、形質測定までを中核的に開発・検証しているため。
abstractwe propose an unsupervised multi-focus fusion framework for reconstructing fully focused stomatal microscopic images.
Reproduction assets foundThe authors state their data and code are publicly available on GitHub, covering the multi-focus stomatal microscopy dataset and the UMF-stomata fusion/phenotyping code.Code · publicOur data and code are available at: https://github.com/Longer-S/UMF-Stomata.Open asset ↗Longer-S/UMF-Stomatahtml-lines:640-655Dataset · publicOur data and code are available at: https://github.com/Longer-S/UMF-Stomata.Open asset ↗Longer-S/UMF-Stomatahtml-lines:683-756Code / dataset availability confirmedCrossref · Europe PMC · checked 5 Sept 2026
Sustainable wheat farming is challenging. Real-time information on crop health, disease transmission, and anticipated yields is essential for farmers. However, they frequently use slow, expensive, or non-communicative tools. This project develops a workable solution. There is no need for massive server farms because the entire system operates on a single graphics card. It incorporates images of wheat fields, Indian farming notes, greenhouse records, harvest statistics, and NASA meteorological data. Consider them as various “eyes” for crop photo analysis, and we tried several lightweight computer vision models. ConvNeXt-Tiny was slower but could operate on older equipment with 75% accuracy; EfficientNetB0 recognised wheat heads with 92% accuracy; and AgroMark, a hybrid solution that merged photo analysis with agricultural metadata (soil type, rainfall, increased to 87%, etc. Combining picture analysis with attention mechanisms (CBAM) allowed us to anticipate the amount of wheat that a field will yield based on these photo insights, and the results showed that our predictions were accurate, with an R 2 score of 0.97. Additionally, we developed a versatile detector that simultaneously detects disease, stress, head count, and pests. It is adjusted to deal with training data that is unbalanced (some diseases are common, while others are rare). As we packed everything into a 16-GB graphics card, we spent real time determining which strategies smaller training sets, removing weak features, and adjusting loss functions, work. We encounter real-world obstacles along the road, such as photographs from different locations not always match, mislabeled photographs from different locations not always match, mislabeled diseases, and neglected rare pests. Our step-by-step instructions, charts, and code are available.
Why it matches plant phenotyping methods小麦画像から病害・ストレス・穂数・収量などの植物形質・状態を推定するマルチモーダル手法を開発し、複数モデルの精度比較と実装上の検証を行っており、表現型取得・推定が研究の中心である。
abstractThis project develops a workable solution.
Reproduction assets foundThe paper builds its multimodal wheat phenotyping analysis on several explicitly cited public data assets: the Kaggle Wheat Plant Diseases image dataset (used for disease classification, Tables 2 and 9), the Global Wheat Head Detection dataset (used for head detection, Tables 1 and 6), FAOSTAT and India Open GovernmentDataset · publicAvailable online at: https://www.fao.org/faostat/ . FAOSTAT statistical database.Open asset ↗lines:1110-1162Code / dataset availability confirmedOpenAlex · checked 11 Sept 2026
Unmanned aerial vehicle (UAV) photogrammetry offers a cost-effective approach to tree-level detection, however, Structure-from-Motion (SfM) outputs are sensitive to processing choices and site conditions, which can alter canopy representation and reduce individual-tree detection accuracy. Here, we systematically evaluate how SfM reconstruction quality and depth-map filtering influence RGB-only individual-tree detection under controlled acquisition conditions. Objectives were to (i) identify an optimal SfM-derived point-cloud configuration for delineating individual trees, and (ii) implement and test a segmentation workflow (local-maxima treetop detection plus Dalponte2016 in lidR) for detecting and counting trees. We assessed RGB-only SfM for individual-tree detection (ITD) across thirteen 1.21-ha loblolly pine ( Pinus taeda ) plots located in two counties in the state of Alabama in the southeastern United States; eight even-aged plantations and five mixed pine-hardwood stands, while holding image acquisition parameters constant. Using Agisoft Metashape Professional (Agisoft LLC, St. Petersburg, Russia), dense-cloud quality (Lowest, Low, Medium, High, Ultra High) and depth-map filtering (Disabled, Mild, Moderate, Aggressive) were varied in a 5 × 4 full-factorial design; assessment metrics included point-cloud density, canopy-surface completeness, canopy-height-model (CHM) agreement with field heights, and ITD precision/recall/F1. We identified a single high-resolution configuration (Ultra High + Disabled) by screening parameter sets for structural accuracy and suppression of false peaks. Using this configuration, CHMs matched field heights in Washington County, Alabama (R 2 = 0.96; RMSE = 0.44 m; bias = − 0.01 m) and in Cullman County, Alabama (R 2 = 0.44; RMSE = 1.14 m; bias = − 0.09 m); pooled performance was R 2 = 0.98; RMSE = 0.54 m; bias = − 0.01 m. ITD accuracy at the primary 3 m match radius yielded a precision of 0.03; recall = 0.29; F1 = 0.05 in the even-aged plantations (Washington) and a precision of 0.03; recall = 0.12; F1 = 0.05 in mixed pine–hardwood stands (Cullman); pooled F1 = 0.05. The selected parameters and workflow are reproducible and transferable, provide insight into RGB-SfM ITD performance, and indicate when lidar remains preferable for crown delineation.
Why it matches plant phenotyping methodsRGB-SfMによる個体樹の検出・樹高推定と、SfM設定およびセグメンテーションワークフローの系統的評価が研究の中心であり、植物の樹冠構造・樹高という形態形質を抽出する方法を検証している。
abstractwe systematically evaluate how SfM reconstruction quality and depth-map filtering influence RGB-only individual-tree detection
Reproduction assets foundThe paper's Code availability statement deposits the authors' SfM/ITD processing scripts publicly on OSF (DOI 10.17605/OSF.IO/UXBCZ). Phenotype/field datasets are only available on request, so they are not public assets.Code · publicThe workflow and processing scripts used in this study are publicly available through the Open Science Framework
(OSF) repository: Singh and Narine, [32]. Code Repository for Optimizing SfM Parameters for RGB-Only Individual-Tree
Detection in Loblolly Pine and Mixed Pine-Hardwood Stands. https://doi.org/10.17605/OSF.IO/UXBCZ.Open asset ↗10.17605/OSF.IO/UXBCZpdf-page:12 lines:1-70Code / dataset availability confirmedEurope PMC · Crossref · checked 5 Sept 2026
Abstract Biotic stress is a major, yet under-quantified, driver of global soybean yield losses, and field-based phenotyping under pest pressure remains a critical bottleneck for crop improvement. Using multi-temporal data from soybean genotypes grown under insecticide-protected and unprotected conditions in Brazil, we present a UAV-based, large-scale and non-invasive framework for evaluating genotype performance under natural pest pressure. We introduce a three-dimensional metric that jointly captures productivity, feature-level similarity as a proxy for tolerance, and phenological response through days to maturity. This unified formulation enables field-based quantification of pest resilience and replaces labor-intensive and often unreliable direct pest collection and counting. To operationalize this framework, we integrate vegetation indices and self-supervised visual embeddings into a common representation space linking feature stability, performance response and phenological development. This approach enables robust identification of genotypes that maintain feature integrity, minimize developmental delay and sustain yield under pest pressure, with genotypic differences peaking during the pod-fill (R3–R4) and grain-fill (R5.1–R5.5) stages. Overall, this work establishes a scalable, field-ready paradigm for quantifying crop resilience to biotic stress and provides a practical pathway to accelerate breeding for stable yields under real-world agricultural conditions.
Why it matches plant phenotyping methodsUAVによる大規模な圃場フェノタイピング基盤と、植生指数・視覚埋め込みを統合した新しい耐虫性表現型の定量手法が研究の中心である。
abstractwe present a UAV-based, large-scale and non-invasive framework for evaluating genotype performance under natural pest pressure
Reproduction assets foundThe paper explicitly states that the analysis code is publicly available in the authors' GitHub repository (jianglong26/soybean-insect-resistance), which directly reproduces this paper's phenotyping pipeline (orthomosaic processing, VI/DINOv3 feature extraction, similarity analysis, genotype ranking). The paper also声明sCode · public540 The code used for analysis is available at https://github.com/jianglong26/Open asset ↗pdf-page:16 lines:1-45Code / dataset availability confirmedOpenAlex · Europe PMC · checked 5 Sept 2026
Orthoimagery derived from unmanned aerial vehicles (UAVs) has become a valuable data source for crop-growth monitoring. Individual plant-level (IPL) information enables high-throughput analyses by capturing plant-to-plant variability within fields. However, reliable IPL-based analysis requires accurate extraction of plant-specific regions, which remains challenging in soybean cultivation due to weed interference and canopy overlap. This study proposed an automatic preprocessing framework for IPL soybean growth monitoring that integrates deep-learning-based semantic segmentation with a furrow-guided region of interest (ROI) generation strategy using UAV imagery. A segmentation model was developed using combinations of RGB and multispectral orthoimagery, and a furrow line detection algorithm was designed to generate IPL ROIs aligned with crop rows. The ensemble model combining U-Net, DeepLabV3+, and SegFormer achieved the most stable performance (F1-score up to 0.94 and IoU up to 0.89). The furrow-guided ROI generation algorithm also accurately estimated crop counts, showing strong agreement with manual observations (R² = 0.90 and RMSE = 6.35). The generated IPL ROIs enabled accurate quantification of growth-related features, with strong agreement between automatically generated and manually delineated ROIs (R² > 0.90). Overall, the proposed preprocessing framework provides a practical and scalable solution for UAV-based high-throughput phenotyping in soybean and other ridge-based cropping systems.
Why it matches plant phenotyping methodsUAV画像から個体単位の植物領域を抽出し、成長形質を定量化する前処理・セグメンテーション手法が研究の中心であるため。
abstractThis study proposed an automatic preprocessing framework for IPL soybean growth monitoring that integrates deep-learning-based semantic segmentation with a furrow-guided region of interest (ROI) generation strategy using UAV imagery.
Reproduction assets foundThe authors state that the complete implementation of their IPL soybean preprocessing pipeline (semantic segmentation + furrow line detection) is publicly available on Zenodo. The annotated sample dataset, however, is only available upon request from the corresponding author, so it is not a public asset.Code · publicThe complete implementation of
this pipeline is publicly available at https://doi.org/10.5281/zenodo.21095307.Open asset ↗zenodo · 10.5281/zenodo.21095307pdf-page:7 lines:1-62Code / dataset availability confirmedEurope PMC · bioRxiv · checked 6 Sept 2026
0. 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. 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 counts. We validated EcoMorph across two ecological scales. At the intermediate scale, EcoMorph-derived floral area agreed closely with manual ImageJ measurements (R 2 = 0.935, n = 74) under simple-background conditions and (R 2 = 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 (R 2 = 0.9997, n = 12). By combining prompt-based segmentation with modular measurement, EcoMorph enables high-throughput quantification of area, size, and abundance 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画像から花の面積など植物形態形質を抽出する汎用システムを開発し、手動測定との一致で検証しており、植物フェノタイピング手法が中心である。
abstractWe present EcoMorph, a modular morphological measurement system that leverages the Segment Anything Model 3 (SAM3) to quantify traits across diverse ecological contexts.
Reproduction assets foundThe paper's Data and code availability statement provides a public Zenodo deposit containing the validation datasets and code used for the EcoMorph phenotyping measurements (floral area, insect morphometrics, counts), plus a public web deployment of the EcoMorph software itself.Code · publicValidation datasets and code are available here on Zenodo
https://zenodo.org/records/20980236.Open asset ↗Zenodo · 20980236pdf-page:2 lines:1-54Code / dataset availability confirmedOpenAlex · Europe PMC · checked 5 Sept 2026
Abstract Background Stomata and pavement cells are fundamental components of the leaf epidermis, jointly regulating gas exchange, water loss, and leaf surface expansion. Stomata size, aperture, density, and pavement cell morphology are critical parameters for assessing plant transpiration efficiency, epidermal growth dynamics, and adaptive responses to environmental constraints. Despite their biological importance, quantifying stomatal and pavement-cell traits remains seldom not generalized, simple, and fast enough . Manual or semi-automated approaches limit large-scale phenotyping and restrict the integration of epidermal morphology into crop-improvement pipelines aimed at developing climate-resilient varieties with optimised stomatal patterning. To address such limitations, we developed Stomatalia , a deep learning-based platform designed to automate and standardise the quantification of stomatal and pavement cell traits. The algorithm was trained on epidermal images of cultivated and wild potato and tomato genotypes grown under optimal and abiotic-stress conditions. Stomatalia automatically detects stomata and pavement cells and extracts a broad range of morphological and integrative epidermal parameters, enabling high-throughput phenotyping within a unified workflow. Results Prior to platform development, we optimised a rapid, minimally-destructive leaf-printing protocol that generates negative impressions of the leaf surface within 40–100 s. Transparent positive prints were subsequently produced and imaged under a light microscope at scale settings ranging from 20 to 200 μm. The resulting images are analysed using Stomatalia’s user-friendly web-based interface, which runs an instance-segmentation deep learning algorithm to detect, count, and calculate stomatal and pavement cell parameters. The platform outputs structured files containing raw measurements, derived integrative traits, and associated metadata, facilitating downstream statistical and physiological analyses. Algorithm evaluation on independent datasets demonstrated high performance within the validated dicot imaging domain, with F 1 -scores ranging from 0.86 to 0.94 depending on image scale, species, and resolution, and high segmentation overlap for both stomata and pavement cells. The generality of stomatal detection was also tested on spring onion, chickpea, balsam poplar, and wheat in cross-species feasibility tests, although performance was more variable in monocots, and pavement-cell segmentation remained species- and architecture-dependent. Benchmarking against another publicly available app further showed that, under the tested web interface settings and image types, Stomatalia exhibited closer agreement with manual counts and substantially faster processing times. The practical performance of Stomatalia was further tested in a proof-of-concept trial with potato plants subjected to optimal irrigation and a long, gradual drought. The platform reliably quantified epidermal traits despite variations in leaf morphology and image quality, supporting the integrated interpretation of stomatal and pavement-cell responses under stress. Conclusions We developed Stomatalia as a robust, user-friendly deep learning platform for automated, high-throughput analysis of bright-field leaf epidermal images across varying magnifications and resolutions. Stomatalia facilitates rapid, reproducible, and coordinated phenotyping of stomatal and pavement cells by integrating methodological standardisation, computational automation, and multi-trait extraction in a single analytical workflow. Its strongest current application is the analysis of high-quality dicot leaf-print images, particularly in species and imaging conditions similar to those used for model training and validation. Cross-species and benchmark analyses further define its current scope: stomatal detection can be transferred to some additional epidermal architectures, whereas robust pavement-cell segmentation in monocots or highly divergent species will require further annotation and model retraining. Within these defined boundaries, Stomatalia provides a flexible and extensible framework for studying stomatal and pavement cell morphology and environmental plasticity, while also supporting broader efforts to dissect and optimise plant responses to abiotic stress.
Why it matches plant phenotyping methods気孔・舗装細胞の形態形質を画像から自動抽出する深層学習プラットフォームを開発し、独立データで性能評価・比較検証しているため、植物フェノタイピング手法が中心である。
abstractwe developed Stomatalia , a deep learning-based platform designed to automate and standardise the quantification of stomatal and pavement cell traits.
Reproduction assets foundThe authors publicly deposited the paper's test image datasets (raw/input leaf-print images, detection outputs, manual ground-truth counts, exported datasets) and the model file on Figshare, and provide a public Google Colab demo for running the Stomatalia algorithm. Both are paper-specific, public, and actionable.Dataset · publicThe test datasets and model file used in this work are available through the following link:
https://doi.org/10.6084/m9.figshare.32532672. The test_sets.zip archive contains the test image datasets
(cross-species and benchmark analysis), including raw/input images, detection output images, manual
ground-truth counts and exported datasets.Open asset ↗Figshare · 10.6084/m9.figshare.32532672pdf-page:25 lines:1-75Code / dataset availability confirmedEurope PMC · checked 5 Sept 2026
Manually counting sunflower seeds on capitula is labor-intensive, requiring approximately one person-hour per head, and can be inconsistent for densely packed heads. Existing phenotyping approaches often depend on laboratory-based equipment, limiting their accessibility. In this study, we developed a benchtop image-based pipeline for rapid, non-destructive estimation of developed and aborted seeds on intact dried sunflower heads. A dataset of 1093 sunflower capitula was imaged under fixed indoor lighting, and individual seeds were annotated as developed or aborted. A YOLOv8m one-stage object detector was trained and evaluated using a counting-focused protocol, in which a single confidence threshold was selected on the validation set and then applied unchanged to an independent test set of 109 images. The baseline model was compared with recent YOLO variants and different augmentation strategies. On the test set, the model achieved a mean absolute count error of 61.3 seeds per image, a mean relative error of 12.0%, and an mAP50 of 0.18 at the locked confidence threshold of 0.15. Only 13.8% of test images had relative errors below 2%. Larger YOLO models and augmentation variants did not improve performance. These findings show that the proposed system provides approximate, non-destructive seed-count estimation under controlled imaging conditions, while highlighting the need for improved localization in dense regions and domain adaptation for fresh heads or field conditions. The annotated dataset and trained model weights are made available to support reproducible research.
Why it matches plant phenotyping methodsヒマワリ頭花の発達・不稔種子数という植物形質を、画像取得とYOLOによる推定パイプラインで定量化する手法を開発・評価しており、方法が研究の中心である。
abstractwe developed a benchtop image-based pipeline for rapid, non-destructive estimation of developed and aborted seeds on intact dried sunflower heads.
Reproduction assets foundThe authors state the source code is available on GitHub and the CVAT-annotated dataset is available via a public share link; the GitHub repository URL is explicitly provided and matches an allowed URL. The dataset link itself is not given, so only the code/checkpoint repository qualifies as an actionable public asset.Code · publicThe developed system is available as a Telegram bot [ 19 ] and the source code is available on GitHub [ 20 ]. The CVAT annotated dataset is available via a public share link.Open asset ↗lines:84-103Code / dataset availability confirmedOpenAlex · Europe PMC · checked 5 Sept 2026
Three dimensional (3D) instance segmentation is essential for precision characterization of tree architecture at the branch level, which supports both tree fruit crop breeding and the development of robotic systems for orchard management. Existing methods usually use sparse convolution-based operation, which requires a coordinate quantization preprocess to generate sparse tensors, risking the loss of geometric details for fine-grained downstream phenotyping tasks. To overcome this challenge, we developed the dynamic sparse point-voxel transformer (DSPVFormer) model for the efficient and accurate 3D instance segmentation of high-resolution point clouds for dormant apple trees. Our hybrid DSPVFormer architecture maximizes the use of raw point features by dynamically mapping and aggregating the raw point features into the sparse voxel embeddings, capturing strong geometric features that may be discarded during quantization. Evaluations demonstrate that DSPVFormer achieved statistically significant improvements over baseline models on most instance segmentation metrics, which are further translated into more accurate phenotyping evaluation including branch counting and pruning map generation. These advances directly benefit downstream applications in plant phenotyping and robotic pruning for tree crops such as apples. Meanwhile, experimental results on phenotyping tasks suggested that phenotyping-specific evaluation metrics should be prioritized over upstream computer vision performance metrics to realize the full potential of high-throughput phenotyping for real-world applications.
Why it matches plant phenotyping methodsリンゴ樹の3D点群から枝レベル形質を抽出するセグメンテーション手法を開発・評価し、枝数や剪定マップへの応用まで検証しており、植物フェノタイピング手法が中心である。
abstractwe developed the dynamic sparse point-voxel transformer (DSPVFormer) model for the efficient and accurate 3D instance segmentation of high-resolution point clouds for dormant apple trees.
Reproduction assets foundThe paper states that its data and code (including the DSPVFormer analysis pipeline built on Plant Segmentation Studio) are publicly available at the authors' PSS GitHub repository. The COS dataset of 98 dormant apple tree point clouds is also referenced as accessible via this repository/statement. Other URLs (spconv,mCode · publicThe data and code are available at the PSS GitHub repository: https://github.com/perrydoremi/PlantSegStudio .Open asset ↗https://github.com/perrydoremi/PlantSegStudiolines:383-408Code / dataset availability confirmedEurope PMC · checked 5 Sept 2026
In-season estimation of wheat grain yield potential is critical for crop management and advancing breeding efforts. Spike and spikelet counts serve as key indicators directly linked to yield potential, yet their assessment still relies on manual counting which is both labor-intensive and error-prone. High-resolution digital (RGB) imagery combined with deep learning-based object detection methods has substantially advanced automatic wheat spike detection and counting. However, precise spikelet-level phenotyping remains largely underexplored. This study evaluates two recent YOLO variants, YOLOv11 and YOLOv12, for wheat spike and spikelet detection and counting using oriented bounding boxes (OBB), and introduces a new large-scale benchmark dataset comprising 48,521 spike and 60,404 spikelet instances with OBB annotations. For spike detection, the pre-trained YOLOv11 achieved superior accuracy (mAP@0.5 = 95.8%, Pearson r = 0.993) with shorter training and inference times compared to YOLOv12. For spikelet detection, the non-pretrained YOLOv11 demonstrated higher accuracy (mAP@0.5 = 99.0%), while counting performance was comparable across models. These results establish OBB-based YOLO detection as a robust and scalable approach for AI-driven wheat phenotyping.
Why it matches plant phenotyping methods小麦の穂・小穂という収量関連形質の画像ベース検出・計数手法を比較評価し、大規模ベンチマークデータセットも構築しているため、フェノタイピング手法が中心である。
abstractThis study evaluates two recent YOLO variants, YOLOv11 and YOLOv12, for wheat spike and spikelet detection and counting using oriented bounding boxes (OBB), and introduces a new large-scale benchmark dataset comprising 48,521 spike and 60,404 spikelet instances with OBB annotations.
Reproduction assets foundThe paper openly states its supporting data (spike/spikelet imagery with OBB annotations) is available on Zenodo, and the underlying models are deployed on the authors' public WheatAI cloud platform.Dataset · publicData availability
The data supporting the findings of this study are openly available at: https://doi.org/10.5281/zenodo.20215489 .Open asset ↗zenodo · 10.5281/zenodo.20215489lines:219-266Code / dataset availability confirmedOpenAlex · Europe PMC · checked 15 Sept 2026
The number of petals in an inflorescence is an important phenotypic indicator for quality evaluation and cultivar identification of cut chrysanthemums ( Chrysanthemum morifolium Ramat.). Current manual measurement methods are time-consuming, error-prone, and poorly suited to the complex geometry of chrysanthemum flowers, which limits their utility for large-scale phenotyping and breeding programs. Although image-based phenotyping has advanced rapidly, automated and reliable methods for petal counting in densely packed or partially obscured inflorescences remain underdeveloped. Here, we developed a deep learning-based framework for automatic extraction of petal number in cut chrysanthemums. Images from multiple varieties were collected to construct a representative dataset, and petal density maps were generated through manual annotation with Gaussian kernel function. We employed a Congested Scene Recognition Network (CSRNet) enhanced with a Squeeze-and-Excitation (SE) channel attention mechanism (SE-CSRNet) for petal density estimation. Spearman correlation analysis revealed strong agreement between visible and actual petal counts (Spearman’s r=0.953, p<0.0001). Compared with the original CSRNet, SE-CSRNet reduced mean absolute error (MAE) and root mean squared error (RMSE) by 5.2% and 7.4%, respectively. Further optimization using regression fitting revealed that random forest achieved the best performance (MAE = 4.24, RMSE = 5.06, R 2 = 0.967), indicating reliable stability and satisfactory generalization under the conditions evaluated in this work. Application of the optimized model to two cut chrysanthemum varieties confirmed its practicality by successfully detecting reductions in petal number under high-temperature stress. Our results demonstrate that integrating dataset construction, deep learning–based density estimation, and machine learning optimization enables efficient and accurate prediction of petal number in cut chrysanthemums.
Why it matches plant phenotyping methods花弁数という植物形質を画像から自動抽出する深層学習手法を開発し、データセット構築、性能比較、検証、実用適用まで行っており、表現型取得手法が研究の中心である。
abstractHere, we developed a deep learning-based framework for automatic extraction of petal number in cut chrysanthemums.
Reproduction assets foundThe article states that some data (the chrysanthemum petal-counting dataset and related materials) will be available at the authors' public GitHub repository (qwsdfgz/petalscount), with other data available from the corresponding author upon reasonable request. The repository URL is explicitly provided by the authors,但Dataset · publicnctional components of bud-leaves and flowers in edible chrysanthemum (Chrysanthemum morifolium Ramat)
Horticulturae 11 5 2025 448
10.3390/horticulturae11050448
Appendix A
Supplementary data
The following is the Supplementary data to this article.
Multimedia component 1
Data availability
Some data will be available at this URL: https://github.com/qwsdfgz/petalscount . Other data are openly available from the corresponding author upon reasonable request.
Appendix A
Supplementary data to this article can be found online at https://doi.org/10.1016/j.plaphe.2026.100238 .Open asset ↗qwsdfgz/petalscountlines:602-636Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Single-molecule fluorescence in situ hybridization (smFISH) has emerged as a powerful tool for studying gene expression dynamics with unparalleled precision and spatial resolution in a variety of biological systems. Recent advancements have expanded its application to encompass plant studies, yet there remains a need for a simple and robust smFISH method adapted to plant tissue sections. Here, we present an optimized smFISH protocol, termed cryo-smFISH, for visualizing and quantifying single mRNA molecules in plant tissue cryosections. This method exhibits remarkable sensitivity, enabling the detection of low-expression transcripts, including long non-coding RNAs. By integrating a deep learning-based algorithm into our image analysis pipeline, our method enables precise assignment of RNA abundance in nuclear and cytoplasmic compartments. The method also enables robust integration with immunofluorescence, as cryosectioning enhances antibody penetration. This allows for the sequential visualization and quantification of both RNAs and endogenous proteins within the same cells. Finally, this study demonstrates the use of smFISH to validate single-cell RNA sequencing (scRNA-seq) expression patterns in plant tissues. By extending smFISH to plant cryosections, plant scientists will be able to exploit the full potential of quantitative transcript analysis at cellular and subcellular resolution.
Why it matches plant phenotyping methods植物組織向けcryo-smFISHプロトコルと画像解析法を開発し、RNA量を細胞・細胞内区画で定量する手法が研究の中心である。分子測定ではあるが、植物組織の状態を定量する方法として技術的貢献が明確。
abstractHere, we present an optimized smFISH protocol, termed cryo-smFISH, for visualizing and quantifying single mRNA molecules in plant tissue cryosections.
Reproduction assets foundThe authors deposit all data underlying graphs/heatmaps plus custom R/Python scripts and Cellpose segmentation models in a public GitHub repository specific to this paper. Third-party tools (FISH-quant, DeconvolutionLab2, Stellaris Designer) are generic and excluded.Code · publicAll custom code, including R/Python scripts and Cellpose segmentation models, is available at https://github.com/xuezhang911/zhang_et_al_smFISH_cyrosections .
Funding
This work was supported by Vetenskapsrådet (2023-03895), the Novo Nordisk Foundation (NFF24OC0093553 and NNF25OC0100533), and the Carl Tryggers Stiftelse (CTS 18- 325).
Acknowledgments
We thank A. Menkis for initial technical support with cryostat operation and Alexandre Berr for scientific feedback. We also thank memOpen asset ↗zhang_et_al_smFISH_cyrosectionslines:122-152Dataset · publictic ( Bolger et al., 2014 ). The raw gene-count matrix was obtained using the pseudoalignment software Kallisto ( Bray et al., 2016 ). RNA-seq reads were normalized as transcripts per million (TPM).
Data and code availability
The supplemental information and all data underlying the graphs and heatmaps presented are available at https://github.com/xuezhang911/zhang_et_al_smFISH_cyrosections .Open asset ↗zhang_et_al_smFISH_cyrosectionslines:106-121Code · publicech.com/stellaris-designer . For mRNA detection, the coding sequence of the target gene was entered into the program, which automatically generated a set of probes complementary to the target mRNA.
The sequences of the probes were then subjected to quality control using an automated local blast R script, available on GitHub at: https://github.com/xuezhang911/zhang_et_al_smFISH_cyrosections/tree/main/smFISHprobes . The smFISH probes used in this study and their respective fluorophores are shown in Supplemental Table 3 . The probes were diluted in Tris-EDTA buffer to a final stock concentration of 25 μM.
Cryo-smFISH
Sample preparationOpen asset ↗zhang_et_al_smFISH_cyrosectionslines:75-85Code / dataset availability confirmedEurope PMC · OpenAlex · Crossref · checked 5 Sept 2026
Mungbean (Vigna radiata (L.) R. Wilczek) is a vital source of digestible proteins and is well-suited for the plant-based protein industry. In this study, we analyzed pod morphological traits in the Iowa Mungbean Diversity (IMD) panel of 372 genotypes (2022-2023) using image-analysis-based phenotyping on 2,418 pod images. Pod morphological traits were extracted using deep learning image analysis, achieving excellent agreement with manual measurements (r > 0.96 for pod length (PL) and seed-per-pod (SPP)). Four complementary genome-wide association studies models identified 65 significant SNPs (-log10(P) ≥ 5.56) associated with pod curvature, length, width, and SPP traits. A significant SNP (5_35265704) on chromosome 4 was linked to pod dimensional traits, length, width, and curvature. A candidate gene, Virad04G0076900, located 15.6 kb from this SNP, is part of the GH3 gene family and has an Arabidopsis ortholog (AT4G27260) known for influencing organ elongation, pod, and seed development. Another SNP, 5_210437 on chromosome 6, has been found to be significantly associated with both PL and SPP. A candidate gene, Virad06G0002400 (36.5 kb from this SNP), encodes a potassium transporter and shares homology with the Arabidopsis gene HAK5 (AT4G13420), known to influence pod growth. Image-based measurements achieved genomic prediction accuracies ranging from 0.61 to 0.85 across various traits, demonstrating comparable accuracy to manual methods for linear traits and up to 22% improvement for complex shape traits. These results highlight the potential of deep learning-assisted phenomics integrated with genomic tools to accelerate selection for improved pod architecture in mungbean breeding programs across the Midwestern United States and globally.
Why it matches plant phenotyping methods深層学習による画像解析でマメ pod の形態形質を抽出し、手動測定との一致度を検証しており、画像ベース表現型取得が研究の中心です。
abstractusing image-analysis-based phenotyping on 2,418 pod images
Reproduction assets foundThe paper's image-based pod phenotyping and genomic analysis scripts are explicitly stated to be publicly available on the authors' GitHub repository. Raw phenotypic data (image-based and manual measurements, BLUEs, BLUPs, GP results) are only in supplementary files without a direct public URL, so they are not listed; Code · publicAll analysis scripts used in this study are publicly available at GitHub: https://github.com/vboddepalli89/Image-based-pod-phenotyping .Open asset ↗https://github.com/vboddepalli89/Image-based-pod-phenotypinglines:395-459Code / dataset availability confirmedEurope PMC · checked 8 Sept 2026
Field / plotMultimodalWhole plant / canopy / plot / fieldClassificationCountingGrowth / development / phenology
Phenological monitoring of Actinidia chinensis is critical for optimising operational costs and yield prediction. However, current manual assessment methods are time-consuming, making them impractical for large-scale precision agriculture applications. Most existing phenological datasets focus exclusively on image data without spatial validation. The Multi-Modal Actinidia chinensis Phenology Dataset is composed of (i) 1 665 annotated images of phenological stages from bud to fruit set and (ii) georeferenced videos with systematic manual ground truth of spatial stage distributions. The dataset employs an adapted 17-class BBCH system that consolidates visually similar stages, excludes problematic categories, and introduces generic structural classes to address practical annotation difficulties. Additionally, the data is organised hierarchically across various plant structures, genders, and phenological stages. The annotated images offer versatility for a range of applications, including training data for computer vision models to detect phenological stages. Furthermore, the georeferenced videos facilitate the validation of automated counting algorithms. This combined approach enables plant-level detection accuracy and provides an illustrative methodology for spatial validation that users can extend to additional orchards, promoting the development and benchmarking of automated phenological monitoring systems for precision agriculture applications in kiwifruit production.
Why it matches plant phenotyping methodsキウイフルーツの生育段階を対象とした注釈画像・地理参照動画データセットであり、自動フェノロジー検出と空間検証のためのベンチマーク基盤が中心である。
abstractThe Multi-Modal Actinidia chinensis Phenology Dataset is composed of (i) 1 665 annotated images of phenological stages from bud to fruit set and (ii) georeferenced videos with systematic manual ground truth of spatial stage distributions.
Reproduction assets foundThe paper describes a public multi-modal Actinidia chinensis phenology dataset (annotated images, georeferenced videos, ground-truth counts) deposited on Zenodo, plus authors' MIT-licensed preprocessing scripts on GitHub. CVAT and FiftyOne are generic third-party tools and excluded.Dataset · publicThe Multi-Modal Actinidia chinensis Phenology Dataset described in this Data Descriptor is publicly available
at Zenodo: https://doi.org/10.5281/zenodo.17371025.Open asset ↗Zenodo · 10.5281/zenodo.17371025pdf-page:12 lines:1-92Code · publicCustom scripts for dataset preparation are publicly available under the MIT License at https://github.com/Open asset ↗GitHubpdf-page:12 lines:1-92Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Field / plotFlowerClassificationCountingFruit / seed / panicle traits
As a crucial agricultural crop in China, litchi exhibits a biennial bearing pattern with alternating high-yield and low-yield cycles, known as on-year and off-year respectively. Research has identified unstable floral initiation as the primary cause of irregular fruiting in mid-to-late maturing cultivars. Rapid and accurate quantification of female to male flower ratios during the flowering phase enables targeted management strategies to optimize floral development and enhance fruit-setting rates. This study proposes Flower Quantification and Gender Recognition Network (FQGR-Net), a three-branch neural network architecture for simultaneous classification and counting of female and male flowers. Through module-level optimization, FQGR-Net improves both counting accuracy and computational efficiency, achieving average MAE of 8.498 and RMSE of 13.209 across categories in experiments conducted on the self-constructed dataset. Comparative experiments with other deep neural network models on public datasets show the proposed method achieves optimal performance. A regression analysis between predictions and ground truth produces R2 values of 0.930 and 0.971 for female and male flower quantification respectively. A dedicated litchi flower phenotyping analyzer was developed to address the technological gap in automated floral census systems. Field trials demonstrated over 80% accuracy in female/male flower counting.
Why it matches plant phenotyping methods雌雄花の画像ベース計数・性別認識手法と専用フェノタイピング解析器を開発し、データセットおよび野外試験で性能評価しているため、植物形質取得法が中心である。
abstractThis study proposes Flower Quantification and Gender Recognition Network (FQGR-Net), a three-branch neural network architecture for simultaneous classification and counting of female and male flowers.
Reproduction assets foundThe authors explicitly state that the code and data for this litchi flower quantification/gender recognition study are publicly downloadable from their GitHub repository. The Roboflow datasets are cited third-party comparison datasets, not paper-specific assets, and the litchi dataset itself is only available upon (un)Code · publicThe code and data mentioned in the article can be downloaded from https://github.com/Mazhe-02/Morphology-based-Litchi-Flower-Quantification-and-Gender-RecognitionOpen asset ↗Mazhe-02/Morphology-based-Litchi-Flower-Quantification-and-Gender-Recognitionlines:583-591Code / dataset availability confirmedEurope PMC · checked 5 Sept 2026
Grain number estimation plays a crucial role in agriculture, serving as a key indicator for crop yield and quality assessment. With advances in computer vision, automatic grain detection has become a significant research area, where deep learning methods have shown remarkable promise. This study proposes a vision transformer model called Swin Transformer, which leverages hierarchical attention mechanisms across shifted windows to effectively capture both local and global features of grains in complex imagery. The model achieves the highest accuracy of 98%, outperforming baseline traditional CNN (ResNet-50) and DINO models in grain counting tasks. To support and validate model performance, explainable AI (XAI) techniques such as Grad-CAM and LIME are employed, highlighting the interpretability and focus of the model on relevant grain regions. Furthermore, a comprehensive empirical analysis is conducted using multiple statistical tests to evaluate the model's robustness and generalizability across various grain morphological parameters, establishing the Swin Transformer as a powerful and interpretable solution for intelligent grain counting in agricultural data analytics.
Why it matches plant phenotyping methods画像から穀粒数を推定する深層学習手法の開発・比較検証が研究の中心であり、植物の収量関連形質を測定するため、植物フェノタイピング手法として収録する。
abstractThis study proposes a vision transformer model called Swin Transformer
Reproduction assets foundThe paper's Data availability statement names a public Kaggle dataset of wheat grain counting images used for the study's grain counting experiments. No author analysis code or trained model checkpoints are disclosed.Dataset · publicThe dataset used and/or analyzed during the current study is publicly available at: https://kaggle.com/datasets/ociule/wheat-grain-counting-100-images.Open asset ↗kaggle · ociule/wheat-grain-counting-100-imageslines:1190-1253Code / dataset availability confirmedEurope PMC · checked 5 Sept 2026
Doubled haploid (DH) technology can fast-track crop breeding. Haploid induction yields haploids with only one set of genomes, which are usually sterile. Haploid fertility (HF) is the ability of haploid plants to set seed, and it is a critical bottleneck in DH pipelines. Genetic mechanisms to restore HF hold immense potential in DH crop breeding, yet its phenotyping remains manual, destructive, and inconsistent. While recent advances in imaging and machine learning have improved throughput for general plant traits, no curated image dataset exists for Arabidopsis thaliana that explicitly represents HF. Here, we present AutoSiQ, a dataset and baseline deep learning pipeline for automated HF quantification. AutoSiQ includes high-resolution scanned inflorescences annotated with a seven-class ontology encompassing green siliques, green fertile siliques, mature siliques, fertile siliques, cracked fertile siliques, cracked siliques, and flowers. This multi-class annotation scheme preserves biologically meaningful information beyond binary fertile/non-fertile distinctions, enabling reliable fertility estimation and future phenotyping applications. We release baseline object detection models (YOLOv5), trained using the AutoSiQ dataset, and evaluate their performance across confidence thresholds. Model predictions strongly correlate with manual counts, achieving R² up to 0.94 for total silique number estimation. We further demonstrate AutoSiQ's utility for automated haploid fertility rate (HFR) estimation and genotype discrimination between two contrasting genotypes (WT and bmf2 mutant). A longitudinal analysis identifies ~60 days after sowing (DAS) as the optimal harvest time for maximizing mature silique counts by balancing between the number of immature buds and silique shattering. By releasing both the dataset and baseline code, AutoSiQ provides a reproducible and extensible foundation for high-throughput fertility phenotyping in haploid Arabidopsis .
Why it matches plant phenotyping methodsハプロイド稔性を画像から定量するデータセットと深層学習パイプラインを開発・評価しており、植物フェノタイピング手法が中心である。
abstractHere, we present AutoSiQ, a dataset and baseline deep learning pipeline for automated HF quantification.
Reproduction assets foundThe paper's AutoSiQ dataset (annotated scanned Arabidopsis inflorescence images with seven-class silique ontology and manual fertility counts) is publicly deposited on Zenodo per the data availability statement. The YOLOv5 GitHub repository is a generic third-party library, not an authors' code asset.Dataset · publicThe datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://zenodo.org/records/17905566 .Open asset ↗zenodo · 17905566lines:367-402Code / dataset availability confirmedEurope PMC · checked 5 Sept 2026
Accurate flower-load assessment is critical for informed thinning strategies in orchard management. UAV-based deep learning automated counting offers efficiency advantages, yet precise counting is heavily dependent on abundant annotated data, which is scarce and costly to obtain in agricultural settings. While semi-supervised learning alleviates dependency on manual annotation, its application to UAV-based orchard imagery faces challenges: complex backgrounds and small target sizes, which undermine pseudo-label reliability. To address these challenges, this study proposes a two-stage framework to achieve separate counting of apple flowers at different phenological stages. First, a color-SAM flower extractor (CSAM-FE) is proposed to preprocess images using a strategy combining color thresholding with the Segment Anything Model (SAM), suppressing background noise and extracting high-quality flower clusters, thereby providing purified inputs for the subsequent counting network. Second, an uncertainty-guided semi-supervised flower counting network (USCount-Net) is proposed for accurate stage-specific flower counting with limited labeled data. The USCount-Net incorporates two key components: an adaptive pseudo-label filtering (PLF) mechanism based on frequent forward uncertainty estimation (FFUE) is designed to dynamically suppress noisy gradient backpropagation, mitigating error propagation from unreliable pseudo-labels; and a noise-sensitive adaptive gated fusion (AGF) module is introduced to fuse cross-scale features without redundancy, addressing significant scale variations across phenological stages and observation angles. Comparative experiments on a self-built apple flower counting dataset demonstrate that USCount-Net achieves lower MAE and RMSE than state-of-the-art methods at 10%, 30%, and 50% labeling ratios. The results demonstrate that the proposed methodology serves as methodological support for rapid and precise apple flower counting in low-annotation agricultural scenarios.
Why it matches plant phenotyping methodsリンゴ花の画像抽出・計数手法と半教師あり解析ネットワークを開発し、データセット上で比較評価しているため、植物表現型取得が中心である。
abstractthis study proposes a two-stage framework to achieve separate counting of apple flowers at different phenological stages.
Reproduction assets foundThe paper's Data availability statement explicitly provides public access to the authors' USCount-Net source code on GitHub and the self-built apple flower counting dataset (UAV images, annotations, flower cluster images) on Google Drive.Code · publicThe source code is publicly available at https://github.com/haohuihui5019/USCount-Net . And the source dataset can be accessed at https://drive.google.com/drive/folders/1KP8H0qIuct56hWre5GV6ZJnzwOpen asset ↗USCount-Netlines:681-780Dataset · publicThe source code is publicly available at https://github.com/haohuihui5019/USCount-Net . And the source dataset can be accessed at https://drive.google.com/drive/folders/1KP8H0qIuct56hWre5GV6ZJnzwOpen asset ↗lines:681-780Code / dataset availability confirmedOpenAlex · Europe PMC · checked 5 Sept 2026
To address the inefficiency and high cost of manual counting of tobacco leaves, this study proposes a UAV-based method for automatic leaf counting in field-grown tobacco using 3D point clouds and an improved PointNext network. Although UAV imagery has been applied to crop phenotyping, most existing UAV-based leaf-counting methods still rely on 2D images or hand-crafted features and rarely exploit 3D point clouds with dedicated leaf-level segmentation, which limits accuracy and robustness under leaf overlap, variable viewing angles, and complex field backgrounds. In this work, oblique UAV photogrammetry is used to reconstruct individual plants into 3D point clouds, and a segmentation network, SRW-PointNext, is developed by integrating an SCSA attention mechanism and a Residual-SegHead to enhance feature extraction and segmentation performance, while a re-weighted loss alleviates class imbalance. Leaf point clouds are then clustered using MeanShift to obtain leaf counts. Experiments on field-grown tobacco demonstrate that the proposed method achieves a point-cloud segmentation precision of 92.09%, a MIoU of 76.13%. Compared with the original PointNext baseline, SRW-PointNext increased MIoU and overall precision by 3.34% and 2.42% respectively. The final accuracy rate of leaf counting was 92.61%, effectively achieving accurate and stable leaf counting under actual field conditions, and providing technical support for digital management, yield estimation and seedling breeding in tobacco production.
Why it matches plant phenotyping methodsUAV三次元画像と改良セグメンテーション手法により圃場タバコの葉数を推定する方法を開発・検証しており、表現型取得が研究の中心である。
abstractthis study proposes a UAV-based method for automatic leaf counting in field-grown tobacco using 3D point clouds and an improved PointNext
Reproduction assets foundThe paper reports a UAV-based tobacco leaf counting method with an annotated 1000-plant point cloud dataset and SRW-PointNext code, both explicitly declared publicly available at author-provided Zenodo and GitHub URLs matching the allowed list.Dataset · publicData supporting the reported results can be found at: https://zenodo.org/records/15130271 .Open asset ↗zenodo · 15130271lines:531-564Code · publicThe code used in this study is available at: https://github.com/Nan20377/SRW-Pointnext.git .Open asset ↗github · Nan20377/SRW-Pointnextlines:531-564Code / dataset availability confirmedEurope PMC · checked 5 Sept 2026
We present a novel method for accurately counting winter wheat tillers based on RGB images from hand-collected samples. An efficient sample preparation method assembles wheat tillers into bundles from which individual tillers are robustly detected automatically, using classical image analysis. A custom-made user interface ('TillerCounter' program) allows adjusting the automatic detections interactively, which leads to highly accurate tiller counts comparable to the ground truth obtained by manual counting. The key contributions of our work include:1.An efficient method for imaging straw tillers based on bundle assembly.2.An extensive study of the obtained image quality and comparison with the ground truth data from manual counting.3.Demonstration of the approach's high accuracy using correlation analysis (Pearson correlation coefficient R = 0.973 compared to ground truth) and error analysis (root mean squared relative errors below 5 %).
Why it matches plant phenotyping methods小麦分げつ数という植物形態形質を、画像取得・古典的画像解析・専用ソフトウェアで自動推定し、手動計数を基準に精度検証しているため、フェノタイピング手法が中心です。
abstractWe present a novel method for accurately counting winter wheat tillers based on RGB images from hand-collected samples.
Reproduction assets foundThe paper's authors publicly released the TillerCounter GUI source code on GitHub, which implements the Hough-transform-based tiller counting analysis used in this study. The paper also cites original image/count data at Zenodo (10.5281/zenodo.14446564), but no Zenodo URL is present in the allowed URL list, so only theCode · publicThe source code of the TillerCounter GUI is given at https://github.com/agroscope-ch/TillerCounterGui. Original data is given at Zenodo repository: 10.5281/zenodo.14446564Open asset ↗agroscope-ch/TillerCounterGuihtml-lines:163-195Code / dataset availability confirmedEurope PMC · checked 5 Sept 2026
Wheat emergence rate and emergence uniformity are key indicators for evaluating seed vigor and sowing quality, and they play an important role in wheat growth and yield formation. Traditional methods for measuring emergence rate and evaluating emergence uniformity rely on manual assessment, which is inefficient, highly subjective, and unable to meet the demand for large scale, high efficiency, and precise acquisition of wheat emergence data. In this study, RGB images and a two-stage deep learning algorithm were used to extract and analyze seedling traits of 420 wheat varieties under two nitrogen levels, and the results were applied to genome wide association studies to elucidate the genetic basis. The two-stage algorithm integrates a Bidirectional Feature Pyramid Network, small object detection layer, large size image input, and FasterNet to improve detection and instance segmentation speed and accuracy. The proposed method achieved an emergence rate accuracy of 0.929, with R 2 = 0.914 and RMSE = 2.448 compared to manual measurements, and required less than 0.2 s per image for analysis. By employing this two-stage algorithm for processing and analysis, varieties (e.g., Gao8901 and ShiYou20) that consistently exhibited high emergence rates and uniformity under multiple nitrogen treatments were identified. Furthermore, genome-wide association study identified the major loci qEmergence rate-3A and qUniformity-6B governing seedling emergence rate and uniformity, which likely enhance wheat seedling traits by modulating energy supply or related signaling molecules. The emergence-rate and uniformity data generated by the two-stage algorithm significantly accelerated the discovery of relevant genes and enabled the identification of wheat varieties with high emergence rate and uniformity, providing valuable insights and practical references for high-quality breeding and gene mining.
Why it matches plant phenotyping methodsRGB画像と二段階深層学習による出芽率・均一性の自動取得手法を開発し、手動測定との精度比較および大規模品種適用を行っており、表現型取得法が研究の中心である。
abstractTraditional methods for measuring emergence rate and evaluating emergence uniformity rely on manual assessment, which is inefficient, highly subjective, and unable to meet the demand for large scale, high efficiency, and precise acquisition of wheat emergence data.
Reproduction assets foundThe authors openly provide test code, base models, and sample test data for the WS-YOLO two-stage wheat seedling phenotyping pipeline in a public GitHub repository. Raw phenotype datasets are only available upon request, so they do not qualify as public assets.Code · publicThe test code, base models, and sample test data are openly available in the GitHub repository: https://github.com/AIWheatLab/WheatSeedling.Open asset ↗AIWheatLab/WheatSeedlinghtml-lines:375-402Code / dataset availability confirmedOpenAlex · arXiv · checked 13 Sept 2026
Semantic reconstruction of agricultural scenes plays a vital role in tasks such as phenotyping and yield estimation. However, traditional approaches based on manual scanning or fixed camera setups remain a major bottleneck, while active-mapping methods based solely on occupancy grids are too coarse for accurate trait estimation. To address this gap, we propose an active 3D reconstruction framework for horticultural environments using a mobile manipulator. The system integrates OctoMap with 3D Gaussian Splatting to enable accurate and efficient target-aware mapping. A low-resolution OctoMap provides probabilistic occupancy information for informative viewpoint selection and collision-free planning, while 3D Gaussian Splatting leverages geometric, photometric, and semantic information to optimize 3D Gaussians for high-fidelity scene reconstruction. We further introduce a robust mapping strategy that mitigates semantic segmentation and depth noise, together with a background pruning method that reduces memory and computational cost. We validate our framework across simulated, laboratory, and real greenhouse scenes, showing consistent improvements across three state-of-the-art Gaussian Splatting backbones. In simulation, where ground-truth geometry is available, our approach outperforms occupancy-based mapping in both reconstruction accuracy and runtime efficiency: compared with a 0.01m-resolution OctoMap, it doubles the fruit-level F1 score under noisy conditions while achieving up to a threefold reduction in runtime. Beyond simulation, novel-view synthesis quality also improves consistently in laboratory and real greenhouse environments, with PSNR and mIoU improving by up to 1.5 dB and 18%, respectively. Finally, the reconstructed semantic maps enable fruit counting and volume estimation with accuracies approaching 80%.
Why it matches plant phenotyping methods園芸ロボット向けの3D再構成・能動マッピング手法を開発し、果実の計数・体積推定という植物形質の取得に適用・検証しているため、フェノタイピング手法が中心的です。
titleOctoSplat: Hybrid OctoMap-Gaussian Splatting for Active Semantic Mapping and Phenotyping with Horticultural Robots
Reproduction assets foundThe paper's supplementary material is hosted on the authors' public project page (jrcuaranv.github.io/octosplat), and the authors state that all code and data are publicly available. The SimSense repository is a third-party depth-sensor simulator tool, not a paper-specific asset.Code · publicAll code and data are publicly available to facilitate reproducibility.Open asset ↗lines:59-163Code / dataset availability confirmedarXiv · OpenAlex · checked 15 Sept 2026
AppleCottonPearField / plotNeRF / 3D Gaussian SplattingFruitCounting2D/3D reconstructionSegmentation
Rigorous crop counting is crucial for effective agricultural management and informed intervention strategies. However, in outdoor field environments, partial occlusions combined with inherent ambiguity in distinguishing clustered crops from individual viewpoints poses an immense challenge for image-based segmentation methods. To address these problems, we introduce a novel crop counting framework designed for exact enumeration via 3D instance segmentation. Our approach utilizes 2D images captured from multiple viewpoints and associates independent instance masks for neural radiance field (NeRF) view synthesis. We introduce crop visibility and mask consistency scores, which are incorporated alongside 3D information from a NeRF model. This results in an effective segmentation of crop instances in 3D and highly-accurate crop counts. Furthermore, our method eliminates the dependence on crop-specific parameter tuning. We validate our framework on three agricultural datasets consisting of cotton bolls, apples, and pears, and demonstrate consistent counting performance despite major variations in crop color, shape, and size. A comparative analysis against the state of the art highlights superior performance on crop counting tasks. Lastly, we contribute a cotton plant dataset to advance further research on this topic.
Why it matches plant phenotyping methodsNeRFと3Dインスタンスセグメンテーションを用いて作物個体・器官数を推定する画像ベース表現型計測手法を開発・検証しており、方法が研究の中心である。
abstractwe introduce a novel crop counting framework designed for exact enumeration via 3D instance segmentation.
Reproduction assets foundThe paper contributes a public infield cotton plant dataset (8 plants, ~150 iPhone images each, ground-truth boll counts, SAM instance masks) and states that source code, dataset, and multimedia are available at the authors' public project page, which is an allowed URL. The spectacularai GitHub URL is a generic third-pDataset · publicthat incorporates crop visibility
and mask consistency, enabling robustness against occlusions and annotation
discrepancies.
•
We release a public infield cotton plant dataset designed for 3D
rendering and cotton boll counting tasks.
The source code, dataset, and multimedia material associated with this project
can be found at
https://robotic-vision-lab.github.io/cropnerf .
II Related Work
II-A Image-Based Techniques
Image-based methods typically employ object detection to identify crops within
images. For example, Chen et al. [ 4 ] utilized multiple
convolutional neural networks (CNNs) to map input images to total fruit counts.
Similarly, Häni et al. [ 5 ] formulated crop counting as a
multOpen asset ↗lines:108-187Code / dataset availability confirmedOpenAlex · Europe PMC · checked 5 Sept 2026
Accurate and efficient leaf trait measurement is essential for plant phenotyping, agronomy, and ecological studies. In this work, we introduce Leaf Analyzer, a novel open-source, fully automated computer vision-based tool for high-throughput leaf morphological trait measurement such as leaf area, dimensions, perimeter, count, and percent damage. Unlike existing methods that rely on strong foreground-background contrast or controlled imaging conditions, Leaf Analyzer employs an unsupervised clustering approach based on the K-means++ clustering algorithm and a novel Leaf Background Separation (LBS) feature, which combines the L∗ and b∗ channels from CIEL∗a∗b∗ color space and the saturation channel from HSV color space. The proposed method and the LBS feature can effectively distinguish leaves from the background across varying lighting conditions, leaf colors, and camera orientations. To evaluate the performance of the new software, we conducted comprehensive quantitative and qualitative comparison experiments with two widely used software tools - Petiole Pro and LeafByte, demonstrating that Leaf Analyzer achieves superior accuracy and consistency, particularly under challenging imaging conditions. Additionally, we explore methods to further enhance measurement precision, including leaf flattening and the integration of supplementary leaf features such as texture features and color specific features. Beyond leaf trait measurement, we showcase the versatility of Leaf Analyzer in a range of applications, including nondestructive plant phenotyping, seed counting, root trait analysis, leaf area measurement for petri dish-grown plants, plant projected silhouette area or crown projection area estimation, leaf damage assessment, and broader plant science applications, making it a valuable tool for researchers working in laboratory and field environments.
Why it matches plant phenotyping methods葉形態形質を自動抽出するオープンソース画像解析ツールの開発と、既存ツールとの定量比較検証が研究の中心であるため。
abstractIn this work, we introduce Leaf Analyzer, a novel open-source, fully automated computer vision-based tool for high-throughput leaf morphological trait measurement such as leaf area, dimensions, perimeter, count, and percent damage.
Reproduction assets foundThe authors state that the Leaf Analyzer source code, installer files, and all data (including evaluation images) used in this study are publicly available on their GitHub repository.Code · publicThe Leaf Analyzer source code, platform-specific installer files, and all data used in this study are publicly available on our GitHub repository at https://github.com/squashking/Leaf-Analyzer .Open asset ↗squashking/Leaf-Analyzerlines:239-277Dataset · publicAll the images used in the evaluation have been published on our Github repository ( https://github.com/squashking/Leaf-Analyzer ).Open asset ↗squashking/Leaf-Analyzerlines:134-155Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
The AI revolution, advanced Graphics Processing Units (GPUs), and open-source platforms have enabled Machine Learning (ML) and Deep Learning (DL) algorithms to rapidly and accurately extract phenotypic features from imagery. Such advancements have led to phenotypic digitization and made rapid yield forecasting possible. Yield predictions are critical to assess the merit of genotypes to propel cultivar development. This trial followed a three-replicated Randomized Complete Block Design (RCBD) with 36 diverse sorghum genotypes in 2023 at Ashland Bottoms, Kansas. The field images were captured 6 m above using a DJI M300 drone at 90° nadir and 45° oblique angles. This research trained YOLO and Faster R-CNN (Detectron2) models to harness yield attributes from UAS field and lab images. The YOLO models outperformed the Faster R-CNN in detecting sorghum panicles, achieving a mean average precision at 50 % IoU (mAP@0.50) scores of 0.92-0.98, compared to 0.61-0.89 for Faster R-CNN. Panicle detection from field imagery showed a linear correlation of 0.86 with ground truth field panicle counts. Lab imagery analyses measured panicle area, seed counts, and seed area with correlation coefficients of 0.79, 0.94, and 0.25 with respective ground truth observations. Support Vector Regression (SVR), Random Forest Regression (RFR), and Decision Tree Regression (DTR) were used to predict yield with correlation coefficients of 0.74, 0.71, and 0.78, respectively, and SHapley Additive exPlanation (SHAP) analysis revealed panicle seed count as the primary driver of yield prediction. We observed YOLO models are well-suited for extracting yield-predictive features from pertinent images. Such features can then be incorporated into ML regression models to predict yield per se performance with greater accuracy. The GitHub link is provided in the Data availability section.
Why it matches plant phenotyping methodsUAS・実験室画像から穂数、穂面積、種子数・面積などの植物形質を深層学習で抽出し、検出精度を検証して収量予測へ利用する方法が研究の中心である。
abstractThis research trained YOLO and Faster R-CNN (Detectron2) models to harness yield attributes from UAS field and lab images.
Reproduction assets foundThe authors explicitly state that scripts, fine-tuned models, datasets, and sample images for this sorghum yield-forecasting study are publicly available on GitHub, matching the allowed URL exactly.Code · publicThe scripts, fine-tuned models, datasets, and sample images pertinent to this manuscript are available on GitHub at https://github.com/mbari78/DL_for_Sorghum_Yield_Prediction.git .Open asset ↗https://github.com/mbari78/DL_for_Sorghum_Yield_Prediction.gitlines:244-299Code / dataset availability confirmedOpenAlex · Europe PMC · checked 15 Sept 2026
Rapeseed / canolaNeRF / 3D Gaussian SplattingLiDAR / point cloudFruitCountingSegmentationFruit / seed / panicle traits
Accurate analysis of plant phenotypic traits is crucial for crop breeding and precision agriculture. This study proposes a lightweight semantic segmentation model named KAN-GLNet (Kolmogorov-Arnold Network with Global-Local Feature Modulation), based on an enhanced PointNet++ architecture and integrated with an optimized Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, to achieve high-precision segmentation and automatic counting of canola siliques. A multi-view point cloud acquisition platform was built, and high-fidelity canola point clouds were reconstructed using Neural Radiance Fields (NeRF) technology. The proposed model includes three key modules: Reverse Bottleneck Kolmogorov-Arnold Network Convolution, a Global-Local Feature Modulation (GLFN) block, and a contrastive learning-based normalization module called ContraNorm. KAN-GLNet contains only 5.72M parameters and achieves 94.50% mIoU, 96.72% mAcc, and 97.77% OAcc in semantic segmentation tasks, outperforming all baseline models. In addition, the DBSCAN workflow was optimized, achieving a counting accuracy of 97.45% in the instance segmentation task. This method achieves an excellent balance between segmentation accuracy and model complexity, providing an efficient solution for high-throughput plant phenotyping. The code and dataset have been made publicly available at: https://anonymous.4open.science/r/KAN-GLNet-6432/.
Why it matches plant phenotyping methodsカノーラ莢のセグメンテーションと自動計数という植物形質抽出手法を、3D点群取得基盤・NeRF再構成・新規モデル・DBSCANワークフローとして開発・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 study proposes a lightweight semantic segmentation model named KAN-GLNet (Kolmogorov-Arnold Network with Global-Local Feature Modulation), based on an enhanced PointNet++ architecture and integrated with an optimized Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, to achieve high-precision segmentation and automatic counting of canola siliques.
Reproduction assets foundThe authors explicitly state that their curated code and dataset (canola silique point cloud phenotyping data and KAN-GLNet analysis code) are publicly available at an anonymous.4open.science repository, which is an allowed URL.Code · publicDBSCAN workflow was optimized, achieving a counting accuracy of 97.45% in the instance segmentation task. This method achieves an excellent balance between segmentation accuracy and model complexity, providing an efficient solution for high-throughput plant phenotyping. The code and dataset have been made publicly available at: https://anonymous.4open.science/r/KAN-GLNet-6432/ .
http://dx.doi.org/10.13039/501100001809 National Natural Science Foundation of China
32301762
Liu Jie
This project is supported by National Natural Science Foundation of China, grant number 32301762.
pmc-status-qastatus 0 pmc-status-live yes pmc-status-embargo no pmc-status-released yes pmc-prop-open-access yes pmc-pOpen asset ↗anonymous.4open.science/r/KAN-GLNet-6432lines:1-65Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
Tea flowers play a crucial role in taxonomic research and hybrid breeding of tea plants. As traditional methods of observing tea flower traits are labor-intensive and inaccurate, TflosYOLO and Tea Flowering Stage Classification (TFSC) models were proposed for tea flowering quantification, which enable the estimation of flower count and flowering period. In this study, a highly representative and diverse dataset was constructed by collecting flower images from 29 tea accessions in 2 years. Based on this dataset, the TflosYOLO model was built on the YOLOv5 architecture and enhanced with the Squeeze-and-Excitation (SE) network, Adaptive Rectangular Convolution, and Attention Free Transformer, which is the first model to offer a viable solution for detecting and counting tea flowers. The TflosYOLO model achieved a mean Average Precision at 50% IoU (mAP50) of 0.844, outperforming YOLOv5, YOLOv7, and YOLOv8. Furthermore, the TflosYOLO model was tested on 31 datasets encompassing 26 tea accessions and five flowering stages, demonstrating high generalization and robustness. The correlation coefficient (R 2 ) between the predicted and actual flower counts was 0.964. Additionally, the TFSC model-a seven-layer neural network-was designed for the automatic classification of the flowering period. The TFSC model was evaluated for 2 years and achieved an accuracy of 0.738 and 0.899. Using the TflosYOLO+TFSC model, the tea flowering dynamics were monitored, and the changes in flowering stages were tracked across various tea accessions. The framework provides crucial support for tea plant breeding programs and the phenotypic analysis of germplasm resources.
Why it matches plant phenotyping methods茶花画像から花数と開花期を推定するモデルを開発・検証しており、植物表現型の取得・抽出手法が研究の中心である。
abstractTflosYOLO and Tea Flowering Stage Classification (TFSC) models were proposed for tea flowering quantification, which enable the estimation of flower count and flowering period.
Reproduction assets foundThe paper's data availability statement explicitly deposits the tea flower datasets and models in a public GitHub repository (sufie-mi/tea-flower-model), which directly supports this paper's tea flower phenotyping measurements and models. The labelImg repository is a generic third-party annotation tool, not a paper-ownDataset · publicThe datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://github.com/sufie-mi/tea-flower-model .Open asset ↗https://github.com/sufie-mi/tea-flower-model · tea-flower-modellines:764-781Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
In modern agricultural production, accurate monitoring of maize growth and leaf counting is crucial for precision management and crop breeding optimization. Current UAV-based methods for detecting maize seedlings and leaves often face challenges in achieving high accuracy due to issues such as low spatial-resolution, complex field environments, variations in plant scale and orientation. To address these challenges, this study develops an integrated detection and visualization software, DP-MaizeTrack, which incorporates the DP-YOLOv8 model based on YOLOv8. The DP-YOLOv8 model integrates three key improvements. The Multi-Scale Feature Enhancement (MSFE) module improves detection accuracy across different scales. The Optimized Spatial Pyramid Pooling-Fast (OSPPF) module enhances feature extraction in diverse field conditions. Experimental results in single-plant detection show that the DP-YOLOv8 model outperforms the baseline YOLOv8 with improvements of 3.9% in Precision (95.1%), 4.1% in Recall (91.5%), and 4.0% in mAP50 (94.9%). The software also demonstrates good accuracy in the visualization results for single-plant and leaf detection tasks. Furthermore, DP-MaizeTrack not only automates the detection process but also integrates agricultural analysis tools, including region segmentation and data statistics, to support precision agricultural management and leaf-age analysis. The source code and models are available at https://github.com/clhclhc/project.
Why it matches plant phenotyping methodsUAV画像からトウモロコシ個体数と葉数を抽出するソフトウェアを開発しており、植物形質取得が研究の中心です。
abstractthis study develops an integrated detection and visualization software, DP-MaizeTrack
Reproduction assets foundThe paper explicitly states that the authors' source code and trained models for DP-MaizeTrack/DP-YOLOv8 are publicly available on GitHub. No public dataset deposit is stated; the UAV image dataset is described but not declared publicly available.Code · publicThe source code and models are available at https://github.com/clhclhc/project .Open asset ↗https://github.com/clhclhc/projectlines:224-300Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
Accurately detecting and counting potatoes during early harvest is essential for estimating yield, automating sorting, and supporting data-driven agricultural decisions. However, field environments often present practical challenges-such as soil occlusion, overlapping tubers, and inconsistent lighting-that hinder robust visual recognition. In response, we introduce SCG-YOLOv8n, a compact and field-adapted detection framework built upon the YOLOv8n architecture and specifically tailored for small-object detection in real-world farming conditions. The model incorporates three practical enhancements: a C-SPD module that preserves spatial detail to improve recognition of partially buried tubers; an S-CARAFE operator that reconstructs fine-scale features during upsampling; and GhostShuffleConv layers that reduce computational overhead without sacrificing accuracy. Through extensive field-based experiments, SCG-YOLOv8n consistently outperforms YOLOv5n and its base version across all key metrics. Float16 quantization compresses the model to 3.2 MB, enabling real-time inference on Android devices. We also developed PotatoDetector, a mobile application that demonstrates stable performance in field trials, achieving an RMSE of 1.38 and [Formula: see text] of 0.96 in counting tasks. These results suggest that SCG-YOLOv8n offers a practical and scalable tool for precision agriculture, with potential applicability to other root and tuber crop monitoring scenarios.
Why it matches plant phenotyping methodsジャガイモ塊茎の画像検出・計数を行うモデルとモバイル実装を開発し、圃場で性能検証している。塊茎数という植物器官形質の取得が中心であり、単なる収量測定ではない。
abstractwe introduce SCG-YOLOv8n, a compact and field-adapted detection framework built upon the YOLOv8n architecture and specifically tailored for small-object detection in real-world farming conditions.
Reproduction assets foundThe paper's custom potato image dataset is not publicly available (available only from the corresponding author on request), but the authors provide a public GitHub repository for the SCG-YOLOv8n analysis code with an explicit availability statement and URL.Code · publicCode availability
Code can be found at https://github.com/AiXia520/SCG-YOLOv8n.git.Open asset ↗https://github.com/AiXia520/SCG-YOLOv8n.githtml-lines:359-392Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Accurate detection and counting of wheat spikes are crucial for yield estimation and variety selection in precision agriculture. However, challenges such as complex field environments, morphological variations, and small target sizes hinder the performance of existing models in real-world applications. This study proposes FEWheat-YOLO, a lightweight and efficient detection framework optimized for deployment on agricultural edge devices. The architecture integrates four key modules: (1) FEMANet, a mixed aggregation feature enhancement network with Efficient Multi-scale Attention (EMA) for improved small-target representation; (2) BiAFA-FPN, a bidirectional asymmetric feature pyramid network for efficient multi-scale feature fusion; (3) ADown, an adaptive downsampling module that preserves structural details during resolution reduction; and (4) GSCDHead, a grouped shared convolution detection head for reduced parameters and computational cost. Evaluated on a hybrid dataset combining GWHD2021 and a self-collected field dataset, FEWheat-YOLO achieved a COCO-style AP of 51.11%, AP@50 of 89.8%, and AP scores of 18.1%, 50.5%, and 61.2% for small, medium, and large targets, respectively, with an average recall (AR) of 58.1%. In wheat spike counting tasks, the model achieved an R 2 of 0.941, MAE of 3.46, and RMSE of 6.25, demonstrating high counting accuracy and robustness. The proposed model requires only 0.67 M parameters, 5.3 GFLOPs, and 1.6 MB of storage, while achieving an inference speed of 54 FPS. Compared to YOLOv11n, FEWheat-YOLO improved AP@50, AP_s, AP_m, AP_l, and AR by 0.53%, 0.7%, 0.7%, 0.4%, and 0.3%, respectively, while reducing parameters by 74%, computation by 15.9%, and model size by 69.2%. These results indicate that FEWheat-YOLO provides an effective balance between detection accuracy, counting performance, and model efficiency, offering strong potential for real-time agricultural applications on resource-limited platforms.
Why it matches plant phenotyping methodsコムギ穂の検出・計数という植物器官形質の画像ベース推定手法を開発し、データセット上で精度・計算効率・堅牢性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。
abstractThis study proposes FEWheat-YOLO, a lightweight and efficient detection framework optimized for deployment on agricultural edge devices.
Reproduction assets foundThe paper uses the public GWHD2021 wheat spike detection dataset (available on Kaggle) as part of its hybrid dataset, with an explicit availability statement and URL. The self-collected Xinjiang field dataset is private and available only on request. No author analysis code, trained model checkpoints, or other paper-特定Dataset · publiciting, W.W., S.L. and Y.L.; supervision, J.C.; project administration, X.Z.; funding acquisition, X.Z. All authors have read and agreed to the published version of the manuscript.
Data Availability Statement
The public part of the dataset used in this study is available from the Global Wheat Head Detection (GWHD2021) dataset at https://www.kaggle.com/competitions/global-wheat-detection , accessed on 30 September 2025. The remaining part of the dataset is private and cannot be shared due to institutional or privacy restrictions. Requests for access to the private dataset may be directed to the corresponding author.
Conflicts of Interest
The authors declare no conflicts of interest. The funderOpen asset ↗GWHD2021lines:854-929Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
Mango is a fruit of great economic importance in India. India is the top mango-producing nation in the world, accounting for over half of global mango output. In order to determine the production capability of the insured orchards, a complete inventory is carried out in situ every three years. The inventory includes counting number of trees, grouping them into yield categories, and assessing damaged ones. Satellite Remote Sensing proves to be a vital tool for estimating ecological parameters such as population density, tree health, volume, biomass, and carbon sequestration rates. The significance of tree counting extends beyond orchard evaluations, playing a vital role in environmental protection, agricultural planning, and crop yield forecast. unfortunately, conventional tree counting methods often require very expensive feature engineering, which leads to more errors as well as lower overall optimization. In order to overcome these obstacles, deep learning-based methods have been used to count trees, exhibiting cutting-edge results in this crucial activity. This paper introduces a novel approach employing deep learning for Image-Based Mango Tree counting in high-resolution satellite imagery data. The proposed model, named Bi-directional Feature Pyramid Network (BiFPN)-YOLOv8m an improved version of YOLOv8, employs object detection to effectively separate, locate, and count mango trees with in orchards. A dataset of 1700 training and 300 testing images of mango orchards with trees of various ages is used to evaluate the various YOLOv8 variants, YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l, YOLOv8x, including YOLOv9, YOLOv10, and BiFPN-YOLOv8m, with a focus on computational efficiency, accuracy, and speed. Experimental findings show that, even under difficult circumstances, the proposed method continuously outperforms state-of-the-art techniques.
Why it matches plant phenotyping methods衛星画像からマンゴー樹木を分離・位置推定・計数する深層学習手法を開発・評価しており、植物個体数という観測可能な形態・構造形質の抽出が中心である。
abstractThis paper introduces a novel approach employing deep learning for Image-Based Mango Tree counting in high-resolution satellite imagery data.
Reproduction assets foundThe paper's satellite remote sensing image dataset used for mango tree counting is publicly deposited on GitHub per the Data Availability Statement. No separate analysis code or trained model checkpoint is explicitly deposited.Dataset · publicRemote Sensing Image Data that support the findings of this study have been deposited in the GitHub. The url to the data uploaded is https://github.com/lbirla/Mango_tree_satellite_data.Open asset ↗https://github.com/lbirla/Mango_tree_satellite_datahtml-lines:497-525Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
Introduction Wheat is a vital global staple crop, where accurate ear detection and counting are essential for yield prediction and field management. However, the complexity of field environments poses significant challenges to achieving lightweight yet high-precision detection. Methods This study proposes YOLOv8-FDA, a lightweight detection and counting method based on YOLOv8. The approach integrates RFAConv for enhanced feature extraction, DySample for efficient multi-scale upsampling, HWD for compressed and accelerated model training, and the SDL loss for improved bounding box regression. Results Experimental results on the GWHD dataset show that YOLOv8-FDA achieves a precision of 86.3%, recall of 77.5%, and mAP@0.5 of 84.9%, outperforming the original YOLOv8n by significant margins. The model size is 2.96MB with a computational cost of 8.3 GFLOPs, and it operates at 19.2 FPS, enabling real-time counting with over 97.5% accuracy using cross-row segmentation. Discussion The proposed YOLOv8-FDA model demonstrates strong detection performance, lightweight characteristics, and efficient real-time capability, indicating its high practicality and suitability for deployment in real-world agricultural applications.
Why it matches plant phenotyping methodsコムギ穂の検出・計数という植物器官形質の画像ベース抽出法をYOLOv8改良モデルとして開発し、データセット上で性能検証しているため、方法が研究の中心である。
abstractThis study proposes YOLOv8-FDA, a lightweight detection and counting method based on YOLOv8.
Reproduction assets foundThe paper's wheat ear detection/counting experiments were run on the public 2021 GWHD dataset, which the authors explicitly link via a Zenodo DOI in the data availability statement. No author-specific code or trained model checkpoints are disclosed.Dataset · publicPublicly available datasets were analyzed in this study. This data can be found here: Zenodo at https://doi.org/10.5281/zenodo.5092309 .Open asset ↗Zenodo · 10.5281/zenodo.5092309lines:698-734Code / dataset availability confirmedCrossref · checked 15 Sept 2026
This study presents a novel and efficient approach to accurately assess post-sowing rice plant density by leveraging unmanned aerial vehicles (UAVs) equipped with high-resolution RGB cameras. In contrast to labor-intensive and spatially limited traditional methods that rely on manual sampling and extrapolation, our proposed methodology uses UAVs to rapidly and comprehensively survey entire paddy fields at optimized altitudes (4, 6, 8, and 10 m). Aerial imagery was autonomously acquired 17 days post-sowing, following a pre-defined flight path. The robust rice plant density estimation process incorporates two key innovations: first, a dynamic system of 12 adaptive segmentation thresholding blocks that effectively detects rice seed presence across diverse and variable background conditions. Second, a tailored three-layer convolutional neural network (CNN) accurately classifies vegetative situations. To maximize the training efficiency and performance, we implemented both a pretrained model and a deep learning model, conducting a rigorous comparative analysis against the state-of-the-art YOLOv10. Notably, under favorable imaging conditions, our findings indicate that a 6-m flight altitude yields optimal results, achieving a high degree of accuracy with rice plant density estimates that closely align with those obtained through traditional ground-based methods. This investigation unequivocally highlights the significant advantages of UAV-based monitoring as an economically viable, spatially comprehensive, and demonstrably accurate tool for precise rice field management, ultimately contributing to enhanced crop yields, improved food security, and the promotion of sustainable agricultural practices.
Why it matches plant phenotyping methodsUAV RGB画像と適応的セグメンテーション、CNNを用いてイネ個体密度を推定する手法を開発・比較・検証しており、植物形質の取得が研究の中心です。
abstractThis study presents a novel and efficient approach to accurately assess post-sowing rice plant density by leveraging unmanned aerial vehicles (UAVs) equipped with high-resolution RGB cameras.
Reproduction assets foundThe paper's data availability statement points to a public Zenodo deposit containing the study's datasets (UAV RGB imagery/labels used for rice plant density estimation). No separate author analysis code repository is stated.Dataset · publicvaluate the accuracy of the proposed labels, subsequently enhancing the training model's speed, convergence, accuracy, and efficiency.
Statements
Data availability statement
The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found at: https://zenodo.org/records/10960906 .
Author contributions
TH: Writing – original draft. TN: Data curation, Resources, Validation, Writing – original draft. QN: Data curation, Writing – review & editing. HN: Funding acquisition, Investigation, Methodology, Writing – review & editing. PP: Methodology, Software, Supervision, Writing – review & editing.
Funding
TheOpen asset ↗zenodo · 10960906lines:500-523Code / dataset availability confirmedCrossref · checked 6 Sept 2026
Object detection is essential for precision agriculture applications like automated plant counting, but the minimum dataset requirements for effective model deployment remain poorly understood for arable crop seedling detection on orthomosaics. This study investigated how much annotated data is required to achieve standard counting accuracy (R2 = 0.85) for maize seedlings across different object detection approaches. We systematically evaluated traditional deep learning models requiring many training examples (YOLOv5, YOLOv8, YOLO11, RT-DETR), newer approaches requiring few examples (CD-ViTO), and methods requiring zero labeled examples (OWLv2) using drone-captured orthomosaic RGB imagery. We also implemented a handcrafted computer graphics algorithm as baseline. Models were tested with varying training sources (in-domain vs. out-of-distribution data), training dataset sizes (10–150 images), and annotation quality levels (10–100%). Our results demonstrate that no model trained on out-of-distribution data achieved acceptable performance, regardless of dataset size. In contrast, models trained on in-domain data reached the benchmark with as few as 60–130 annotated images, depending on architecture. Transformer-based models (RT-DETR) required significantly fewer samples (60) than CNN-based models (110–130), though they showed different tolerances to annotation quality reduction. Models maintained acceptable performance with only 65–90% of original annotation quality. Despite recent advances, neither few-shot nor zero-shot approaches met minimum performance requirements for precision agriculture deployment. These findings provide practical guidance for developing maize seedling detection systems, demonstrating that successful deployment requires in-domain training data, with minimum dataset requirements varying by model architecture.
Why it matches plant phenotyping methodsトウモロコシ幼苗の個体数という植物形質を画像から推定する物体検出手法について、複数モデル、データ量、アノテーション品質を系統的に比較・評価しており、手法の性能検証が中心である。
abstractThis study investigated how much annotated data is required to achieve standard counting accuracy (R2 = 0.85) for maize seedlings across different object detection approaches.
Reproduction assets foundThe paper's Data Availability Statement provides two paper-specific public assets: the authors' handcrafted-method analysis code on a GitHub gist and the ID (in-distribution) annotation datasets created for this study on Zenodo. Both have explicit availability language and public URLs.Code · publicThe code for the handcrafted methods used in this study is available at
https://gist.github.com/SamueleBumbaca/4a227bbe7b78d6be3424899c16c60bb4 (accessed on 20
June 2025).Open asset ↗gist.github.com/SamueleBumbacapdf-page:23 lines:1-52Dataset · publicThe datasets created during this study (ID datasets) are available at the Zenodo repository
https://doi.org/10.5281/zenodo.15235602 (accessed on 20 June 2025)Open asset ↗Zenodo · 10.5281/zenodo.15235602pdf-page:23 lines:1-52Code / dataset availability confirmedOpenAlex · checked 6 Sept 2026
Rice panicle detection is a key technology for improving rice yield and agricultural management levels. Traditional manual counting methods are labor-intensive and inefficient, making them unsuitable for large-scale farmlands. This paper proposes FRPNet, a novel lightweight convolutional neural network optimized for multi-altitude rice panicle detection in UAV images. The architecture integrates three core innovations: a CSP-ScConv backbone with self-calibrating convolutions for efficient multi-scale feature extraction; a Feature Pyramid Shared Convolution (FPSC) module that replaces pooling with multi-branch dilated convolutions to preserve fine-grained spatial information; and a Dynamic Bidirectional Feature Pyramid Network (DynamicBiFPN) employing input-adaptive kernels to optimize cross-scale feature fusion. The model was trained and evaluated on the open-access Dense Rice Panicle Detection (DRPD) dataset, which comprises UAV images captured at 7 m, 12 m, and 20 m altitudes. Experimental results demonstrate that our method significantly outperforms existing advanced models, achieving an AP50 of 0.8931 and an F2 score of 0.8377 on the test set. While ensuring model accuracy, the parameters of the proposed model decreased by 42.87% and the GFLOPs by 48.95% compared to Panicle-AI. Grad-CAM visualizations reveal that FRPNet exhibits superior background noise suppression in 20 m altitude images compared to mainstream models. This work establishes an accuracy-efficiency balanced solution for UAV-based field phenotyping.
Why it matches plant phenotyping methodsUAV画像からイネ穂の検出・計数という植物形質を抽出する軽量深層学習手法を開発し、公開データセットで評価しており、表現型取得手法が中心である。
abstractThis paper proposes FRPNet, a novel lightweight convolutional neural network optimized for multi-altitude rice panicle detection in UAV images.
Reproduction assets foundThe paper states its data (the DRPD rice panicle UAV dataset used for training/evaluation) is publicly available via a GitHub release URL, which matches an allowed URL.Dataset · publicData Availability Statement: Data is available at https://github.com/changcaiyang/Panicle-AI/
releases/tag/v1.0.Open asset ↗Panicle-AI · v1.0pdf-page:22 lines:1-59Code / dataset availability confirmedOpenAlex · Crossref · Europe PMC · checked 6 Sept 2026
BACKGROUND: Plant phenotyping has become increasingly important for advancing plant science, agriculture, and biotechnology. Classic manual methods are labor-intensive and time-consuming, while existing computational tools often require advanced coding skills, high-performance hardware, or PC-based environments, making them inaccessible to non-experts, to resource-constrained users, and to field technicians. RESULTS: To respond to these challenges, we introduce OpenPheno, an open-access, user-friendly, and smartphone-based platform encapsulated within a WeChat Mini-Program for instant plant phenotyping. The platform is designed for ease of use, enabling users to phenotype plant traits quickly and efficiently with only a smartphone at hand. We currently instantiate the use of the platform with tools such as SeedPheno, WheatHeadPheno, LeafAnglePheno, SpikeletPheno, CanopyPheno, TomatoPheno, and CornPheno; each offering specific functionalities such as seed size and count analysis, wheat head detection, leaf angle measurement, spikelet counting, canopy structure analysis, and tomato fruit measurement. In particular, OpenPheno allows developers to contribute new algorithmic tools, further expanding its capabilities to continuously facilitate the plant phenotyping community. CONCLUSIONS: By leveraging cloud computing and a widely accessible interface, OpenPheno democratizes plant phenotyping, making advanced tools available to a broader audience, including plant scientists, breeders, and even amateurs. It can function as a role in AI-driven breeding by providing the necessary data for genotype-phenotype analysis, thereby accelerating breeding programs. Its integration with smartphones also positions OpenPheno as a powerful tool in the growing field of mobile-based agricultural technologies, paving the way for more efficient, scalable, and accessible agricultural research and breeding.
Why it matches plant phenotyping methodsスマートフォンで植物形質を取得・解析するソフトウェアプラットフォームの開発が中心であり、複数の具体的な表現型解析ツールを提供している。
abstractwe introduce OpenPheno, an open-access, user-friendly, and smartphone-based platform encapsulated within a WeChat Mini-Program for instant plant phenotyping.
Reproduction assets foundThe paper's authors publicly release the OpenPheno platform code (GitHub repository) and the evaluation sample data used for algorithm validation and demonstration (dataset subdirectory). Both are paper-specific, public, and actionable.Dataset · publicEvaluation sample data used for algorithm validation and demonstration has been made publicly available at out GitHub repository: https://github.com/openpheno/OpenPheno/tree/main/dataset .Open asset ↗openpheno/OpenPheno · tree/main/datasetlines:171-191Code / dataset availability confirmedEurope PMC · Crossref · checked 14 Sept 2026
Chloroplast density in cells varies among different types of cells and plants. In current single-cell spatiotemporal analysis, the automatic detection and quantification of chloroplasts at the single-cell level is crucial. We developed DeepD&Cchl (Deep-learning-based Detecting-and-Counting-chloroplasts), an AI tool for single-cell chloroplast detection and cell-type clustering. It utilizes You-Only-Look-Once (YOLO), a real-time detection algorithm, for accurate and efficient performance. DeepD&Cchl has been proved to identify chloroplasts in plant cells across various imaging types, including light microscopy, electron microscopy, and fluorescence microscopy. Integrated with an Intersection Over Union (IOU) module, DeepD&Cchl precisely counts chloroplasts in single- or multi-layered images, while eliminating double-counting errors. Furthermore, when combined with Cellpose, a single-cell segmentation tool, DeepD&Cchl enhances its effectiveness at the single-cell level. By counting chloroplasts within individual cells, it supports cell-type-specific clustering based on chloroplast number versus cell size, offering valuable morphological insights for single-cell studies. In summary, DeepD&Cchl is a significant advancement in plant cell analysis. It offers accuracy and efficiency in chloroplast identification, counting and cell-type classification, providing a useful tool for plant research.
Why it matches plant phenotyping methods植物細胞画像から葉緑体を検出・計数し、細胞型をクラスタリングするAIツールの開発が中心であり、植物の形態的状態を定量化するフェノタイピング手法に該当する。
abstractWe developed DeepD&Cchl (Deep-learning-based Detecting-and-Counting-chloroplasts), an AI tool for single-cell chloroplast detection and cell-type clustering.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicThe raw dataset, as well as the scripts for the DeepD&Cchl model training and 17application macro, were shared on GitHub https://github.com/Shaokai9/AI4LifeScience_ECNU/tree/main/Deep%20subcellular%20detection .Open asset ↗Shaokai9/AI4LifeScience_ECNUlines:400-410Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
High resolution three-dimensional (3D) point clouds enable the mapping of cotton boll spatial distribution, aiding breeders in better understanding the correlation between boll positions on branches and overall yield and fiber quality. This study developed a segmentation workflow for point clouds of 18 cotton genotypes to map the spatial distribution of bolls on the plants. The data processing workflow includes two independent approaches to map the vertical and horizontal distribution of cotton bolls. The vertical distribution was mapped by segmenting bolls using PointNet++ and identifying individual instances through Euclidean clustering. For horizontal distribution, TreeQSM segmented the plant into the main stem and individual branches. PointNet++ and Euclidean clustering were then used to achieve cotton boll instance segmentation. The horizontal distribution was determined by calculating the Euclidean distance of each cotton boll relative to the main stem. Additionally, branch types were classified using point cloud meshing completion and the Dijkstra shortest path algorithm. The results highlight that the accuracy and mean intersection over union (mIoU) of the 2-class segmentation based on PointNet++ reached 0.954 and 0.896 on the whole plant dataset, and 0.968 and 0.897 on the branch dataset, respectively. The coefficient of determination (R 2 ) for the boll counting was 0.99 with a root mean squared error (RMSE) of 5.4. For the first time, this study accomplished high-granularity spatial mapping of cotton bolls and branches, but directly predicting fiber quality from 3D point clouds remains a challenge. This method provides a promising tool for 3D cotton plant mapping of different genotypes, which potentially could accelerate plant physiological studies and breeding programs.
Why it matches plant phenotyping methods3D点群の分割・個体抽出ワークフローを開発し、綿花の果実数と枝・果実の空間分布という植物形質を定量化・検証しており、フェノタイピング手法が研究の中心である。
abstractThis study developed a segmentation workflow for point clouds of 18 cotton genotypes to map the spatial distribution of bolls on the plants.
Reproduction assets foundThe authors explicitly state that the code, data, and trained PointNet++ weights for cotton boll and branch mapping are publicly available in their GitHub repository, which directly reproduces this paper's phenotyping analysis.Code · publicThe code, data, and training weights for cotton boll and branch mapping are available at https://github.com/UGA-BSAIL/cotton_organ_mapping.git .Open asset ↗UGA-BSAIL/cotton_organ_mappinglines:101-109Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
The real-time monitoring and counting of maize seed germination at seedling stage is of great significance for seed quality detection, field management and yield estimation. Traditional manual monitoring and counting is very time-consuming, cumbersome and error-prone. In order to quickly and accurately identify and count maize seedlings in a complex field environment, this study proposes an end-to-end maize seedling plant detection model H-RT-DETR (Hierarchical-Real-Time DEtection TRansformer) based on hierarchical feature extraction and RT-DETR (Real-Time DEtection TRansformer). H-RT-DETR uses Hierarchical Feature Representation and Efficient Self-Attention as the backbone network for feature extraction, thereby improving the network's ability to extract features of maize seedling stage in UAV remote sensing images. Through experiments on the UAV remote sensing data set of maize seedling stage, the mean Average Precision mAP0.5-0.95, mAP0.5 and mAP0.75 of the improved H-RT-DETR model reached 51.2%, 94.7% and 48.1%, respectively, and the Average Recall (AR) reached 68.5%. In order to verify the efficiency of the proposed method, H-RT-DETR is compared with the widely used and advanced target recognition methods. The results show that the detection accuracy of H-RT-DETR is better than that of the comparison methods. In terms of detection speed, the H-RT-DETR model does not require Non-Maximum Suppression (NMS) post-processing operations, the Frames Per Second (FPS) on the test dataset reaches 84f/s, which is 19,12,11 and 21 higher than that of YOLOv5, YOLOv7, YOLOv8 and YOLOX, respectively, under the same hardware environment. This model can provide technical support for real-time detection of maize seedlings under UAV remote sensing images in terms of both detection accuracy and speed (see https://github.com/wylSUGAR/H-RT-DETR for model implementation and results).
Why it matches plant phenotyping methodsUAV画像からトウモロコシ幼苗を検出・計数する深層学習手法を開発し、既存手法と精度・速度を比較検証しているため、植物フェノタイピング手法が中心である。
abstractIn order to quickly and accurately identify and count maize seedlings in a complex field environment, this study proposes an end-to-end maize seedling plant detection model H-RT-DETR
Reproduction assets foundThe authors provide a public GitHub repository containing the H-RT-DETR model implementation and results for maize seedling detection in UAV images. The UAV image dataset itself is not stated as publicly available, and other linked repositories (labelme, YOLOv5, ultralytics) are generic third-party tools, not paper-Code · publicthe test dataset reaches 84f/s, which is 19,12,11 and 21 higher than that of YOLOv5, YOLOv7, YOLOv8 and YOLOX, respectively, under the same hardware environment. This model can provide technical support for real-time detection of maize seedlings under UAV remote sensing images in terms of both detection accuracy and speed (see https://github.com/wylSUGAR/H-RT-DETR for model implementation and results).
Keywords
Maize seedling stage UAV remote sensing RT-DETR Target recognition Real-time detection Plant counting the National Key Research and Development Program of China 2023YFD1900704 2023YFD1900704 pmc-status-qastatus 0 pmc-status-live yes pmc-status-embargo no pmc-status-released yes pmOpen asset ↗wylSUGAR/H-RT-DETRlines:1-26Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
The spike number (SN) is an important trait that significantly impacts grain yield in wheat. Manual counting of SN is time-consuming, hindering large-scale breeding efforts. Hence, there is an urgent need to develop efficient and accurate methodologies for SN counting. A YOLOX algorithm was used to determine the optimal growth stage for developing wheat spike detection models among recombinant inbred lines (RILs) across Zhongmai 175 × Lunxuan 987 and a diverse panel of 166 cultivars. We subsequently increased the precision of spike identification by developing a new YOLOX-P algorithm that incorporates the convolutional block attention module and increasing the resolution of the input images. We also used these SN data to identify underlying loci in the Zhongmai 578 × Jimai 22 RIL population. The results revealed that the late grain-filling stage presented the highest precision among the SN detection models, with accuracies ranging from 91.8 to 95.02 %. The improved YOLOX-P algorithm demonstrated higher mean average precision scores (5.30-5.99 %) and F1 scores (0.06) than did the YOLOX algorithm when it was applied to the same subsets. Three new SN loci, namely, QSN . caas-4A2, QSN . caas-4D and QSN . caas-5B2 , were identified using the 50k SNP arrays. Two kompetitive allele-specific PCR markers linked with QSN . caas-4A2 and QSN . caas-5B2 were developed, and their genetic effects were validated in a diverse panel of 166 cultivars. These findings provide useful tools for high-throughput identification of SNs and novel loci in wheat.
Why it matches plant phenotyping methodsRGB画像とコンピュータビジョンによりコムギの穂数を自動推定する手法を開発・比較し、精度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。
abstractHence, there is an urgent need to develop efficient and accurate methodologies for SN counting.
Reproduction assets foundThe paper publicly releases two paper-specific assets: (1) a wheat spike number image dataset (subsets CD&DD&XX) on GitHub, and (2) the YOLOX-P analysis code on Google Drive. Both have explicit availability statements with author-provided URLs.Dataset · publicThe image set for CD&DD&XX is publicly available on GitHub ( https://github.com/lileimax/YOLOXP-wheat-spike-identification ).Open asset ↗https://github.com/lileimax/YOLOXP-wheat-spike-identificationlines:223-246Code · publicThe code for YOLOX-P is publicly available on Google Drive ( https://drive.google.com/drive/folders/1urCDUdyrq14FuwG2I3YwCZraUGEEl_8X?usp=sharing ).Open asset ↗lines:247-250Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
Precisely identifying missing virus-free strawberry mother plants in nutrient pots post-transplantation is crucial for optimizing seedling management and maximizing yields in glass greenhouses. Thus, we present an automated method for detecting and counting missing seedlings based on SSP-MambaNet. Challenges in this process include the variable growth morphology of seedlings and complex environmental conditions in the greenhouse. Our approach starts with SPDFFA (Spatial-to-Depth Feature Fusion Attention) to enhance feature representation while retaining critical information, ensuring the preservation of key details. Additionally, the multi-scale CVSSB(Complex Visual State Space) and CVSSB-E(Expanded CVSSB) modules combine multi-scale and multi-directional spatial features, augmenting the model's capacity to recognize inter-image dependencies. Secondly, the MPDIoU is a novel loss function to tackle the optimization challenge of bounding boxes with similar shapes but different sizes, which enhances the accuracy of localizing strawberry seedlings and nutrient pots. Finally, Distance Intersection over Union is utilized for establishing a belongingness relationship between strawberry seedlings and pots, accurately identifying missing seedlings and counting the corresponding pots. Experimental results demonstrate that SSP-MambaNet achieves 94.9 %in average precision, 92.8 % in recall rate,88.1 % in precision, and 90.4 % F1 score for strawberry seedlings and pots. It outperforms the YOLOv7 by 4.7 % in average precision, and 2.6 % in recall rate while reducing 66.7 f/s in FPS. Furthermore, the proposed method shows 94.29 % accuracy in detecting missing seedlings and 97.14 % accuracy in counting nutrient pots with missing seedlings. These results showcase its effectiveness in improving overall seedling quality and providing timely replanting guidance in glass greenhouses.
Why it matches plant phenotyping methods幼苗の欠損状態を画像から検出・計数する自動化手法の開発が研究の中心であり、植物の状態を直接推定しているため。
abstractwe present an automated method for detecting and counting missing seedlings based on SSP-MambaNet.
Reproduction assets foundThe paper's Data Availability statement explicitly provides the authors' source code and the strawberry seedling/nutrient pot image dataset via a public GitHub repository, matching an allowed URL.Code · publicThis study's source code and datasets can be accessed at https://github.com/STRABf5/SSPMambaNet.git.Open asset ↗STRABf5/SSPMambaNet · STRABf5/SSPMambaNethtml-lines:448-494Dataset · publicThis study's source code and datasets can be accessed at https://github.com/STRABf5/SSPMambaNet.git.Open asset ↗STRABf5/SSPMambaNet · STRABf5/SSPMambaNethtml-lines:538-610Code / dataset availability confirmedarXiv · checked 13 Sept 2026
Crop yield estimation is a relevant problem in agriculture, because an accurate yield estimate can support farmers' decisions on harvesting or precision intervention. Robots can help to automate this process. To do so, they need to be able to perceive the surrounding environment to identify target objects such as trees and plants. In this paper, we introduce a novel approach to address the problem of hierarchical panoptic segmentation of apple orchards on 3D data from different sensors. Our approach is able to simultaneously provide semantic segmentation, instance segmentation of trunks and fruits, and instance segmentation of trees (a trunk with its fruits). This allows us to identify relevant information such as individual plants, fruits, and trunks, and capture the relationship among them, such as precisely estimate the number of fruits associated to each tree in an orchard. To efficiently evaluate our approach for hierarchical panoptic segmentation, we provide a dataset designed specifically for this task. Our dataset is recorded in Bonn, Germany, in a real apple orchard with a variety of sensors, spanning from a terrestrial laser scanner to a RGB-D camera mounted on different robots platforms. The experiments show that our approach surpasses state-of-the-art approaches in 3D panoptic segmentation in the agricultural domain, while also providing full hierarchical panoptic segmentation. Our dataset is publicly available at https://www.ipb.uni-bonn.de/data/hops/. The open-source implementation of our approach is available at https://github.com/PRBonn/hapt3D.
Why it matches plant phenotyping methodsリンゴ樹・果実・幹を3Dセグメンテーションし、樹ごとの果実数を推定する手法と専用データセットを中心に開発・評価しており、植物の器官形態・収量関連形質の取得に該当する。
abstractwe introduce a novel approach to address the problem of hierarchical panoptic segmentation of apple orchards on 3D data from different sensors.
Reproduction assets foundThe paper introduces the HOPS dataset of annotated 3D apple orchard point clouds (TLS, UAV, UGV, SfM) for hierarchical panoptic segmentation, publicly available at the authors' IPB Bonn page, and releases the open-source implementation (hapt3D) on GitHub. Both are paper-specific, public, and actionable.Code · publicThe open-source implementation of our approach is available at https://github.com/PRBonn/hapt3D .Open asset ↗PRBonn/hapt3Dlines:1-59Code / dataset availability confirmedOpenAlex · Crossref · checked 15 Sept 2026
Published12 Mar 2025Investigaciones Geográficas Boletín del Instituto de GeografíaCited by 1 · OpenAlex ↗
This study employs photogrammetry to evaluate and monitor the recovery of the cypress forest on Guadalupe Island, Mexico, an ecosystem significantly impacted by fires and overgrazing. Two drone surveys were conducted over the forest area during the summers of 2016 and 2019 using natural color (RGB) and near-infrared (NIR) cameras. This work presents the first complete 3D reconstruction of the cypress forest on the island. The image processing products include the canopy height model (CHM), digital surface model (DSM), and digital terrain model (DTM), which were utilized to calculate the number, density, height and crown projected areas of trees. The CHM showed a high correlation with the forest's structure (R = 0.92), based on field measurements of tree heights. Our study accounted for approximately 67,340 trees taller than two meters in 2019. Over 90% of the cypress population consisted of young trees between 2 and 3 meters tall, which have recovered significantly following a fire in 2008 that burned 70% of its extent. A horizontal expansion of 134 hectares was observed from 2016 to 2019 in the regeneration process.
Why it matches plant phenotyping methodsドローン画像のフォトグラメトリによる3D再構成を用いて樹木の高さ・密度・樹冠面積を推定し、現地測定との相関で検証しているため、植物形質の取得手法が中心です。
abstractThis study employs photogrammetry to evaluate and monitor the recovery of the cypress forest on Guadalupe Island, Mexico
Reproduction assets foundThe paper's photogrammetric phenotyping products (2016/2019 point clouds, orthomosaics, DSMs, CHMs) are publicly downloadable via a DOI data repository, and supplemental crown/treetop features are in CICESE's institutional repository. Both URLs appear in allowed_urls.Dataset · publicees. This phenomenon can be seen
in the three years observation window (2016-2019)
using photogrammetry.
AVAILABILITY OF DATA
AND MATERIALS
Point clouds from the 2016 and 2019 photogram-
metric reconstructions, as well as orthomosaics,
digital surface models (DSMs), and canopy height
models (CHMs), are available for download in
https://doi.org/10.5069/G9668BDD and https://
doi.org/10.5069/G92J693D. Supplemental infor-
mation such as Features related to crown and tree-
tops are accessible through CICESE’s institutional
repository (https://repositoriobiblioteca.cicese.mx/jspui/handle/123456789/44)
REFERENCES
Aljos-Farjon. (2017). A handbook of the world’s conifers
(second ed., vol. 1).Open asset ↗10.5069/G9668BDD · 10.5069/G9668BDDpdf-raw-page:15 lines:1-89Code / dataset availability confirmedOpenAlex · Europe PMC · checked 6 Sept 2026
Machine learning models for crop image analysis and phenomics are highly important for precision agriculture and breeding and have been the subject of intensive research. However, the lack of publicly available high-quality image datasets with detailed annotations has severely hindered the development of these models. In this work, we present a comprehensive multicultivar and multiview rice plant image dataset (CVRP) created from 231 landraces and 50 modern cultivars grown under dense planting in paddy fields. The dataset includes images capturing rice plants in their natural environment, as well as indoor images focusing specifically on panicles, allowing for a detailed investigation of cultivar-specific differences. A semiautomatic annotation process using deep learning models was designed for annotations, followed by rigorous manual curation. We demonstrated the utility of the CVRP by evaluating the performance of four state-of-the-art (SOTA) semantic segmentation models. We also conducted 3D plant reconstruction with organ segmentation via images and annotations. The database not only facilitates general-purpose image-based panicle identification and segmentation but also provides valuable resources for challenging tasks such as automatic rice cultivar identification, panicle and grain counting, and 3D plant reconstruction. The database and the model for image annotation are available at https://bic.njau.edu.cn/CVRP.html.
Why it matches plant phenotyping methodsイネ画像データセットとアノテーションモデルを開発・評価し、セグメンテーション、器官再構成、穂・粒数計測などの再利用可能な表現型解析を中心に扱っているため。
abstractwe present a comprehensive multicultivar and multiview rice plant image dataset (CVRP)
Reproduction assets foundThe paper's own CVRP rice image dataset (images + annotations), accompanying code, and trained Mask2Former annotation model are explicitly stated as publicly available on Hugging Face and the authors' NJAU site.Dataset · publicThe CVRP dataset is publicly available on Hugging Face at https://huggingface.co/datasets/CVRPDataset/CVRP for academic use under the specified license.Open asset ↗CVRPDataset/CVRPhtml-lines:236-252Code · publicThe accompanying code and trained models are available at https://huggingface.co/CVRPDataset/Model.Open asset ↗CVRPDataset/Modelhtml-lines:236-252Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
Location-based methods for counting rice panicles have often been underestimated, primarily due to their perceived inferior performance when compared to detection-based techniques. However, we argue that the potential of these location-based methods has not been fully realized, largely owing to the limitations of existing model architectures. In response to this challenge, we introduce LKNet, an innovative model developed on the foundation of the location-based framework P2Pnet. To enhance the performance of panicle counting across diverse types and growth stages, we implemented several key strategies. Firstly, we reconstructed the localization loss function as a predictive probability distribution to reduce the influence of manual labeling. Additionally, we dynamically adapted the receptive field to better accommodate different panicle types through the use of large kernel convolutional blocks. We evaluated LKNet on several publicly available counting task datasets and achieved state-of-the-art performance on the Diverse Rice Panicle Detection dataset. Furthermore, we employed a rice panicle dataset collected at an altitude of 7 m, which includes various panicle types and growth stages for model training and evaluation. The results showed that LKNet effectively accommodates variations in panicle morphology, with R 2 values ranging from 0.903 to 0.989. These findings highlight LKNet's potential to enhance precision in panicle counting in rice breeding programs.
Why it matches plant phenotyping methodsイネ穂の画像ベース計数モデルを開発し、複数データセットで評価しており、植物表現型取得・抽出手法が中心である。
abstractwe introduce LKNet, an innovative model developed on the foundation of the location-based framework P2Pnet.
Reproduction assets foundThe paper's authors explicitly state that the LKNet analysis code is publicly available on GitHub, matching an allowed URL. No separate phenotype dataset deposit by the authors is stated (the 7 m rice panicle dataset and public benchmarks like DPRD/MTC/SHTech are described but no authors' dataset URL is given).Code · publicCode is available at https://github.com/L129921/LKnet .Open asset ↗LKnetlines:297-319Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
The soybean-cyst nematode (SCN; Heterodera glycines) is one of the most destructive pests affecting soybean crops. Effective management of SCN is imperative for the sustainability of soybean agriculture. A promising approach to achieving this goal is the development and breeding of new resistant soybean varieties. Researchers and breeders typically employ exploratory methods such as Genome-Wide Association Studies or Quantitative Trait Loci mapping to identify genes linked to resistance. These methods depend on extensive phenotypic screening. The primary phenotypic measure for assessing SCN resistance is often the number of cysts that form on a plant's root system. Manual counting hundreds of cysts on a given root system is not only laborious but also subject to variability due to individual assessor differences. Additionally, while measuring cyst size could provide valuable insights due to its correlation with cyst development, this aspect is frequently overlooked because it demands even more hands-on work. To address these challenges, we have created Nemacounter, an intuitive software designed to detect, count, and measure the size of cysts autonomously. Nemacounter boasts a user-friendly graphical interface, simplifying the process for users to obtain reliable results. It enhances productivity by delivering annotated images and compiling data into csv files for easy analysis and reporting.
Why it matches plant phenotyping methodsダイズ根上の線虫シスト数とサイズという植物病害抵抗性関連形質を、画像から自動検出・計測するソフトウェアを開発しており、表現型取得手法が研究の中心です。
abstractwe have created Nemacounter, an intuitive software designed to detect, count, and measure the size of cysts autonomously.
Reproduction assets foundThe paper's SCN cyst phenotyping assets are publicly available: the authors' Nemacounter analysis software on GitHub, two annotated cyst image datasets on Roboflow (bounding-box and segmentation/area annotations), and the authors' trained YOLOv5-xl model (cystmodel.pt) on Iowa State's Box. The SAM weights and ultralyptCode · publicThe Nemacounter software can be downloaded here: https://github.com/DjampaKozlowski/NemaCounter and we provide an installation manual and utilization manual as supplementary data.Open asset ↗DjampaKozlowski/NemaCounterlines:65-70Dataset · publicThe complete dataset is accessible on the Roboflow website at: https://universe.roboflow.com/iowa-state-university-cwvqa/cystnewboundingboxv2Open asset ↗lines:118-138Dataset · publicAll training datasets are available on Roboflow website at : https://universe.roboflow.com/iowa-state-university-cwvqa/cystnewboundingboxv2 and https://universe.roboflow.com/iowa-state-university-cwvqa/cyst-detectors-area.Open asset ↗lines:139-197Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
Viticulture benefits significantly from rapid grape bunch identification and counting, enhancing yield and quality. Recent technological and machine learning advancements, particularly in deep learning, have provided the tools necessary to create more efficient, automated processes that significantly reduce the time and effort required for these tasks. On one hand, drone, or Unmanned Aerial Vehicles (UAV) imagery combined with deep learning algorithms has revolutionised agriculture by automating plant health classification, disease identification, and fruit detection. However, these advancements often remain inaccessible to farmers due to their reliance on specialized hardware like ground robots or UAVs. On the other hand, most farmers have access to smartphones. This article proposes a novel approach combining UAVs and smartphone technologies. An AI-based framework is introduced, integrating a 5-stage AI pipeline combining object detection and pixel-level segmentation algorithms to automatically detect grape bunches in smartphone images of a commercial vineyard with vertical trellis training. By leveraging UAV-captured data for training, the proposed model not only accelerates the detection process but also enhances the accuracy and adaptability of grape bunch detection across different devices, surpassing the efficiency of traditional and purely UAV-based methods. To this end, using a dataset of UAV videos recorded during early growth stages in July (BBCH77-BBCH79), the X-Decoder segments vegetation in the front of the frames from their background and surroundings. X-Decoder is particularly advantageous because it can be seamlessly integrated into the AI pipeline without requiring changes to how data is captured, making it more versatile than other methods. Then, YOLO is trained using the videos and further applied to images taken by farmers with common smartphones (Xiaomi Poco X3 Pro and iPhone X). In addition, a web app was developed to connect the system with mobile technology easily. The proposed approach achieved a precision of 0.92 and recall of 0.735, with an F1 score of 0.82 and an Average Precision (AP) of 0.802 under different operation conditions, indicating high accuracy and reliability in detecting grape bunches. In addition, the AI-detected grape bunches were compared with the actual ground truth, achieving an R 2 value as high as 0.84, showing the robustness of the system. This study highlights the potential of using smartphone imaging and web applications together, making an effort to integrate these models into a real platform for farmers, offering a practical, affordable, accessible, and scalable solution. While smartphone-based image collection for model training is labour-intensive and costly, incorporating UAV data accelerates the process, facilitating the creation of models that generalise across diverse data sources and platforms. This blend of UAV efficiency and smartphone precision significantly cuts vineyard monitoring time and effort.
Why it matches plant phenotyping methodsスマートフォン画像とUAVデータを用いてブドウ房を検出・計数するAIパイプラインを開発・評価し、実測値との比較も行っているため、植物器官形質の取得手法が中心である。
abstractAn AI-based framework is introduced, integrating a 5-stage AI pipeline combining object detection and pixel-level segmentation algorithms to automatically detect grape bunches in smartphone images of a commercial vineyard with vertical trellis training.
Reproduction assets foundThe paper's Data Availability Statement points to a public, paper-specific dataset (EscaYard: geotagged smartphone vineyard images, phytosanitary status, UAV 3D point clouds and orthomosaics) published as a Data Brief with a DOI, which directly underpins the smartphone/UAV grape detection phenotyping analysis. No code,Dataset · publicData is available at https://doi.org/10.1016/j.dib.2024.110497 [ 55 ].Open asset ↗10.1016/j.dib.2024.110497lines:202-204Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
Accurate counting of crop plants is essential for agricultural science, particularly for yield forecasting, field management, and experimental studies. Traditional methods are labor-intensive and prone to errors. Unmanned Aerial Vehicle (UAV) technology offers a promising alternative; however, varying UAV altitudes can impact image quality, leading to blurred features and reduced accuracy in early maize seedling counts. To address these challenges, we developed RC-Dino, a deep learning methodology based on DINO, specifically designed to enhance the precision of seedling counts from UAV-acquired images. RC-Dino introduces two innovative components: a novel self-calibrating convolutional layer named RSCconv and an adaptive spatial feature fusion module called ASCFF. The RSCconv layer improves the representation of early maize seedlings compared to non-seedling elements within feature maps by calibrating spatial domain features. The ASCFF module enhances the discriminability of early maize seedlings by adaptively fusing feature maps extracted from different layers of the backbone network. Additionally, transfer learning was employed to integrate pre-trained weights with RSCconv, facilitating faster convergence and improved accuracy. The efficacy of our approach was validated using the Early Maize Seedlings Dataset (EMSD), comprising 1,233 annotated images of early maize seedlings, totaling 83,404 individual annotations. Testing on this dataset demonstrated that RC-Dino outperformed existing models, including DINO, Faster R-CNN, RetinaNet, YOLOX, and Deformable DETR. Specifically, RC-Dino achieved improvements of 16.29% in Average Precision (AP) and 8.19% in Recall compared to the DINO model. Our method also exhibited superior coefficient of determination (R²) values across different datasets for seedling counting. By integrating RSCconv and ASCFF into other detection frameworks such as Faster R-CNN, RetinaNet, and Deformable DETR, we observed enhanced detection and counting accuracy, further validating the effectiveness of our proposed method. These advancements make RC-Dino particularly suitable for accurate early maize seedling counting in the field. The source code for RSCconv and ASCFF is publicly available at https://github.com/collapser-AI/RC-Dino, promoting further research and practical applications.
Why it matches plant phenotyping methodsUAV画像からトウモロコシ幼苗数を抽出する深層学習手法を開発し、公開データセット上で既存手法と比較検証しており、植物表現型取得法が研究の中心です。
abstractwe developed RC-Dino, a deep learning methodology based on DINO, specifically designed to enhance the precision of seedling counts from UAV-acquired images.
Reproduction assets foundThe paper's EMSD UAV image dataset is explicitly not publicly available, but the authors' RSCconv and ASCFF analysis code for the RC-Dino model is publicly released on GitHub.Code · publicHowever, our code is open to the public. The RSCconv and ASCFF code mentioned in this paper can be found here: https://github.com/collapser-AI/RC-Dino .Open asset ↗collapser-AI/RC-Dinolines:727-739Code / dataset availability confirmedCrossref · Europe PMC · checked 14 Sept 2026
Crop field monitoring using unmanned aerial vehicles (UAVs) is one of the most important technologies for plant growth control in modern precision agriculture. One of the important and widely used tasks in field monitoring is plant stand counting. The accurate identification of plants in field images provides estimates of plant number per unit area, detects missing seedlings, and predicts crop yield. Current methods are based on the detection of plants in images obtained from UAVs by means of computer vision algorithms and deep learning neural networks. These approaches depend on image spatial resolution and the quality of plant markup. The performance of automatic plant detection may affect the efficiency of downstream analysis of a field cropping pattern. In the present work, a method is presented for detecting the plants of five species in images acquired via a UAV on the basis of image segmentation by deep learning algorithms (convolutional neural networks). Twelve orthomosaics were collected and marked at several sites in Russia to train and test the neural network algorithms. Additionally, 17 existing datasets of various spatial resolutions and markup quality levels from the Roboflow service were used to extend training image sets. Finally, we compared several texture features between manually evaluated and neural-network-estimated plant masks. It was demonstrated that adding images to the training sample (even those of lower resolution and markup quality) improves plant stand counting significantly. The work indicates how the accuracy of plant detection in field images may affect their cropping pattern evaluation by means of texture characteristics. For some of the characteristics (GLCM mean, GLRM long run, GLRM run ratio) the estimates between images marked manually and automatically are close. For others, the differences are large and may lead to erroneous conclusions about the properties of field cropping patterns. Nonetheless, overall, plant detection algorithms with a higher accuracy show better agreement with the estimates of texture parameters obtained from manually marked images.
Why it matches plant phenotyping methodsUAV画像から植物個体をセグメンテーションし、株数・欠株などの植物状態を推定する画像解析手法を開発・評価しており、手法が研究の中心です。
abstractIn the present work, a method is presented for detecting the plants of five species in images acquired via a UAV on the basis of image segmentation by deep learning algorithms (convolutional neural networks).
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Supplement · publicThe following supporting information can be downloaded at: https://www.mdpi.com/article/10.3390/jimaging11010028/s1 , “Supplementary Material.pdf” contains the following Supplementary Materials: Table S1. The field location of the crop image dataset from Russia (2019–2023); Table S2. Public datasets from Roboflow used for the analysis (accessed on 25 November 2023); Table S3. The row spacing (for different crops) used in the work to mark up images from the additional datasets (not ours); Table S4. Description of the ResNet neural network architectures for models RN18, RN34, and RN50; Table S5. Description of the texture characteristics; Table S6. Estimates of the four texture characteristicsOpen asset ↗lines:344-359Code / dataset availability confirmedOpenAlex · Crossref · checked 6 Sept 2026
Time to maturity and yield are important traits for highbush blueberry (Vaccinium corymbosum) breeding. Proper determination of the time to maturity of blueberry varieties and breeding lines informs the harvest window, ensuring that the fruits are harvested at optimum maturity and quality. On the other hand, high-yielding crops bring in high profits per acre of planting. Harvesting and quantifying the yield for each blueberry breeding accession are labor-intensive and impractical. Instead, visual ratings as an estimation of yield are often used as a faster way to quantify the yield, which is categorical and subjective. In this study, we developed and shared a high-throughput phenotyping method using neural networks to predict blueberry time to maturity and to provide a proxy for yield, overcoming the labor constraints of obtaining high-frequency data. We aim to facilitate further research in computer vision and precision agriculture by publishing the labeled image dataset and the trained model. In this research, true-color images of blueberry bushes were collected, annotated, and used to train a deep neural network object detection model [You Only Look Once (YOLOv11)] to detect mature and immature berries. Different versions of YOLOv11 were used, including nano, small, and medium, which had similar performance, while the medium version had slightly higher metrics. The YOLOv11m model shows strong performance for the mature berry class, with a precision of 0.90 and an F1 score of 0.90. The precision and recall for detecting immature berries were 0.81 and 0.79. The model was tested on 10 blueberry bushes by hand harvesting and weighing blueberries. The results showed that the model detects approximately 25% of the berries on the bushes, and the correlation coefficients between model-detected and hand-harvested traits were 0.66, 0.86, and 0.72 for mature fruit count, immature fruit count, and mature ratio, respectively. The model applied to 91 blueberry advance selections and categorized them into groups with diverse levels of maturity and productivity using principal component analysis (PCA). These results inform the harvest window and yield of these breeding lines with precision and objectivity through berry classification and quantification. This model will be helpful for blueberry breeders, enabling more efficient selection, and for growers, helping them accurately estimate optimal harvest windows. This open-source tool can potentially enhance research capabilities and agricultural productivity.
Why it matches plant phenotyping methodsブルーベリーの成熟度・収量 proxy を画像とニューラルネットワークで推定する高スループット表現型計測法を開発・検証し、モデルとラベル付きデータセットを共有しているため、方法が研究の中心である。
abstractwe developed and shared a high-throughput phenotyping method using neural networks to predict blueberry time to maturity and to provide a proxy for yield
Reproduction assets foundThe paper publishes its labeled blueberry image dataset on Zenodo (record 14014858) and its trained YOLOv11-based blueberry fruit counting model/code on GitHub (jeromemaleski/blueberry), both directly supporting the paper's phenotyping measurements and analysis.Dataset · public32. Zhang, J. Blueberry Images and Labels for YOLO Model Training. Zenodo. 2024. Available online: https://zenodo.org/records/Open asset ↗zenodopdf-page:14 lines:1-36Code / dataset availability confirmedEurope PMC · OpenAlex · checked 15 Sept 2026
Common beanAerial / UAVField / plotLiDAR / point cloudRGB / grayscaleWhole plant / canopy / plot / fieldCountingMorphology / geometry measurementGrowth / time-series analysisGrowth / development / phenology
Substantial effort has been made in manually tracking plant maturity and to measure early-stage plant density and crop height in experimental fields. In this study, RGB drone imagery and deep learning (DL) approaches are explored to measure relative maturity (RM), stand count (SC), and plant height (PH), potentially offering higher throughput, accuracy, and cost-effectiveness than traditional methods. A time series of drone images was utilized to estimate dry bean RM employing a hybrid convolutional neural network (CNN) and long short-term memory (LSTM) model. For early-stage SC assessment, Faster RCNN object detection algorithm was evaluated. Flight frequencies, image resolution, and data augmentation techniques were investigated to enhance DL model performance. PH was obtained using a quantile method from digital surface model (DSM) and point cloud (PC) data sources. The CNN-LSTM model showed high accuracy in RM prediction across various conditions, outperforming traditional image preprocessing approaches. The inclusion of growing degree days (GDD) data improved the model's performance under specific environmental stresses. The Faster R-CNN model effectively identified early-stage bean plants, demonstrating superior accuracy over traditional methods and consistency across different flight altitudes. For PH estimation, moderate correlations with ground-truth data were observed across both datasets analyzed. The choice between PC and DSM source data may depend on specific environmental and flight conditions. Overall, the CNN-LSTM and Faster R-CNN models proved more effective than conventional techniques in quantifying RM and SC. The subtraction method proposed for estimating PH without accurate ground elevation data yielded results comparable to the difference-based method. Additionally, the pipeline and open-source software developed hold potential to significantly benefit the phenotyping community.
Why it matches plant phenotyping methodsドローン画像と深層学習を用いて成熟度、株数、草丈を推定する手法を開発・評価し、パイプラインとオープンソースソフトウェアも提示しており、植物表現型取得が研究の中心である。
abstractIn this study, RGB drone imagery and deep learning (DL) approaches are explored to measure relative maturity (RM), stand count (SC), and plant height (PH)
Reproduction assets foundThe paper explicitly states that all R/Python analysis code, apps, and the complete datasets (orthomosaics, shapefiles, ground notes, clipped plots) are publicly available via the authors' GitHub organization and three Zenodo deposits for RM, SC, and PH.Dataset · publicof the manuscript.
Competing interests: The authors declare that they have no competing interests.
Data Availability
Developed software and analysis are available in the GitHub repositories at https://github.com/msudrybeanbreeding and datasets can be download at Zenodo deposit page ( https://zenodo.org/ ) using the links to RM: https://doi.org/10.5281/zenodo.7922565; SC: https://doi.org/10.5281/zenodo.7922584; and PH: https://doi.org/10.5281/zenodo.7922589 .
Supplementary Materials
Supplementary 1
Figs. S1 to S14
Tables S1 and S2
Data files S1 to 21
References
1.
Uebersax
MA , Cichy
KA , Gomez
FE , Porch
TG , Heitholt
J , Osorno
JM , Kamfwa
K , Snapp
SS , Bales
S
.
Dry beans ( Phaseolus vuOpen asset ↗zenodo · 10.5281/zenodo.7922565lines:677-730Dataset · publicauthors declare that they have no competing interests.
Data Availability
Developed software and analysis are available in the GitHub repositories at https://github.com/msudrybeanbreeding and datasets can be download at Zenodo deposit page ( https://zenodo.org/ ) using the links to RM: https://doi.org/10.5281/zenodo.7922565; SC: https://doi.org/10.5281/zenodo.7922584; and PH: https://doi.org/10.5281/zenodo.7922589 .
Supplementary Materials
Supplementary 1
Figs. S1 to S14
Tables S1 and S2
Data files S1 to 21
References
1.
Uebersax
MA , Cichy
KA , Gomez
FE , Porch
TG , Heitholt
J , Osorno
JM , Kamfwa
K , Snapp
SS , Bales
S
.
Dry beans ( Phaseolus vulgaris L.) as a vital component of sustainabOpen asset ↗zenodo · 10.5281/zenodo.7922584lines:677-730Dataset · publicrests.
Data Availability
Developed software and analysis are available in the GitHub repositories at https://github.com/msudrybeanbreeding and datasets can be download at Zenodo deposit page ( https://zenodo.org/ ) using the links to RM: https://doi.org/10.5281/zenodo.7922565; SC: https://doi.org/10.5281/zenodo.7922584; and PH: https://doi.org/10.5281/zenodo.7922589 .
Supplementary Materials
Supplementary 1
Figs. S1 to S14
Tables S1 and S2
Data files S1 to 21
References
1.
Uebersax
MA , Cichy
KA , Gomez
FE , Porch
TG , Heitholt
J , Osorno
JM , Kamfwa
K , Snapp
SS , Bales
S
.
Dry beans ( Phaseolus vulgaris L.) as a vital component of sustainable agriculture and food security—A review
. LeguOpen asset ↗zenodo · 10.5281/zenodo.7922589lines:677-730Code · publics from each individual breeding plot were extracted from the time series of images (6 and 9 flights date), and the RM was estimated using an optimized threshold value of 0.06. To perform the VI extractions from each breeding plot in the field, an open-source Streamlit app in Python was implemented and can be accessed online at: https://msudrybeanbreeding-vegetation-index--vi-extractions-v0-3-9knpzt.streamlit.app/ . Additionally, to accommodate user preferences, an R script is available to perform VI extractions analysis (Data S7 ).
SC DL model
The SC pipeline deployed in this study comprised 6 distinct steps, starting from the raw images and annotations, and ending with the final SC predictiOpen asset ↗lines:139-147Code / dataset availability confirmedEurope PMC · checked 7 Sept 2026
Background Quantitative disease resistance (QR) is a complex, dynamic trait that is most reliably quantified in field-grown crops. Traditional disease assessments offer limited potential to disentangle the contributions of different components to overall QR at critical crop developmental stages. Yet, a better functional understanding of QR could greatly support a more targeted, knowledge-based selection for QR and improve predictions of seasonal epidemics. Image-based approaches together with advanced image processing methodologies recently emerged as valuable tools to standardize relevant disease assessments, increase measurement throughput, and describe diseases along multiple dimensions. Results We present a simple, affordable, and easy-to-operate imaging set-up and imaging procedure for in-field acquisition of wheat leaf image sequences. The development of Septoria tritici blotch and leaf rusts was monitored over time via robust methods for symptom detection and segmentation, spatial alignment of images, symptom tracking, and leaf- and symptom characterization. The average accuracy of the spatial alignment of images in a time series was approximately 5 pixels (~ 0.15 mm). Leaf-level symptom counts as well as individual symptom property measurements revealed stable patterns over time that were generally in excellent agreement with visual impressions. This provided strong evidence for the robustness of the methodology to variability typically inherent in field data. Contrasting patterns in the number of lesions resulting from separate infection events and lesion expansion dynamics were observed across wheat genotypes. The number of separate infection events and average lesion size contributed to different degrees to overall disease intensity, possibly indicating distinct and complementary mechanisms of QR. Conclusions The proposed methodology enables rapid, non-destructive, and reproducible measurement of several key epidemiological parameters under field conditions. Such data can support decomposition and functional understanding of QR as well as the parameterization, fine-tuning, and validation of epidemiological models. Details of pathogenesis can translate into specific symptom phenotypes resolvable using time series of high-resolution RGB images, which may improve biological understanding of plant-pathogen interactions as well as interactions in disease complexes.
Why it matches plant phenotyping methods圃場での植物病徴を画像から取得・追跡・定量する撮像および画像解析手法を開発・検証しており、植物表現型測定が中心である。
abstractWe present a simple, affordable, and easy-to-operate imaging set-up and imaging procedure for in-field acquisition of wheat leaf image sequences.
Reproduction assets foundThe paper explicitly states that all image-processing/analysis code is publicly available on the authors' GitHub repository, and that a sample dataset plus the trained reference mark detection model are downloadable from the ETH Research Collection. Both are paper-specific, public, and actionable.Code · publicAll code related to the processing of image time series and leaf- and lesion-level trait extraction is available from https://github.com/and-jonas/sympathique-wheat for documentation.Open asset ↗and-jonas/sympathique-wheatlines:98-107Dataset · publicA sample data set and the trained reference mark detection model can be downloaded from ETH research collection at https://doi.org/10.3929/ethz-b-000659812 .Open asset ↗10.3929/ethz-b-000659812lines:98-107Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
The increase in the global population is leading to a doubling of the demand for protein. Soybean ( Glycine max ), a key contributor to global plant-based protein supplies, requires ongoing yield enhancements to keep pace with increasing demand. Precise, on-plant seed counting and localization may catalyze breeding selection of shoot architectures and seed localization patterns related to superior performance in high planting density and contribute to increased yield. Traditional manual counting and localization methods are labor-intensive and prone to error, necessitating more efficient approaches for yield prediction and seed distribution analysis. To solve this, we propose MSANet: a novel deep learning framework tailored for counting and localization of soybean seeds on mature field-grown soy plants. A multi-scale attention map mechanism was applied to maximize model performance in seed counting and localization in soybean breeding fields. We compared our model with a previous state-of-the-art model using the benchmark dataset and an enlarged dataset, including various soybean genotypes. Our model outperforms previous state-of-the-art methods on all datasets across various soybean genotypes on both counting and localization tasks. Furthermore, our model also performed well on in-canopy 360° video, dramatically increasing data collection efficiency. We also propose a technique that enables previously inaccessible insights into the phenotypic and genetic diversity of single plant vertical seed distribution, which may accelerate the breeding process. To accelerate further research in this domain, we have made our dataset and software publicly available: https://github.com/UTokyo-FieldPhenomics-Lab/MSANet.
Why it matches plant phenotyping methods大豆種子の計数・位置推定と垂直分布という植物形質を対象に、深層学習手法を開発・比較検証し、データセットとソフトウェアも公開しているため、フェノタイピング手法が中心である。
abstractwe propose MSANet: a novel deep learning framework tailored for counting and localization of soybean seeds on mature field-grown soy plants.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicwe have made our dataset and software publicly available: https://github.com/UTokyo-FieldPhenomics-Lab/MSANet .Open asset ↗UTokyo-FieldPhenomics-Lab/MSANetlines:1-25Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Plant population counts are highly valued by crop producers as important early-season indicators of field health. Traditionally, emergence rate estimates have been acquired through manual counting, an approach that is labor-intensive and relies heavily on sampling techniques. By applying deep learning-based object detection models to aerial field imagery, accurate plant population counts can be obtained for much larger areas of a field. Unfortunately, current detection models often perform poorly when they are faced with image conditions that do not closely resemble the data found in their training sets. In this paper, we explore how specific facets of a plant detector's training set can affect its ability to generalize to unseen image sets. In particular, we examine how a plant detection model's generalizability is influenced by the size, diversity, and quality of its training data. Our experiments show that the gap between in-distribution and out-of-distribution performance cannot be closed by merely increasing the size of a model's training set. We also demonstrate the importance of training set diversity in producing generalizable models, and show how different types of annotation noise can elicit different model behaviors in out-of-distribution test sets. We conduct our investigations with a large and diverse dataset of canola field imagery that we assembled over several years. We also present a new web tool, Canola Counter, which is specifically designed for remote-sensed aerial plant detection tasks. We use the Canola Counter tool to prepare our annotated canola seedling dataset and conduct our experiments. Both our dataset and web tool are publicly available.
Why it matches plant phenotyping methods航空画像からカノーラ個体数（個体群密度）を推定する検出モデルの汎化性能を検証し、注釈付きデータセットと専用Webツールを提示しており、植物表現型取得手法が中心である。
abstractBy applying deep learning-based object detection models to aerial field imagery, accurate plant population counts can be obtained for much larger areas of a field.
Reproduction assets foundThe paper's aerial canola seedling dataset (images and annotations) is publicly deposited on Zenodo, and the authors' Canola Counter analysis/annotation tool is open source on GitHub. The arXiv 2108.05789 entry is a cited prior work (CropAndWeed dataset), not a paper-specific asset.Dataset · publicData Availability Statement
The canola seedling dataset used in this study is publicly available and can be found at: https://doi.org/10.5281/zenodo.11055599 . The Canola Counter tool is open source and is available at: https://github.com/eandvaag/agricounter .Open asset ↗zenodo · 10.5281/zenodo.11055599lines:236-237Code · publicData Availability Statement
The canola seedling dataset used in this study is publicly available and can be found at: https://doi.org/10.5281/zenodo.11055599 . The Canola Counter tool is open source and is available at: https://github.com/eandvaag/agricounter .Open asset ↗github · eandvaag/agricounterlines:236-237Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Introduction The emergence rate of crop seedlings is an important indicator for variety selection, evaluation, field management, and yield prediction. To address the low recognition accuracy caused by the uneven size and varying growth conditions of crop seedlings under salt-alkali stress, this research proposes a peanut seedling recognition model, MS-YOLOv8. Methods This research employs close-range remote sensing from unmanned aerial vehicles (UAVs) to rapidly recognize and count peanut seedlings. First, a lightweight adaptive feature fusion module (called MSModule) is constructed, which groups the channels of input feature maps and feeds them into different convolutional layers for multi-scale feature extraction. Additionally, the module automatically adjusts the channel weights of each group based on their contribution, improving the feature fusion effect. Second, the neck network structure is reconstructed to enhance recognition capabilities for small objects, and the MPDIoU loss function is introduced to effectively optimize the detection boxes for seedlings with scattered branch growth. Results Experimental results demonstrate that the proposed MS-YOLOv8 model achieves an AP50 of 97.5% for peanut seedling detection, which is 12.9%, 9.8%, 4.7%, 5.0%, 11.2%, 5.0%, and 3.6% higher than Faster R-CNN, EfficientDet, YOLOv5, YOLOv6, YOLOv7, YOLOv8, and RT-DETR, respectively. Discussion This research provides valuable insights for crop recognition under extreme environmental stress and lays a theoretical foundation for the development of intelligent production equipment.
Why it matches plant phenotyping methodsUAVリモートセンシング画像からピーナッツ幼苗を認識・計数するモデルを開発し、検出性能を比較検証している。幼苗数・出現率という植物状態の推定が研究の中心である。
abstractthis research proposes a peanut seedling recognition model, MS-YOLOv8
Reproduction assets foundThe paper's data availability statement explicitly deposits the peanut seedling UAV image dataset (and associated model resources) in a public GitHub repository, matching an allowed URL.Dataset · publicy close-range remote sensing. It provides a certain theoretical guidance for the development of an intelligent monitoring platform for peanut.
Data availability statement
The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://github.com/zfvincent1997/MS-YOLOV8 .
Author contributions
FZ: Investigation, Resources, Software, Writing – original draft. LZ: Conceptualization, Supervision, Writing – review & editing. DW: Investigation, Writing – review & editing. JW: Investigation, Writing – review & editing. IS: Software, Visualization, Writing – review & editing. JL: Conceptualization, Open asset ↗https://github.com/zfvincent1997/MS-YOLOV8lines:667-765Code / dataset availability confirmedCrossref · checked 14 Sept 2026
Accurate coffee plant counting is a crucial metric for yield estimation and a key component of precision agriculture. While multispectral UAV technology provides more accurate crop growth data, the varying spectral characteristics of coffee plants across different phenological stages complicate automatic plant counting. This study compared the performance of mainstream YOLO models for coffee detection and segmentation, identifying YOLOv9 as the best-performing model, with it achieving high precision in both detection (P = 89.3%, mAP50 = 94.6%) and segmentation performance (P = 88.9%, mAP50 = 94.8%). Furthermore, we studied various spectral combinations from UAV data and found that RGB was most effective during the flowering stage, while RGN (Red, Green, Near-infrared) was more suitable for non-flowering periods. Based on these findings, we proposed an innovative dual-channel non-maximum suppression method (dual-channel NMS), which merges YOLOv9 detection results from both RGB and RGN data, leveraging the strengths of each spectral combination to enhance detection accuracy and achieving a final counting accuracy of 98.4%. This study highlights the importance of integrating UAV multispectral technology with deep learning for coffee detection and offers new insights for the implementation of precision agriculture.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像とYOLOv9、二重チャネルNMSを用いてコーヒー植物の検出・セグメンテーション・個体数推定手法を開発し、精度評価しているため、植物フェノタイピング手法が中心である。
titleA Coffee Plant Counting Method Based on Dual-Channel NMS and YOLOv9 Leveraging UAV Multispectral Imaging
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicWe will publish all the codes and datasets in this study after the article is accepted
https://github.com/legend2588/Coffee-plant-counting.gitOpen asset ↗https://github.com/legend2588/Coffee-plant-counting.gitpdf-page:19 lines:1-58Code / dataset availability confirmedCrossref · checked 13 Sept 2026
Field robots are an important tool when improving the efficiency and decreasing the climatic impact of food production. Although several commercial field robots are available, the advantages, limitations, and optimal utilization methods of this technology are still not well understood due to its novelty. This study aims to evaluate the performance of a commercial field robot for seeding and weeding tasks. The evaluation was carried out in a 2-hectare sugar beet field. The robot’s performance was assessed by counting plants and weeds using image processing. The YOLOv8 model was trained to detect sugar beets and weeds. The plant and weed densities were compared on a robotically weeded area of the field, a chemically weeded control area, and an untreated control area. The average weed density on the robotically treated area was about two times lower than that on the untreated area and about three times higher than on the chemically treated area. The testing robot in the specific testing environment and mode showed intermediate results, weeding a majority of the weeds between the rows; however, it left the most harmful weeds close to the plants. Software for robot performance assessment can be used for monitoring robot performance and plant conditions several times during plant growth according to the weeding frequency.
Why it matches plant phenotyping methodsYOLOv8画像処理で作物・雑草を検出し、植物密度を定量化する手法とロボット性能評価ソフトが研究の中心であり、植物状態の反復モニタリングに用いるため。
abstractThe robot’s performance was assessed by counting plants and weeds using image processing.
Reproduction assets foundThe paper's field image dataset (2272 sugar beet/weed images) is openly available on Zenodo, and the authors' Matlab robot-performance analysis software is publicly hosted on GitHub. Both are paper-specific, public, and actionable.Dataset · publicThe dataset consisting of 2272 images collected in this study is available in open
access (https://zenodo.org/records/10716274, accessed 18 September 2024).Open asset ↗zenodo · 10716274pdf-page:3 lines:1-146Code / dataset availability confirmedCrossref · checked 14 Sept 2026
Published13 Sept 2024Tenth International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2024)Cited by 1 · OpenAlex ↗
Precision agriculture is the application of correct amount of fertilizers and water pesticide to achieve higher agricultural productivity. Furthermore, under the framework of precision agriculture is the automated estimation of yield with advanced technologies including Artificial Intelligence (AI) and Remote Sensing (RS). The use of RS has advanced crop yield estimations and predictions in recent years. However, to validate RS-based models it is important to perform in-situ exercises such as fruit counting, which is a time-consuming task that increases the production costs. Drones, robots, and in-situ cameras in combination with AI algorithms are widely used to efficiently address these issues. The recent advancement in computational resources and power available has enabled the utilization of Deep Learning AI models. One of the best-performing models for object detection is the You-Only-Look-Once (YOLO). In this study, the YOLOv5s is used for object detection, which is the second smallest and fastest YOLOv5 architecture, on two different benchmark datasets collected from AgML. The first dataset consists of 1730 images of mango trees in Australia during night, and the second dataset consists of 6512 images of wheat heads collected from different regions around the world. The main objective of this work is to demonstrate the capabilities of light AI models for object detection and to evaluate their performance, which will serve as a benchmark for future comparison with the on-board environment.
Why it matches plant phenotyping methods植物器官の検出・カウントによる収量推定を対象とし、YOLOv5sの性能評価とベンチマーク化が主目的であるため、計算画像フェノタイピング手法として採用。
abstractIn this study, the YOLOv5s is used for object detection, which is the second smallest and fastest YOLOv5 architecture, on two different benchmark datasets collected from AgML.
Reproduction assets foundThe paper evaluates YOLOv5s on two public benchmark datasets. The MangoYOLO dataset is explicitly cited with public access URLs and was directly used for the paper's mango yield-estimation experiments, qualifying as a paper-specific public asset. The Global Wheat Head Detection dataset is also used but its Zenodo URL (Dataset · publicAnand Koirala, C McCarthy, Kerry Walsh, and Z Wang, ‘MangoYOLO data set’. Central Queensland University,
2021. Accessed: May 23, 2024. [Online]. Available: http://hdl.handle.net/10018/1261224,
https://researchdata.edu.au/mangoyolo-setOpen asset ↗pdf-page:7 lines:1-50Code / dataset availability confirmedEurope PMC · OpenAlex · checked 7 Sept 2026
High-throughput phenotyping is the bottleneck for advancing field trait characterization and yield improvement in major field crops. Specifically for sorghum ( Sorghum bicolor L.), rapid plant-level yield estimation is highly dependent on characterizing the number of grains within a panicle. In this context, the integration of computer vision and artificial intelligence algorithms with traditional field phenotyping can be a critical solution to reduce labor costs and time. Therefore, this study aims to improve sorghum panicle detection and grain number estimation from smartphone-capture images under field conditions. A preharvest benchmark dataset was collected at field scale (2023 season, Kansas, USA), with 648 images of sorghum panicles retrieved via smartphone device, and grain number counted. Each sorghum panicle image was manually labeled, and the images were augmented. Two models were trained using the Detectron2 and Yolov8 frameworks for detection and segmentation, with an average precision of 75% and 89%, respectively. For the grain number, 3 models were trained: MCNN (multiscale convolutional neural network), TCNN-Seed (two-column CNN-Seed), and Sorghum-Net (developed in this study). The Sorghum-Net model showed a mean absolute percentage error of 17%, surpassing the other models. Lastly, a simple equation was presented to relate the count from the model (using images from only one side of the panicle) to the field-derived observed number of grains per sorghum panicle. The resulting framework obtained an estimation of grain number with a 17% error. The proposed framework lays the foundation for the development of a more robust application to estimate sorghum yield using images from a smartphone at the plant level.
Why it matches plant phenotyping methodsスマートフォン画像からソルガム穂の検出・分割と粒数推定を開発・検証しており、植物形質取得手法が研究の中心である。
abstractthis study aims to improve sorghum panicle detection and grain number estimation from smartphone-capture images under field conditions.
Reproduction assets foundThe paper's authors explicitly state that the code used to train, test, and analyze the data is publicly available on GitHub. The phenotype image datasets are only available upon request.Code · publicThe code used to train, test, and analyze the data is available at https://github.com/GustavoSantiago113/Sorghum_Grain_Counter .Open asset ↗GustavoSantiago113/Sorghum_Grain_Counterlines:169-296Code / dataset availability confirmedarXiv · OpenAlex · checked 13 Sept 2026
AppleCitrusMangoPeachPearPlumField / plotLiDAR / point cloudRGB / grayscaleFruit
We introduce FruitNeRF, a unified novel fruit counting framework that leverages state-of-the-art view synthesis methods to count any fruit type directly in 3D. Our framework takes an unordered set of posed images captured by a monocular camera and segments fruit in each image. To make our system independent of the fruit type, we employ a foundation model that generates binary segmentation masks for any fruit. Utilizing both modalities, RGB and semantic, we train a semantic neural radiance field. Through uniform volume sampling of the implicit Fruit Field, we obtain fruit-only point clouds. By applying cascaded clustering on the extracted point cloud, our approach achieves precise fruit count.The use of neural radiance fields provides significant advantages over conventional methods such as object tracking or optical flow, as the counting itself is lifted into 3D. Our method prevents double counting fruit and avoids counting irrelevant fruit.We evaluate our methodology using both real-world and synthetic datasets. The real-world dataset consists of three apple trees with manually counted ground truths, a benchmark apple dataset with one row and ground truth fruit location, while the synthetic dataset comprises various fruit types including apple, plum, lemon, pear, peach, and mango.Additionally, we assess the performance of fruit counting using the foundation model compared to a U-Net.
Why it matches plant phenotyping methods果実を対象に、画像・NeRF・点群クラスタリングを組み合わせて3D果実数を推定する手法を開発し、実データおよび合成データで評価しているため、植物表現型取得法が中心である。
abstractWe introduce FruitNeRF, a unified novel fruit counting framework that leverages state-of-the-art view synthesis methods to count any fruit type directly in 3D.
Reproduction assets foundThe paper's real-world apple tree image dataset with manual ground-truth counts and synthetic Blender fruit tree data are publicly released via the project website, and the FruitNeRF analysis code is open-source on GitHub. The Zenodo DOI refers to the third-party BlenderNeRF plugin (cited tool), not a paper-specific.Dataset · publicThe data has been made publicly available, and visualizations can be accessed on the project website.Open asset ↗lines:183-221Code · publicFruitNeRF code: https://github.com/meyerls/FruitNeRF has been made open-source.Open asset ↗meyerls/FruitNeRFlines:74-108Code / dataset availability confirmedOpenAlex · checked 7 Sept 2026
Soybean pod count is a crucial aspect of soybean plant phenotyping, offering valuable reference information for breeding and planting management. Traditional manual counting methods are not only costly but also prone to errors. Existing detection-based soybean pod counting methods face challenges due to the crowded and uneven distribution of soybean pods on the plants. To tackle this issue, we propose a Soybean Pod Counting Network (SPCN) for accurate soybean pod counting. SPCN is a density map-based architecture based on Hybrid Dilated Convolution (HDC) strategy and attention mechanism for feature extraction, using the Unbalanced Optimal Transport (UOT) loss function for supervising density map generation. Additionally, we introduce a new diverse dataset, BeanCount-1500, comprising of 24,684 images of 316 soybean varieties with various backgrounds and lighting conditions. Extensive experiments on BeanCount-1500 demonstrate the advantages of SPCN in soybean pod counting with an Mean Absolute Error(MAE) and an Mean Squared Error(MSE) of 4.37 and 6.45, respectively, significantly outperforming the current competing method by a substantial margin. Its excellent performance on the Renshou2021 dataset further confirms its outstanding generalization potential. Overall, the proposed method can provide technical support for intelligent breeding and planting management of soybean, promoting the digital and precise management of agriculture in general.
Why it matches plant phenotyping methods大豆莢数という植物形質を画像から自動推定する手法を開発し、データセット上で性能評価しているため、植物フェノタイピング手法が研究の中心です。
abstractSoybean pod count is a crucial aspect of soybean plant phenotyping
Reproduction assets foundThe paper's SPCN analysis code is stated to be publicly available on GitHub. The BeanCount-1500 dataset itself has no public deposit or availability statement (authors must be contacted), so it does not qualify as a public asset.Code · publicThe source code is available at https://github.com/johnhamtom/
soybean_counting_SPCN (accessed on 10 August 2024).Open asset ↗pdf-page:2 lines:1-58Code / dataset availability confirmedCrossref · checked 15 Sept 2026
Fusarium head blight (FHB) is one of the most significant diseases affecting wheat and other small-grain cereals worldwide. Developing FHB-resistant cultivars is critical but requires field and greenhouse disease assessment, which are typically laborious and time consuming. In this work, we developed automated applications based on three-dimensional (3D) convolutional neural networks (CNNs) that detect FHB symptoms expressed in wheat, estimate the total number of spikelets versus the total number of infected spikelets on a wheat head, and subsequently calculate FHB severity index. Such tools are an important step toward the creation of automated and efficient phenotyping methods. The data used to generate the results are 3D point clouds consisting of four colour channels—red, green, blue (RGB), and near-infrared (NIR)—collected using a multispectral 3D scanner. Our 3D CNN models for FHB detection achieved 100% accuracy. The influence of the multispectral information on performance was evaluated; the results showed the dominance of the RGB channels over both the NIR (720 nm peak wavelength) and the NIR plus RGB channels combined. Our best 3D CNN models for estimation of total and infected number of spikelets achieved mean absolute errors (MAEs) of 1.13 and 1.56, respectively. Our best 3D CNN models for FHB severity estimation achieved 8.6 MAE. A linear regression analysis between the visual FHB severity assessment and the FHB severity predicted by our 3D CNN showed a significant correlation.
Why it matches plant phenotyping methods3Dマルチスペクトルスキャンと3D CNNを用いて、コムギのFHB症状、穂の小穂数、感染小穂数、病害重症度を自動推定する手法を開発・評価しており、植物表現型取得が中心である。
abstractwe developed automated applications based on three-dimensional (3D) convolutional neural networks (CNNs) that detect FHB symptoms expressed in wheat, estimate the total number of spikelets versus the total number of infected spikelets on a wheat head, and subsequently calculate FHB severity index.
Plant phenotype detection plays a crucial role in understanding and studying plant biology, agriculture, and ecology. It involves the quantification and analysis of various physical traits and characteristics of plants, such as plant height, leaf shape, angle, number, and growth trajectory. By accurately detecting and measuring these phenotypic traits, researchers can gain insights into plant growth, development, stress tolerance, and the influence of environmental factors, which has important implications for crop breeding. Among these phenotypic characteristics, the number of leaves and growth trajectory of the plant are most accessible. Nonetheless, obtaining these phenotypes is labor intensive and financially demanding. With the rapid development of computer vision technology and artificial intelligence, using maize field images to fully analyze plant-related information can greatly eliminate repetitive labor and enhance the efficiency of plant breeding. However, it is still difficult to apply deep learning methods in field environments to determine the number and growth trajectory of leaves and stalks due to the complex backgrounds and serious occlusion problems of crops in field environments. To preliminarily explore the application of deep learning technology to the acquisition of the number of leaves and stalks and the tracking of growth trajectories in field agriculture, in this study, we developed a deep learning method called Point-Line Net, which is based on the Mask R-CNN framework, to automatically recognize maize field RGB images and determine the number and growth trajectory of leaves and stalks. The experimental results demonstrate that the object detection accuracy (mAP50) of our Point-Line Net can reach 81.5%. Moreover, to describe the position and growth of leaves and stalks, we introduced a new lightweight "keypoint" detection branch that achieved a magnitude of 33.5 using our custom distance verification index. Overall, these findings provide valuable insights for future field plant phenotype detection, particularly for datasets with dot and line annotations.
Why it matches plant phenotyping methodsトウモロコシの葉・茎の数と成長軌跡をRGB画像から抽出する深層学習手法を開発し、精度評価も行っており、植物表現型取得が研究の中心である。
abstractin this study, we developed a deep learning method called Point-Line Net, which is based on the Mask R-CNN framework, to automatically recognize maize field RGB images and determine the number and growth trajectory of leaves and stalks.
Reproduction assets foundThe authors explicitly deposit the code (and data) supporting this maize leaf/stalk trajectory phenotyping study in a public GitHub repository, matching an allowed URL.Code · publicThe computer code and data that support the findings of this study are deposited in a GitHub repository at https://github.com/VEGETALOADING/Point-Line-Net .Open asset ↗VEGETALOADING/Point-Line-Netlines:319-524Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Accurate wheat ear counting is one of the key indicators for wheat phenotyping. Convolutional neural network (CNN) algorithms for counting wheat have evolved into sophisticated tools, however because of the limitations of sensory fields, CNN is unable to simulate global context information, which has an impact on counting performance. In this study, we present a hybrid attention network (CTHNet) for wheat ear counting from RGB images that combines local features and global context information. On the one hand, to extract multi-scale local features, a convolutional neural network is built using the Cross Stage Partial framework. On the other hand, to acquire better global context information, tokenized image patches from convolutional neural network feature maps are encoded as input sequences using Pyramid Pooling Transformer. Then, the feature fusion module merges the local features with the global context information to significantly enhance the feature representation. The Global Wheat Head Detection Dataset and Wheat Ear Detection Dataset are used to assess the proposed model. There were 3.40 and 5.21 average absolute errors, respectively. The performance of the proposed model was significantly better than previous studies.
Why it matches plant phenotyping methods小麦穂数という植物形質をRGB画像から推定する深層学習手法を開発し、複数データセットで性能評価しており、表現型取得・抽出法が中心である。
abstractAccurate wheat ear counting is one of the key indicators for wheat phenotyping.
Reproduction assets foundThe paper uses two publicly available wheat ear image datasets (GWHD and WEDD) as its phenotyping inputs, with explicit public URLs in the data availability statement. No authors' analysis code or trained model is deposited.Dataset · publics generalization ability. This will provide real-time and accurate information for agricultural production, help farmers make scientific decisions, and improve crop management and yield.
Data availability statement
Publicly available datasets were analyzed in this study. This data can be found here: http://www.global-wheat.com/
https://github.com/simonMadec .
Author contributions
QH: Conceptualization, Formal analysis, Investigation, Methodology, Validation, Visualization, Writing – review & editing. WL: Conceptualization, Formal analysis, Investigation, Methodology, Software, Validation, Visualization, Writing – original draft. YZ: Software, Writing – review & editing. TR: SoftwaOpen asset ↗https://github.com/simonMadeclines:388-410Code / dataset availability confirmedEurope PMC · bioRxiv · checked 15 Sept 2026
SUMMARY There is an increasing demand to boost photosynthesis in rice to increase yield potential. Chloroplasts are the site of photosynthesis, and increasing the number and size of these organelles in the in leaf is a potential route to elevate leaf-level photosynthetic activity. Notably, bundle sheath cells do not make a significant contribution to overall carbon fixation in rice and thus various attempts are being made to increase chloroplast content in this cell type. In this study we developed and applied a deep learning tool named Chloro-Count to demonstrate that loss of OsHAP3H function in rice increases chloroplast occupancy in bundle sheath cells by 50%. Although limited to a single season, when grown in the field Oshap3H mutants exhibited increased numbers of tillers and panicles as compared to controls or gain of function mutants. The implementation of Chloro-Count enabled precise quantification of chloroplasts in loss- and gain-of-function OsHAP3H mutants and facilitated a comparison between 2D and 3D quantification methods. In wild-type rice, as the dimensions of bundle sheath cells increase, the volume of individual chloroplasts also increases. However, the larger the chloroplasts the fewer there are per bundle sheath cell. This observation revealed that a mechanism operates in bundle sheath cells to restrict chloroplast occupancy as cell dimensions increase. That mechanism is unperturbed in Oshap3H mutants. The use of Chloro-Count also revealed that 2D quantification, upon which most previous studies have relied, is compromised by the positioning of chloroplasts within the cell. Chloro-Count is therefore a valuable tool for accurate and high-throughput quantification of chloroplasts that has enabled the robust characterization of OsHAP3H effects on chloroplast biogenesis in rice. Whereas previous studies have increased chloroplast occupancy in bundle sheath cells by increasing the size of individual chloroplasts, loss of OsHAP3H function leads to an increase in chloroplast numbers.
Why it matches plant phenotyping methodsChloro-Countという深層学習ツールを開発し、葉肉細胞内の葉緑体数・占有率を高精度かつハイスループットに定量する手法が研究の中心であるため。
abstractwe developed and applied a deep learning tool named Chloro-Count
Reproduction assets foundThe paper's Chloro-Count deep learning tool (Mask R-CNN segmentation of chloroplasts and bundle sheath cells) is the authors' own analysis code, explicitly stated to be publicly available on GitHub. No public image/phenotype dataset deposit is stated; training images and Table S1 raw data are not linked to a public URLCode · publicn validated, they are mapped to
566 individual organelles/cells for volumetric analysis. An overview of the system for detecting and
567 measuring volumes of chloroplasts is presented in Figure 3A. The process for detecting and
568 measuring bundle sheaths follows an analogous workflow. The Chloro-Count code is available on
569 https://github.com/pedropgusmao/chloro-count.
570
571 Data collection and pre-processing
572 A total of 327 slices from 39 different cells were used during the training of both image segmentation
573 networks. Images from 29 cells were used for training, five for validation and five for testing. A total of
574 3,790 segments of chloroplasts were used for training, 287Open asset ↗pedropgusmao/chloro-countpdf-layout-page:16 lines:1-47Code / dataset availability confirmedEurope PMC · OpenAlex · checked 7 Sept 2026
The pod and seed counts are important yield-related traits in soybean. High-precision soybean breeders face the major challenge of accurately phenotyping the number of pods and seeds in a high-throughput manner. Recent advances in artificial intelligence, especially deep learning (DL) models, have provided new avenues for high-throughput phenotyping of crop traits with increased precision. However, the available DL models are less effective for phenotyping pods that are densely packed and overlap in in situ soybean plants; thus, accurate phenotyping of the number of pods and seeds in soybean plant is an important challenge. To address this challenge, the present study proposed a bottom-up model, DEKR-SPrior (disentangled keypoint regression with structural prior), for in situ soybean pod phenotyping, which considers soybean pods and seeds analogous to human people and joints, respectively. In particular, we designed a novel structural prior (SPrior) module that utilizes cosine similarity to improve feature discrimination, which is important for differentiating closely located seeds from highly similar seeds. To further enhance the accuracy of pod location, we cropped full-sized images into smaller and high-resolution subimages for analysis. The results on our image datasets revealed that DEKR-SPrior outperformed multiple bottom-up models, viz., Lightweight-OpenPose, OpenPose, HigherHRNet, and DEKR, reducing the mean absolute error from 25.81 (in the original DEKR) to 21.11 (in the DEKR-SPrior) in pod phenotyping. This paper demonstrated the great potential of DEKR-SPrior for plant phenotyping, and we hope that DEKR-SPrior will help future plant phenotyping.
Why it matches plant phenotyping methods大豆の莢・種子数を高スループットに推定する画像解析モデルを開発し、既存モデルと比較検証しているため、植物表現型取得手法が研究の中心です。
abstractthe present study proposed a bottom-up model, DEKR-SPrior (disentangled keypoint regression with structural prior), for in situ soybean pod phenotyping
Reproduction assets foundThe paper's DEKR-SPrior analysis code is publicly available on GitHub with an explicit availability statement and URL. The homemade soybean pod/seed image datasets are not publicly deposited and require contacting the corresponding author.Code · publicThe source code is publicly available. It can be accessed at the following GitHub repository: https://github.com/Cyncihe/DEKR-SPrior.gitOpen asset ↗https://github.com/Cyncihe/DEKR-SPrior.gitlines:300-403Code / dataset availability confirmedEurope PMC · checked 7 Sept 2026
Grape cluster architecture and compactness are complex traits influencing disease susceptibility, fruit quality, and yield. Evaluation methods for these traits include visual scoring, manual methodologies, and computer vision, with the latter being the most scalable approach. Most of the existing computer vision approaches for processing cluster images often rely on conventional segmentation or machine learning with extensive training and limited generalization. The Segment Anything Model (SAM), a novel foundation model trained on a massive image dataset, enables automated object segmentation without additional training. This study demonstrates out-of-the-box SAM's high accuracy in identifying individual berries in 2-dimensional (2D) cluster images. Using this model, we managed to segment approximately 3,500 cluster images, generating over 150,000 berry masks, each linked with spatial coordinates within their clusters. The correlation between human-identified berries and SAM predictions was very strong (Pearson's r 2 = 0.96). Although the visible berry count in images typically underestimates the actual cluster berry count due to visibility issues, we demonstrated that this discrepancy could be adjusted using a linear regression model (adjusted R 2 = 0.87). We emphasized the critical importance of the angle at which the cluster is imaged, noting its substantial effect on berry counts and architecture. We proposed different approaches in which berry location information facilitated the calculation of complex features related to cluster architecture and compactness. Finally, we discussed SAM's potential integration into currently available pipelines for image generation and processing in vineyard conditions.
Why it matches plant phenotyping methodsSAMを用いたブドウ房画像からの個別果粒セグメンテーション、検証、補正、および房構造・コンパクトネス形質の算出が研究の中心であるため。
abstractThis study demonstrates out-of-the-box SAM's high accuracy in identifying individual berries in 2-dimensional (2D) cluster images.
Reproduction assets foundThe authors state that all data and code to reproduce the study's grapevine cluster segmentation and architecture analysis are publicly available in their GitHub repository. Other URLs (SAM checkpoint, pycocotools, RMBG, arXiv refs) are generic third-party resources, not paper-specific assets.Code · publicAll the data and code to reproduce the results of this study are available at https://github.com/diazgarcialab/SAM-cluster-segmentation .Open asset ↗diazgarcialab/SAM-cluster-segmentationlines:105-230Code / dataset availability confirmedCrossref · Europe PMC · checked 7 Sept 2026
Recent advancements in computer vision, especially deep learning models, have shown considerable promise in tasks related to plant image object detection. However, the efficiency of these deep learning models heavily relies on input image quality, with low-resolution images significantly hindering model performance. Therefore, reconstructing high-quality images through specific techniques will help extract features from plant images, thus improving model performance. In this study, we explored the value of super-resolution technology for improving object detection model performance on plant images. Firstly, we built a comprehensive dataset comprising 1030 high-resolution plant images, named the PlantSR dataset. Subsequently, we developed a super-resolution model using the PlantSR dataset and benchmarked it against several state-of-the-art models designed for general image super-resolution tasks. Our proposed model demonstrated superior performance on the PlantSR dataset, indicating its efficacy in enhancing the super-resolution of plant images. Furthermore, we explored the effect of super-resolution on two specific object detection tasks: apple counting and soybean seed counting. By incorporating super-resolution as a pre-processing step, we observed a significant reduction in mean absolute error. Specifically, with the YOLOv7 model employed for apple counting, the mean absolute error decreased from 13.085 to 5.71. Similarly, with the P2PNet-Soy model utilized for soybean seed counting, the mean absolute error decreased from 19.159 to 15.085. These findings underscore the substantial potential of super-resolution technology in improving the performance of object detection models for accurately detecting and counting specific plants from images. The source codes and associated datasets related to this study are available at Github.
Why it matches plant phenotyping methods植物画像向け超解像モデルとデータセットを開発・ベンチマークし、リンゴおよびダイズ種子の計数性能を評価しており、表現型取得・抽出法が中心である。
abstractwe built a comprehensive dataset comprising 1030 high-resolution plant images, named the PlantSR dataset.
Reproduction assets foundThe paper's authors publicly released their analysis code (PlantSR super-resolution model and experiments) on GitHub, and also deposited the PlantSR dataset and HR soybean images on figshare; however, only the GitHub URL is among the allowed URLs, so only the code asset is reported.Code · publicThe source code is available at https://github.com/SkyCol/PlantSR (accessed on 28 November 2023).Open asset ↗SkyCol/PlantSRlines:94-293Code / dataset availability confirmedCrossref · Europe PMC · checked 7 Sept 2026
Abstract Background The sweet potato whitefly ( Bemisia tabaci ) is a globally important insect pest that damages crops through direct feeding and by transmitting viruses. Current B. tabaci management revolves around the use of insecticides, which are economically and environmentally costly. Host plant resistance is a sustainable option to reduce the impact of whiteflies, but progress in deploying resistance in crops has been slow. A major obstacle is the high cost and low throughput of screening plants for B. tabaci resistance. Oviposition rate is a popular metric for host plant resistance to B. tabaci because it does not require tracking insect development through the entire life cycle, but accurate quantification is still limited by difficulties in observing B. tabaci eggs, which are microscopic and translucent. The goal of our study was to improve quantification of B. tabaci eggs on several important crop species: cassava, cowpea, melon, sweet potato and tomato. Results We tested a selective staining process originally developed for leafhopper eggs: submerging the leaves in McBryde’s stain (acetic acid, ethanol, 0.2% aqueous acid Fuchsin, water; 20:19:2:1) for three days, followed by clearing under heat and pressure for 15 min in clearing solution (LGW; lactic acid, glycerol, water; 17:20:23). With a less experienced individual counting the eggs, B. tabaci egg counts increased after staining across all five crops. With a more experienced counter, egg counts increased after staining on melons, tomatoes, and cowpeas. For all five crops, there was significantly greater agreement on egg counts across the two counting individuals after the staining process. The staining method worked particularly well on melon, where egg counts universally increased after staining for both counting individuals. Conclusions Selective staining aids visualization of B. tabaci eggs across multiple crop plants, particularly species where leaf morphological features obscure eggs, such as melons and tomatoes. This method is broadly applicable to research questions requiring accurate quantification of B. tabaci eggs, including phenotyping for B. tabaci resistance.
Why it matches plant phenotyping methods植物葉上のコナジラミ卵を染色して定量し、計数値と計数者間一致を改善する方法を評価しており、抵抗性フェノタイピングへの応用が明示された中心的な手法研究。
abstractThe goal of our study was to improve quantification of B. tabaci eggs on several important crop species: cassava, cowpea, melon, sweet potato and tomato.
Reproduction assets foundThe paper's Data availability statement explicitly deposits the study's egg-count datasets and the R Markdown analysis code in a Dryad repository, which is a public, paper-specific asset directly reproducing the phenotyping measurements and analysis.Dataset · publicThe datasets generated and analyzed during this study, and an R Markdown document containing the code used to perform these analyses are available in a Dryad repository (DOI: doi: https://doi.org/10.5061/dryad.vmcvdnd1m ).Open asset ↗Dryad · 10.5061/dryad.vmcvdnd1mlines:138-163Code / dataset availability confirmedEurope PMC · Crossref · checked 14 Sept 2026
Recent advancements in computer vision, especially deep learning models, have shown considerable promise in tasks related to plant image object detection. However, the efficiency of these deep learning models heavily relies on input image quality, with low-resolution images significantly hindering model performance. Therefore, reconstructing high-quality images through specific techniques will help extract features from plant images, thus improve model performance. In this study, we explored the value of super-resolution technology for improving object detection model performance on plant images. Firstly, we built a comprehensive dataset comprising 1030 high-resolution plant images, named the PlantSR dataset. Subsequently, we developed a super-resolution model using the PlantSR dataset and benchmarked it against several state-or-the-art models designed for general image super-resolution tasks. Our proposed model demonstrated superior performance on the PlantSR dataset, indicating its efficacy in enhancing the super-resolution of plant images. Furthermore, we explored the effect of super-resolution on two specific object detection tasks: apple counting and soybean seed counting. By incorporating super-resolution as a pre-processing step, we observed a significant reduction in mean absolute error. Specifically, on the YOLOv7 model employed for apple counting, the mean absolute error decreased from 13.085 to 5.71. Similarly, on the P2PNet-Soy model utilized for soybean seed counting, the mean absolute error decreased from 19.159 to 15.085. These findings underscore the substantial potential of super-resolution technology in improving the performance of object detection models for accurately detecting and counting specific plants from images. The source codes and associated datasets are available at https://github.com/SkyCol/PlantSR.
Why it matches plant phenotyping methods植物画像の超解像モデルとデータセットを開発・ベンチマークし、リンゴおよびダイズ種子のカウント性能を改善する手法を検証しており、植物器官数の画像ベース推定が中心である。
abstractwe built a comprehensive dataset comprising 1030 high-resolution plant images, named the PlantSR dataset.
Reproduction assets foundThe paper publicly releases its authors' analysis code (GitHub), the PlantSR plant image dataset (figshare), and the high-resolution soybean seed images used for transfer learning (figshare). The P2PNet-Soy repository is cited prior work, not a paper-specific asset.Code · publicThe source codes and associated
datasets are available at https://github.com/SkyCol/PlantSR.Open asset ↗SkyCol/PlantSRpdf-page:2 lines:1-63Code / dataset availability confirmedEurope PMC · bioRxiv · checked 15 Sept 2026
Summary StomaVision is an automated tool designed for high-throughput detection and measurement of stomatal traits, such as stomatal number, pore size, and closure rate. It provides insights into plant responses to environmental cues, streamlining the analysis of micrographs from field-grown plants across various species, including monocots and dicots. Enhanced by a novel collection method that utilizes video recording, StomaVision increases the number of captured images for robust statistical analysis. Accessible via an intuitive web interface at and available for local use in a containerized environment at , this tool ensures long-term usability by minimizing the impact of software updates and maintaining functionality with minimal setup requirements. The application of StomaVision has provided significant physiological insights, such as variations in stomatal density, opening rates, and total pore area under heat stress. These traits correlate with critical physiological processes, including gas exchange, carbon assimilation, and water use efficiency, demonstrating the tool’s utility in advancing our understanding of plant physiology. The ability of StomaVision to identify differences in responses to varying durations of heat treatment highlights its value in plant science research. Plain language summary StomaVision is a tool that automatically counts and measures tiny openings on plant leaves, helping us learn how plants deal with their surroundings. It is easy to use and works well with various plant species. This tool helps scientists see how plants change under stress, making plant research easier and more accurate.
Why it matches plant phenotyping methods気孔数、孔サイズ、閉鎖率などの植物形質を画像から自動抽出するツールの開発・提供が研究の中心であり、植物フェノタイピング手法に該当する。
abstractStomaVision is an automated tool designed for high-throughput detection and measurement of stomatal traits, such as stomatal number, pore size, and closure rate.
Reproduction assets foundThe authors publicly release their StomaVision source code, trained YOLOv7-seg model, and all labeled stomata images on GitHub, plus a public Streamlit web portal for stomatal trait analysis. Cited datasets (Dryad/LeafNet, Cuticle Database) and generic libraries (VDP, Detectron2, Ultralytics, Label Studio) are prior/thCode · publicl for advancing our understanding of stomatal behavior,
841
particularly in an era in which plant resilience and adaptation are of paramount
842
concern.
843
844
845
Data Availability
846
The source code, trained model, user installation and training guideline, and all the
847
labeled images of leaf stomata are available at
848
https://github.com/YaoChengLab/StomaVision. The web portal of extracting stomatal
849
traits is available at https://stomavision.streamlit.app/.850
851
852
Author Contributions
853
TLW, PYC, XD, PLC, and YCL conceived the research. TLW, JYO, PXZ, YLW, RHW,
854
TCH, CYL, and YCL conducted the field and growth chamber experiments. TLW,
855
JYO, PXZ, YLW, and RHW produceOpen asset ↗YaoChengLab/StomaVisionpdf-raw-page:27 lines:1-65Code / dataset availability confirmedCrossref · Europe PMC · checked 15 Sept 2026
The world’s most significant yield by production quantity is sugarcane. It is the primary source for sugar, ethanol, chipboards, paper, barrages, and confectionery. Many people are affiliated with sugarcane production and their products around the globe. The sugarcane industries make an agreement with farmers before the tillering phase of plants. Industries are keen on knowing the sugarcane field’s pre-harvest estimation for planning their production and purchases. The proposed research contribution is twofold: by publishing our newly developed dataset, we also present a methodology to estimate the number of sugarcane plants in the tillering phase. The dataset has been obtained from sugarcane fields in the fall season. In this work, a modified architecture of Faster R-CNN with feature extraction using VGG-16 with Inception-v3 modules and sigmoid threshold function has been proposed for the detection and classification of sugarcane plants. Significantly promising results with 82.10% accuracy have been obtained with the proposed architecture, showing the viability of the developed methodology.
Why it matches plant phenotyping methodsサトウキビ個体数という植物形態・群落状態を画像から推定する手法を開発し、データセット公開と精度評価も行っており、表現型取得が研究の中心である。
abstractby publishing our newly developed dataset, we also present a methodology to estimate the number of sugarcane plants in the tillering phase
Reproduction assets foundThe authors publicly deposited their sugarcane tillering-phase video-derived image dataset and the annotated (bounding-box) dataset on Mendeley Data, both explicitly cited in the Data Availability Statement. No analysis code or trained model checkpoint is reported as available.Dataset · publicuthors have read and agreed to the published version of the manuscript.
Institutional Review Board Statement
Not applicable.
Informed Consent Statement
Not applicable.
Data Availability Statement
Dataset is available at the following: Ubaid, Talha; Javaid, Sameena (2024), “Sugarcane Plant in Tillering Phase”, Mendeley Data, V1, https://doi.org/10.17632/m5zxyznvgz.1 . Ubaid, Talha; Javaid, Sameena (2024), “Annotated Sugarcane Plants”, Mendeley Data, V1, https://doi.org/10.17632/ydr8vgg64w.1 .
Conflicts of Interest
The authors declare no conflicts of interest.
Funding Statement
This research received no external funding.
Footnotes
Disclaimer/Publisher’s Note: The statements, opinions and daOpen asset ↗Mendeley Data · 10.17632/m5zxyznvgz.1lines:147-178Dataset · publicformed Consent Statement
Not applicable.
Data Availability Statement
Dataset is available at the following: Ubaid, Talha; Javaid, Sameena (2024), “Sugarcane Plant in Tillering Phase”, Mendeley Data, V1, https://doi.org/10.17632/m5zxyznvgz.1 . Ubaid, Talha; Javaid, Sameena (2024), “Annotated Sugarcane Plants”, Mendeley Data, V1, https://doi.org/10.17632/ydr8vgg64w.1 .
Conflicts of Interest
The authors declare no conflicts of interest.
Funding Statement
This research received no external funding.
Footnotes
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the ediOpen asset ↗Mendeley Data · 10.17632/ydr8vgg64w.1lines:147-178Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
The deployment of intelligent surveillance systems to monitor tomato plant growth poses substantial challenges due to the dynamic nature of disease patterns and the complexity of environmental conditions such as background and lighting. In this study, an integrated cascade framework that synergizes detectors and trackers was introduced for the simultaneous identification of tomato leaf diseases and fruit counting. We applied an autonomous robot with smartphone camera to collect images for leaf disease and fruits in greenhouses. Further, we improved the deep learning network YOLO-TGI by incorporating Ghost and CBAM modules, which was trained and tested in conjunction with premier lightweight detection models like YOLOX and NanoDet in evaluating leaf health conditions. For the cascading with various base detectors, we integrated state-of-the-art trackers such as Byte-Track, Motpy, and FairMot to enable fruit counting in video streams. Experimental results indicated that the combination of YOLO-TGI and Byte-Track achieved the most robust performance. Particularly, YOLO-TGI-N emerged as the model with the least computational demands, registering the lowest FLOPs at 2.05 G and checkpoint weights at 3.7 M, while still maintaining a mAP of 0.72 for leaf disease detection. Regarding the fruit counting, the combination of YOLO-TGI-S and Byte-Track achieved the best R 2 of 0.93 and the lowest RMSE of 9.17, boasting an inference speed that doubles that of the YOLOX series, and is 2.5 times faster than the NanoDet series. The developed network framework is a potential solution for researchers facilitating the deployment of similar surveillance models for a broad spectrum of fruit and vegetable crops.
Why it matches plant phenotyping methodsトマト葉の病害状態と果実数という植物形質を、ロボット撮影画像から検出・計数する深層学習および追跡フレームワークを開発・評価しており、表現型取得手法が中心である。
abstractan integrated cascade framework that synergizes detectors and trackers was introduced for the simultaneous identification of tomato leaf diseases and fruit counting.
Reproduction assets foundThe paper's greenhouse tomato leaf/fruit image dataset is publicly hosted on Roboflow, and the authors' analysis code (YOLO-TGI detection/tracking framework) is publicly available on GitHub. NanoDet is a cited third-party library, not a paper-specific asset.Code · publicssisted in the creation and programming of the deep learning networks. R.K. was responsible for drafting the manuscript and conducting all programming tasks, under the supervision of N.R. and S.S.
Competing interests: The authors declare that they have no competing interests.
Data Availability
Dataset and code can be reached at https://github.com/RuiKangnj/TGI/tree/main .
References
1. Dorais M, Ehret DL, Papadopoulos AP.Open asset ↗github.com/RuiKangnj/TGIlines:272-285Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Wheat head detection and counting using deep learning techniques has gained considerable attention in precision agriculture applications such as wheat growth monitoring, yield estimation, and resource allocation. However, the accurate detection of small and dense wheat heads remains challenging due to the inherent variations in their size, orientation, appearance, aspect ratios, density, and the complexity of imaging conditions. To address these challenges, we propose a novel approach called the Oriented Feature Pyramid Network (OFPN) that focuses on detecting rotated wheat heads by utilizing oriented bounding boxes. In order to facilitate the development and evaluation of our proposed method, we introduce a novel dataset named the Rotated Global Wheat Head Dataset (RGWHD). This dataset is constructed by manually annotating images from the Global Wheat Head Detection (GWHD) dataset with oriented bounding boxes. Furthermore, we incorporate a Path-aggregation and Balanced Feature Pyramid Network into our architecture to effectively extract both semantic and positional information from the input images. This is achieved by leveraging feature fusion techniques at multiple scales, enhancing the detection capabilities for small wheat heads. To improve the localization and detection accuracy of dense and overlapping wheat heads, we employ the Soft-NMS algorithm to filter the proposed bounding boxes. Experimental results indicate the superior performance of the OFPN model, achieving a remarkable mean average precision of 85.77% in oriented wheat head detection, surpassing six other state-of-the-art models. Moreover, we observe a substantial improvement in the accuracy of wheat head counting, with an accuracy of 93.97%. This represents an increase of 3.12% compared to the Faster R-CNN method. Both qualitative and quantitative results demonstrate the effectiveness of the proposed OFPN model in accurately localizing and counting wheat heads within various challenging scenarios.
Why it matches plant phenotyping methods小麦穂の検出・計数という植物器官形質の画像ベース推定手法を開発し、専用データセットを構築して性能評価しているため、方法が中心的である。
abstractwe propose a novel approach called the Oriented Feature Pyramid Network (OFPN) that focuses on detecting rotated wheat heads by utilizing oriented bounding boxes.
Reproduction assets foundThe paper introduces the RGWHD dataset (oriented-bounding-box annotations of GWHD wheat images), publicly released via Baidu pan with extraction code, and makes its experiment scripts publicly available on GitHub. The underlying GWHD image dataset (public on Kaggle) is the image source used for the paper's phenotyping.Dataset · publiction, Validation, Writing—original draft preparation. N.L.: Formal analysis, Resources, Project ad-ministration.C .F.: Investigation, Data curation. All authors have read and agreed to the published version of the manuscript.
Data availability
The datasets generated and analysed during the current study are available in RGWHD ( https://pan.baidu.com/s/1Fy3HpIfAeQhRef_ZuKu4iw ) and the extraction code is vbiy. The datasets generated during and/or analyzed during the current study areavailable from the corresponding author on reasonable request. The scripts to run all experiments are publicly available through our GitHub page https://github.com/cwr0821/OFPN .
Competing interests
The authors deOpen asset ↗RGWHDlines:445-520Code · publicdy are available in RGWHD ( https://pan.baidu.com/s/1Fy3HpIfAeQhRef_ZuKu4iw ) and the extraction code is vbiy. The datasets generated during and/or analyzed during the current study areavailable from the corresponding author on reasonable request. The scripts to run all experiments are publicly available through our GitHub page https://github.com/cwr0821/OFPN .
Competing interests
The authors declare no competing interests.
Footnotes
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
References
1. Sharma, S., Kooner, R., Arora, R., Insect pests and crop losses. Breeding insect resistant crops for suOpen asset ↗cwr0821/OFPNlines:445-520Dataset · public. The GWHD dataset is a comprehensive collection of well-annotated wheat head images, compiled by nine research institutions across seven countries. It serves as a valuable resource for training robust models to accurately estimate the location and density of wheat heads in seven categories. The GWHD dataset can be accessed at https://www.kaggle.com/competitions/global-wheat-detection/data . The SPIKE dataset comprises 335 images captured at three distinct growth stages, covering ten different wheat varieties. The UWHD dataset consists of 550 images captured by a drone at an altitude of 10 m. The ACID dataset consists of 520 images taken in controlled greenhouse conditions, featuring 4158 laOpen asset ↗lines:52-149Code / dataset availability confirmedEurope PMC · checked 7 Sept 2026
Deep learning and computer vision, using remote sensing and drones, are 2 promising nondestructive methods for plant monitoring and phenotyping. However, their applications are infeasible for many crop systems under tree canopies, such as coffee crops, making it challenging to perform plant monitoring and phenotyping at a large spatial scale at a low cost. This study aims to develop a geographic-scale monitoring method for coffee cherry counting, supported by an artificial intelligence (AI)-powered citizen science approach. The approach uses basic smartphones to take a few pictures of coffee trees; 2,968 trees were investigated with 8,904 pictures in Junín and Piura (Peru), Cauca, and Quindío (Colombia) in 2022, with the help of nearly 1,000 smallholder coffee farmers. Then, we trained and validated YOLO (You Only Look Once) v8 for detecting cherries in the dataset in Peru. An average number of cherries per picture was multiplied by the number of branches to estimate the total number of cherries per tree. The model's performance in Peru showed an R 2 of 0.59. When the model was tested in Colombia, where different varieties are grown in different biogeoclimatic conditions, the model showed an R 2 of 0.71. The overall performance in both countries reached an R 2 of 0.72. The results suggest that the method can be applied to much broader scales and is transferable to other varieties, countries, and regions. To our knowledge, this is the first AI-powered method for counting coffee cherries and has the potential for a geographic-scale, multiyear, photo-based phenotypic monitoring for coffee crops in low-income countries worldwide.
Why it matches plant phenotyping methodsスマートフォン画像と深層学習でコーヒー果実数を推定する方法を開発・検証しており、植物形質の取得が研究の中心です。
abstractThis study aims to develop a geographic-scale monitoring method for coffee cherry counting, supported by an artificial intelligence (AI)-powered citizen science approach.
Reproduction assets foundThe paper's Data Availability statement explicitly deposits representative coffee cherry pictures (phenotyping image data) and the authors' Python analysis script in a public GitHub repository, matching the paper's smartphone-image cherry counting analysis. Other URLs (FAOSTAT, SENAMHI, IDEAM, Label Studio, YOLOv5 docsCode · publicSome representative pictures and the Python script used for the study are available at the GitHub repository: https://github.com/j-river1/Croppie .Open asset ↗j-river1/Croppielines:207-221Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Unmanned aerial vehicle (UAV)-based imagery has become widely used to collect time-series agronomic data, which are then incorporated into plant breeding programs to enhance crop improvements. To make efficient analysis possible, in this study, by leveraging an aerial photography dataset for a field trial of 233 different inbred lines from the maize diversity panel, we developed machine learning methods for obtaining automated tassel counts at the plot level. We employed both an object-based counting-by-detection (CBD) approach and a density-based counting-by-regression (CBR) approach. Using an image segmentation method that removes most of the pixels not associated with the plant tassels, the results showed a dramatic improvement in the accuracy of object-based (CBD) detection, with the cross-validation prediction accuracy ( r 2 ) peaking at 0.7033 on a detector trained with images with a filter threshold of 90. The CBR approach showed the greatest accuracy when using unfiltered images, with a mean absolute error (MAE) of 7.99. However, when using bootstrapping, images filtered at a threshold of 90 showed a slightly better MAE (8.65) than the unfiltered images (8.90). These methods will allow for accurate estimates of flowering-related traits and help to make breeding decisions for crop improvement.
Why it matches plant phenotyping methodsトウモロコシ雄穂を画像から自動計数し、画像セグメンテーションと2種類の機械学習手法の精度を検証する研究であり、植物表現型取得法が中心である。
abstractwe developed machine learning methods for obtaining automated tassel counts at the plot level.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Supplement · publicThe following supporting information can be downloaded at: https://www.mdpi.com/article/10.3390/s24072172/s1 , Data S1 containing training images and annotations, Figures S1–S7.Open asset ↗10.3390/s24072172/s1lines:127-146Code / dataset availability confirmedbioRxiv · checked 15 Sept 2026
Variation in Drosophila compound eye size is studied across research fields, from evolutionary biology to biomedical studies, requiring the collection of large datasets to ensure robust statistical analyses. To address this, we present EyeHex, a tool for automatic segmentation of fruit fly compound eyes from brightfield and scanning electron microscopy (SEM) images. EyeHex features two integrated modules: the first utilizes machine learning to generate probability maps of the eye and ommatidia locations, while the second, a hard-coded module, leverages the hexagonal organization of the compound eye to map individual ommatidia. This iterative segmentation process, which adds one ommatidium at a time based on registered neighbors, ensures robustness to local perturbations. EyeHex also includes an analysis tool that calculates key metrics of the eye, such as ommatidia count and diameter distribution across the eye. With minimal user input for training and application, EyeHex achieves exceptional accuracy (>99.6% compared to manual counts on SEM images) and adapts to different fly strains, species, and image types. EyeHex offers a cost-effective, rapid, and flexible pipeline for extracting detailed statistical data on Drosophila compound eye variation, making it a valuable resource for high-throughput studies.
Why it matches plant phenotyping methods昆虫（ショウジョウバエ）の眼を対象としており植物ではないため、植物フェノタイピング文献の対象外です。
abstractautomatic segmentation of fruit fly compound eyes from brightfield and scanning electron microscopy (SEM) images
Reproduction assets foundThe paper's EyeHex MATLAB toolbox (with manual and sample images) and the post-segmentation analysis code are publicly available on GitHub, as stated in the Declarations. The segmentation results/analysis supplement is only a PDF supplement; the toolbox and analysis code are the paper-specific public assets.Code · publict of abbreviations
A-P: Anterior-Posterior
CT: Micro Computed Tomography
SEM: Scanning Electron Microscopy
GUI: Graphical User Interface
Declarations
Ethics approval and consent to participate
Not applicable
Consent for publication
Not applicable
Availability of data and Supplementary materials
EyeHex toolbox is available from https://github.com/huytran216/EyeHex-toolbox.
The analysis code following EyeHex segmentation for all eyes in the dataset can be
downloaded from https://github.com/huytran216/EyeHex_analysis.
Segmentation results and analysis for Hikone-AS (26 eyes) and Canton-SBH (12 eyes):
Supplementary_file.pdf
Competing interests
The authors declare that they have no competing intOpen asset ↗huytran216/EyeHex-toolboxpdf-layout-page:22 lines:1-53Code · publictions
Ethics approval and consent to participate
Not applicable
Consent for publication
Not applicable
Availability of data and Supplementary materials
EyeHex toolbox is available from https://github.com/huytran216/EyeHex-toolbox.
The analysis code following EyeHex segmentation for all eyes in the dataset can be
downloaded from https://github.com/huytran216/EyeHex_analysis.
Segmentation results and analysis for Hikone-AS (26 eyes) and Canton-SBH (12 eyes):
Supplementary_file.pdf
Competing interests
The authors declare that they have no competing interests.
Author’s contributions
AR collected the data (sample preparation and imaging), HT created EyeHex toolbox
and analyzed the data, AR and HTOpen asset ↗huytran216/EyeHex_analysispdf-layout-page:22 lines:1-53Code / dataset availability confirmedOpenAlex · Europe PMC · checked 7 Sept 2026
Introduction: ) serves as a vital staple crop that feeds over half the world's population. Optimizing rice breeding for increasing grain yield is critical for global food security. Heading-date-related or Flowering-time-related traits, is a key factor determining yield potential. However, traditional manual phenotyping methods for these traits are time-consuming and labor-intensive. Method: Here we show that aerial imagery from unmanned aerial vehicles (UAVs), when combined with deep learning-based panicle detection, enables high-throughput phenotyping of heading-date-related traits. We systematically evaluated various state-of-the-art object detectors on rice panicle counting and identified YOLOv8-X as the optimal detector. Results: Applying YOLOv8-X to UAV time-series images of 294 rice recombinant inbred lines (RILs) allowed accurate quantification of six heading-date-related traits. Utilizing these phenotypes, we identified quantitative trait loci (QTL), including verified loci and novel loci, associated with heading date. Discussion: Our optimized UAV phenotyping and computer vision pipeline may facilitate scalable molecular identification of heading-date-related genes and guide enhancements in rice yield and adaptation.
Why it matches plant phenotyping methodsUAV画像と深層学習によるイネ穂検出・計数を中核とし、出穂関連形質を高スループットに定量するフェノタイピング手法およびワークフローを評価・適用している。
abstractaerial imagery from unmanned aerial vehicles (UAVs), when combined with deep learning-based panicle detection, enables high-throughput phenotyping of heading-date-related traits
Reproduction assets foundThe article states that all relevant code for the UAV phenotyping and panicle detection pipeline is publicly available in the authors' GitHub repository r1cheu/phenocv. Other URLs (Ultralytics, COCO, WinQTLCart) are generic third-party tools, not paper-specific assets.Code · publicAll relevant code can be accessed at https://github.com/r1cheu/phenocv .Open asset ↗r1cheu/phenocvlines:317-328Code / dataset availability confirmedCrossref · checked 15 Sept 2026
This study presents an approach to address the challenges of recognizing the maturity stage and counting sweet peppers of varying colors (green, yellow, orange, and red) within greenhouse environments. The methodology leverages the YOLOv5 model for real-time object detection, classification, and localization, coupled with the DeepSORT algorithm for efficient tracking. The system was successfully implemented to monitor sweet pepper production, and some challenges related to this environment, namely occlusions and the presence of leaves and branches, were effectively overcome. We evaluated our algorithm using real-world data collected in a sweet pepper greenhouse. A dataset comprising 1863 images was meticulously compiled to enhance the study, incorporating diverse sweet pepper varieties and maturity levels. Additionally, the study emphasized the role of confidence levels in object recognition, achieving a confidence level of 0.973. Furthermore, the DeepSORT algorithm was successfully applied for counting sweet peppers, demonstrating an accuracy level of 85.7% in two simulated environments under challenging conditions, such as varied lighting and inaccuracies in maturity level assessment.
Why it matches plant phenotyping methods深層学習による果実の成熟段階認識と計数が研究の中心であり、植物器官の状態（成熟度）を画像から抽出・評価しているため、植物フェノタイピング手法として含める。
abstractThis study presents an approach to address the challenges of recognizing the maturity stage and counting sweet peppers of varying colors
Reproduction assets foundThe authors explicitly state their dataset and supporting data are publicly available via their own GitHub repository (YOLOv5 + DeepSORT sweet pepper detection/counting), with an exact URL given in the text and Data Availability Statement. The Kaggle and Roboflow datasets are cited external/prior datasets, not paper-.Dataset · publicData Availability Statement: The data that support the findings of this study are available on GitHub
via [41].Open asset ↗pdf-raw-page:29 lines:1-51Code / dataset availability confirmedarXiv · checked 13 Sept 2026
The process of estimating and counting tree density using only a single aerial or satellite image is a difficult task in the fields of photogrammetry and remote sensing. However, it plays a crucial role in the management of forests. The huge variety of trees in varied topography severely hinders tree counting models to perform well. The purpose of this paper is to propose a framework that is learnt from the source domain with sufficient labeled trees and is adapted to the target domain with only a limited number of labeled trees. Our method, termed as AdaTreeFormer, contains one shared encoder with a hierarchical feature extraction scheme to extract robust features from the source and target domains. It also consists of three subnets: two for extracting self-domain attention maps from source and target domains respectively and one for extracting cross-domain attention maps. For the latter, an attention-to-adapt mechanism is introduced to distill relevant information from different domains while generating tree density maps; a hierarchical cross-domain feature alignment scheme is proposed that progressively aligns the features from the source and target domains. We also adopt adversarial learning into the framework to further reduce the gap between source and target domains. Our AdaTreeFormer is evaluated on six designed domain adaptation tasks using three tree counting datasets, \ie Jiangsu, Yosemite, and London. Experimental results show that AdaTreeFormer significantly surpasses the state of the art, \eg in the cross domain from the Yosemite to Jiangsu dataset, it achieves a reduction of 15.9 points in terms of the absolute counting errors and an increase of 10.8\% in the accuracy of the detected trees' locations. The codes and datasets are available at https://github.com/HAAClassic/AdaTreeFormer.
Why it matches plant phenotyping methods単一の航空・衛星画像から樹木数・密度を推定する画像解析手法を開発し、複数データセットとドメイン適応タスクで評価しており、植物形質の取得が中心である。
abstractThe purpose of this paper is to propose a framework that is learnt from the source domain with sufficient labeled trees and is adapted to the target domain with only a limited number of labeled trees.
Reproduction assets foundThe paper publicly releases its AdaTreeFormer code and datasets, and evaluates on three publicly available tree-counting image/annotation datasets (Jiangsu, London, Yosemite) with explicit GitHub availability statements.Code · publicThe codes and datasets are available at https://github.com/HAAClassic/AdaTreeFormer .Open asset ↗HAAClassic/AdaTreeFormerlines:1-70Dataset · publicThis dataset encompasses 24 satellite images taken by the GaofenII satellite with a ground sample distance (GSD) of 0.8m (available at https://github.com/sddpltwanqiu/TreeCountNet/tree/main).Open asset ↗sddpltwanqiu/TreeCountNetlines:201-252Dataset · publicThis dataset consists of high-resolution images captured at 0.2m GSD from London, United Kingdom for training and testing (available at https://github.com/HAAClassic/TreeFormer/tree/main).Open asset ↗HAAClassic/TreeFormerlines:201-252Dataset · publicThe study area for this dataset revolves around Yosemite National Park, located in California, United States of America (available at https://github.com/nightonion/yosemite-tree-dataset ).Open asset ↗nightonion/yosemite-tree-datasetlines:201-252Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Published4 Feb 2024The Plant journal : for cell and molecular biologyCited by 0 · OpenAlex ↗
Confocal microscopy has greatly aided our understanding of the major cellular processes and trafficking pathways responsible for plant growth and development. However, a drawback of these studies is that they often rely on the manual analysis of a vast number of images, which is time-consuming, error-prone, and subject to bias. To overcome these limitations, we developed Dot Scanner, a Python program for analyzing the densities, lifetimes, and displacements of fluorescently tagged particles in an unbiased, automated, and efficient manner. Dot Scanner was validated by performing side-by-side analysis in Fiji-ImageJ of particles involved in cellulose biosynthesis. We found that the particle densities and lifetimes were comparable in both Dot Scanner and Fiji-ImageJ, verifying the accuracy of Dot Scanner. Dot Scanner largely outperforms Fiji-ImageJ, since it suffers far less selection bias when calculating particle lifetimes and is much more efficient at distinguishing between weak signals and background signal caused by bleaching. Not only does Dot Scanner obtain much more robust results, but it is a highly efficient program, since it automates much of the analyses, shortening workflow durations from weeks to minutes. This free and accessible program will be a highly advantageous tool for analyzing live-cell imaging in plants.
Why it matches plant phenotyping methods植物のライブセル画像から粒子密度・寿命・変位を自動抽出するソフトウェアを開発し、Fiji-ImageJと比較検証しており、表現型取得・解析手法が中心である。
abstractwe developed Dot Scanner, a Python program for analyzing the densities, lifetimes, and displacements of fluorescently tagged particles
Reproduction assets foundThe paper's own computational analysis tool, Dot Scanner (Python software for quantifying densities, lifetimes, and displacements of fluorescently labeled particles in plant tissues), is explicitly stated to be publicly available on GitHub with a full URL. No public phenotype/trait datasets or raw imaging data depositsCode · public= 2, blob size = 5, dot lower = 0.9, dot
upper = 4.5, and blob lower = 2, skips = 1, and remove edge
frames = false. All lifetimes that were 60 sec long were removed
from the analysis.
Dot scanner
Dot Scanner was developed using the Python programming lan-
guage. The software is available on GitHub, and the project home-
page (https://github.com/bdavis222/dotscanner) contains all the
documentation needed for its installation and use, including
the README file (https://github.com/bdavis222/dot-scanner/blob/main/README.md). As mentioned in the README, Python 3 must
be installed prior to Dot Scanner installation (https://www.python.org/downloads/).ACKNOWLEDGMENTS
We thank S. Bednarek for provOpen asset ↗bdavis222/dotscannerpdf-raw-page:9 lines:1-87Code / dataset availability confirmedOpenAlex · Europe PMC · checked 15 Sept 2026
Plant image analysis is a significant tool for plant phenotyping. Image analysis has been used to assess plant trails, forecast plant growth, and offer geographical information about images. The area segmentation and counting of the leaf is a major component of plant phenotyping, which can be used to measure the growth of the plant. Therefore, this paper developed a convolutional neural network-based leaf counting model called LC-Net. The original plant image and segmented leaf parts are fed as input because the segmented leaf part provides additional information to the proposed LC-Net. The well-known SegNet model has been utilised to obtain segmented leaf parts because it outperforms four other popular Convolutional Neural Network (CNN) models, namely DeepLab V3+, Fast FCN with Pyramid Scene Parsing (PSP), U-Net, and Refine Net. The proposed LC-Net is compared to the other recent CNN-based leaf counting models over the combined Computer Vision Problems in Plant Phenotyping (CVPPP) and KOMATSUNA datasets. The subjective and numerical evaluations of the experimental results demonstrate the superiority of the LC-Net to other tested models.
Why it matches plant phenotyping methodsロゼット植物の葉数という表現型を画像から推定するCNN手法を開発し、既存モデルおよび標準データセットで比較評価しており、方法が研究の中心である。
abstractTherefore, this paper developed a convolutional neural network-based leaf counting model called LC-Net.
Reproduction assets foundThe paper's leaf-counting experiments were run on the CVPPP and KOMATSUNA plant image datasets, which the authors explicitly state are publicly available with download links. No author code or trained model is released.Dataset · publication, Investigation, Validation. L.A.: Supervision, Validation, Writing-Reviewing and Editing. A.G.: Software, Visualization, Writing-Reviewing.
Funding
Open access funding provided by Linköping University.
Data availibility
The datasets that support the findings of this study are publicly available. Link for CVPPP dataset is: http://www.plant-phenotyping.org/datasets. Link for KOMATSUNA dataset is: https://limu.ait.kyushu-u.ac.jp/ agri/komatsuna/.
Competing interests
The authors declare no competing interests.
Footnotes
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
References
1. Furbank RT, Tester M. Open asset ↗plant-phenotyping.org · CVPPPlines:275-305Code / dataset availability confirmedEurope PMC · Crossref · bioRxiv · checked 15 Sept 2026
Chloroplasts are essential organelles in plants that are involved in plant development and photosynthesis. Accurate quantification of chloroplast numbers is important for understanding the status and type of plant cells, as well as assessing photosynthetic potential and efficiency. Traditional methods of counting chloroplasts using microscopy are time-consuming and face challenges such as the possibility of missing out-of-focus samples or double counting when adjusting the focal position. Here, we developed an innovative approach called Detecting- and-Counting-chloroplasts (D&Cchl) for automated detection and counting of chloroplasts. This approach utilizes a deep-learning-based object detection algorithm called You-Only-Look-Once (YOLO), along with the Intersection Over Union (IOU) strategy. The application of D&Cchl has shown excellent performance in accurately identifying and quantifying chloroplasts. This holds true when applied to both a single image and a three-dimensional (3D) structure composed of a series of images. Furthermore, by integrating Cellpose, a cell-segmentation tool, we were able to successfully perform single-cell 3D chloroplast counting. Compared to manual counting methods, this approach improved the accuracy of detection and counting to over 95%. Together, our work not only provides an efficient and reliable tool for accurately analyzing the status of chloroplasts, enhancing our understanding of plant photosynthetic cells and growth characteristics, but also makes a significant contribution to the convergence of botany and deep learning. One-sentence summary This deep learning-based approach enables the accurate complete detection and counting of chloroplasts in 3D single cells using microscopic image stacks, and showcases a successful example of utilizing deep learning methods to analyze subcellular spatial information in plant cells. The authors responsible for distribution of materials integral to the findings presented in this article in accordance with the policy described in the Instructions for Authors ( https://academic.oup.com/plcell/ ) is: Zhao Dong ( dongzhao@hebeu.edu.cn ), Shaokai Yang, ( shaokai1@ualberta.ca ), Ningjing Liu ( liuningjing1@yeah.net ), and Qiong Zhao ( qzhao@bio.ecnu.edu.cn ).
Why it matches plant phenotyping methods植物細胞の顕微鏡画像から葉緑体数を自動検出・定量する深層学習手法を開発し、手動計数と比較して精度検証しているため、植物フェノタイピング手法が中心である。
abstractHere, we developed an innovative approach called Detecting- and-Counting-chloroplasts (D&Cchl) for automated detection and counting of chloroplasts.
Reproduction assets foundThe authors explicitly state that all code and the training dataset (annotated chloroplast microscopy images) are shared on their public GitHub repository, which is a paper-specific asset for this chloroplast counting study. Other URLs (labelImg, yolov7, ImageJ Falk plugins) are generic third-party tools, not paper-ownCode · publicltiple times during the stacking process. Through this approach, we
460
successfully constructed a comprehensive 3D cell model from the series of 2D
461
images, enabling more accurate chloroplast detection and counting in a 3D space.
462
463
Code and software
464
All the code and training dataset have been shared on GitHub
465
(https://github.com/xiaoli111111111/-AI4CELLBIO-ECNU), with detailed
466
explanations in the supplementary manual.
467
468
References
469
preprint (which was not certified by peer review) is the author/funder. All rights reserved. No reuse allowed without permission.
The copyright holder for this
this version posted December 18, 2023.
;
https://doi.org/10.1101/2023.12.Open asset ↗xiaoli111111111/-AI4CELLBIO-ECNUpdf-raw-page:16 lines:1-65Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Background Karyotype, as a basic characteristic of species, provides valuable information for fundamental theoretical research and germplasm resource innovation. However, traditional karyotyping techniques, including fluorescence in situ hybridization (FISH), are challenging and low in efficiency, especially when karyotyping aneuploid and polyploid plants. The use of low coverage whole-genome resequencing (lcWGR) data for karyotyping was explored, but existing methods are complicated and require control samples. Results In this study, a new protocol for molecular karyotype analysis was provided, which proved to be a simpler, faster, and more accurate method, requiring no control. Notably, our method not only provided the copy number of each chromosome of an individual but also an accurate evaluation of the genomic contribution from its parents. Moreover, we verified the method through FISH and published resequencing data. Conclusions This method is of great significance for species evolution analysis, chromosome engineering, crop improvement, and breeding.
Why it matches plant phenotyping methods植物個体の染色体コピー数と親由来ゲノム寄与を推定する分子カリオタイピング法を開発し、FISHおよび公開データで検証しており、植物の状態・特性取得法が研究の中心である。
abstractIn this study, a new protocol for molecular karyotype analysis was provided, which proved to be a simpler, faster, and more accurate method, requiring no control.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicAll codes (including detailed notes) and test data are available on GitHub ( https://github.com/kangluzhao/karyotyping ).Open asset ↗kangluzhao/karyotypinglines:129-157Code / dataset availability confirmedEurope PMC · checked 7 Sept 2026
Background Inflorescence properties such length, spikelet number, and their spatial distribution across the rachis, are fundamental indicators of seed productivity in grasses and have been a target of selection throughout domestication and crop improvement. However, quantifying such complex morphology is laborious, time-consuming, and commonly limited to human-perceived traits. These limitations can be exacerbated by unfavorable trait correlations between inflorescence architecture and seed yield that can be unconsciously selected for. Computer vision offers an alternative to conventional phenotyping, enabling higher throughput and reducing subjectivity. These approaches provide valuable insights into the determinants of seed yield, and thus, aid breeding decisions. Results Here, we described SpykProps, an inexpensive Python-based imaging system to quantify morphological properties in unilateral inflorescences, that was developed and tested on images of perennial grass (Lolium perenne L.) spikes. SpykProps is able to rapidly and accurately identify spikes (RMSE 2 = 0.96), and number of spikelets (R 2 = 0.61). It also quantifies color and shape from hundreds of interacting descriptors that are accurate predictors of architectural and agronomic traits such as seed yield potential (R 2 = 0.94), rachis weight (R 2 = 0.83), and seed shattering (R 2 = 0.85). Conclusions SpykProps is an open-source platform to characterize inflorescence architecture in a wide range of grasses. This imaging tool generates conventional and latent traits that can be used to better characterize developmental and agronomic traits associated with inflorescence architecture, and has applications in fields that include breeding, physiology, evolution, and development biology.
Why it matches plant phenotyping methodsイネ科花序の形態を画像から定量化するPythonベースの表現型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・抽出が研究の中心である。
abstractHere, we described SpykProps, an inexpensive Python-based imaging system to quantify morphological properties in unilateral inflorescences
Reproduction assets foundThe paper's SpykProps Python pipeline is openly available on GitHub, and the original/processed spike images, data files, and analysis code are deposited in the University of Minnesota DRUM repository. Both are paper-specific, public, and actionable.Code · publicSpykProps is an open-source program that can be accessed from https://github.com/joanmanbar/SpykProps along with detailed instructions to analyze single spikes using a Python integrated development environment, or to automate it on a set of images using Bash and the SpykBatch.py function.Open asset ↗joanmanbar/SpykPropslines:69-75Dataset · publicAll the original and processed images, along with the data files and code to analyze them, can be accessed through the Data Repository for University of Minnesota (DRUM) at https://hdl.handle.net/11299/256105 .Open asset ↗Data Repository for University of Minnesota (DRUM) · 11299/256105lines:134-257Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Measurements of rice physical traits, such as length, width, and percentage of filled/unfilled grains, are essential steps of rice breeding. A new approach for measuring the physical traits of rice grains for breeding purposes was presented in this study, utilizing image processing techniques. Backlight photography was used to capture a grayscale image of a group of rice grains, which was then analyzed using a clustering algorithm to differentiate between filled and unfilled grains based on their grayscale values. The impact of backlight intensity on the accuracy of the method was also investigated. The results show that the proposed method has excellent accuracy and high efficiency. The mean absolute percentage error of the method was 0.24% and 1.36% in calculating the total number of grain particles and distinguishing the number of filled grains, respectively. The grain size was also measured with a little margin of error. The mean absolute percentage error of grain length measurement was 1.11%, while the measurement error of grain width was 4.03%. The method was found to be highly accurate, non-destructive, and cost-effective when compared to conventional methods, making it a promising approach for characterizing physical traits for crop breeding.
Why it matches plant phenotyping methodsイネ籾の長さ・幅・充実度を画像処理で測定する方法を開発し、精度とバックライト条件の影響を検証しており、植物表現型取得が中心です。
abstractA new approach for measuring the physical traits of rice grains for breeding purposes was presented in this study, utilizing image processing techniques.
Reproduction assets foundThe paper's phenotype reference measurements (grain counts, filled/unfilled counts, and grain sizes for the validation experiments) are reported in Appendices A–C, which are included in the article's supplementary material, publicly available at the Frontiers supplementary-material URL. No author analysis code or imageSupplement · publicof their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.
Supplementary material
The Supplementary Material for this article can be found online at: https://www.frontiersin.org/articles/10.3389/fpls.2023.1213486/full#supplementary-material
Click here for additional data file.
References
Al-Tam F., Adam H., Anjos A. D., Lorieux M., Larmande P., Ghesquière A., et al. (2013). P-TRAP: a panicle trait phenotyping tool. BMC Plant Biol.
13 (1), 1–14. doi: 10.1186/1471-2229-13-122Open asset ↗lines:182-208Code / dataset availability confirmedEurope PMC · checked 7 Sept 2026
Phenotyping is used in plant breeding to identify genotypes with desirable characteristics, such as drought tolerance, disease resistance, and high-yield potentials. It may also be used to evaluate the effect of environmental circumstances, such as drought, heat, and salt, on plant growth and development. Wheat spike density measure is one of the most important agronomic factors relating to wheat phenotyping. Nonetheless, due to the diversity of wheat field environments, fast and accurate identification for counting wheat spikes remains one of the challenges. This study proposes a meticulously curated and annotated dataset, named as SPIKE-segm, taken from the publicly accessible SPIKE dataset, and an optimal instance segmentation approach named as WheatSpikeNet for segmenting and counting wheat spikes from field imagery. The proposed method is based on the well-known Cascade Mask RCNN architecture with model enhancements and hyperparameter tuning to provide state-of-the-art detection and segmentation performance. A comprehensive ablation analysis incorporating many architectural components of the model was performed to determine the most efficient version. In addition, the model's hyperparameters were fine-tuned by conducting several empirical tests. ResNet50 with Deformable Convolution Network (DCN) as the backbone architecture for feature extraction, Generic RoI Extractor (GRoIE) for RoI pooling, and Side Aware Boundary Localization (SABL) for wheat spike localization comprises the final instance segmentation model. With bbox and mask mean average precision (mAP) scores of 0.9303 and 0.9416, respectively, on the test set, the proposed model achieved superior performance on the challenging SPIKE datasets. Furthermore, in comparison with other existing state-of-the-art methods, the proposed model achieved up to a 0.41% improvement of mAP in spike detection and a significant improvement of 3.46% of mAP in the segmentation tasks that will lead us to an appropriate yield estimation from wheat plants.
Why it matches plant phenotyping methods小麦穂の圃場画像から穂をセグメンテーション・計数する画像解析手法と注釈付きデータセットを開発・評価しており、植物形質取得が研究の中心である。
abstractThis study proposes a meticulously curated and annotated dataset, named as SPIKE-segm, taken from the publicly accessible SPIKE dataset, and an optimal instance segmentation approach named as WheatSpikeNet for segmenting and counting wheat spikes from field imagery.
Reproduction assets foundThe paper's data availability statement explicitly deposits the authors' codebase and the curated SPIKE-segm wheat spike segmentation dataset in a public Figshare project, which qualifies as a paper-specific public asset. The Roboflow URL is only a cited generic tool and does not qualify.Dataset · publicThe codebase developed and the datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://figshare.com/projects/WheatSpikeNet_An_Improved_Wheat_Spike_Segmentation_Model_for_Accurate_Counting_from_Field_Imaging/163225 .Open asset ↗figshare · 163225lines:914-939Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Background: Inflorescence properties such length, spikelet number, and their spatial distribution across the rachis, are fundamental indicators of fitness and seed productivity in grasses, and have been a target of selection throughout domestication and crop improvement. However, quantifying such complex morphology is laborious, time-consuming, and commonly limited to human-perceived traits. These limitations can be exacerbated by unfavorable trait correlations between inflorescence architecture and seed yield that can be unconsciously selected for. Computer vision offers an alternative to conventional phenotyping, enabling higher throughput and reducing subjectivity. These approaches provide valuable insights into the determinants of seed yield, and thus, aid breeding decisions. Results Here, we described SpykProps, an inexpensive Python-based imaging system to quantify morphological properties in unilateral inflorescences, that was developed and tested on images of perennial grass ( Lolium perenne L.) spikes. SpykProps is able to rapidly and accurately identify spikes (RMSE < 1), estimate their length (R 2 = 0.96), and number of spikelets (R 2 = 0.61). It also quantifies color and shape from hundreds of interacting descriptors that are accurate predictors of architectural and agronomic traits such as seed yield potential (R 2 = 0.94), rachis weight (R 2 = 0.83), and seed shattering (R 2 = 0.85). Conclusions SpykProps is an open-source platform to characterize inflorescence architecture in a wide range of grasses. This imaging tool generates conventional and latent traits that can be used to better characterize developmental and agronomic traits associated with inflorescence architecture, and has applications in fields that include breeding, physiology, evolution, and development biology.
Why it matches plant phenotyping methodsイネ科花序の形態形質を画像から抽出するPythonベースの画像解析システムを開発・検証しており、植物フェノタイピング手法が研究の中心である。
abstractHere, we described SpykProps, an inexpensive Python-based imaging system to quantify morphological properties in unilateral inflorescences
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicSpykProps is an open-source program that can be accessed from https://github.com/joanmanbar/SpykProps along with detailed instructions to analyze single spikes using a Python integrated development environment, or to automate it on a set of images using Bash and the SpykBatch.py function.Open asset ↗joanmanbar/SpykPropslines:59-64Code / dataset availability confirmedEurope PMC · Crossref · checked 7 Sept 2026
Background Rust is a damaging disease affecting vital crops, including pea, and identifying highly resistant genotypes remains a challenge. Accurate measurement of infection levels in large germplasm collections is crucial for finding new resistance sources. Current evaluation methods rely on visual estimation of disease severity and infection type under field or controlled conditions. While they identify some resistance sources, they are error-prone and time-consuming. An image analysis system proves useful, providing an easy-to-use and affordable way to quickly count and measure rust-induced pustules on pea samples. This study aimed to develop an automated image analysis pipeline for accurately calculating rust disease progression parameters under controlled conditions, ensuring reliable data collection. Results A highly efficient and automatic image-based method for assessing rust disease in pea leaves was developed using R. The method's optimization and validation involved testing different segmentation indices and image resolutions on 600 pea leaflets with rust symptoms. The approach allows automatic estimation of parameters like pustule number, pustule size, leaf area, and percentage of pustule coverage. It reconstructs time series data for each leaf and integrates daily estimates into disease progression parameters, including latency period and area under the disease progression curve. Significant variation in disease responses was observed between genotypes using both visual ratings and image-based analysis. Among assessed segmentation indices, the Normalized Green Red Difference Index (NGRDI) proved fastest, analysing 600 leaflets at 60% resolution in 62 s with parallel processing. Lin's concordance correlation coefficient between image-based and visual pustule counting showed over 0.98 accuracy at full resolution. While lower resolution slightly reduced accuracy, differences were statistically insignificant for most disease progression parameters, significantly reducing processing time and storage space. NGRDI was optimal at all time points, providing highly accurate estimations with minimal accumulated error. Conclusions A new image-based method for monitoring pea rust disease in detached leaves, using RGB spectral indices segmentation and pixel value thresholding, improves resolution and precision. It rapidly analyses hundreds of images with accuracy comparable to visual methods and higher than other image-based approaches. This method evaluates rust progression in pea, eliminating rater-induced errors from traditional methods. Implementing this approach to evaluate large germplasm collections will improve our understanding of plant-pathogen interactions and aid future breeding for novel pea cultivars with increased rust resistance.
Why it matches plant phenotyping methodsエンドツーエンドのRGB画像解析パイプラインを開発・最適化・検証し、エンドウ葉のさび病症状と病勢進展を定量化する方法が研究の中心である。
abstractThis study aimed to develop an automated image analysis pipeline for accurately calculating rust disease progression parameters under controlled conditions, ensuring reliable data collection.
Reproduction assets foundThe authors deposited the R analysis script and the 600 pea leaflet images used in this rust phenotyping study in a public Zenodo repository, explicitly cited in the Data Availability statement and reference list.Dataset · publicThe datasets generated during and/or analysed during the current study are available in the Zenodo repository, https://doi.org/10.5281/zenodo.7991462 [ 93 ].Open asset ↗Zenodo · 10.5281/zenodo.7991462lines:147-229Code / dataset availability confirmedEurope PMC · checked 7 Sept 2026
Improving soybean ( Glycine max L. (Merr.)) yield is crucial for strengthening national food security. Predicting soybean yield is essential to maximize the potential of crop varieties. Non-destructive methods are needed to estimate yield before crop maturity. Various approaches, including the pod-count method, have been used to predict soybean yield, but they often face issues with the crop background color. To address this challenge, we explored the application of a depth camera to real-time filtering of RGB images, aiming to enhance the performance of the pod-counting classification model. Additionally, this study aimed to compare object detection models (YOLOV7 and YOLOv7-E6E) and select the most suitable deep learning (DL) model for counting soybean pods. After identifying the best architecture, we conducted a comparative analysis of the model's performance by training the DL model with and without background removal from images. Results demonstrated that removing the background using a depth camera improved YOLOv7's pod detection performance by 10.2% precision, 16.4% recall, 13.8% mAP@50, and 17.7% mAP@0.5:0.95 score compared to when the background was present. Using a depth camera and the YOLOv7 algorithm for pod detection and counting yielded a mAP@0.5 of 93.4% and mAP@0.5:0.95 of 83.9%. These results indicated a significant improvement in the DL model's performance when the background was segmented, and a reasonably larger dataset was used to train YOLOv7.
Why it matches plant phenotyping methods深度カメラと物体検出モデルを用いてダイズ莢数という植物形質を非破壊推定する手法を開発・比較・評価しており、表現型取得が中心的である。
abstractwe explored the application of a depth camera to real-time filtering of RGB images, aiming to enhance the performance of the pod-counting classification model.
Reproduction assets foundThe paper's Data Availability Statement points to an authors' public GitHub repository containing the datasets generated and analyzed (soybean depth-camera images and pod-count segmentation data). Other URLs (labelImg, scikit-learn, CC license) are generic tools/licenses, not paper-specific assets.Dataset · publicThe datasets generated and analyzed for this study can be found in the Github repository Soybean pod count depth segmentation project 2022 accessible at https://github.com/jithin8mathew/soybean_pod_count_Depth_segmentation_project (accessed on 28 June 2023).Open asset ↗jithin8mathew/soybean_pod_count_Depth_segmentation_projectlines:183-198Code / dataset availability confirmedOpenAlex · Europe PMC · Crossref · checked 15 Sept 2026
Abstract Background Significant effort has been made in manually tracking plant maturity and to measure early-stage plant density, and crop height in experimental breeding plots. Agronomic traits such as relative maturity (RM), stand count (SC) and plant height (PH) are essential to cultivar development, production recommendations and management practices. The use of RGB images collected via drones may replace traditional measurements in field trials with improved throughput, accuracy, and reduced cost. Recent advances in deep learning (DL) approaches have enabled the development of automated high-throughput phenotyping (HTP) systems that can quickly and accurately measure target traits using low-cost RGB drones. In this study, a time series of drone images was employed to estimate dry bean relative maturity (RM) using a hybrid model combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) for features extraction and capturing the sequential behavior of time series data. The performance of the Faster-RCNN object detection algorithm was also examined for stand count (SC) assessment during the early growth stages of dry beans. Various factors, such as flight frequencies, image resolution, and data augmentation, along with pseudo-labeling techniques, were investigated to enhance the performance and accuracy of DL models. Traditional methods involving pre-processing of images were also compared to the DL models employed in this study. Moreover, plant architecture was analyzed to extract plant height (PH) using digital surface model (DSM) and point cloud (PC) data sources. Results The CNN-LSTM model demonstrated high performance in predicting the RM of plots across diverse environments and flight datasets, regardless of image size or flight frequency. The DL model consistently outperformed the pre-processing images approach using traditional analysis (LOESS and SEG models), particularly when comparing errors using mean absolute error (MAE), providing less than two days of error in prediction across all environments. When growing degree days (GDD) data was incorporated into the CNN-LSTM model, the performance improved in certain environments, especially under unfavorable environmental conditions or weather stress. However, in other environments, the CNN-LSTM model performed similarly to or slightly better than the CNN-LSTM + GDD model. Consequently, incorporating GDD may not be necessary unless weather conditions are extreme. The Faster R-CNN model employed in this study was successful in accurately identifying bean plants at early growth stages, with correlations between the predicted SC and ground truth (GT) measurements of 0.8. The model performed consistently across various flight altitudes, and its accuracy was better compared to traditional segmentation methods using pre-processing images in OpenCV and the watershed algorithm. An appropriate growth stage should be carefully targeted for optimal results, as well as precise boundary box annotations. On average, the PC data source marginally outperformed the CSM/DSM data to estimating PH, with average correlation results of 0.55 for PC and 0.52 for CSM/DSM. The choice between them may depend on the specific environment and flight conditions, as the PH performance estimation is similar in the analyzed scenarios. However, the ground and vegetation elevation estimates can be optimized by deploying different thresholds and metrics to classify the data and perform the height extraction, respectively. Conclusions The results demonstrate that the CNN-LSTM and Faster R-CNN deep learning models outperforms other state-of-the-art techniques to quantify, respectively, RM and SC. The subtraction method proposed for estimating PH in the absence of accurate ground elevation data yielded results comparable to the difference-based method. In addition, open-source software developed to conduct the PH and RM analyses can contribute greatly to the phenotyping community.
Why it matches plant phenotyping methodsRGBドローン画像と深層学習を用いて、乾燥豆の成熟期、株数、草高を推定する手法を開発・比較・検証しており、表現型取得が研究の中心である。
abstractThe use of RGB images collected via drones may replace traditional measurements in field trials with improved throughput, accuracy, and reduced cost.
Reproduction assets foundThe preprint explicitly states that the authors' open-source phenotyping software (RM, SC, PH pipelines) is available on GitHub, with specific tools (matuRity, Vegetation index calculator, PlantHeightR, draw-plots-qgis) hosted at public URLs, and that the datasets (orthomosaics, shapefiles, ground notes, clipped plots,Code · publicle 2: Data S1). The GCPs were input and identified into the Pix4D project using the basic manual editor before initial processing.
R [ 57 ] software integrated with QGIS [ 58 ] was used to generate the polygon shapefiles according to plot boundary delimitation using the function ‘Draw plots from clicks’ available at https://github.com/diegojgris/draw-plots-qgis (Fig. 1 -b). Shapefiles were defined using images collected from the first flight available from each location. GDAL (Geospatial Data Abstraction Library) tool plugin in QGIS was used to spatial polygon vectors (or shapefiles) adjustments with a buffer zone for each plot to prevent any influence of neighboring plots. AdditOpen asset ↗diegojgris/draw-plots-qgislines:82-143Code · public3
4. DISCUSSION
The available open source HTP tools, matuRity [ 69 ], PlantHeightR [ 93 ], and Vegetation index calculator provided in this study, have the potential to facilitate and increase the data analysis performance in plant breeding and related areas. The user can either access them on-line or download the repository at https://github.com/msudrybeanbreeding?tab=repositories . Additionally, the step-by-step pipelines deployed in this study using DL methods are available at the GitHub repositories, as well as the complete data set used to perform the analysis including orthomosaics, shapefiles, ground notes, clipped plots, and programming codes. Thus, researchers may be able to replicaOpen asset ↗msudrybeanbreedinglines:572-648Code / dataset availability confirmedarXiv · OpenAlex · checked 15 Sept 2026
Automatic tree density estimation and counting using single aerial and satellite images is a challenging task in photogrammetry and remote sensing, yet has an important role in forest management. In this paper, we propose the first semisupervised transformer-based framework for tree counting which reduces the expensive tree annotations for remote sensing images. Our method, termed as TreeFormer, first develops a pyramid tree representation module based on transformer blocks to extract multi-scale features during the encoding stage. Contextual attention-based feature fusion and tree density regressor modules are further designed to utilize the robust features from the encoder to estimate tree density maps in the decoder. Moreover, we propose a pyramid learning strategy that includes local tree density consistency and local tree count ranking losses to utilize unlabeled images into the training process. Finally, the tree counter token is introduced to regulate the network by computing the global tree counts for both labeled and unlabeled images. Our model was evaluated on two benchmark tree counting datasets, Jiangsu, and Yosemite, as well as a new dataset, KCL-London, created by ourselves. Our TreeFormer outperforms the state of the art semi-supervised methods under the same setting and exceeds the fully-supervised methods using the same number of labeled images. The codes and datasets are available at https://github.com/HAAClassic/TreeFormer.
Why it matches plant phenotyping methods樹木の個体数・密度という植物状態を航空・衛星画像から推定する画像解析手法を開発し、複数データセットで評価しているため、植物フェノタイピング手法が中心である。
abstractAutomatic tree density estimation and counting using single aerial and satellite images is a challenging task
Reproduction assets foundThe paper's authors publicly release their analysis code and the KCL-London tree counting dataset via GitHub, and the paper's annotation workflow directly uses the public London Datastore local-authority-maintained trees dataset for tree locations.Code · publichmark tree counting datasets, Jiangsu, and Yosemite, as well as a new dataset, KCL-London, created by ourselves. Our TreeFormer outperforms the state of the art semi-supervised methods under the same setting and exceeds the fully-supervised methods using the same number of labeled images. The codes and datasets are available at https://github.com/HAAClassic/TreeFormer .
Index Terms:
Tree counting, semi-supervised model, transformer, pyramid learning strategy, remote sensing.
I Introduction
Trees are the pulse of the earth and are vital organisms in maintaining the ecological functioning and health of the planet [ 1 ] . Tree counting using high-resolution images is useful in various fields suOpen asset ↗HAAClassic/TreeFormerlines:1-71Dataset · publicmages are gathered and stitched together from Google Maps at 0.2 m ground sampling distance (GSD). The gathered images are divided into images with 1024 × 1024 pixels.
To aid the identification of tree locations and numbers of selected images, we employed the accessible tree locations of London in London Datastore website 1 1
1
https://data.london.gov.uk/dataset/local-authority-maintained-trees .
Although these data show the locations and species information for over 880,000 of London’s trees, the data mainly contains information on trees in the main streets and does not cover trees that are dense between houses or parks. We manually annotated the latter.
To this end, Global Mapper as geograOpen asset ↗lines:124-145Code / dataset availability confirmedEurope PMC · checked 13 Sept 2026
There is a growing body of literature that recognises the importance of UAVs in precision agriculture tasks. Currently, flowering thinning tasks in orchard management rely on the decisions derived from time-consuming manual flower cluster counting in the field by an agrotechnician. Yet it is hard to guarantee the counting accuracy due to numerous human factors. The present dataset contains UAV images during the full blooming period of an apple orchard for three consecutive years, 2018, 2019, and 2020. It is directly linked to a research article entitled "Feasibility assessment of tree-level flower intensity quantification from UAV RGB imagery: A triennial study in an apple orchard". The data collection site was an apple orchard located at Randwijk, Overbetuwe, The Netherlands (51.938, 5.7068 in WGS84 UTM 31U). Moreover, the flower cluster number and floridity ground truth are also provided in one row from the orchard. The UAV flights were conducted with different flying altitudes, camera resolutions, and lighting conditions. This dataset aims to support researchers focussing on remote sensing, machine vision, deep learning, and image classification, and the stakeholders interested in precision horticulture and orchard management. It can be used for flowering intensity estimation and prediction, and spatial and temporal flowering variability mapping by using digital photogrammetry and 3D reconstruction.
Why it matches plant phenotyping methodsリンゴ樹の開花強度という植物形質をUAV RGB画像から推定するための3年間の画像・地上真値データセットであり、再利用可能なフェノタイピング基盤として中心的です。
abstractThe present dataset contains UAV images during the full blooming period of an apple orchard for three consecutive years, 2018, 2019, and 2020.
Reproduction assets foundThis Data in Brief article describes the authors' own public Zenodo deposit containing the paper-specific UAV RGB images, flower cluster/floridity ground truth, and GCP files for the apple orchard flowering monitoring study, with direct download URL provided.Dataset · publicRepository name: Zenodo
Data identification number: https://doi.org/10.5281/zenodo.6802308
Direct URL to data: https://zenodo.org/record/6802308#.YvvMFuxBz0pOpen asset ↗Zenodo · 10.5281/zenodo.6802308lines:1-51Code / dataset availability confirmedCrossref · checked 15 Sept 2026
Fusarium ear rot (FER) is a common disease in maize caused by the pathogen Fusarium verticillioides. Because of the quantitative nature of the disease, scoring disease severity is difficult and nuanced, relying on various ways to quantify the damage caused by the pathogen. Towards the goal of designing a system with greater objectivity, reproducibility, and accuracy than subjective scores or estimations of the infected area, a system of semi-automated image acquisition and subsequent image analysis was designed. The tool created for image acquisition, “The Ear Unwrapper”, successfully obtained images of the full exterior of maize ears. A set of images produced from The Ear Unwrapper was then used as an example of how machine learning could be used to estimate disease severity from unannotated images. A high correlation (0.74) was found between the methods estimating the area of disease, but low correlations (0.47 and 0.28) were found between the number of infected kernels and the area of disease, indicating how different methods can result in contrasting severity scores. This study provides an example of how a simplified image acquisition tool can be built and incorporated into a machine learning pipeline to measure phenotypes of interest. We also present how the use of machine learning in image analysis can be adapted from open-source software to estimate complex phenotypes such as Fusarium ear rot.
Why it matches plant phenotyping methodsトウモロコシ雌穂の病徴画像取得装置と画像解析・機械学習による病害重症度推定を開発しており、表現型取得法が研究の中心である。
abstracta system of semi-automated image acquisition and subsequent image analysis was designed
Reproduction assets foundThe authors publicly deposited the codebase for The Ear Unwrapper image acquisition pipeline on GitHub, which is the paper-specific computational/hardware asset for this phenotyping study. The raw phenotype data (Supplemental Table S1) is hosted as an MDPI supplement rather than a separate repository, and the Ilastik/GCode · publiciculture–National Institute of Food and Agriculture Tactical Sciences for Agricultural Biosecurity
Institute of Food and Agricultural Sciences Project 13117320.
Data Availability Statement: The raw dataset used to generate these results can be found in Sup-
plemental Table S1. The codebase for The Ear Unwrapper can be found at (https://github.com/ohudson1/The-Ear-Unwrapper-.git (accessed on 24 May 2023)). All code used is open source and
code bases for both Ilastik (https://github.com/ilastik (accessed on 1 January 2023)).
Acknowledgments: Marcio Resende and the Sweetcorn Lab for assistance with the field trials.
Conflicts of Interest: The authors declare no conflict of interest.
AbbreviatioOpen asset ↗ohudson1/The-Ear-Unwrapper-pdf-raw-page:9 lines:1-50Code / dataset availability confirmedEurope PMC · OpenAlex · checked 14 Sept 2026
Data competitions have become a popular approach to crowdsource new data analysis methods for general and specialized data science problems. Data competitions have a rich history in plant phenotyping, and new outdoor field datasets have the potential to embrace solutions across research and commercial applications. We developed the Global Wheat Challenge as a generalization competition in 2020 and 2021 to find more robust solutions for wheat head detection using field images from different regions. We analyze the winning challenge solutions in terms of their robustness when applied to new datasets. We found that the design of the competition had an influence on the selection of winning solutions and provide recommendations for future competitions to encourage the selection of more robust solutions.
Why it matches plant phenotyping methods圃場画像からコムギ穂を検出・計数するモデルのチャレンジ設計と、異なるデータセットへの頑健性評価を中心に扱うため、画像ベースの表現型解析手法・ベンチマーク研究に該当します。
abstractWe developed the Global Wheat Challenge as a generalization competition in 2020 and 2021 to find more robust solutions for wheat head detection using field images from different regions.
Reproduction assets foundThe paper's wheat head detection analysis relies on two paper-specific public assets: the Global Wheat Head Dataset 2021 (annotated field RGB images used for training/testing the challenge solutions) openly deposited on Zenodo, and the winning challenge solutions' code made open-source on GitHub. Both have explicit, inDataset · publiccquisition. W.G., F.B., and I.S. participated in the design of the challenges and data analysis. All authors participated in the writing of the paper. Competing interes ts: The authors declare that there is no conflict of interest regarding the publication of this article.
Data Availability
The GWHD 2021 can be downloaded here: https://zenodo.org/record/5092309#.YrvsTBXP2Uk
Supplementary Materials
Supplementary 1
Sections S1 to S4
Figs. S1 to S2
Tables S1 to S3
References [ 45 , 46 ]
Click here for additional data file.
References
1.
Gao
H , Barbier
G , Goolsby
R
.
Harnessing the crowdsourcing power of social media for disaster relief
. IEEE Intell Syst . 2011 ; 26 ( 3 ): 10 – 14 .
2.
Prill
Open asset ↗Zenodo · 5092309lines:381-537Code / dataset availability confirmedEurope PMC · checked 7 Sept 2026
With the increasing popularity of online fruit sales, accurately predicting fruit yields has become crucial for optimizing logistics and storage strategies. However, existing manual vision-based systems and sensor methods have proven inadequate for solving the complex problem of fruit yield counting, as they struggle with issues such as crop overlap and variable lighting conditions. Recently CNN-based object detection models have emerged as a promising solution in the field of computer vision, but their effectiveness is limited in agricultural scenarios due to challenges such as occlusion and dissimilarity among the same fruits. To address this issue, we propose a novel variant model that combines the self-attentive mechanism of Vision Transform, a non-CNN network architecture, with Yolov7, a state-of-the-art object detection model. Our model utilizes two attention mechanisms, CBAM and CA, and is trained and tested on a dataset of apple images. In order to enable fruit counting across video frames in complex environments, we incorporate two multi-objective tracking methods based on Kalman filtering and motion trajectory prediction, namely SORT, and Cascade-SORT. Our results show that the Yolov7-CA model achieved a 91.3% mAP and 0.85 F1 score, representing a 4% improvement in mAP and 0.02 improvement in F1 score compared to using Yolov7 alone. Furthermore, three multi-object tracking methods demonstrated a significant improvement in MAE for inter-frame counting across all three test videos, with an 0.642 improvement over using yolov7 alone achieved using our multi-object tracking method. These findings suggest that our proposed model has the potential to improve fruit yield assessment methods and could have implications for decision-making in the fruit industry.
Why it matches plant phenotyping methodsリンゴ果実を画像から検出・追跡して収量（果実数）を推定する手法を開発・評価しており、植物表現型取得が研究の中心です。
titleFruit Detection and Counting in Apple Orchards Based on Improved Yolov7 and Multi-Object Tracking Methods.
Reproduction assets foundThe paper's apple detection/counting dataset was assembled from publicly available sources, and the Data Availability Statement explicitly links the public tropical fruit dataset of Pawara et al. used as image input. No author analysis code, trained model checkpoints, or paper-specific supplements are disclosed.Dataset · publicPublicly available datasets were analyzed in this study. This data can be found here: https://www.ai.rug.nl/~p.pawara/ (accessed on 23 May 2023).Open asset ↗lines:234-247Code / dataset availability confirmedEurope PMC · checked 7 Sept 2026
Multicellular organisms result from complex developmental processes largely orchestrated through the quantitative spatiotemporal regulation of gene expression. Yet, obtaining absolute counts of messenger RNAs at a three-dimensional resolution remains challenging, especially in plants, owing to high levels of tissue autofluorescence that prevent the detection of diffraction-limited fluorescent spots. In situ hybridization methods based on amplification cycles have recently emerged, but they are laborious and often lead to quantification biases. In this article, we present a simple method based on single-molecule RNA fluorescence in situ hybridization to visualize and count the number of mRNA molecules in several intact plant tissues. In addition, with the use of fluorescent protein reporters, our method also enables simultaneous detection of mRNA and protein quantity, as well as subcellular distribution, in single cells. With this method, research in plants can now fully explore the benefits of the quantitative analysis of transcription and protein levels at cellular and subcellular resolution in plant tissues.
Why it matches plant phenotyping methods植物組織内のmRNA・タンパク質量を細胞および細胞内解像度で可視化・定量するsmFISH法の開発であり、植物の状態を測定する方法が中心的です。
abstractIn this article, we present a simple method based on single-molecule RNA fluorescence in situ hybridization to visualize and count the number of mRNA molecules in several intact plant tissues.
Reproduction assets foundThe authors openly deposited all raw microscopy images (WM-smFISH mRNA/protein imaging of Arabidopsis and barley tissues) used for their quantification pipeline on Figshare. No separate author analysis code repository with explicit availability language is stated in the supplied text.Dataset · publicAll the raw microscopy images used in this manuscript are openly available in Figshare at https://doi.org/10.6084/m9.figshare.22699132 .Open asset ↗Figshare · 10.6084/m9.figshare.22699132lines:110-216Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Background The flowering period is a critical time for the growth of rape plants. Counting rape flower clusters can help farmers to predict the yield information of the corresponding rape fields. However, counting in-field is a time-consuming and labor-intensive task. To address this, we explored a deep learning counting method based on unmanned aircraft vehicle (UAV). The proposed method developed the in-field counting of rape flower clusters as a density estimation problem. It is different from the object detection method of counting the bounding boxes. The crucial step of the density map estimation using deep learning is to train a deep neural network that maps from an input image to the corresponding annotated density map. Results We explored a rape flower cluster counting network series: RapeNet and RapeNet+. A rectangular box labeling-based rape flower clusters dataset (RFRB) and a centroid labeling-based rape flower clusters dataset (RFCP) were used for network model training. To verify the performance of RapeNet series, the paper compares the counting result with the real values of manual annotation. The average accuracy (Acc), relative root mean square error (rrMSE) and [Formula: see text] of the metrics are up to 0.9062, 12.03 and 0.9635 on the dataset RFRB, and 0.9538, 5.61 and 0.9826 on the dataset RFCP, respectively. The resolution has little influence for the proposed model. In addition, the visualization results have some interpretability. Conclusions Extensive experimental results demonstrate that the RapeNet series outperforms other state-of-the-art counting approaches. The proposed method provides an important technical support for the crop counting statistics of rape flower clusters in field.
Why it matches plant phenotyping methodsUAV-RGB画像から菜種の花房数という植物器官形質を推定する深層学習手法を開発・評価しており、フェノタイピング手法が中心である。
abstractwe explored a deep learning counting method based on unmanned aircraft vehicle (UAV).
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicThe codes, datasets RFRB and RFCP used in the study are available online at: https://github.com/CV-Wang/RapeNet .Open asset ↗CV-Wang/RapeNetlines:216-232Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Flowering is a crucial developing stage for rapeseed ( Brassica napus L.) plants. Flowers develop on the main and branch inflorescences of rapeseed plants and then grow into siliques. The seed yield of rapeseed heavily depends on the total flower numbers per area throughout the whole flowering period. The number of rapeseed inflorescences can reflect the richness of rapeseed flowers and provide useful information for yield prediction. To count rapeseed inflorescences automatically, we transferred the counting problem to a detection task. Then, we developed a low-cost approach for counting rapeseed inflorescences using YOLOv5 with the Convolutional Block Attention Module (CBAM) based on unmanned aerial vehicle (UAV) Red-Green-Blue (RGB) imagery. Moreover, we constructed a Rapeseed Inflorescence Benchmark (RIB) to verify the effectiveness of our model. The RIB dataset captured by DJI Phantom 4 Pro V2.0, including 165 plot images and 60,000 manual labels, is to be released. Experimental results showed that indicators R 2 for counting and the mean Average Precision (mAP) for location were over 0.96 and 92%, respectively. Compared with Faster R-CNN, YOLOv4, CenterNet, and TasselNetV2+, the proposed method achieved state-of-the-art counting performance on RIB and had advantages in location accuracy. The counting results revealed a quantitative dynamic change in the number of rapeseed inflorescences in the time dimension. Furthermore, a significant positive correlation between the actual crop yield and the automatically obtained rapeseed inflorescence total number on a field plot level was identified. Thus, a set of UAV- assisted methods for better determination of the flower richness was developed, which can greatly support the breeding of high-yield rapeseed varieties.
Why it matches plant phenotyping methodsUAV RGB画像と深層学習を用いてナタネの花序数を自動計数する手法を開発し、ベンチマークデータセットで検証しているため、植物表現型取得が中心である。
abstractwe developed a low-cost approach for counting rapeseed inflorescences using YOLOv5 with the Convolutional Block Attention Module (CBAM) based on unmanned aerial vehicle (UAV) Red-Green-Blue (RGB) imagery.
Reproduction assets foundThe paper's Rapeseed Inflorescence Benchmark (RIB) — 165 UAV RGB plot images with 60,000 manual inflorescence labels used for the counting model — is stated as publicly available at the authors' GitHub repository. The YOLOv5 repository is a generic third-party library, not a paper-specific asset.Dataset · publicg. Considering the insufficient data of the whole flowering period, we will increase the sampling frequency in flowering period to better fit the change curve of the number of rapeseed inflorescences in future work.
Data availability statement
Publicly available datasets were analyzed in this study. This data can be found here: https://github.com/LYLWYH/Rapeseed-Data .
Author contributions
All authors made significant contributions to this manuscript. JL, YL, and JQ performed field data collection and wrote the manuscript. JQ and LL designed the experiment. JY, XW, and GL provided suggestions on the experiment design. All authors read and approved the final manuscript.
Acknowledgments
A larOpen asset ↗LYLWYH/Rapeseed-Datalines:437-471Code / dataset availability confirmedEurope PMC · Crossref · checked 7 Sept 2026
Rice plant counting is crucial for many applications in rice production, such as yield estimation, growth diagnosis, disaster loss assessment, etc. Currently, rice counting still heavily relies on tedious and time-consuming manual operation. To alleviate the workload of rice counting, we employed an UAV (unmanned aerial vehicle) to collect the RGB images of the paddy field. Then, we proposed a new rice plant counting, locating, and sizing method (RiceNet), which consists of one feature extractor frontend and 3 feature decoder modules, namely, density map estimator, plant location detector, and plant size estimator. In RiceNet, rice plant attention mechanism and positive-negative loss are designed to improve the ability to distinguish plants from background and the quality of the estimated density maps. To verify the validity of our method, we propose a new UAV-based rice counting dataset, which contains 355 images and 257,793 manual labeled points. Experiment results show that the mean absolute error and root mean square error of the proposed RiceNet are 8.6 and 11.2, respectively. Moreover, we validated the performance of our method with two other popular crop datasets. On these three datasets, our method significantly outperforms state-of-the-art methods. Results suggest that RiceNet can accurately and efficiently estimate the number of rice plants and replace the traditional manual method.
Why it matches plant phenotyping methodsUAV画像からイネ個体の位置・サイズ・個体数を推定する手法RiceNetを開発し、データセット構築と性能検証まで行っており、植物表現型取得が研究の中心です。
abstractwe proposed a new rice plant counting, locating, and sizing method (RiceNet)
Reproduction assets foundThe paper explicitly states that all RiceNet source code is publicly available at the authors' GitHub repository. The URC dataset (355 UAV images, 257,793 labeled points) is described but no explicit public deposit URL is given, so it is not listed as an actionable asset.Code · publicAll the source code of RiceNet is available at https://github.com/xdbai-source/Rice-Plant-Counting .Open asset ↗xdbai-source/Rice-Plant-Countinglines:51-58Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
RiceSeed / grainCountingSegmentationGrowth / development / phenology
The germination rate of rice grain is recognized as one of the most significant indicators of seed quality assessment. Currently, grain germination rate is generally determined manually by experienced researchers, which is time-consuming and labor-intensive. In this paper, a new method is proposed for counting the number of grains and germinated grains. In the coarse segmentation process, the k-means clustering algorithm is applied to obtain rough grain-connected regions. We further refine the segmentation results obtained by the k-means algorithm using a one-dimensional Gaussian filter and a fifth-degree polynomial. Next, the optimal single grain area is determined based on the area distribution curve. Accordingly, the number of grains contained in the connected region is equal to the area of the connected region divided by the optimal single grain area. Finally, a novel algorithm is proposed for counting germinated grains. This algorithm is based on the idea that the length of the intersection between the germ and the grain is less than the circumference of the germ. The experimental results show that the mean absolute error of the proposed method for germination rate is 2.7%. And the performance of the proposed method is robust to changes in grain number, grain varieties, scale, illumination, and rotation.
Why it matches plant phenotyping methodsイネ種子の発芽率という植物形質を画像処理で自動抽出・定量する手法を開発し、誤差と頑健性を評価しており、表現型取得法が中心である。
abstractIn this paper, a new method is proposed for counting the number of grains and germinated grains.
Reproduction assets foundThe paper's Data Availability statement explicitly deposits the authors' analysis code and the 90 rice grain images used for germination-rate phenotyping in a public GitHub repository, matching an allowed URL. The web application URL is a live service, not a deposited asset, and is excluded.Code · publicges of Luyou 911 and the germination detection results.
(DOCX)
Click here for additional data file.
Acknowledgments
We are deeply grateful to the editor and reviewers for their assistance with reviews and guidance of the paper.
Data Availability
The code and 90 images used in this study are available from our GitHub repository: https://github.com/DoctorXiong123456/CodeOfPaper .
Funding Statement
This study was supported by the National Natural Science Foundation of China (Grants No. 61373004). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
References
1. Wu W, Zhou L, Chen J, Qiu Z, He Y. GainTKW: a measurement sysOpen asset ↗DoctorXiong123456/CodeOfPaperlines:233-285Dataset · publicmages of II you 534 and the germination detection results.
(DOCX)
Click here for additional data file.
S3 Table
30 images of Luyou 911 and the germination detection results.
(DOCX)
Click here for additional data file.
Data Availability Statement
The code and 90 images used in this study are available from our GitHub repository: https://github.com/DoctorXiong123456/CodeOfPaper .Open asset ↗DoctorXiong123456/CodeOfPaperlines:286-308Code / dataset availability confirmedEurope PMC · Crossref · checked 8 Sept 2026
SoybeanField / plotRootSeed / grainCountingGrowth / development / phenologyRoot system architecture
The symbiotic relationship between soybean [ Glycine max L. (Merr.)] roots and bacteria ( Bradyrhizobium japonicum ) lead to the development of nodules, important legume root structures where atmospheric nitrogen (N 2 ) is fixed into bio-available ammonia (NH 3 ) for plant growth and development. With the recent development of the Soybean Nodule Acquisition Pipeline (SNAP), nodules can more easily be quantified and evaluated for genetic diversity and growth patterns across unique soybean root system architectures. We explored six diverse soybean genotypes across three field year combinations in three early vegetative stages of development and report the unique relationships between soybean nodules in the taproot and non-taproot growth zones of diverse root system architectures of these genotypes. We found unique growth patterns in the nodules of taproots showing genotypic differences in how nodules grew in count, size, and total nodule area per genotype compared to non-taproot nodules. We propose that nodulation should be defined as a function of both nodule count and individual nodule area resulting in a total nodule area per root or growth regions of the root. We also report on the relationships between the nodules and total nitrogen in the seed at maturity, finding a strong correlation between the taproot nodules and final seed nitrogen at maturity. The applications of these findings could lead to an enhanced understanding of the plant- Bradyrhizobium relationship and exploring these relationships could lead to leveraging greater nitrogen use efficiency and nodulation carbon to nitrogen production efficiency across the soybean germplasm.
Why it matches plant phenotyping methodsSNAPという機械学習ベースの表現型取得・解析パイプラインを用いて、根粒数・サイズ・面積を定量化することが研究の中心的手法として明示されている。
titleUsing machine learning enabled phenotyping to characterize nodulation in three early vegetative stages in soybean
Reproduction assets foundThe paper states that all data and code will be shared through the authors' Singh group GitHub. This is the only paper-specific availability statement; it points to a lab-level GitHub organization rather than a specific repository, and uses future tense ('will be shared'), so the exact deposit for this paper's nod phenCode · publicAll data and code will be shared through the Singh group GitHub https://github.com/SoylabSingh .Open asset ↗SoylabSinghlines:1171-1263Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Counting the number of grape bunches at an early stage of development offers relevant information to the winegrower about the potential yield to be harvested. However, manual counting on the fields is laborious and time-consuming. Remote sensing, and more precisely unmanned aerial vehicles mounted with RGB or multispectral cameras, facilitate this task rapidly and accurately. This dataset contains 40 RGB videos from a 1.06-ha vineyard located in northern Spain. Moreover, the dataset includes mask labels of visible grape bunches. The videos were acquired throughout four UAV flights with an RGB camera tilted at 60 degrees. Each flight recorded one side of a row of the vineyard. The grape berries were between pea-size (BBCH75) and bunch closure (BBCH79) stage, which is two months before harvesting. No operations other than those usual in a commercial vineyard, such as pruning, cane tying, fertilization, and pest treatment, have been carried out, hence, the dataset presents leaf occlusion. The dataset was gathered and labelled to train object detection and tracking algorithms for grape bunch counting. Furthermore, it eases the work of winegrowers to check the sanitary status of the vineyard.
Why it matches plant phenotyping methodsブドウ房数という植物の収量関連形質をUAV画像から推定するための、ラベル付き動画データセットであり、物体検出・追跡手法の開発を支援する中心的な成果である。
abstractThis dataset contains 40 RGB videos from a 1.06-ha vineyard located in northern Spain. Moreover, the dataset includes mask labels of visible grape bunches.
Reproduction assets foundThis Data in Brief article describes its own public dataset: 40 UAV RGB videos over a vineyard with grape bunch mask annotations (MOTS-style PNG labels) for object detection/tracking and phenotyping, deposited on Zenodo with an explicit direct URL and DOI. This is a paper-specific, publicly available, directly reproducDataset · publice location
Institution: Wageningen University & Research
City/Town/Region: Tomiño, Pontevedra, Galicia
Country: Spain
Latitude and longitude (and GPS coordinates) for collected samples/data:
41°57′18.3″N 8°47′41.9″W
Data accessibility
Repository name: Zenodo
Data identification number: 10.5281/zenodo.7330951
Direct URL to data: https://zenodo.org/record/7330951#.Y3tU3nbMKUk
Related research article
Ariza-Sentís, M., Vélez, S., Baja, H., & Valente, J. (2022). IPPS 2022 Conference Book . 231.
Value of the Data
•
Dataset is useful for researchers interested in instance segmentation, as it allows the detection and tracking of the clusters [2] .
•
Dataset can be employed to count the number of viOpen asset ↗Zenodo · 10.5281/zenodo.7330951lines:1-68Code / dataset availability confirmedEurope PMC · checked 8 Sept 2026
Background Cyst nematodes are one of the major groups of plant-parasitic nematode, responsible for considerable crop losses worldwide. Improving genetic resources, and therefore resistant cultivars, is an ongoing focus of many pest management strategies. One of the major bottlenecks in identifying the plant genes that impact the infection, and thus the yield, is phenotyping. The current available screening method is slow, has unidimensional quantification of infection limiting the range of scorable parameters, and does not account for phenotypic variation of the host. The ever-evolving field of computer vision may be the solution for both the above-mentioned issues. To utilise these tools, a specialised imaging platform is required to take consistent images of nematode infection in quick succession. Results Here, we describe an open-source, easy to adopt, imaging hardware and trait analysis software method based on a pre-existing nematode infection screening method in axenic culture. A cost-effective, easy-to-build and -use, 3D-printed imaging device was developed to acquire images of the root system of Arabidopsis thaliana infected with the cyst nematode Heterodera schachtii, replacing costly microscopy equipment. Coupling the output of this device to simple analysis scripts allowed the measurement of some key traits such as nematode number and size from collected images, in a semi-automated manner. Additionally, we used this combined solution to quantify an additional trait, root area before infection, and showed both the confounding relationship of this trait on nematode infection and a method to account for it. Conclusion Taken together, this manuscript provides a low-cost and open-source method for nematode phenotyping that includes the biologically relevant nematode size as a scorable parameter, and a method to account for phenotypic variation of the host. Together these tools highlight great potential in aiding our understanding of nematode parasitism.
Why it matches plant phenotyping methods根系感染像の取得プラットフォームと画像解析ソフトウェアを開発し、線虫数・サイズや感染前根面積を測定する手法が研究の中心であるため。
abstractwe describe an open-source, easy to adopt, imaging hardware and trait analysis software method
Reproduction assets foundThe paper's authors publicly release the imaging tower hardware design (STL files) and all ImageJ/Python analysis scripts used for nematode counting, root area quantification, and colour normalization in a GitHub repository, explicitly stated in the Availability of data and materials section.Code · publicAll scripts used in this experiment are available under the following github repository: https://github.com/OlafKranse/A_low_cost_imaging_tower .Open asset ↗OlafKranse/A_low_cost_imaging_towerlines:141-197Code / dataset availability confirmedarXiv · OpenAlex · checked 15 Sept 2026
In this paper, we present a method for creating high-quality 3D models of sorghum panicles for phenotyping in breeding experiments. This is achieved with a novel reconstruction approach that uses seeds as semantic landmarks in both 2D and 3D. To evaluate the performance, we develop a new metric for assessing the quality of reconstructed point clouds without having a ground-truth point cloud. Finally, a counting method is presented where the density of seed centers in the 3D model allows 2D counts from multiple views to be effectively combined into a whole-panicle count. We demonstrate that using this method to estimate seed count and weight for sorghum outperforms count extrapolation from 2D images, an approach used in most state of the art methods for seeds and grains of comparable size.
Why it matches plant phenotyping methodsソルガム穂の3D再構成と種子計数という植物形質取得手法を開発し、再構成品質評価指標と種子数・重量推定を検証しており、フェノタイピング手法が中心である。
abstractwe present a method for creating high-quality 3D models of sorghum panicles for phenotyping in breeding experiments
Reproduction assets foundThe paper's authors publicly release their sorghum panicle stereo-image dataset (camera poses, human-labeled seed segmentations, panicle weights, seed counts) via the CMU AIIRA resources page, which is an allowed URL.Dataset · publicection, some unremoved husks were counted as seeds by the counting machine despite manual efforts to separate seeds from husks. We expect the effect on the ground truth to be small. The stereo images, camera poses, human-labeled seed segmentations, panicle weights, and human-counted seed counts can be found in our dataset 3 3
3
https://labs.ri.cmu.edu/aiira/resources/ .
Figure 8: (a) 100 sorghum panicles from 10 different sorghum species. (b) Our data collection system, a stereo camera attached to the UR5 robot arm. (c) Seeds were manually stripped and (d) counted using a seed counting machine.
IV-B 3D Reconstruction Quality
We assess the effectiveness of our approach with ablation tests usiOpen asset ↗lines:141-165Code / dataset availability confirmedOpenAlex · Europe PMC · checked 14 Sept 2026
Unmanned aerial vehicle (UAV)-based imagery has become widely used in collecting agronomic traits, enabling a much greater volume of data to be generated in a time-series manner. As one of the cutting-edge imagery analysis tools, machine learning-based object detection provides automated techniques to analyze these imagery data. In our previous study, UAVs have been used to collect aerial photography for field trials of 233 diverse inbred lines, grown under different nitrogen treatments. Images were collected during different plant developmental stages throughout the growing season. This dataset of images has here been used in developing machine learning techniques to obtain automated tassel counts at the plot level through the season. To improve detection accuracy, we have developed an image segmentation method to remove non-tassel pixels and then feed these filtered images into machine learning algorithms. As a result, our method showed a significant improvement in the accuracy of maize tassel detection. This method can be used in future research to produce time-series counts of tassels at the plot level, and will allow for accurate estimates of flowering-related traits, such as the earliest detected flowering date and the duration of each plot's flowering period. This phenotypic data and the trait-associated genes provide new opportunities for crop improvement and to facilitate future plant breeding.
Why it matches plant phenotyping methodsUAV画像からトウモロコシの雄穂数と開花関連形質を自動推定する画像分割・機械学習手法の開発が中心であり、植物表現型測定法に該当する。
abstractThis dataset of images has here been used in developing machine learning techniques to obtain automated tassel counts at the plot level through the season.
Reproduction assets foundThe paper's UAV imagery, plot-level images, and metadata are publicly deposited in CyVerse under DOI 10.25739/4t1v-ab64, per the Data Availability Statement. No author analysis code or trained model checkpoints are reported as publicly available.Dataset · publicThe original UAV images, the clipped plot-level images, and the associated metadata used in this study
have been deposited in CyVerse (10.25739/4t1v-ab64).Open asset ↗CyVerse · 10.25739/4t1v-ab64pdf-raw-page:5 lines:1-39Code / dataset availability confirmedEurope PMC · checked 8 Sept 2026
Pollen grains, the male gametophytes for reproduction in higher plants, are vulnerable to various stresses that lead to loss of viability and eventually crop yield. A conventional method for assessing pollen viability is manual counting after staining, which is laborious and hinders high-throughput screening. We developed an automatic detection tool (PollenDetect) to distinguish viable and nonviable pollen based on the YOLOv5 neural network, which is adjusted to adapt to the small target detection task. Compared with manual work, PollenDetect significantly reduced detection time (from approximately 3 min to 1 s for each image). Meanwhile, PollenDetect can maintain high detection accuracy. When PollenDetect was tested on cotton pollen viability, 99% accuracy was achieved. Furthermore, the results obtained using PollenDetect show that high temperature weakened cotton pollen viability, which is highly similar to the pollen viability results obtained using 2,3,5-triphenyltetrazolium formazan quantification. PollenDetect is an open-source software that can be further trained to count different types of pollen for research purposes. Thus, PollenDetect is a rapid and accurate system for recognizing pollen viability status, and is important for screening stress-resistant crop varieties for the identification of pollen viability and stress resistance genes during genetic breeding research.
Why it matches plant phenotyping methods植物花粉の生存性という状態を画像から自動推定する深層学習ツールを開発し、手動計数および染色法と精度・速度を比較検証しているため、方法が研究の中心である。
abstractWe developed an automatic detection tool (PollenDetect) to distinguish viable and nonviable pollen based on the YOLOv5 neural network, which is adjusted to adapt to the small target detection task.
Reproduction assets foundThe paper's PollenDetect source code and model details are openly available on the authors' GitHub repository, as stated in the Data Availability Statement. The supplement describes dataset composition and annotation but does not explicitly state it contains the pollen images/annotations themselves, so only the code/reCode · publicDetails and source code of the PollenDetect model used in this study are openly available at https://github.com/Tanzhihao1998/Identification-of-pollen-activity.git/ (accessed on 1 April 2022).Open asset ↗https://github.com/Tanzhihao1998/Identification-of-pollen-activity.git/lines:99-142Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Background Researchers interested in the seed size of rapeseed need to quantify the cell size and number of cells in the seed coat, embryo and silique wall. Scanning electron microscope-based methods have been demonstrated to be feasible but laborious and costly. After image preparation, the cell parameters are generally evaluated manually, which is time consuming and a major bottleneck for large-scale analysis. Recently, two machine learning-based algorithms, Trainable Weka Segmentation (TWS) and Cellpose, were released to overcome this long-standing problem. Moreover, the MorphoLibJ and LabelsToROIs plugins in Fiji provide user-friendly tools to deal with cell segmentation files. We attempted to verify the practicability and efficiency of these advanced tools for various types of cells in rapeseed. Results We simplified the current image preparation procedure by skipping the fixation step and demonstrated the feasibility of the simplified procedure. We developed three methods to automatically process multicellular images of various tissues in rapeseed. The TWS-Fiji (TF) method combines cell detection with TWS and cell measurement with Fiji, enabling the accurate quantification of seed coat cells. The Cellpose-Fiji (CF) method, based on cell segmentation with Cellpose and quantification with Fiji, achieves good performance but exhibits systematic error. By removing border labels with MorphoLibJ and detecting regions of interest (ROIs) with LabelsToROIs, the Cellpose-MorphoLibJ-LabelsToROIs (CML) method achieves human-level performance on bright-field images of seed coat cells. Intriguingly, the CML method needs very little manual calibration, a property that makes it suitable for massive-scale image processing. Through a large-scale quantitative evaluation of seed coat cells, we demonstrated the robustness and high efficiency of the CML method at both the single-cell level and the sample level. Furthermore, we extended the application of the CML method to developing seed coat, embryo and silique wall cells and acquired highly precise and reliable results, indicating the versatility of this method for use in multiple scenarios. Conclusions The CML method is highly accurate and free of the need for manual correction. Hence, it can be applied for the low-cost, high-throughput quantification of diverse cell types in rapeseed with high efficiency. We envision that this method will facilitate the functional genomics and microphenomics studies of rapeseed and other crops.
Why it matches plant phenotyping methodsアブラナの種皮・胚・長角果壁の細胞形質を画像から自動定量する手法を開発・検証しており、フェノタイピング手法が研究の中心です。
abstractWe developed three methods to automatically process multicellular images of various tissues in rapeseed.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Dataset · publicA cell image of 30 DAF silique wall acquired under 100 × optical microscope.Open asset ↗lines:547-634Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Field / plotMicroscopyClassificationCountingMorphology / geometry measurement
Stingless bees are effective pollinators of native tropical flora. Their environmental service maintains flow of pollen through pollination, increase reproductive success and influence genetic structure in plants. The management of stingless bees "meliponiculture", is an activity limited to the countryside in Ecuador. The lack of knowledge of their managers about pollen resources can affect the correct maintenance/production of nests. The objective is to identify botanical families and genera of pollen grains collected by stingless bees by morphological features and differentiate potential species using geometric morphometry. Thirty-six pot pollen samples were collected from three Ecuadorian provinces located in two climatically different zones. Pollen type identification was based on the Number, Position, Character system. Using morphological features, the families and genera were established. Morphometry landmarks were used to show variation for species differentiation. Abundance, diversity, similarity and dominance indices were established by counting pollen grains, as well as spatial distribution relationships by means of Poisson regression. Forty-six pollen types were determined in two study areas, classified into 27 families and 18 genera. In addition, it was possible to identify more than one species, classified within the same family and genus, thanks to morphometric analysis. 1148 ± 799 (max 4211; min 29) pollen grains were counting in average. The diversity showed a high richness, low dominance and similarity between pollen resources. Families Melastomataceae and Asteraceae, genera Miconia and Bidens, were found as the main pollen resources. The stingless bee of this study are mostly generalist as shown the interaction network. The results of the present survey showed that stingless bees do not collect pollen from a single species, although there is evidence of a predilection for certain plant families. The diversity indexes showed high richness but low uniformity in the abundance of each family identified. The results of the study are also meaningful to the meliponiculture sector as there is a need to improve management practices to preserve the biodiversity and the environment.
Why it matches plant phenotyping methods花粉の形態特徴と幾何学的形態計測を用いて植物種・分類群を識別する方法が研究の中心であり、植物器官の形態形質を抽出している。
abstractMorphometry landmarks were used to show variation for species differentiation.
Reproduction assets foundThe paper's pollen phenotyping measurements (morphological descriptions, size/shape parameters, and diversity/dominance/similarity indices) are published as public supporting information files on PLOS ONE. No author analysis code or trained models are deposited; the S1 Table is a literature review compilation rather a Supplement · publicmilies features used as pollen and nectar resources by stingless bees [ 41 – 91 , 126 ].
https://doi.org/10.1371/journal.pone.0272580.s001
(DOCX)
S2 Table. Morphological description, and their parameters, of pollen grains with the highest representation in the three study areas [ 43 , 47 , 52 , 84 , 86 , 99 , 100 , 118 – 129 ].
https://doi.org/10.1371/journal.pone.0272580.s002
(DOCX)
S3 Table. Indexes explaining chart.
Comparison between the diversity, dominance and similarity indices in each study area.
https://doi.org/10.1371/journal.pone.0272580.s003
(DOCX)
Acknowledgments
This work would not have been accomplished without the help of Ecuadorian meliponicultors, regular and thesis studentOpen asset ↗10.1371/journal.pone.0272580.s002lines:320-367Code / dataset availability confirmedbioRxiv · checked 15 Sept 2026
Field / plotWhole plant / canopy / plot / fieldCounting
O_LIThe estimation of population size and its variation across space and time largely relies on counts of individuals, generally carried out within spatial units such as quadrats or sites. Missing individuals during counting (i.e. imperfect detection) results in biased estimates of population size and trends. Imperfect detection has been shown to be the rule in animal studies, and most studies now correct for this bias by estimating detection probability. Yet this correction remains exceptional in plant studies, suggesting that most plant ecologists implicitly assume that all individuals are always detected. C_LIO_LITo assess if this assumption is valid, we conducted a field experiment to estimate individual detection probability in plant counts conducted in 1x1 m quadrats. We selected 30 herbaceous plant species along a gradient of conspicuousness at 24 sites along a gradient of habitat closure, and asked groups of observers to count individuals in 10 quadrats using three counting methods requiring progressively increasing times to complete (quick count, unlimited count and cell count). In total, 158 participants took part in the experiment, allowing an analysis of the results of 5,024 counts. C_LIO_LIOver all field sessions, no observer succeeded in detecting all the individuals in the 10 quadrats. The mean detection rate was 0.44 (ranging from 0.11 to 0.82) for the quick count, 0.59 for the unlimited count (range 0.18-0.87) and 0.74 for the cell count (range 0.46-0.94). C_LIO_LIDetection probability increased with the conspicuousness of the target species and decreased with the density of individuals and habitat closure. The observers experience in botany had little effect on detection probability, whereas detection was strongly affected by the time observers spent counting. Yet although the more time-consuming methods increased detection probability, none achieved perfect detection, nor did they reduce the effect on detection probability of the variables we measured. C_LIO_LISynthesis. Our results show that detection is imperfect and highly heterogeneous when counting plants. To avoid biased estimates when assessing the size, temporal or spatial trends of plant populations, plant ecologists should use methods that estimate the detection probability of individuals rather than relying on raw counts. C_LI
Why it matches plant phenotyping methods植物個体数の計数における検出確率を、複数の計数法・多数の観察者・反復データで評価しており、植物個体群サイズの測定法の妥当性検証が研究の中心です。
abstractwe conducted a field experiment to estimate individual detection probability in plant counts conducted in 1x1 m quadrats.
Reproduction assets foundThe paper's data availability statement explicitly deposits all data (5,024 plant counts from 300 quadrats) and analysis code in a public GitHub repository, which is listed in allowed_urls.Code · publicanised and conducted the field sessions; J.P. analysed the data and led the writing of the
503
manuscript. All authors critically contributed to the drafts and gave their final approval for
504
publication.
505
506
Data availability statement
507
All data and code used for this work are available from the GitHub repository:
508
https://github.com/JanPerret/Individual_detection_in_plant_counts
509
510
.
CC-BY-NC-ND 4.0 International license
available under a
(which was not certified by peer review) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made
The copyright holder for this preprint
this version posted December 21, 2022.
;
https://doiOpen asset ↗JanPerret/Individual_detection_in_plant_countspdf-raw-page:31 lines:1-41Code / dataset availability confirmedCrossref · checked 14 Sept 2026
Abstract The stomata on the leaf surface are mainly responsible for the material exchange between the internal and external environments of the plant, a large number of methods have been proposed to automatically measure the distribution position and number of stomatal, but few methods could achieve both stomatal count and open/closed‐state judgment. Therefore, this study proposes an automatic detection method for leaf stomatal morphology analysis based on an attention mechanism and deep learning. In order to obtain more stomatal feature information and send it to the network for learning, the proposed method adds a coordinate attention (CA) mechanism to the YOLOV5 backbone part. At the same time, in order to avoid the overfitting of the model during the training process, the authors added the training trick of label smoothing. Finally, the detection ability of the proposed method for stomata is verified on the broad bean leaves stomata dataset. The experimental results show that our method achieves a detection accuracy of 0.934 and an mAP of 0.968. By comparing with other state‐of‐the‐art algorithms, the detection capability of our method has been significantly improved. The generalization of the model is verified on the wheat leaf stomatal dataset. The experimental results show that our method can achieve a detection accuracy of 0.894 and an mAP of 0.907.
Why it matches plant phenotyping methods植物葉の気孔形態を自動検出し、数と開閉状態を推定する画像解析法を開発・検証しており、植物フェノタイピング手法が研究の中心である。
abstractthis study proposes an automatic detection method for leaf stomatal morphology analysis based on an attention mechanism and deep learning.
Reproduction assets foundThe paper's broad bean/wheat leaf stomata microscopy image dataset (951 broad bean + 160 wheat images with YOLO-format annotations) is openly deposited on Zenodo per the data availability statement. No code or trained model deposit is explicitly stated.Dataset · publicOF INTEREST
problems, and its indicators are better than the six comparison The authors declare that there are no conflict of interests, we do
algorithms above. not have any possible conflicts of interest.
DATA AVAILABILITY STATEMENT
5 CONCLUSIONS The data that support the findings of this study are openly
available in zendo at https://doi.org/10.5281/zenodo.6302925.
In order to better detect and count the position, number, and
open/closed-status of stomata in plant leaves, we introduce a AUTHOR CONTRIBUTIONS
modified end-to-end target detection model YOLOv5 in this Xin Li: Conceptualization; Data curation; Formal analysis;
study. In order to improve the ability of YOLOv5s model to InvestiOpen asset ↗zenodo · 10.5281/zenodo.6302925pdf-layout-page:9 lines:1-55Code / dataset availability confirmedEurope PMC · checked 8 Sept 2026
RootCountingMorphology / geometry measurementSegmentationRoot system architecture
Convolutional neural networks (CNNs) are a powerful tool for plant image analysis, but challenges remain in making them more accessible to researchers without a machine-learning background. We present RootPainter, an open-source graphical user interface based software tool for the rapid training of deep neural networks for use in biological image analysis. We evaluate RootPainter by training models for root length extraction from chicory (Cichorium intybus L.) roots in soil, biopore counting, and root nodule counting. We also compare dense annotations with corrective ones that are added during the training process based on the weaknesses of the current model. Five out of six times the models trained using RootPainter with corrective annotations created within 2 h produced measurements strongly correlating with manual measurements. Model accuracy had a significant correlation with annotation duration, indicating further improvements could be obtained with extended annotation. Our results show that a deep-learning model can be trained to a high accuracy for the three respective datasets of varying target objects, background, and image quality with < 2 h of annotation time. They indicate that, when using RootPainter, for many datasets it is possible to annotate, train, and complete data processing within 1 d.
Why it matches plant phenotyping methodsRootPainterは植物画像から根長・バイオポア・根粒を抽出する深層学習ソフトウェアであり、補正アノテーション、精度、手動測定との相関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す。
abstractWe present RootPainter, an open-source graphical user interface based software tool for the rapid training of deep neural networks for use in biological image analysis.
Reproduction assets foundThe paper's Data availability statement explicitly deposits the authors' analysis software (client/server source code and installers on GitHub) and a Colab notebook, all with public URLs. The paper-specific phenotype/training datasets (nodules, biopores, roots) and trained models are on Zenodo (DOIs 10.5281/zenodo.3755Code · publicThe source code for both client and server is available from https://github.com/Abe404/root_painter .Open asset ↗github.com/Abe404/root_painterlines:332-520Code / dataset availability confirmedEurope PMC · Crossref · checked 8 Sept 2026
Yield estimation (YE) of the crop is one of the main tasks in fruit management and marketing. Based on the results of YE, the farmers can make a better decision on the harvesting period, prevention strategies for crop disease, subsequent follow-up for cultivation practice, etc. In the current scenario, crop YE is performed manually, which has many limitations such as the requirement of experts for the bigger fields, subjective decisions and a more time-consuming process. To overcome these issues, an intelligent YE system was proposed which detects, localizes and counts the number of tomatoes in the field using SegNet with VGG19 (a deep learning-based semantic segmentation architecture). The dataset of 672 images was given as an input to the SegNet with VGG19 architecture for training. It extracts features corresponding to the tomato in each layer and detection was performed based on the feature score. The results were compared against the other semantic segmentation architectures such as U-Net and SegNet with VGG16. The proposed method performed better and unveiled reasonable results. For testing the trained model, a case study was conducted in the real tomato field at Manapparai village, Trichy, India. The proposed method portrayed the test precision, recall and F1-score values of 89.7%, 72.55% and 80.22%, respectively along with reasonable localization capability for tomatoes.
Why it matches plant phenotyping methodsトマト果実の検出・局在化・計数による収量推定手法を開発し、複数モデルと比較・実地検証しており、植物フェノタイピング手法が中心である。
abstractan intelligent YE system was proposed which detects, localizes and counts the number of tomatoes in the field using SegNet with VGG19
Reproduction assets foundThe paper's phenotyping input images come from a publicly available annotated tomato image dataset (Rob2Pheno, 123 RGB images) hosted on 4TU under CC BY 4.0, which the authors explicitly used for training their SegNet-VGG19 yield estimation model. No author analysis code or trained model is reported as publicly shared.Dataset · publicThe dataset of 123 RGB images 18 used for this work is acquired from the publicly available dataset under a creative common license. ( https://data.4tu.nl/articles/dataset/Rob2Pheno_Annotated_Tomato_Image_Dataset/13173422 ), ( https://creativecommons.org/licenses/by/4.0/ ).Open asset ↗data.4tu.nl · Rob2Pheno_Annotated_Tomato_Image_Dataset/13173422lines:74-89Code / dataset availability confirmedEurope PMC · checked 8 Sept 2026
Background Characterizing plant genetic resources and their response to the environment through accurate measurement of relevant traits is crucial to genetics and breeding. Spatial organization of the maize ear provides insights into the response of grain yield to environmental conditions. Current automated methods for phenotyping the maize ear do not capture these spatial features. Results We developed EARBOX, a low-cost, open-source system for automated phenotyping of maize ears. EARBOX integrates open-source technologies for both software and hardware that facilitate its deployment and improvement for specific research questions. The imaging platform consists of a customized box in which ears are repeatedly imaged as they rotate via motorized rollers. With deep learning based on convolutional neural networks, the image analysis algorithm uses a two-step procedure: ear-specific grain masks are first created and subsequently used to extract a range of trait data per ear, including ear shape and dimensions, the number of grains and their spatial organisation, and the distribution of grain dimensions along the ear. The reliability of each trait was validated against ground-truth data from manual measurements. Moreover, EARBOX derives novel traits, inaccessible through conventional methods, especially the distribution of grain dimensions along grain cohorts, relevant for ear morphogenesis, and the distribution of abortion frequency along the ear, relevant for plant response to stress, especially soil water deficit. Conclusions The proposed system provides robust and accurate measurements of maize ear traits including spatial features. Future developments include grain type and colour categorisation. This method opens avenues for high-throughput genetic or functional studies in the context of plant adaptation to a changing environment.
Why it matches plant phenotyping methodsトウモロコシ雌穂の画像取得・深層学習による形質抽出システムを開発し、手動測定との比較で各形質の信頼性を検証しており、植物フェノタイピング手法が研究の中心です。
abstractWe developed EARBOX, a low-cost, open-source system for automated phenotyping of maize ears.
Reproduction assets foundThe authors' full analysis pipeline (MATLAB GUI plus Python deep-learning code for grain segmentation and phenotypic trait extraction) is explicitly stated to be fully available on a public GitHub repository. The phenotype datasets themselves are only available on request, so they do not qualify as public assets.Code · publicThe code for the analysis using a Graphical User Interface in MATLAB is fully available on a public repository ( https://github.com/Phymea-Systems/Earbox ). It is used in combination with a Python code applying the trained neural network to extract the DL2 images, also available in the same public repository.Open asset ↗Phymea-Systems/Earboxlines:104-113Code / dataset availability confirmedOpenAlex · Europe PMC · checked 8 Sept 2026
High-throughput phenotyping of yield-related traits is meaningful and necessary for rice breeding and genetic study. The conventional method for rice yield-related trait evaluation faces the problems of rice threshing difficulties, measurement process complexity, and low efficiency. To solve these problems, a novel intelligent system, which includes an integrated threshing unit, grain conveyor-imaging units, threshed panicle conveyor-imaging unit, and specialized image analysis software has been proposed to achieve rice yield trait evaluation with high throughput and high accuracy. To improve the threshed panicle detection accuracy, the Region of Interest Align, Convolution Batch normalization activation with Leaky Relu module, Squeeze-and-Excitation unit, and optimal anchor size have been adopted to optimize the Faster-RCNN architecture, termed 'TPanicle-RCNN,' and the new model achieved F1 score 0.929 with an increase of 0.044, which was robust to indica and japonica varieties. Additionally, AI cloud computing was adopted, which dramatically reduced the system cost and improved flexibility. To evaluate the system accuracy and efficiency, 504 panicle samples were tested, and the total spikelet measurement error decreased from 11.44 to 2.99% with threshed panicle compensation. The average measuring efficiency was approximately 40 s per sample, which was approximately twenty times more efficient than manual measurement. In this study, an automatic and intelligent system for rice yield-related trait evaluation was developed, which would provide an efficient and reliable tool for rice breeding and genetic research.
Why it matches plant phenotyping methodsイネの収量関連形質を高スループットに取得する統合計測・画像解析システムを開発し、検出精度と測定効率を検証しているため、植物フェノタイピング手法が中心である。
abstracta novel intelligent system, which includes an integrated threshing unit, grain conveyor-imaging units, threshed panicle conveyor-imaging unit, and specialized image analysis software has been proposed to achieve rice yield trait evaluation with high throughput and high accuracy.
Reproduction assets foundThe article explicitly states that all threshed panicle training and testing data (1,072 threshed panicle images with PASCAL VOC annotations, augmented to 3,432 training and 856 testing images) are publicly available via a Baidu Netdisk link with an extraction code for non-commercial research. This is a paper-specific,Dataset · publicAll the training and testing data are available at https://pan.baidu.com/s/1-XawHGseIc5bboVOP48Fkw?pwd=153w with the extraction code ‘153w’ for non-commercial research purposes.Open asset ↗pan.baidu.com · 1-XawHGseIc5bboVOP48Fkw?pwd=153wlines:330-340Code / dataset availability confirmedEurope PMC · bioRxiv · checked 15 Sept 2026
Background Cyst nematodes are one of the major groups of plant-parasitic nematode, responsible for considerable crop losses worldwide. Improving genetic resources, and therefore resistant cultivars, is an ongoing focus of many pest management strategies. One of the major bottlenecks in identifying the plant genes that impact the infection, and thus the yield, is phenotyping. The current available screening method is slow, has unidimensional quantification of infection limiting the range of scorable parameters, and does not account for phenotypic variation of the host. The ever-evolving field of computer vision may be the solution for both the above-mentioned issues. To utilise these tools, a specialised imaging platform is required to take consistent images of nematode infection in quick succession. Results Here, we describe an open-source, easy to adopt, imaging hardware and trait analysis software method based on a pre-existing nematode infection screening method in axenic culture. A cost-effective, easy-to-build and -use, 3D-printed imaging device was developed to acquire images of the root system of Arabidopsis thaliana infected with the cyst nematode Heterodera schachtii , replacing costly microscopy equipment. Coupling the output of this device to simple analysis scripts allowed the measurement of some key traits such as nematode number and size from collected images, in a semi-automated manner. Additionally, we used this combined solution to quantify an additional trait, root area before infection, and showed both the confounding relationship of this trait on nematode infection and a method to account for it. Conclusion Taken together, this manuscript provides a low-cost and open-source method for nematode phenotyping that includes the biologically relevant nematode size as a scorable parameter, and a method to account for phenotypic variation of the host. Together these tools highlight great potential in aiding our understanding of nematode parasitism.
Why it matches plant phenotyping methods植物寄生性線虫感染の画像取得・解析を自動化する低コストの装置とソフトウェアを開発し、線虫数・サイズおよび根面積を測定する手法が中心であるため。
abstractHere, we describe an open-source, easy to adopt, imaging hardware and trait analysis software method
Reproduction assets foundThe paper's ImageJ analysis scripts (root surface area, colored-agar variant, leaf surface count) and a custom Python color-normalization script are explicitly deposited in the authors' public GitHub repository (OlafKranse/A_low_cost_imaging_tower), directly reproducing this paper's phenotyping analysis. No phenotype/тCode · publici.org/10.1101/2022.07.14.500020; this version posted July 15, 2022. The copyright holder for this preprint
(which was not certified by peer review) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is
made available under a CC-BY 4.0 International license.
described in the script
(https://github.com/OlafKranse/A_low_cost_imaging_tower/blob/main/Imaging and
Analyses/automated_root_surface_area.ijm). A slightly adjusted script was used for plates
containing dye (https://github.com/OlafKranse/A_low_cost_imaging_tower/blob/main/Imaging and
Analyses/automated_root_surface_area_colored_agar.ijm). The root surface area for all the images
in the folderOpen asset ↗OlafKranse/A_low_cost_imaging_towerpdf-layout-page:6 lines:1-37Code · publicing and quantifiable traits
Automatic counting was performed on images taken as described above. Depending on the
treatment a different script was used to calculate the number and size of females. Before isolation,
the colour histogram for all images was normalised to the first image in the dataset using a custom
python script (https://github.com/OlafKranse/A_low_cost_imaging_tower/tree/main/Imaging and
Analyses/Normalise colour). The images were then processed in ImageJ for two different nematode
life stages: i) tanned cyst nematodes; ii) female nematodes.Open asset ↗OlafKranse/A_low_cost_imaging_towerpdf-layout-page:6 lines:1-37Code / dataset availability confirmedEurope PMC · checked 8 Sept 2026
The soybean flower and the pod drop are important factors in soybean yield, and the use of computer vision techniques to obtain the phenotypes of flowers and pods in bulk, as well as in a quick and accurate manner, is a key aspect of the study of the soybean flower and pod drop rate (PDR). This paper compared a variety of deep learning algorithms for identifying and counting soybean flowers and pods, and found that the Faster R-CNN model had the best performance. Furthermore, the Faster R-CNN model was further improved and optimized based on the characteristics of soybean flowers and pods. The accuracy of the final model for identifying flowers and pods was increased to 94.36 and 91%, respectively. Afterward, a fusion model for soybean flower and pod recognition and counting was proposed based on the Faster R-CNN model, where the coefficient of determination R 2 between counts of soybean flowers and pods by the fusion model and manual counts reached 0.965 and 0.98, respectively. The above results show that the fusion model is a robust recognition and counting algorithm that can reduce labor intensity and improve efficiency. Its application will greatly facilitate the study of the variable patterns of soybean flowers and pods during the reproductive period. Finally, based on the fusion model, we explored the variable patterns of soybean flowers and pods during the reproductive period, the spatial distribution patterns of soybean flowers and pods, and soybean flower and pod drop patterns.
Why it matches plant phenotyping methodsダイズの花・莢数という植物形質を画像から自動認識・計数する深層学習手法を比較、改良、検証しており、表現型取得法が研究の中心である。
abstractthe use of computer vision techniques to obtain the phenotypes of flowers and pods in bulk, as well as in a quick and accurate manner, is a key aspect of the study
Reproduction assets foundThe authors publicly deposited the soybean flower and pod image datasets (the phenotyping inputs used for detection/counting) in an online repository via a Baidu Netdisk link with password, stated in the Data availability statement. No author analysis code or trained model checkpoints are explicitly shared; LabelImg isDataset · publicThe datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://pan.baidu.com/s/1j ZE6BHlpVjGay_JqVmOew:password: ate8 .Open asset ↗pan.baidu.com · ZE6BHlpVjGay_JqVmOewlines:751-822Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Counting wheat heads is a time-consuming process in agricultural production, which is currently primarily carried out by humans. Manually identifying wheat heads and statistically analyzing the findings has a rigorous requirement for the workforce and is prone to error. With the advancement of machine vision technology, computer vision detection algorithms have made wheat head detection and counting feasible. To accomplish this traditional labor-intensive task and tackle various tricky matters in wheat images, a high-precision wheat head detection model with strong generalizability was presented based on a one-stage network structure. The model's structure was referred to as that of the YOLO network; meanwhile, several modules were added and adjusted in the backbone network. The one-stage backbone network received an attention module and a feature fusion module, and the Loss function was improved. When compared to various other mainstream object detection networks, our model outperforms them, with a mAP of 0.688. In addition, an iOS-based intelligent wheat head counting mobile app was created, which could calculate the number of wheat heads in images shot in an agricultural environment in less than a second.
Why it matches plant phenotyping methodsコムギ穂数という植物器官形質を画像から検出・計数するモデルを開発し、性能比較とモバイルアプリ化まで行っており、表現型取得手法が研究の中心である。
abstracta high-precision wheat head detection model with strong generalizability was presented based on a one-stage network structure.
Reproduction assets foundThe paper's wheat head detection model was trained and evaluated on the public Global Wheat Head Detection dataset hosted on Kaggle, which directly provides the plant-phenotyping images and bounding-box annotations used in this study. No authors' code or trained model repository is disclosed; the Data Availability onlyDataset · publicThe data set used in this study was retrieved from the Global Wheat Head data set (Kaggle, 2020 ).Open asset ↗Kagglelines:40-55Code / dataset availability confirmedOpenAlex · Europe PMC · checked 8 Sept 2026
Deep learning-based methods have recently provided a means to rapidly and effectively extract various plant traits due to their powerful ability to depict a plant image across a variety of species and growth conditions. In this study, we focus on dealing with two fundamental tasks in plant phenotyping, i.e., plant segmentation and leaf counting, and propose a two-steam deep learning framework for segmenting plants and counting leaves with various size and shape from two-dimensional plant images. In the first stream, a multi-scale segmentation model using spatial pyramid is developed to extract leaves with different size and shape, where the fine-grained details of leaves are captured using deep feature extractor. In the second stream, a regression counting model is proposed to estimate the number of leaves without any pre-detection, where an auxiliary binary mask from segmentation stream is introduced to enhance the counting performance by effectively alleviating the influence of complex background. Extensive pot experiments are conducted CVPPP 2017 Leaf Counting Challenge dataset, which contains images of Arabidopsis and tobacco plants. The experimental results demonstrate that the proposed framework achieves a promising performance both in plant segmentation and leaf counting, providing a reference for the automatic analysis of plant phenotypes.
Why it matches plant phenotyping methods植物画像からのセグメンテーションと葉数推定を中核とする深層学習フェノタイピング手法の開発であり、植物形質の自動抽出性能も評価しているため。
abstractwe focus on dealing with two fundamental tasks in plant phenotyping, i.e., plant segmentation and leaf counting, and propose a two-steam deep learning framework
Reproduction assets foundThe paper's experiments use the public CVPPP 2017 Leaf Counting Challenge dataset (Arabidopsis and tobacco plant images with segmentation masks and leaf counts), which the authors explicitly link in the data availability statement. No author code or trained models are disclosed.Dataset · publicPublicly available datasets were analyzed in this study. This data can be found here: https://www.plant-phenotyping.org/CVPPP2017 .Open asset ↗CVPPP2017 · CVPPP2017lines:527-601Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Background Quinoa is an increasingly popular seed crop frequently studied for its tolerance to various abiotic stresses as well as its susceptibility to heat. Estimations of quinoa pollen viability through staining methods have resulted in conflicting results. A more effective alternative to stains is to estimate pollen viability through in vitro germination. Here we report a method for in vitro quinoa pollen germination that could be used to understand the impact of various stresses on quinoa fertility and therefore seed yield or to identify male-sterile lines for breeding. Results A semi-automated method to count germinating pollen was developed in PlantCV, which can be widely used by the community. Pollen collected on day 4 after first anthesis at zeitgeber time 5 was optimum for pollen germination with an average germination of 68% for accession QQ74 (PI 614886). The optimal length of pollen incubation was found to be 48 h, because it maximizes germination rates while minimizing contamination. The pollen germination medium's pH, boric acid, and sucrose concentrations were optimized. The highest germination rates were obtained with 16% sucrose, 0.03% boric acid, 0.007% calcium nitrate, and pH 5.5. This medium was tested on quinoa accessions QQ74, and cherry vanilla with 68%, and 64% germination efficiencies, respectively. Conclusions We provide an in vitro pollen germination method for quinoa with average germination rates of 64 and 68% on the two accessions tested. This method is a valuable tool to estimate pollen viability in quinoa, and to test how stress affects quinoa fertility. We also developed an image analysis tool to semi-automate the process of counting germinating pollen. Quinoa produces many new flowers during most of its panicle development period, leading to significant variation in pollen maturity and viability between different flowers of the same panicle. Therefore, collecting pollen at 4 days after first anthesis is very important to collect more uniformly developed pollen and to obtain high germination rates.
Why it matches plant phenotyping methodsキノア花粉の生存性を測定するin vitro発芽法を開発・最適化し、PlantCVによる発芽花粉の半自動画像計数も開発しており、植物形質取得法が中心である。
abstractA semi-automated method to count germinating pollen was developed in PlantCV, which can be widely used by the community.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産2件を確認しました。Code · publicThis workflow is available at https://github.com/danforthcenter/quinoa-pollen-germination and a tutorial is availabe at https://github.com/danforthcenter/plantcv-tutorial-interactive-pollent-count .Open asset ↗GitHub · danforthcenter/quinoa-pollen-germinationlines:134-159Code · publicThis workflow is available at https://github.com/danforthcenter/quinoa-pollen-germination and a tutorial is availabe at https://github.com/danforthcenter/plantcv-tutorial-interactive-pollent-count .Open asset ↗GitHub · danforthcenter/plantcv-tutorial-interactive-pollent-countlines:134-159Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
The total boll count from a plant is one of the most important phenotypic traits for cotton breeding and is also an important factor for growers to estimate the final yield. With the recent advances in deep learning, many supervised learning approaches have been implemented to perform phenotypic trait measurement from images for various crops, but few studies have been conducted to count cotton bolls from field images. Supervised learning models require a vast number of annotated images for training, which has become a bottleneck for machine learning model development. The goal of this study is to develop both fully supervised and weakly supervised deep learning models to segment and count cotton bolls from proximal imagery. A total of 290 RGB images of cotton plants from both potted (indoor and outdoor) and in-field settings were taken by consumer-grade cameras and the raw images were divided into 4350 image tiles for further model training and testing. Two supervised models (Mask R-CNN and S-Count) and two weakly supervised approaches (WS-Count and CountSeg) were compared in terms of boll count accuracy and annotation costs. The results revealed that the weakly supervised counting approaches performed well with RMSE values of 1.826 and 1.284 for WS-Count and CountSeg, respectively, whereas the fully supervised models achieve RMSE values of 1.181 and 1.175 for S-Count and Mask R-CNN, respectively, when the number of bolls in an image patch is less than 10. In terms of data annotation costs, the weakly supervised approaches were at least 10 times more cost efficient than the supervised approach for boll counting. In the future, the deep learning models developed in this study can be extended to other plant organs, such as main stalks, nodes, and primary and secondary branches. Both the supervised and weakly supervised deep learning models for boll counting with low-cost RGB images can be used by cotton breeders, physiologists, and growers alike to improve crop breeding and yield estimation.
Why it matches plant phenotyping methods綿花ボール数という植物表現型を画像からセグメンテーション・計数する深層学習手法を開発し、教師あり・弱教師ありモデルの精度とアノテーションコストを比較しており、表現型取得手法が研究の中心である。
abstractThe goal of this study is to develop both fully supervised and weakly supervised deep learning models to segment and count cotton bolls from proximal imagery.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Dataset · publicThe dataset used in this study can be accessed at the following link: https://doi.org/10.6084/m9.figshare.19665096.v1 .Open asset ↗figshare · 10.6084/m9.figshare.19665096.v1lines:228-245Code / dataset availability confirmedEurope PMC · checked 8 Sept 2026
Estimation of cotton yield before harvest offers many benefits to breeding programs, researchers and producers. Remote sensing enables efficient and consistent estimation of cotton yields, as opposed to traditional field measurements and surveys. The overall goal of this study was to develop a data processing pipeline to perform fast and accurate pre-harvest yield predictions of cotton breeding fields from aerial imagery using machine learning techniques. By using only a single plot image extracted from an orthomosaic map, a Support Vector Machine (SVM) classifier with four selected features was trained to identify the cotton pixels present in each plot image. The SVM classifier achieved an accuracy of 89%, a precision of 86%, a recall of 75%, and an F1-score of 80% at recognizing cotton pixels. After performing morphological image processing operations and applying a connected components algorithm, the classified cotton pixels were clustered to predict the number of cotton bolls at the plot level. Our model fitted the ground truth counts with an R 2 value of 0.93, a normalized root mean squared error of 0.07, and a mean absolute percentage error of 13.7%. This study demonstrates that aerial imagery with machine learning techniques can be a reliable, efficient, and effective tool for pre-harvest cotton yield prediction.
Why it matches plant phenotyping methods航空画像と機械学習による綿花の収量・果球数推定パイプラインを開発し、画素分類と地上計数で性能検証しており、植物表現型の取得・抽出が研究の中心である。
abstractThe overall goal of this study was to develop a data processing pipeline to perform fast and accurate pre-harvest yield predictions of cotton breeding fields from aerial imagery using machine learning techniques.
Reproduction assets foundThe paper's cotton boll classification/counting pipeline is publicly available: a Dockerized web app on Docker Hub and code with sample test images on GitHub, both explicitly stated by the authors. Raw aerial imagery/ground truth data are only available on request.Code · publicAdditionally, we will provide the code and some sample images for testing at https://github.com/Javi-RS/Cotton_Yield_Estimation .Open asset ↗Javi-RS/Cotton_Yield_Estimationlines:394-495Code / dataset availability confirmedOpenAlex · Europe PMC · Crossref · checked 8 Sept 2026
Abstract Background: A tiller is a branch on a grass plant, and the number of tillers is one of the most important determinants of yield. Traditionally, the tiller number is usually counted by hand, and so an automated approach is necessary for high-throughput phenotyping. Conventional methods use heuristic features to estimate the tiller number. Based on the successful application of DNNs in the field of computer vision, the use of DNN-based features instead of heuristic features is expected to improve the estimation accuracy. However, as DNNs generally require large volumes of data for training, it is difficult to apply them to estimation problems for which large training datasets are unavailable. In this paper, we use two strategies to overcome the problem of insufficient training data: the use of a pretrained DNN model and the use of pretext tasks for learning the feature representation. We extract features using the resulting DNNs and estimate the tiller numbers through a regression technique. Results: We conducted experiments using a dataset of Setaria viridis. Experiments show that the proposed methods using a pretrained model and specific pretext tasks achieve better performance than the conventional method. The best mean absolute error between the hand-labeled and estimated tiller numbers by the proposed method is 0.57. Conclusions: We realized applying DNN methods to tiller number estimation methods by using pretext tasks. The proposed method outperformed the conventional approach.
Why it matches plant phenotyping methods深層ニューラルネットワークを用いて植物の分げつ数を自動推定する手法を開発・比較しており、植物表現型の取得が研究の中心である。
abstractan automated approach is necessary for high-throughput phenotyping
Reproduction assets foundThe paper's tiller estimation experiments use the Setaria viridis image dataset (25,570 images, 576 with hand-labeled tiller numbers), which the authors explicitly state is publicly available in the figshare repository. No author analysis code or trained models are reported as deposited.Dataset · publicThe dataset analyzed during the current study are available in the figshare repository,
https://figshare.com/articles/dataset/DDPSC_Phenotyping_Manuscript_1_Files/1272859 [11].Open asset ↗figshare · 1272859pdf-page:12 lines:1-70Code / dataset availability confirmedEurope PMC · checked 8 Sept 2026
The number of wheat spikes per unit area is one of the most important agronomic traits associated with wheat yield. However, quick and accurate detection for the counting of wheat spikes faces persistent challenges due to the complexity of wheat field conditions. This work has trained a RetinaNet (SpikeRetinaNet) based on several optimizations to detect and count wheat spikes efficiently. This RetinaNet consists of several improvements. First, a weighted bidirectional feature pyramid network (BiFPN) was introduced into the feature pyramid network (FPN) of RetinaNet, which could fuse multiscale features to recognize wheat spikes in different varieties and complicated environments. Then, to detect objects more efficiently, focal loss and attention modules were added. Finally, soft non-maximum suppression (Soft-NMS) was used to solve the occlusion problem. Based on these improvements, the new network detector was created and tested on the Global Wheat Head Detection (GWHD) dataset supplemented with wheat-wheatgrass spike detection (WSD) images. The WSD images were supplemented with new varieties of wheat, which makes the mixed dataset richer in species. The method of this study achieved 0.9262 for mAP50, which improved by 5.59, 49.06, 2.79, 1.35, and 7.26% compared to the state-of-the-art RetinaNet, single-shot multiBox detector (SSD), You Only Look Once version3 (Yolov3), You Only Look Once version4 (Yolov4), and faster region-based convolutional neural network (Faster-RCNN), respectively. In addition, the counting accuracy reached 0.9288, which was improved from other methods as well. Our implementation code and partial validation data are available at https://github.com/wujians122/The-Wheat-Spikes-Detecting-and-Counting.
Why it matches plant phenotyping methods小麦穂の検出・計数という植物形質を対象に、改良した画像解析モデルを開発し、データセット上で性能検証しているため、フェノタイピング手法が中心である。
abstractThis work has trained a RetinaNet (SpikeRetinaNet) based on several optimizations to detect and count wheat spikes efficiently.
Reproduction assets foundThe authors explicitly state that their implementation code and partial validation data for the SpikeRetinaNet wheat spike detection/counting method are publicly available on GitHub. Other referenced repositories (COCO Annotator, YOLOv5, LabelImg) are generic third-party tools, not paper-specific assets.Code · publicOur implementation code and partial validation data are available at https://github.com/wujians122/The-Wheat-Spikes-Detecting-and-Counting .Open asset ↗wujians122/The-Wheat-Spikes-Detecting-and-Countinglines:227-316Code / dataset availability confirmedOpenAlex · Crossref · Europe PMC · checked 8 Sept 2026
Summary Revealing the contributions of genes to plant phenotype is frequently challenging because loss‐of‐function effects may be subtle or masked by varying degrees of genetic redundancy. Such effects can potentially be detected by measuring plant fitness, which reflects the cumulative effects of genetic changes over the lifetime of a plant. However, fitness is challenging to measure accurately, particularly in species with high fecundity and relatively small propagule sizes such as Arabidopsis thaliana . An image segmentation‐based method using the software I mage J and an object detection‐based method using the Faster Region‐based Convolutional Neural Network (R‐CNN) algorithm were used for measuring two Arabidopsis fitness traits: seed and fruit counts. The segmentation‐based method was error‐prone (correlation between true and predicted seed counts, r 2 = 0.849) because seeds touching each other were undercounted. By contrast, the object detection‐based algorithm yielded near perfect seed counts ( r 2 = 0.9996) and highly accurate fruit counts ( r 2 = 0.980). Comparing seed counts for wild‐type and 12 mutant lines revealed fitness effects for three genes; fruit counts revealed the same effects for two genes. Our study provides analysis pipelines and models to facilitate the investigation of Arabidopsis fitness traits and demonstrates the importance of examining fitness traits when studying gene functions.
Why it matches plant phenotyping methodsFaster R-CNNによる種子・果実数という植物形質の画像ベース測定法を開発・比較検証し、解析パイプラインとモデルを提示しているため、フェノタイピング手法が中心的です。
abstractAn image segmentation‐based method using the software I mage J and an object detection‐based method using the Faster Region‐based Convolutional Neural Network (R‐CNN) algorithm were used for measuring two Arabidopsis fitness traits: seed and fruit counts.
Reproduction assets foundThe paper's Data availability statement explicitly deposits all analysis scripts and the final seed and fruit counting models (trained Faster R-CNN phenotyping models) in a public GitHub repository under the authors' ShiuLab account, making it a paper-specific, publicly actionable asset.Code · publicAll the scripts used in this study and the final seed and fruit counting models are available on GitHub at: https://github.com/ShiuLab/Manuscript_Code/tree/master/2022_Arabidopsis_seed_and_fruit_count .Open asset ↗ShiuLab/Manuscript_Code · 2022_Arabidopsis_seed_and_fruit_countlines:244-645Code / dataset availability confirmedEurope PMC · checked 8 Sept 2026
Abstract Background: Quinoa is an increasingly popular seed crop frequently studied for its tolerance to various abiotic stresses as well as its susceptibility to heat. Estimations of quinoa pollen viability through staining methods have resulted in conflicting results. A more effective alternative to stains is to estimate pollen viability through in vitro germination. Here we report a method for in vitro quinoa pollen germination that could be used to understand the impact of various stresses on quinoa fertility and therefore seed yield or to identify male-sterile lines for breeding. Results: A semi-automated method to count germinating pollen was developed in PlantCV, which can be widely used by the community. Pollen collected on day 4 after first anthesis at ZT5 was optimum for pollen germination with an average germination of 68% for accession QQ74 (PI 614886). The optimal length of pollen incubation was found to be 48 hours, because it maximizes germination rates while minimizing contamination. The pollen germination medium’s pH, boric acid, and sucrose concentrations were optimized. The highest germination rates were obtained with 16% sucrose, 0.03% boric acid, 0.007% calcium nitrate, and pH 5.5. This medium was tested on quinoa accessions QQ74, and cherry vanilla with 68%, and 64% germination efficiencies, respectively. Conclusions: We provide an in vitro pollen germination method for quinoa with average germination rates of 64 and 68% on the two accessions tested. This method is a valuable tool to estimate pollen viability in quinoa, and to test how stress affects quinoa fertility. We also developed an image analysis tool to semi-automate the process of counting germinating pollen. Quinoa produces many new flowers during most of its panicle development period, leading to significant variation in pollen maturity and viability between different flowers of the same panicle. Therefore, collecting pollen at 4 days after first anthesis is very important to collect more uniformly developed pollen and to obtain high germination rates.
Why it matches plant phenotyping methodsキノア花粉の生存性を評価するin vitro発芽法を開発・最適化し、PlantCVによる発芽花粉の画像カウントも半自動化しており、植物形質取得法が研究の中心である。
abstractA semi-automated method to count germinating pollen was developed in PlantCV, which can be widely used by the community.
Reproduction assets foundThe paper's pollen germination microscopy images are deposited on Zenodo and the PlantCV analysis workflow/scripts plus extracted numerical data are on the authors' GitHub, both explicitly stated with URLs.Dataset · publicImages are available here:
https://doi.org/10.5281/zenodo.5909573.Open asset ↗Zenodo · 10.5281/zenodo.5909573pdf-page:9 lines:1-47Code · publicScripts and extracted numerical data are available on
GitHub: https://github.com/danforthcenter/quinoa-pollen-germination.Open asset ↗GitHub · danforthcenter/quinoa-pollen-germinationpdf-page:11 lines:1-46Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Fruit yield estimation is crucial for establishing fruit harvest and marketing strategies. Recently, computer vision and deep learning techniques have been used to estimate citrus fruit yield and have exhibited notable fruit detection ability. However, computer-vision-based citrus fruit counting has two key limitations: inconsistent fruit detection accuracy and double-counting of the same fruit. Using oranges as the experimental material, this paper proposes a deep-learning-based orange counting algorithm using video sequences to help overcome these problems. The algorithm consists of two sub-algorithms, OrangeYolo for fruit detection and OrangeSort for fruit tracking. The OrangeYolo backbone network is partially based on the YOLOv3 algorithm, which has been improved upon to detect small objects (fruits) at multiple scales. The network structure was adjusted to detect small-scale targets while enabling multiscale target detection. A channel attention and spatial attention multiscale fusion module was introduced to fuse the semantic features of the deep network with the shallow textural detail features. OrangeYolo can achieve mean Average Precision (mAP) values of 0.957 in the citrus dataset, higher than the 0.905, 0.911, and 0.917 achieved with the YOLOv3, YOLOv4, and YOLOv5 algorithms. OrangeSort was designed to alleviate the double-counting problem associated with occluded fruits. A specific tracking region counting strategy and tracking algorithm based on motion displacement estimation were established. Six video sequences taken from two fields containing 22 trees were used as the validation dataset. The proposed method showed better performance (Mean Absolute Error (MAE) = 0.081, Standard Deviation (SD) = 0.08) than video-based manual counting and produced more accurate results than the existing standards Sort and DeepSort (MAE = 0.45 and 1.212; SD = 0.4741 and 1.3975).
Why it matches plant phenotyping methods柑橘果実の検出・追跡により樹上果実数（収量推定に使う形質）を定量する画像解析手法を開発し、既存手法および手動計数と検証・比較しており、植物フェノタイピング手法が中心です。
abstractthis paper proposes a deep-learning-based orange counting algorithm using video sequences to help overcome these problems.
Reproduction assets foundThe authors publicly released the annotated orange fruit image dataset used to train and test OrangeYolo on GitHub, with explicit data availability statement. A supplementary tracking example video is also on YouTube. No analysis code release is stated.Dataset · publicW.W., and Y. S. collected field data with self-designed field rover. All authors discussed, wrote the manuscript, and gave final approval for publication.
Data availability
The dataset used during this study is available in a repository in accordance with funder data retention policies. We have published the dataset at GitHub ( https://github.com/I3-Laboratory/orange-dataset ).
Conflict of interest statement
The authors declare that they have no conflicts of interest.
Supplementary data
Supplementary data is available at Horticulture Research online.
Supplementary Material
Web_Material_uhac003
Click here for additional data file.
Reference
1.
Anderson
NT
, Walsh KB , Wulfsohn D
.
TechnologieOpen asset ↗GitHub · I3-Laboratory/orange-datasetlines:986-1102Code / dataset availability confirmedEurope PMC · checked 9 Sept 2026
Determining the grain yield potential contributed by grain number is a step towards advancing the yield of cereal crops. To achieve this aim, it is pivotal to recognize the maximum yield potential (MYP) of the crop. In barley (Hordeum vulgare L.), the MYP is defined as the maximum spikelet primordia number of a spike. Many barley studies assumed the awn primordium (AP) stage to be the MYP stage regardless of genotypes and growth conditions. From our spikelet-tracking experiments using the two-rowed cultivar Bowman, we found that the MYP stage can be different from the AP stage. Importantly, we find that the occurrence of inflorescence meristem deformation and its loss of activity coincided with the MYP stage, indicating the end of further spikelet initiation. Thus, we recommend validating the barley MYP stage with the shape of the inflorescence meristem and propose this approach (named 'spikelet stop') for MYP staging. To clarify the relevance of AP and MYP stages, we compared the MYP stage and the MYP in 27 barley accessions (two- and six-rowed accessions) grown in the greenhouse and in the field. Our results reveal that the MYP stage can be reached at various developmental stages, which greatly depend on the genotype and growth conditions. Furthermore, we propose that the MYP stage and the time to reach the MYP stage can be used to determine yield potential in barley. Based on our findings, we suggest key steps for the identification of the MYP stage in barley that may also be applied in a related crop such as wheat.
Why it matches plant phenotyping methods花序メリステムの形状と活動停止から最大収量ポテンシャル段階を判定する「spikelet stop」手法を提案・検証しており、植物発達形質の取得法が中心である。
abstractThus, we recommend validating the barley MYP stage with the shape of the inflorescence meristem and propose this approach (named 'spikelet stop') for MYP staging.
Reproduction assets foundThe paper's spikelet-tracking phenotype data (spikelet ridge numbers, Waddington stages, GDDs, grain numbers for Bowman experiments and the 27-accession panel) are openly deposited in the Dryad Digital Repository, as stated in the Data availability statement.Dataset · publicThe data that support the findings of this study are openly available in Dryad Digital Repository at https://doi.org/10.5061/dryad.ffbg79cth ; Thirulogachandar and Schnurbusch, (2021) .Open asset ↗Dryad Digital Repository · 10.5061/dryad.ffbg79cthlines:71-101Code / dataset availability confirmedOpenAlex · checked 13 Sept 2026
This work presents an advanced photogrammetric pipeline for inspecting apple trees in the field, automatically detecting fruits from videos and quantifying their size and number. The proposed approach is intended to facilitate and accelerate farmers’ and agronomists’ fieldwork, making apple measurements more objective and giving a more extended collection of apples measured in the field while also estimating harvesting/apple-picking dates. In order to do this rapidly and automatically, we propose a pipeline that uses smartphone-based videos and combines photogrammetry, deep learning and geometric algorithms. Synthetic, laboratory and on-field experiments demonstrate the accuracy of the results and the potential of the proposed method. Acquired data, labelled images, code and network weights, are available at 3DOM-FBK GitHub account.
Why it matches plant phenotyping methodsリンゴ果実の数とサイズを動画から自動抽出するフォトグラメトリ手法を開発し、実験で精度を検証しており、植物フェノタイピング手法が中心である。
abstractThis work presents an advanced photogrammetric pipeline for inspecting apple trees in the field, automatically detecting fruits from videos and quantifying their size and number.
Reproduction assets foundThe authors explicitly state that acquired data, labelled images, code, and network weights for the apple phenotyping pipeline are publicly available on the 3DOM-FBK GitHub account, with a concrete URL given in reference [56]. This is a paper-specific, public, actionable asset covering the Mask R-CNN retraining code/权重Code · publicData Availability Statement: Data acquired and used in the presented experiments, labelled im-
ages, code, and network weights, are available to the scientific community at 3DOM-FBK-GitHub
[56].Open asset ↗pdf-page:16 lines:1-58Dataset · publicAcquired
data, labelled images, code and network weights, are available at 3DOM-FBK GitHub account.Open asset ↗pdf-page:1 lines:1-67Code / dataset availability confirmedEurope PMC · checked 9 Sept 2026
Quantifying symptoms of tar spot of corn has been conducted through visual-based estimations of the proportion of leaf area covered by the pathogenic structures generated by Phyllachora maydis (stromata). However, this traditional approach is costly in terms of time and labor, as well as prone to human subjectivity. An objective and accurate method, which is also time and labor-efficient, is of an urgent need for tar spot surveillance and high-throughput disease phenotyping. Here, we present the use of contour-based detection of fungal stromata to quantify disease intensity using Red-Green-Blue (RGB) images of tar spot-infected corn leaves. Image blocks ( n = 1,130) generated by uniform partitioning the RGB images of leaves, were analyzed for their number of stromata by two independent, experienced human raters using ImageJ (visual estimates) and the experimental stromata contour detection algorithm (SCDA; digital measurements). Stromata count for each image block was then categorized into five classes and tested for the agreement of human raters and SCDA using Cohen's weighted kappa coefficient (κ). Adequate agreements of stromata counts were observed for each of the human raters to SCDA (κ = 0.83) and between the two human raters (κ = 0.95). Moreover, the SCDA was able to recognize "true stromata," but to a lesser extent than human raters (average median recall = 90.5%, precision = 89.7%, and Dice = 88.3%). Furthermore, we tracked tar spot development throughout six time points using SCDA and we obtained high agreement between area under the disease progress curve (AUDPC) shared by visual disease severity and SCDA. Our results indicate the potential utility of SCDA in quantifying stromata using RGB images, complementing the traditional human, visual-based disease severity estimations, and serve as a foundation in building an accurate, high-throughput pipeline for the scoring of tar spot symptoms.
Why it matches plant phenotyping methodsRGB画像からトウモロコシ葉のタースポット病徴（病斑・病害強度）を自動定量する輪郭検出アルゴリズムを開発・検証しており、植物病害表現型の取得法が中心である。
abstractHere, we present the use of contour-based detection of fungal stromata to quantify disease intensity using Red-Green-Blue (RGB) images of tar spot-infected corn leaves.
Reproduction assets foundThe paper's data availability statement explicitly states the original contributions (RGB leaf images, image blocks, and SCDA-related data) are publicly available at a Purdue PURR repository URL, which is an allowed URL.Dataset · publicThe original contributions presented in the study are publicly available. This data can be found here: https://purr.purdue.edu/publications/3820/2Open asset ↗purr.purdue.edu · publications/3820/2lines:669-700Code / dataset availability confirmedEurope PMC · checked 9 Sept 2026
This paper proposes a novel approach for semi-supervised domain adaptation for holistic regression tasks, where a DNN predicts a continuous value y∈R given an input image x . The current literature generally lacks specific domain adaptation approaches for this task, as most of them mostly focus on classification. In the context of holistic regression, most of the real-world datasets not only exhibit a covariate (or domain) shift, but also a label gap-the target dataset may contain labels not included in the source dataset (and vice versa). We propose an approach tackling both covariate and label gap in a unified training framework. Specifically, a Generative Adversarial Network (GAN) is used to reduce covariate shift, and label gap is mitigated via label normalisation. To avoid overfitting, we propose a stopping criterion that simultaneously takes advantage of the Maximum Mean Discrepancy and the GAN Global Optimality condition. To restore the original label range-that was previously normalised-a handful of annotated images from the target domain are used. Our experimental results, run on 3 different datasets, demonstrate that our approach drastically outperforms the state-of-the-art across the board. Specifically, for the cell counting problem, the mean squared error (MSE) is reduced from 759 to 5.62; in the case of the pedestrian dataset, our approach lowered the MSE from 131 to 1.47. For the last experimental setup, we borrowed a task from plant biology, i.e., counting the number of leaves in a plant, and we ran two series of experiments, showing the MSE is reduced from 2.36 to 0.88 (intra-species), and from 1.48 to 0.6 (inter-species).
Why it matches plant phenotyping methods植物の葉数という形態形質を画像から推定する計算手法を開発し、種内・種間で性能評価している。植物課題は複数実験の一部だが、ドメイン適応と葉数カウントの技術評価が明示されており、単なるルーチン測定ではない。
abstractWe propose an approach tackling both covariate and label gap in a unified training framework.
Reproduction assets foundThe paper's authors explicitly state their implementation code is publicly available on GitHub; this is the authors' analysis code for the leaf/cell/pedestrian counting domain adaptation experiments. The CVPPP (Zenodo) and other datasets are cited prior-work datasets, not paper-specific assets.Code · publicOur code is available at https://github.com/MattiaLitrico/Semi-supervised-Domain-Adaptation-for-Holistic-Counting-under-Label-Gap (accessed on 20 September 2021).Open asset ↗MattiaLitrico/Semi-supervised-Domain-Adaptation-for-Holistic-Counting-under-Label-Gaplines:104-121Code / dataset availability confirmedOpenAlex · Europe PMC · checked 8 Sept 2026
The stomatal index of the leaf is the ratio of the number of stomata to the total number of stomata and epidermal cells. Comparing with the stomatal density, the stomatal index is relatively constant in environmental conditions and the age of the leaf and, therefore, of diagnostic characteristics for a given genotype or species. Traditional assessment methods involve manual counting of the number of stomata and epidermal cells in microphotographs, which is labor-intensive and time-consuming. Although several automatic measurement algorithms of stomatal density have been proposed, no stomatal index pipelines are currently available. The main aim of this research is to develop an automated stomatal index measurement pipeline. The proposed method employed Faster regions with convolutional neural networks (R-CNN) and U-Net and image-processing techniques to count stomata and epidermal cells, and subsequently calculate the stomatal index. To improve the labeling speed, a semi-automatic strategy was employed for epidermal cell annotation in each micrograph. Benchmarking the pipeline on 1,000 microscopic images of leaf epidermis in the wheat dataset (Triticum aestivum L.), the average counting accuracies of 98.03 and 95.03% for stomata and epidermal cells, respectively, and the final measurement accuracy of the stomatal index of 95.35% was achieved. R2 values between automatic and manual measurement of stomata, epidermal cells, and stomatal index were 0.995, 0.983, and 0.895, respectively. The average running time (ART) for the entire pipeline could be as short as 0.32 s per microphotograph. The proposed pipeline also achieved a good transferability on the other families of the plant using transfer learning, with the mean counting accuracies of 94.36 and 91.13% for stomata and epidermal cells and the stomatal index accuracy of 89.38% in seven families of the plant. The pipeline is an automatic, rapid, and accurate tool for the stomatal index measurement, enabling high-throughput phenotyping, and facilitating further understanding of the stomatal and epidermal development for the plant physiology community. To the best of our knowledge, this is the first deep learning-based microphotograph analysis pipeline for stomatal index assessment.
Why it matches plant phenotyping methods葉の顕微鏡画像から気孔と表皮細胞を検出・計数し、気孔指数を自動推定する画像解析パイプラインの開発とベンチマーク検証が研究の中心である。
abstractThe main aim of this research is to develop an automated stomatal index measurement pipeline.
Reproduction assets foundThe authors explicitly state the stomatal index pipeline code is fully open-source on GitHub and the wheat microscopic image dataset is downloadable as a zip release from the same repository. Both are paper-specific, public, and directly actionable.Code · publicThe code is fully open-source for academic usage and can be downloaded at https://github.com/WeizhenLiuBioinform/stomatal_indexOpen asset ↗WeizhenLiuBioinform/stomatal_indexlines:361-376Dataset · publicThe wheat dataset is available for downloading at https://github.com/WeizhenLiuBioinform/stomatal_index/releases/download/wheat1.0/wheat_dataset.zipOpen asset ↗WeizhenLiuBioinform/stomatal_index · wheat1.0lines:361-376Supplement · publicSupplementary Table 2
Description of the cuticle dataset used for training and testing the stomatal index measurement model.Open asset ↗lines:651-703Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Early-stage plant density is an essential trait that determines the fate of a genotype under given environmental conditions and management practices. The use of RGB images taken from UAVs may replace the traditional visual counting in fields with improved throughput, accuracy, and access to plant localization. However, high-resolution images are required to detect the small plants present at the early stages. This study explores the impact of image ground sampling distance (GSD) on the performances of maize plant detection at three-to-five leaves stage using Faster-RCNN object detection algorithm. Data collected at high resolution (GSD ≈ 0.3 cm) over six contrasted sites were used for model training. Two additional sites with images acquired both at high and low (GSD ≈ 0.6 cm) resolutions were used to evaluate the model performances. Results show that Faster-RCNN achieved very good plant detection and counting (rRMSE = 0.08) performances when native high-resolution images are used both for training and validation. Similarly, good performances were observed (rRMSE = 0.11) when the model is trained over synthetic low-resolution images obtained by downsampling the native training high-resolution images and applied to the synthetic low-resolution validation images. Conversely, poor performances are obtained when the model is trained on a given spatial resolution and applied to another spatial resolution. Training on a mix of high- and low-resolution images allows to get very good performances on the native high-resolution (rRMSE = 0.06) and synthetic low-resolution (rRMSE = 0.10) images. However, very low performances are still observed over the native low-resolution images (rRMSE = 0.48), mainly due to the poor quality of the native low-resolution images. Finally, an advanced super resolution method based on GAN (generative adversarial network) that introduces additional textural information derived from the native high-resolution images was applied to the native low-resolution validation images. Results show some significant improvement (rRMSE = 0.22) compared to bicubic upsampling approach, while still far below the performances achieved over the native high-resolution images.
Why it matches plant phenotyping methodsUAV画像とFaster-RCNNを用いてトウモロコシの個体密度を検出・計数し、空間解像度や超解像手法の性能を比較・検証しており、植物表現型取得法が研究の中心です。
abstractThe use of RGB images taken from UAVs may replace the traditional visual counting in fields with improved throughput, accuracy, and access to plant localization.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicThe Cycle-ESRGAN network was implemented using Keras [ 56 ] deep learning library in Python. The codes will be made available on Github at the following link: https://github.com/kaaviyave/Cycle-ESRGAN .Open asset ↗kaaviyave/Cycle-ESRGANlines:231-249Code / dataset availability confirmedOpenAlex · Europe PMC · bioRxiv · checked 15 Sept 2026
Summary Revealing the contributions of genes to plant phenotype is frequently challenging because the effects of loss of gene function may be subtle or be masked by genetic redundancy. Such effects can potentially be detected by measuring plant fitness, which reflects the cumulative effects of genetic changes over the lifetime of a plant. However, fitness is challenging to measure accurately, particularly in species with high fecundity and relatively small propagule sizes such as Arabidopsis thaliana . An image segmentation-based (ImageJ) and a Faster Region Based Convolutional Neural Network (R-CNN) approach were used for measuring two Arabidopsis fitness traits: seed and fruit counts. Although straightforward to use, ImageJ was error-prone (correlation between true and predicted seed counts, r 2 =0.849) because seeds touching each other were undercounted. In contrast, Faster R-CNN yielded near perfect seed counts (r 2 =0.9996) and highly accurate fruit counts (r 2 =0.980). By examining seed counts, we were able to reveal fitness effects for genes that were previously reported to have no or condition-specific loss-of-function phenotypes. Our study provides models to facilitate the investigation of Arabidopsis fitness traits and demonstrates the importance of examining fitness traits in the study of gene functions.
Why it matches plant phenotyping methods画像分割とFaster R-CNNを用いて種子数・果実数という植物形質を高スループット測定し、精度比較・検証を行うことが中心であるため。
titleHigh throughput measurement of Arabidopsis thaliana fitness traits using transfer learning
Reproduction assets foundThe paper's Data availability statement explicitly deposits all analysis scripts and the final seed and fruit counting models (trained Faster R-CNN phenotyping models) on the authors' public GitHub repository, which is listed in allowed_urls.Code · public, PD, SH,
713
NLP, EV, EW, JKC, PJK, and MDL performed data collection and analysis. PW, FM,
714
MDL, and SHS wrote the manuscript. All authors read and approved the final manuscript.
715
716
Data availability
717
All the scripts used in this study and the final seed and fruit counting models are available
718
on Github at:
719
https://github.com/ShiuLab/Manuscript_Code/tree/master/2021_Arabidopsis_seed_and_f
720
ruit_count
721
722
References
723
Abadi M, Barham P, Chen JM, Chen ZF, Davis A, Dean J, Devin M, Ghemawat S,
724
Irving G, Isard M et al. 2016. TensorFlow: A system for large-scale machine
725
learning. 12th USENIX Symposium on Operating Systems Design and
726
Implementation. USENIXOpen asset ↗ShiuLab/Manuscript_Code · 2021_Arabidopsis_seed_and_fpdf-raw-page:33 lines:1-52Code / dataset availability confirmedCrossref · checked 9 Sept 2026
Solving many phenotyping problems involves not only automatic detection of objects in an image, but also counting the number of parts per object. We propose a solution in the form of a single deep network, tested for three agricultural datasets pertaining to bananas-per-bunch, spikelets-per-wheat-spike, and berries-per-grape-cluster. The suggested network incorporates object detection, object resizing, and part counting as modules in a single deep network, with several variants tested. The detection module is based on a Retina-Net architecture, whereas for the counting modules, two different architectures are examined: the first based on direct regression of the predicted count, and the other on explicit parts detection and counting. The results are promising, with the mean relative deviation between estimated and visible part count in the range of 9.2% to 11.5%. Further inference of count-based yield related statistics is considered. For banana bunches, the actual banana count (including occluded bananas) is inferred from the count of visible bananas. For spikelets-per-wheat-spike, robust estimation methods are employed to get the average spikelet count across the field, which is an effective yield estimator.
Why it matches plant phenotyping methods植物器官の可視パーツ数を画像から検出・計数する深層学習手法を開発し、複数作物データセットで評価しているため、表現型取得・推定法が中心です。
abstractWe propose a solution in the form of a single deep network, tested for three agricultural datasets pertaining to bananas-per-bunch, spikelets-per-wheat-spike, and berries-per-grape-cluster.
Reproduction assets foundThe paper's grape experiments use the public Embrapa WGISD dataset, extended by the authors with berry dot annotations that they state were made publicly available as part of that dataset extension. The banana and wheat datasets (Israel Phenomics Consortium) and the authors' code/models have no stated public release,; Dataset · publicThe dot annotations were made
publicly available as part of Embrapa WGISD dataset extension.Open asset ↗Embrapa WGISDpdf-page:5 lines:1-59Code / dataset availability confirmedCrossref · checked 14 Sept 2026
Phenotyping wheat (Triticum aestivum L.) is time-consuming and new methods are necessary to decrease labor. To develop a heterotic pool of male wheat lines for hybrid breeding, there must be an efficient way to measure both anther extrusion and the size of anthers. Five hundred and ninety-four soft red winter wheat lines in two replications of randomized complete block design were phenotyped for anther extrusion, a key trait for hybrid wheat production. A device was constructed to capture images using a mobile device. Four heads were sampled per line when anthesis was evident for half the heads in the plot. The extruded anthers were scraped onto a surface, their image was captured, and the area of the anthers was taken via ImageJ. The number of anthers extruded was estimated by counting the number of anthers per image and dividing by the number of heads sampled. The area per anther was taken by dividing the area of anthers per spike by the number of anthers per spike. A significant correlation (R=0.9, p
Why it matches plant phenotyping methods小麦の葯突出数と葯サイズを画像取得・ImageJ解析で測定する手法を開発し、大規模材料で適用・評価しており、表現型取得法が中心である。
abstractTo develop a heterotic pool of male wheat lines for hybrid breeding, there must be an efficient way to measure both anther extrusion and the size of anthers.
Reproduction assets foundThe paper's Data Availability Statement points to a public GitHub repository containing the paper's anther extrusion phenotyping data (HD, AD, AOAPS, NOAPS, APA for the HGAWN population), alongside request-based access via the corresponding author. The ImageJ macro and R analysis code are described but no separate codeDataset · publicof 7
Funding: This research was funded by USDA National Institute of Food and Agriculture, grant
number 2017-67007-25939.
Institutional Review Board Statement: Not applicable.
Informed Consent Statement: Not applicable.
Data Availability Statement: Data is available upon request via contact with the corresponding
author and at <https://github.com/zjwinn/Phenotyping-Anther-Extrusion-of-Wheat-Using-Image-Analysis>.
Acknowledgments: This work is supported by the Agriculture and Food Research Initiative Competi-
tive Grant 2017-67007-25939 (Wheat-CAP) from the USDA National Institute of Food and Agriculture.
Conflicts of Interest: The author claims no conflict of interest.
Abbreviations
NOAPS NuOpen asset ↗https://github.com/zjwinn/Phenotyping-Anther-Extrusion-of-Wheat-Using-Image-Analysispdf-raw-page:7 lines:1-53Code / dataset availability confirmedOpenAlex · Europe PMC · checked 8 Sept 2026
Leaf counting in potted plants is an important building block for estimating their health status and growth rate and has obtained increasing attention from the visual phenotyping community in recent years. Two novel deep learning approaches for visual leaf counting tasks are proposed, evaluated, and compared in this study. The first method performs counting via direct regression but using multiple image representation resolutions to attend leaves of multiple scales. The leaf count from multiple resolutions is fused using a novel technique to get the final count. The second method is detection with a regression model that counts the leaves after locating leaf center points and aggregating them. The algorithms are evaluated on the Leaf Counting Challenge (LCC) dataset of the Computer Vision Problems in Plant Phenotyping (CVPPP) conference 2017, and a new larger dataset of banana leaves. Experimental results show that both methods outperform previous CVPPP LCC challenge winners, based on the challenge evaluation metrics, and place this study as the state of the art in leaf counting. The detection with regression method is found to be preferable for larger datasets when the center-dot annotation is available, and it also enables leaf center localization with a 0.94 average precision. When such annotations are not available, the multiple scale regression model is a good option.
Why it matches plant phenotyping methods植物画像から葉数を推定する2つの深層学習手法を開発・比較し、既存および新規データセットで評価しているため、表現型取得手法が中心である。
abstractTwo novel deep learning approaches for visual leaf counting tasks are proposed, evaluated, and compared in this study.
Reproduction assets foundThe paper's authors explicitly state their full leaf-counting code (MSR and DRN models) is freely available on GitHub. The banana leaf dataset is proprietary and not public; the LCC datasets are external community benchmarks, not paper-specific assets.Code · publicThe entire code is freely accessible at https://github.com/farjon/Leaf-Counting .Open asset ↗farjon/Leaf-Countinglines:300-310Code / dataset availability confirmedOpenAlex · Crossref · Europe PMC · checked 15 Sept 2026
BACKGROUND: Maize (Zea mays L.) is one of the most important food sources in the world and has been one of the main targets of plant genetics and phenotypic research for centuries. Observation and analysis of various morphological phenotypic traits during maize growth are essential for genetic and breeding study. The generally huge number of samples produce an enormous amount of high-resolution image data. While high throughput plant phenotyping platforms are increasingly used in maize breeding trials, there is a reasonable need for software tools that can automatically identify visual phenotypic features of maize plants and implement batch processing on image datasets. RESULTS: On the boundary between computer vision and plant science, we utilize advanced deep learning methods based on convolutional neural networks to empower the workflow of maize phenotyping analysis. This paper presents Maize-IAS (Maize Image Analysis Software), an integrated application supporting one-click analysis of maize phenotype, embedding multiple functions: (I) Projection, (II) Color Analysis, (III) Internode length, (IV) Height, (V) Stem Diameter and (VI) Leaves Counting. Taking the RGB image of maize as input, the software provides a user-friendly graphical interaction interface and rapid calculation of multiple important phenotypic characteristics, including leaf sheath points detection and leaves segmentation. In function Leaves Counting, the mean and standard deviation of difference between prediction and ground truth are 1.60 and 1.625. CONCLUSION: The Maize-IAS is easy-to-use and demands neither professional knowledge of computer vision nor deep learning. All functions for batch processing are incorporated, enabling automated and labor-reduced tasks of recording, measurement and quantitative analysis of maize growth traits on a large dataset. We prove the efficiency and potential capability of our techniques and software to image-based plant research, which also demonstrates the feasibility and capability of AI technology implemented in agriculture and plant science.
Why it matches plant phenotyping methodsトウモロコシ画像から複数の形態形質を自動抽出するソフトウェアを開発・評価しており、植物フェノタイピング手法が研究の中心である。
abstractThis paper presents Maize-IAS (Maize Image Analysis Software), an integrated application supporting one-click analysis of maize phenotype
Reproduction assets foundThe authors' Maize-IAS analysis software (the paper's phenotyping analysis code) is publicly available on GitHub. The maize image datasets are explicitly not public and require request.Code · publicl development prospects of visual phenotype detection using deep learning methods. The methods and workflow provided in this article can also be easily applied to other crops.
Availability and requirements
Project name: A Maize Image Analysis Software using Deep Learning for High-throughput Plant Phenotyping.
Project home page: https://github.com/surefyyq/Maize-IAS
Operating system: Ubuntu18.04.
Programming language: Python3.
Other requirements: Pytorch 1.1.0 or higher, Torchvision 0.3.0 or higher.
Any restrictions to use by non-academic: None.
Supplementary information
Additional file 1. Installation and debug guidelines.
Publisher’s Note
Springer Nature remains neutral with regard to juOpen asset ↗surefyyq/Maize-IASlines:403-475Code / dataset availability confirmedbioRxiv · Europe PMC · Crossref · checked 8 Sept 2026
Progresses in agronomy rely on accurate measurement of the experimentations conducted to improve the yield component. Measurement of the plant density is required for a number of applications since it drives part of the crop fate. The standard manual measurements in the field could be efficiently replaced by high-throughput techniques based on high-spatial resolution images taken from UAVs. This study compares several automated detection of individual plants in the images from which the plant density can be estimated. It is based on a large dataset of high resolution Red/Green/Blue (RGB) images acquired from Unmanned Aerial Vehicules (UAVs) during several years and experiments over maize, sugar beet and sunflower crops at early stages. A total of 16247 plants have been labelled interactively on the images. Performances of handcrafted method (HC) were compared to those of deep learning (DL). The HC method consists in segmenting the image into green and background pixels, identifying rows, then objects corresponding to plants thanks to knowledge of the sowing pattern as prior information. The DL method is based on the Faster Region with Convolutional Neural Network (Faster RCNN) model trained over 2/3 of the images selected to represent a good balance between plant development stage and sessions. One model is trained for each crop. Results show that simple DL methods generally outperforms simple HC, particularly for maize and sunflower crops. A significant level of variability of plant detection performances is observed between the several experiments. This was explained by the variability of image acquisition conditions including illumination, plant development stage, background complexity and weed infestation. The image quality determines part of the performances for HC methods which makes the segmentation step more difficult. Performances of DL methods are limited mainly by the presence of weeds. A hybrid method (HY) was proposed to eliminate weeds between the rows using the rules developed for the HC method. HY improves slightly DL performances in the case of high weed infestation. When few images corresponding to the conditions of the testing dataset were complementing the training dataset for DL, a drastic increase of performances for all the crops is observed, with relative RMSE below 5% for the estimation of the plant density.
Why it matches plant phenotyping methodsUAV画像から個体を検出・計数し、作物密度を推定する画像解析手法を比較・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 compares several automated detection of individual plants in the images from which the plant density can be estimated.
Reproduction assets foundThe paper's authors explicitly state that the deep-learning model architecture and data augmentation details are given in their public code repository on GitHub, which is an authors' public URL implementing the paper's plant detection/counting analysis.Code · public258 architectural details are given in the code (https://github.com/EtienneDavid/plants-counting-detection)Open asset ↗EtienneDavid/plants-counting-detectionpdf-page:9 lines:1-52Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Japanese cedar ( Cryptomeria japonica ) is the most important timber species in Japan; however, its pollen is the primary cause of pollinosis in Japan. The total number of pollen grains produced by a single tree is determined by the number of male strobili (male flowers) and the number of pollen grains per male strobilus. While the number of male strobili is a visible and well-investigated trait, little is known about the number of pollen grains per male strobilus. We hypothesized that genetic and environmental factors affect the pollen number per male strobilus and explored the factors that affect pollen production and genetic variation among clones. We counted pollen numbers of 523 male strobili from 26 clones using a cell counter method that we recently developed. Piecewise Structural Equation Modeling (pSEM) revealed that the pollen number is mostly affected by genetic variation, male strobilus weight, and pollen size. Although we collected samples from locations with different environmental conditions, statistical modeling succeeded in predicting pollen numbers for different clones sampled from branches facing different directions. Comparison of predicted pollen numbers revealed that they varied >3-fold among the 26 clones. The determination of the factors affecting pollen number and a precise evaluation of genetic variation will contribute to breeding strategies to counter pollinosis. Furthermore, the combination of our efficient counting method and statistical modeling will provide a powerful tool not only for Japanese cedar but also for other plant species.
Why it matches plant phenotyping methods花粉数という植物形質を測定する新開発のセルカウンター法を適用し、統計モデルと組み合わせた再利用可能な計測手法として位置づけているため、方法論的役割が中心的です。
abstractWe counted pollen numbers of 523 male strobili from 26 clones using a cell counter method that we recently developed.
Reproduction assets foundThe paper's phenotype measurements (pollen number, pollen size, male strobilus weight, direction/height for all 523 samples from 26 clones) are published as Supplementary Table S1, publicly available at the MDPI supplementary URL. No author analysis code or trained models are deposited; the Data Availability Statement仅Supplement · publicions will also be useful for examining other traits in the field research.
Acknowledgments
We thank Yukiko Ito (Niigata Prefectural Forest Research Institute) for providing breeding materials, and Naoto-Benjamin Hamaya (University of Zurich) for valuable suggestions.
Supplementary Materials
The following are available online at https://www.mdpi.com/article/10.3390/plants10050856/s1 . Supplementary Figure S1. Scatterplot of male strobilus weight and area. All samples are shown in this figure. Weight and area are strongly correlated (r = 0.892). Different clones are represented by different symbols (see Table 1 ). Supplementary Table S1. Data for all samples.
Click here for additional data filOpen asset ↗lines:258-292Code / dataset availability confirmedEurope PMC · checked 9 Sept 2026
Sphagnum peatmosses play an important part in water table management of many peatland ecosystems. Keeping the ecosystem saturated, they slow the breakdown of organic matter and release of greenhouse gases, facilitating peatland's function as a carbon sink rather than a carbon source. Although peatland monitoring and restoration programs have increased recently, there are few tools to quantify traits that Sphagnum species display in their ecosystems. Colony density is often described as an important determinant in the establishment and performance in Sphagnum but detailed evidence for this is limited. In this study, we describe an image analysis pipeline that accurately annotates Sphagnum capitula and estimates plant density using open access computer vision packages. The pipeline was validated using images of different Sphagnum species growing in different habitats, taken on different days and with different smartphones. The developed pipeline achieves high accuracy scores, and we demonstrate its utility by estimating colony densities in the field and detecting intra and inter-specific colony densities and their relationship with habitat. This tool will enable ecologists and conservationists to rapidly acquire accurate estimates of Sphagnum density in the field without the need of specialised equipment.
Why it matches plant phenotyping methodsSphagnumの植物密度という明示的な形態・生態形質を、画像解析パイプラインで抽出する手法を開発し、異なる種・生育地・撮影条件で検証しているため、植物フェノタイピング手法が中心です。
abstractwe describe an image analysis pipeline that accurately annotates Sphagnum capitula and estimates plant density using open access computer vision packages.
Reproduction assets foundThe paper's field Sphagnum images and annotation data are deposited publicly (DOI 10.20391/9ba4df8f-2d28-4bce-b9b8-ec6368b636e0), and the authors' Capitula-Counter image analysis pipeline is freely available on the NPPC GitHub. Both are paper-specific, public, and actionable.Dataset · publicAll images used are available at https://doi.org/10.20391/9ba4df8f-2d28-4bce-b9b8-ec6368b636e0 (accessed on 21 April 2021).Open asset ↗10.20391/9ba4df8f-2d28-4bce-b9b8-ec6368b636e0lines:69-74Code / dataset availability confirmedOpenAlex · Europe PMC · Crossref · checked 14 Sept 2026
Abstract Background : Maize (Zea mays L.) is one of the most important food sources in the world and has been one of the main targets of plant genetics and phenotypic research for centuries. Observation and analysis of various morphological phenotypic traits during maize growth are essential for genetic and breeding study. The generally huge number of samples produce an enormous amount of high-resolution image data. While high throughput plant phenotyping platforms are increasingly used in maize breeding trials, there is a reasonable need for software tools that can automatically identify visual phenotypic features of maize plants and implement batch processing on image datasets. Results : On the boundary between computer vision and plant science, we utilize advanced deep learning methods based on convolutional neural networks to empower the workflow of maize phenotyping analysis. This paper presents Maize-PAS ( Maize Phenotyping Analysis Software), an integrated application supporting one-click analysis of maize phenotype, embedding multiple functions: I. Projection, II. Color Analysis, III. Internode length, IV. Height, V. Stem Diameter and VI. Leaves Counting. Taking the RGB image of maize as input, the software provides a user-friendly graphical interaction interface and rapid calculation of multiple important phenotypic characteristics, including leaf sheath points detection and leaves segmentation. In function Leaves Counting, the mean and standard deviation of difference between prediction and ground truth are 1.60 and 1.625. Conclusion : The Maize-PAS is easy-to-use and demands neither professional knowledge of computer vision nor deep learning. All functions for batch processing are incorporated, enabling automated and labor-reduced tasks of recording, measurement and quantitative analysis of maize growth traits on a large dataset. We prove the efficiency and potential capability of our techniques and software to image-based plant research, which also demonstrates the feasibility and capability of AI technology implemented in agriculture and plant science. Keywords : Maize phenotyping; Instance segmentation; Computer vision; Deep learning; Convolutional neural network
Why it matches plant phenotyping methodsトウモロコシ画像から複数の形態形質を自動抽出する深層学習ソフトウェアを開発・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 Maize-PAS ( Maize Phenotyping Analysis Software), an integrated application supporting one-click analysis of maize phenotype, embedding multiple functions: I. Projection, II. Color Analysis, III. Internode length, IV. Height, V. Stem Diameter and VI. Leaves Counting.
Reproduction assets foundThe paper's maize phenotyping software (Maize-IAS), which implements the paper's image analysis functions (RoI extraction, color analysis, internode/height/stem diameter, leaf counting), is publicly available via the authors' GitHub project home page. The maize image datasets and annotations are not public and require Code · publicWe
reveal the potential development prospects of visual phenotype detection using deep
learning methods. The methods and workflow provided in this article can also be
easily applied to other crops.
Availability and requirements
Project name: Automated Maize Phenotyping Analysis Software using Deep Learn-
ing.
Project home page: https://github.com/sureatgithub/Maize- IAS
Operating system: Ubuntu18.04.
Programming language: Python3.
Other requirements: Pytorch 1.1.0 or higher, Torchvision 0.3.0 or higher.
Any restrictions to use by non-academic: None
Ethics approval and consent to participate
Not applicable.
Consent for publication
Not applicable.
Availability of data and materials
The datasOpen asset ↗sureatgithub/Maize-pdf-raw-page:18 lines:1-46Code / dataset availability confirmedOpenAlex · Europe PMC · checked 14 Sept 2026
In plant breeding, unmanned aerial vehicles (UAVs) carrying multispectral cameras have demonstrated increasing utility for high-throughput phenotyping (HTP) to aid the interpretation of genotype and environment effects on morphological, biochemical, and physiological traits. A key constraint remains the reduced resolution and quality extracted from "stitched" mosaics generated from UAV missions across large areas. This can be addressed by generating high-quality reflectance data from a single nadir image per plot. In this study, a pipeline was developed to derive reflectance data from raw multispectral UAV images that preserve the original high spatial and spectral resolutions and to use these for phenotyping applications. Sequential steps involved (i) imagery calibration, (ii) spectral band alignment, (iii) backward calculation, (iv) plot segmentation, and (v) application. Each step was designed and optimised to estimate the number of plants and count sorghum heads within each breeding plot. Using a derived nadir image of each plot, the coefficients of determination were 0.90 and 0.86 for estimates of the number of sorghum plants and heads, respectively. Furthermore, the reflectance information acquired from the different spectral bands showed appreciably high discriminative ability for sorghum head colours (i.e., red and white). Deployment of this pipeline allowed accurate segmentation of crop organs at the canopy level across many diverse field plots with minimal training needed from machine learning approaches.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像から反射率を抽出し、圃場区画内の植物数・穂数・穂色を推定するパイプラインの開発と精度評価が中心であり、植物表現型取得手法に該当する。
abstractIn this study, a pipeline was developed to derive reflectance data from raw multispectral UAV images that preserve the original high spatial and spectral resolutions and to use these for phenotyping applications.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicTrial details, sample imagery, and essential codes used in this article can be accessed through https://github.com/YanZhao15/AltumApplication.git .Open asset ↗YanZhao15/AltumApplicationlines:150-152Code / dataset availability confirmedOpenAlex · arXiv · checked 14 Sept 2026
Plant phenotyping tasks such as leaf segmentation and counting are fundamental to the study of phenotypic traits. Since it is well-suited for these tasks, deep supervised learning has been prevalent in recent works proposing better performing models at segmenting and counting leaves. Despite good efforts from research groups, one of the main challenges for proposing better methods is still the limitation of labelled data availability. The main efforts of the field seem to be augmenting existing limited data sets, and some aspects of the modelling process have been under-discussed. This paper explores such topics and present experiments that led to the development of the best-performing method in the Leaf Segmentation Challenge and in another external data set of Komatsuna plants. The model has competitive performance while been arguably simpler than other recently proposed ones. The experiments also brought insights such as the fact that model cardinality and test-time augmentation may have strong applications in object segmentation of single class and high occlusion, and regarding the data distribution of recently proposed data sets for benchmarking.
Why it matches plant phenotyping methods葉のセグメンテーションと計数という植物形態形質の抽出手法を開発・評価し、チャレンジと外部データセットで性能比較しているため、方法が研究の中心である。
abstractPlant phenotyping tasks such as leaf segmentation and counting are fundamental to the study of phenotypic traits.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Dataset · publicThe CVPPP data set represents perhaps that largest effort to address the ongoing problem of lacking benchmark data sets and metrics for specific tasks such as leaf segmentation and counting on a controlled environment. First presented in 2014, but updated in 2017, the data set comprises images of mainly Arabidopsis and a small portion of Tobacco plants and can be accessed by Minervini et al. (2015b) .Open asset ↗lines:78-92Code / dataset availability confirmedOpenAlex · Crossref · Europe PMC · checked 8 Sept 2026
Plant counting runs through almost every stage of agricultural production from seed breeding, germination, cultivation, fertilization, pollination to yield estimation, and harvesting. With the prevalence of digital cameras, graphics processing units and deep learning-based computer vision technology, plant counting has gradually shifted from traditional manual observation to vision-based automated solutions. One of popular solutions is a state-of-the-art object detection technique called Faster R-CNN where plant counts can be estimated from the number of bounding boxes detected. It has become a standard configuration for many plant counting systems in plant phenotyping. Faster R-CNN, however, is expensive in computation, particularly when dealing with high-resolution images. Unfortunately high-resolution imagery is frequently used in modern plant phenotyping platforms such as unmanned aerial vehicles, engendering inefficient image analysis. Such inefficiency largely limits the throughput of a phenotyping system. The goal of this work hence is to provide an effective and efficient tool for high-throughput plant counting from high-resolution RGB imagery. In contrast to conventional object detection, we encourage another promising paradigm termed object counting where plant counts are directly regressed from images, without detecting bounding boxes. In this work, by profiling the computational bottleneck, we implement a fast version of a state-of-the-art plant counting model TasselNetV2 with several minor yet effective modifications. We also provide insights why these modifications make sense. This fast version, TasselNetV2+, runs an order of magnitude faster than TasselNetV2, achieving around 30 fps on image resolution of 1980 × 1080, while it still retains the same level of counting accuracy. We validate its effectiveness on three plant counting tasks, including wheat ears counting, maize tassels counting, and sorghum heads counting. To encourage the use of this tool, our implementation has been made available online at https://tinyurl.com/TasselNetV2plus.
Why it matches plant phenotyping methods高速・高スループットな植物カウント手法を開発し、複数作物で検証した植物フェノタイピング手法の中心的研究。
abstractThe goal of this work hence is to provide an effective and efficient tool for high-throughput plant counting from high-resolution RGB imagery.
Reproduction assets foundThe paper's authors publicly released their TasselNetV2+ PyTorch implementation (the paper's plant counting/phenotyping analysis code) online. The three plant counting datasets used are cited prior datasets, not paper-specific deposits.Code · publicTo encourage the use of this tool, our implementation has been made available online at https://tinyurl.com/TasselNetV2plusOpen asset ↗TasselNetV2pluslines:225-304Code / dataset availability confirmedEurope PMC · OpenAlex · checked 15 Sept 2026
Early generation breeding nurseries with thousands of genotypes in single-row plots are well suited to capitalize on high throughput phenotyping. Nevertheless, methods to monitor the intrinsically hard-to-phenotype early development of wheat are yet rare. We aimed to develop proxy measures for the rate of plant emergence, the number of tillers, and the beginning of stem elongation using drone-based imagery. We used RGB images (ground sampling distance of 3 mm pixel -1 ) acquired by repeated flights (≥ 2 flights per week) to quantify temporal changes of visible leaf area. To exploit the information contained in the multitude of viewing angles within the RGB images, we processed them to multiview ground cover images showing plant pixel fractions. Based on these images, we trained a support vector machine for the beginning of stem elongation (GS30). Using the GS30 as key point, we subsequently extracted plant and tiller counts using a watershed algorithm and growth modeling, respectively. Our results show that determination coefficients of predictions are moderate for plant count ( R 2 = 0.52), but strong for tiller count ( R 2 = 0.86) and GS30 ( R 2 = 0.77). Heritabilities are superior to manual measurements for plant count and tiller count, but inferior for GS30 measurements. Increasing the selection intensity due to throughput may overcome this limitation. Multiview image traits can replace hand measurements with high efficiency (85-223%). We therefore conclude that multiview images have a high potential to become a standard tool in plant phenomics.
Why it matches plant phenotyping methodsドローン多視点画像と画像解析により、コムギの出芽・分げつ数・茎伸長を推定する手法を開発・評価しており、植物表現型取得が研究の中心である。
abstractWe aimed to develop proxy measures for the rate of plant emergence, the number of tillers, and the beginning of stem elongation using drone-based imagery.
Reproduction assets foundThe paper publicly releases its authors' phenotyping processing code (multiview image generation, segmentation, early growth trait extraction) on ETH GitLab and secondary plot-based phenotype data (BLUEs, BLUPs, repeatability, heritability) on the ETH Research Collection. Raw UAS images are only available upon request,Code · publicfor the field management and freezing damage ratings at site FIP (all persons ETH Zurich, Zürich, Switzerland). We thank the anonymous reviewers for the thorough evaluation and constructive suggestions.
Additional Points
Source Code . Maintained source code for processing is publicly available on the ETH Zurich GitLab server ( https://gitlab.ethz.ch/crop_phenotyping/PhenoFly_data_processing_tools ); archived versions can be found in Roth [ 62 , 63 ]. The GitLab repository includes following preprocessing steps: (1) Image mask generation (Standalone Agisoft Metashape Script) ( https://gitlab.ethz.ch/crop_phenotyping/PhenoFly_data_processing_tools/ImageProjectionAgisoft ). (2) Image segmentatiOpen asset ↗PhenoFly_data_processing_toolslines:218-251Code · publiccode for processing is publicly available on the ETH Zurich GitLab server ( https://gitlab.ethz.ch/crop_phenotyping/PhenoFly_data_processing_tools ); archived versions can be found in Roth [ 62 , 63 ]. The GitLab repository includes following preprocessing steps: (1) Image mask generation (Standalone Agisoft Metashape Script) ( https://gitlab.ethz.ch/crop_phenotyping/PhenoFly_data_processing_tools/ImageProjectionAgisoft ). (2) Image segmentation with random forest ( https://gitlab.ethz.ch/crop_phenotyping/PhenoFly_data_processing_tools/ActiveLearningSegmentation ). (3) Multiview image generation ( https://gitlab.ethz.ch/crop_phenotyping/PhenoFly_data_processing_tools/MultiViewImage ). The GiOpen asset ↗PhenoFly_data_processing_tools/ImageProjectionAgisoftlines:218-251Code · publictools ); archived versions can be found in Roth [ 62 , 63 ]. The GitLab repository includes following preprocessing steps: (1) Image mask generation (Standalone Agisoft Metashape Script) ( https://gitlab.ethz.ch/crop_phenotyping/PhenoFly_data_processing_tools/ImageProjectionAgisoft ). (2) Image segmentation with random forest ( https://gitlab.ethz.ch/crop_phenotyping/PhenoFly_data_processing_tools/ActiveLearningSegmentation ). (3) Multiview image generation ( https://gitlab.ethz.ch/crop_phenotyping/PhenoFly_data_processing_tools/MultiViewImage ). The GitLab repository furthermore includes the following trait extraction method: (4) Early growth trait extraction ( https://gitlab.ethz.ch/crop_pOpen asset ↗PhenoFly_data_processing_tools/ActiveLearningSegmentationlines:218-251Code / dataset availability confirmedarXiv · checked 9 Sept 2026
Supervised learning is often used to count objects in images, but for counting small, densely located objects, the required image annotations are burdensome to collect. Counting plant organs for image-based plant phenotyping falls within this category. Object counting in plant images is further challenged by having plant image datasets with significant domain shift due to different experimental conditions, e.g. applying an annotated dataset of indoor plant images for use on outdoor images, or on a different plant species. In this paper, we propose a domain-adversarial learning approach for domain adaptation of density map estimation for the purposes of object counting. The approach does not assume perfectly aligned distributions between the source and target datasets, which makes it more broadly applicable within general object counting and plant organ counting tasks. Evaluation on two diverse object counting tasks (wheat spikelets, leaves) demonstrates consistent performance on the target datasets across different classes of domain shift: from indoor-to-outdoor images and from species-to-species adaptation.
Why it matches plant phenotyping methods植物器官数を画像から推定するドメイン適応・密度マップ推定法を開発し、コムギ小穂と葉の計数で評価しており、表現型取得手法が中心である。
abstractCounting plant organs for image-based plant phenotyping falls within this category.
Reproduction assets foundThe paper provides two paper-specific public assets: the authors' implementation code for the domain-adversarial counting model on GitHub, and the authors' newly created GWHD dot annotations deposited on figshare. Other URLs are cited prior-work datasets, not paper-specific assets.Code · publicAll experiments were performed on a GeForce RTX 2070 GPU with 8GB memory using the Pytorch framework. The implementation is available at: https://github.com/p2irc/UDA4POCOpen asset ↗p2irc/UDA4POClines:81-104Dataset · publicTo evaluate our method, we created dot annotations for 67 images from the GWHD which are used as ground truth. These annotations are made publicly available at https://doi.org/10.6084/m9.figshare.12652973.v2 .Open asset ↗10.6084/m9.figshare.12652973.v2lines:105-155Code / dataset availability confirmedarXiv · checked 15 Sept 2026
Providing an accurate evaluation of palm tree plantation in a large region can bring meaningful impacts in both economic and ecological aspects. However, the enormous spatial scale and the variety of geological features across regions has made it a grand challenge with limited solutions based on manual human monitoring efforts. Although deep learning based algorithms have demonstrated potential in forming an automated approach in recent years, the labelling efforts needed for covering different features in different regions largely constrain its effectiveness in large-scale problems. In this paper, we propose a novel domain adaptive oil palm tree detection method, i.e., a Multi-level Attention Domain Adaptation Network (MADAN) to reap cross-regional oil palm tree counting and detection. MADAN consists of 4 procedures: First, we adopted a batch-instance normalization network (BIN) based feature extractor for improving the generalization ability of the model, integrating batch normalization and instance normalization. Second, we embedded a multi-level attention mechanism (MLA) into our architecture for enhancing the transferability, including a feature level attention and an entropy level attention. Then we designed a minimum entropy regularization (MER) to increase the confidence of the classifier predictions through assigning the entropy level attention value to the entropy penalty. Finally, we employed a sliding window-based prediction and an IOU based post-processing approach to attain the final detection results. We conducted comprehensive ablation experiments using three different satellite images of large-scale oil palm plantation area with six transfer tasks. MADAN improves the detection accuracy by 14.98% in terms of average F1-score compared with the Baseline method (without DA), and performs 3.55%-14.49% better than existing domain adaptation methods.
Why it matches plant phenotyping methods油ヤシ個体の計数・検出という植物形態／個体数形質を衛星画像から推定する手法を開発し、アブレーション実験と既存手法比較で検証しており、フェノタイピング手法が中心である。
abstractwe propose a novel domain adaptive oil palm tree detection method, i.e., a Multi-level Attention Domain Adaptation Network (MADAN) to reap cross-regional oil palm tree counting and detection.
Reproduction assets foundThe authors explicitly state that their code and datasets (satellite images and annotations used for oil palm tree detection) are publicly available on GitHub.Code · publiche oil palm tree detection performance across different
remotely sensed images acquired from different sensors, regions and dates, without using labeled samples in the
target region. Our MADAN is proposed for enhancing both the generalization capacity and the transferability of
our model. Our codes and datasets are available on https://github.com/rs-dl/MADAN. The major contributions of
our work are as follows:
(1) We propose an adaptive object detector named MADAN for oil palm tree counting and detection across different
satellite images, which is the first work for large-scale domain adaptive tree crown detection using multi-source and
multi-temporal remote sensing images.
(2) WeOpen asset ↗rs-dl/MADANpdf-raw-page:6 lines:1-22Code / dataset availability confirmedEurope PMC · checked 9 Sept 2026
Rice density is closely related to yield estimation, growth diagnosis, cultivated area statistics, and management and damage evaluation. Currently, rice density estimation heavily relies on manual sampling and counting, which is inefficient and inaccurate. With the prevalence of digital imagery, computer vision (CV) technology emerges as a promising alternative to automate this task. However, challenges of an in-field environment, such as illumination, scale, and appearance variations, render gaps for deploying CV methods. To fill these gaps towards accurate rice density estimation, we propose a deep learning-based approach called the Scale-Fusion Counting Classification Network (SFC 2 Net) that integrates several state-of-the-art computer vision ideas. In particular, SFC 2 Net addresses appearance and illumination changes by employing a multicolumn pretrained network and multilayer feature fusion to enhance feature representation. To ameliorate sample imbalance engendered by scale, SFC 2 Net follows a recent blockwise classification idea. We validate SFC 2 Net on a new rice plant counting (RPC) dataset collected from two field sites in China from 2010 to 2013. Experimental results show that SFC 2 Net achieves highly accurate counting performance on the RPC dataset with a mean absolute error (MAE) of 25.51, a root mean square error (MSE) of 38.06, a relative MAE of 3.82%, and a R 2 of 0.98, which exhibits a relative improvement of 48.2% w.r.t. MAE over the conventional counting approach CSRNet. Further, SFC 2 Net provides high-throughput processing capability, with 16.7 frames per second on 1024 × 1024 images. Our results suggest that manual rice counting can be safely replaced by SFC 2 Net at early growth stages. Code and models are available online at https://git.io/sfc2net.
Why it matches plant phenotyping methodsイネ個体数という植物形態・密度形質を画像から自動推定する深層学習手法を開発し、新規データセットで精度検証しているため、方法が中心である。
abstractwe propose a deep learning-based approach called the Scale-Fusion Counting Classification Network (SFC 2 Net)
Reproduction assets foundThe paper's rice plant counting (RPC) dataset (382 field images with 211,971 dot annotations) and the authors' SFC2Net code and trained models are explicitly stated to be publicly available at the authors' URL https://git.io/sfc2net, which matches an allowed URL.Dataset · publicThe RPC dataset has been made available at https://git.io/sfc2net .Open asset ↗lines:403-419Code · publicCode and models are available online at https://git.io/sfc2net .Open asset ↗lines:1-28Code / dataset availability confirmedOpenAlex · Europe PMC · checked 9 Sept 2026
BACKGROUND: The population of plants is a crucial indicator in plant phenotyping and agricultural production, such as growth status monitoring, yield estimation, and grain depot management. To enhance the production efficiency and liberate labor force, many automated counting methods have been proposed, in which computer vision-based approaches show great potentials due to the feasibility of high-throughput processing and low cost. In particular, with the success of deep learning, more and more deeper learning-based approaches are introduced to deal with agriculture automation. Since different detection- and regression-based counting models have distinct characteristics, how to choose an appropriate model given the target task at hand remains unexplored and is important for practitioners. RESULTS: Targeting in-field maize tassels as a representative case study, the goal of this work is to present a comprehensive benchmark of state-of-the-art object detection and object counting methods, including Faster R-CNN, YOLOv3, FaceBoxes, RetinaNet, and the leading counting model of maize tassels-TasselNet. We create a Maize Tassel Detection Counting (MTDC) dataset by supplementing bounding box annotations to the Maize Tassels Counting (MTC) dataset to allow the training of detection models. We investigate key factors effecting the practical applications of the models, such as convergence behavior, scale robustness, speed-accuracy trade-off, as well as parameter sensitivity. Based on our benchmark, we summarise the advantages and limitations of each method and suggest several possible directions to improve current detection- and regression-based counting approaches to benefit next-generation intelligent agriculture. CONCLUSIONS: error. While detection-based methods are more robust than regression-based methods in scale variations and can infer extra information (e.g., object positions and sizes), the latter ones have significantly faster convergence behaviors and inference speed. To choose an appropriate in-filed plant counting method, accuracy, robustness, speed and some other algorithm-specific factors should be taken into account with the same priority. This work sheds light on different aspects of existing detection and counting approaches and provides guidance on how to tackle in-field plant counting. The MTDC dataset is made available at https://git.io/MTDC.
Why it matches plant phenotyping methodsトウモロコシ雄穂の検出・計数という植物形質の取得を対象に、複数の画像認識手法をベンチマークし、専用データセットも構築しているため、表現型計測手法が中心である。
abstractWe create a Maize Tassel Detection Counting (MTDC) dataset by supplementing bounding box annotations to the Maize Tassels Counting (MTC) dataset
Reproduction assets foundThe paper's MTDC dataset (MTC maize tassel images with new bounding box annotations, 13,562 boxes) is explicitly released publicly at the authors' URL https://git.io/MTDC, stated in both the abstract and Data Availability Statement. No author analysis code or trained model checkpoints are explicitly deposited.Dataset · publicThe MTDC dataset and other supporting materials are made available at https://git.io/MTDC .Open asset ↗lines:201-255Code / dataset availability confirmedEurope PMC · checked 9 Sept 2026
Background Wheat yield is influenced by the number of ears per unit area, and manual counting has traditionally been used to estimate wheat yield. To realize rapid and accurate wheat ear counting, K-means clustering was used for the automatic segmentation of wheat ear images captured by hand-held devices. The segmented data set was constructed by creating four categories of image labels: non-wheat ear, one wheat ear, two wheat ears, and three wheat ears, which was then was sent into the convolution neural network (CNN) model for training and testing to reduce the complexity of the model. Results The recognition accuracy of non-wheat, one wheat, two wheat ears, and three wheat ears were 99.8, 97.5, 98.07, and 98.5%, respectively. The model R 2 reached 0.96, the root mean square error (RMSE) was 10.84 ears, the macro F1-score and micro F1-score both achieved 98.47%, and the best performance was observed during late grain-filling stage ( R 2 = 0.99, RMSE = 3.24 ears). The model could also be applied to the UAV platform ( R 2 = 0.97, RMSE = 9.47 ears). Conclusions The classification of segmented images as opposed to target recognition not only reduces the workload of manual annotation but also improves significantly the efficiency and accuracy of wheat ear counting, thus meeting the requirements of wheat yield estimation in the field environment.
Why it matches plant phenotyping methods小麦穂数という植物形態・収量関連形質を、画像セグメンテーションとCNNで自動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。
abstractTo realize rapid and accurate wheat ear counting, K-means clustering was used for the automatic segmentation of wheat ear images captured by hand-held devices.
Reproduction assets foundThe authors publicly released their analysis code (K-means segmentation + CNN wheat ear counting pipeline) on GitHub. The image/phenotype datasets are only available on request from the corresponding author, so they do not qualify as public assets.Code · publicThe code can be found at https://github.com/xuxin468/earcouting .Open asset ↗xuxin468/earcoutinglines:190-213Code / dataset availability confirmedOpenAlex · checked 15 Sept 2026
Abstract Background: Maize (Zea mays L.) is one of the most important food sources in the world and has been one of the main targets of plant genetics and phenotypic research for centuries. Observation and analysis of various morphological phenotypic traits during maize growth are essential for genetic and breeding study. The generally huge number of samples produce an enormous amount of high-resolution image data. While high throughput plant phenotyping platforms are increasingly used in maize breeding trials, there is a reasonable need for software tools that can automatically identify visual phenotypic features of maize plants and implement batch processing on image datasets.Results: On the boundary between computer vision and plant science, we utilize advanced deep learning methods based on convolutional neural networks to empower the workflow of maize phenotyping analysis. This paper presents Maize-PAS ( Maize Phenotyping Analysis Software), an integrated application supporting one-click analysis of maize phenotype, embedding multiple functions: I. Projection, II. Color Analysis, III. Internode length, IV. Height, V. Stem Diameter and VI. Leaves Counting. Taking the RGB image of maize as input, the software provides a user-friendly graphical interaction interface and rapid calculation of multiple important phenotypic characteristics, including leaf sheath points detection and leaves segmentation. In function Leaves Counting, the mean and standard deviation of difference between prediction and ground truth are 1.60 and 1.625.Conclusion: The Maize-PAS is easy-to-use and demands neither professional knowledge of computer vision nor deep learning. All functions for batch processing are incorporated, enabling automated and labor-reduced tasks of recording, measurement and quantitative analysis of maize growth traits on a large dataset. We prove the efficiency and potential capability of our techniques and software to image-based plant research, which also demonstrates the feasibility and capability of AI technology implemented in agriculture and plant science.
Why it matches plant phenotyping methodsトウモロコシ画像から複数の形態形質を自動抽出するソフトウェアを開発し、精度評価も行っているため、植物フェノタイピング手法が中心である。
abstractThis paper presents Maize-PAS ( Maize Phenotyping Analysis Software), an integrated application supporting one-click analysis of maize phenotype
Reproduction assets foundThe authors' Maize-PAS phenotyping analysis software is publicly available on GitHub with an explicit project home page. The maize image/annotation datasets are explicitly not public (available only on request), and Labelme is a generic third-party annotation tool, not a paper-specific asset.Code · publicWe
reveal the potential development prospects of visual phenotype detection using deep
learning methods. The methods and workflow provided in this article can also be
easily applied to other crops.
Availability and requirements
Project name: Automated Maize Phenotyping Analysis Software using Deep Learn-
ing.
Project home page: https://github.com/sureatgithub/MaizePAS
Operating system: Ubuntu18.04.
Programming language: Python3.
Other requirements: Pytorch 1.1.0 or higher, Torchvision 0.3.0 or higher.
Any restrictions to use by non-academic: None
Ethics approval and consent to participate
Not applicable.
Consent for publication
Not applicable.
Availability of data and materials
The datasetsOpen asset ↗sureatgithub/MaizePASpdf-raw-page:16 lines:1-46Code / dataset availability confirmedEurope PMC · Crossref · checked 9 Sept 2026
Rapeseed is an important oil crop in China. Timely estimation of rapeseed stand count at early growth stages provides useful information for precision fertilization, irrigation, and yield prediction. Based on the nature of rapeseed, the number of tillering leaves is strongly related to its growth stages. However, no field study has been reported on estimating rapeseed stand count by the number of leaves recognized with convolutional neural networks (CNNs) in unmanned aerial vehicle (UAV) imagery. The objectives of this study were to provide a case for rapeseed stand counting with reference to the existing knowledge of the number of leaves per plant and to determine the optimal timing for counting after rapeseed emergence at leaf development stages with one to seven leaves. A CNN model was developed to recognize leaves in UAV-based imagery, and rapeseed stand count was estimated with the number of recognized leaves. The performance of leaf detection was compared using sample sizes of 16, 24, 32, 40, and 48 pixels. Leaf overcounting occurred when a leaf was much bigger than others as this bigger leaf was recognized as several smaller leaves. Results showed CNN-based leaf count achieved the best performance at the four- to six-leaf stage with F-scores greater than 90% after calibration with overcounting rate. On average, 806 out of 812 plants were correctly estimated on 53 days after planting (DAP) at the four- to six-leaf stage, which was considered as the optimal observation timing. For the 32-pixel patch size, root mean square error (RMSE) was 9 plants with relative RMSE (rRMSE) of 2.22% on 53 DAP, while the mean RMSE was 12 with mean rRMSE of 2.89% for all patch sizes. A sample size of 32 pixels was suggested to be optimal accounting for balancing performance and efficiency. The results of this study confirmed that it was feasible to estimate rapeseed stand count in field automatically, rapidly, and accurately. This study provided a special perspective in phenotyping and cultivation management for estimating seedling count for crops that have recognizable leaves at their early growth stage, such as soybean and potato.
Why it matches plant phenotyping methodsUAV画像とCNNを用いて rapeseed の葉を認識し、植物体数（stand count）を自動推定する手法の開発・性能評価が研究の中心であるため、植物フェノタイピング方法論に該当します。
abstractA CNN model was developed to recognize leaves in UAV-based imagery, and rapeseed stand count was estimated with the number of recognized leaves.
Reproduction assets foundThe paper's data availability statement explicitly deposits the 'Rapeseed_seedling_counting' data (supporting the UAV imagery-based stand count findings) in a public GitHub repository with an authors' URL, qualifying as a paper-specific public asset.Dataset · publicThe “Rapeseed_seedling_counting” data that support the findings of this study are available in “LARSC-Lab/Rapeseed_seedling_counting” in GitHub, which can be found at https://github.com/LARSC-Lab/Rapeseed_seedling_counting .Open asset ↗LARSC-Lab/Rapeseed_seedling_countinglines:590-664Code / dataset availability confirmedEurope PMC · checked 9 Sept 2026
The traits of rice panicles play important roles in yield assessment, variety classification, rice breeding, and cultivation management. Most traditional grain phenotyping methods require threshing and thus are time-consuming and labor-intensive; moreover, these methods cannot obtain 3D grain traits. In this work, based on X-ray computed tomography, we proposed an image analysis method to extract twenty-two 3D grain traits. After 104 samples were tested, the R 2 values between the extracted and manual measurements of the grain number and grain length were 0.980 and 0.960, respectively. We also found a high correlation between the total grain volume and weight. In addition, the extracted 3D grain traits were used to classify the rice varieties, and the support vector machine classifier had a higher recognition accuracy than the stepwise discriminant analysis and random forest classifiers. In conclusion, we developed a 3D image analysis pipeline to extract rice grain traits using X-ray computed tomography that can provide more 3D grain information and could benefit future research on rice functional genomics and rice breeding.
Why it matches plant phenotyping methodsX線CTを用いてイネ穀粒の22種類の3D形質を抽出する画像解析パイプラインを開発し、手動測定との一致性で検証しているため、植物フェノタイピング手法が研究の中心です。
abstractIn this work, based on X-ray computed tomography, we proposed an image analysis method to extract twenty-two 3D grain traits.
Reproduction assets foundThe paper's MATLAB 3D image analysis pipeline for extracting rice grain traits from X-ray CT is explicitly stated to be publicly available, with an authors' GitHub repository URL matching an allowed URL. The phenotypic data (Supplementary File 1) is only available as a PMC supplement with no allowed URL, so it is not aCode · publicthe source codes of all the scripts are available online in Supplementary File 3 or at the following link: http://plantphenomics.hzau.edu.cn/download_checkiflogin_en.action , or https://github.com/cancanzc/ricePanicle_grainTraits_ProcessingOpen asset ↗cancanzc/ricePanicle_grainTraits_Processinglines:109-117Code / dataset availability confirmedEurope PMC · checked 9 Sept 2026
Laboratory / benchtopSeed / grainCountingGrowth / development / phenology
Background Plant parasitic weeds belonging to the genus Striga are a major threat for food production in Sub-Saharan Africa and Southeast Asia. The parasite's life cycle starts with the induction of seed germination by host plant-derived signals, followed by parasite attachment, infection, outgrowth, flowering, reproduction, seed set and dispersal. Given the small seed size of the parasite ( Striga seed germination. Results Here, we introduce DiSCount ( Di gital S triga Count er): a computer vision tool for automated quantification of total and germinated Striga seed numbers in standard glass fibre filter assays. We developed the software using a machine learning approach trained with a dataset of 98 manually annotated images. Then, we validated and tested the model against a total dataset of 188 manually counted images. The results showed that DiSCount has an average error of 3.38 percentage points per image compared to the manually counted dataset. Most importantly, DiSCount achieves a 100 to 3000-fold speed increase in image analysis when compared to manual analysis, with an inference time of approximately 3 s per image on a single CPU and 0.1 s on a GPU. Conclusions DiSCount is accurate and efficient in quantifying total and germinated Striga seeds in a standardized germination assay. This automated computer vision tool enables for high-throughput, large-scale screening of chemical compound libraries and biological control agents of this devastating parasitic weed. The complete software and manual are hosted at https://gitlab.com/lodewijk-track32/discount_paper and the archived version is available at Zenodo with the DOI 10.5281/zenodo.3627138. The dataset used for testing is available at Zenodo with the DOI 10.5281/zenodo.3403956.
Why it matches plant phenotyping methodsStriga種子の発芽状態を画像から自動定量するコンピュータビジョン手法の開発・検証が研究の中心であり、植物状態の表現型取得に該当する。
abstractwe introduce DiSCount ( Di gital S triga Count er): a computer vision tool for automated quantification of total and germinated Striga seed numbers
Reproduction assets foundThe paper's DiSCount software (code, manual, trained YOLOv3 model) is hosted on GitLab and archived on Zenodo; the manually counted test image dataset and the installation-test input dataset are also publicly available on Zenodo. The pytorch-yolo-v3 repository is a third-party code base, not a paper-specific asset.Code · publicThe complete software and manual are hosted at https://gitlab.com/lodewijk-track32/discount_paper and the archived version is available at Zenodo with the DOI https://doi.org/10.5281/zenodo.3627138 .Open asset ↗lodewijk-track32/discount_paperlines:1-79Code · publicThe DiSCount software is available at https://doi.org/10.5281/zenodo.3627138 along with detailed training settings and a complete installation and user manual.Open asset ↗10.5281/zenodo.3627138lines:84-90Dataset · publicThe dataset analysed to assess the performance of the software is publically available at https://doi.org/10.5281/zenodo.3403956 .Open asset ↗10.5281/zenodo.3403956lines:122-173Dataset · publicThe input dataset used to test the installation of the software is publically available at https://doi.org/10.5281/zenodo.3404131 .Open asset ↗10.5281/zenodo.3404131lines:122-173Code / dataset availability confirmedOpenAlex · Europe PMC · checked 14 Sept 2026
Abstract Background Seed size and number are important plant traits from an ecological and horticultural/agronomic perspective. However, in small-seeded species such as Arabidopsis thaliana, research on seed size and number is limited by the absence of suitable high throughput phenotyping methods. Results We report on the development of a high throughput method for counting seeds and measuring individual seed sizes. The method uses a large-particle flow cytometer to count individual seeds and sort them according to size, allowing an average of 12,000 seeds/hour to be processed. To achieve this high throughput, post harvested seeds are first separated from remaining plant material (dust and chaff) using a rapid sedimentation-based method. Then, classification algorithms are used to refine the separation process in silico. Accurate identification of all seeds in the samples was achieved, with relative errors below 2%. Conclusion The tests performed reveal that there is no single classification algorithm that performs best for all samples, so the recommended strategy is to train and use multiple algorithms and use the median predictions of seed size and number across all algorithms. To facilitate the use of this method, an R package (SeedSorter) that implements the methodology has been developed and made freely available. The method was validated with seed samples from several natural accessions of Arabidopsis thaliana, but our analysis pipeline is applicable to any species with seed sizes smaller than 1.5 mm.
Why it matches plant phenotyping methods種子数と種子サイズという植物形質を高スループットに取得するフローサイトメトリー法を開発・検証し、解析用Rパッケージも提供しているため、植物フェノタイピング手法が研究の中心である。
abstractWe report on the development of a high throughput method for counting seeds and measuring individual seed sizes.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産2件を確認しました。Code · publicTo facilitate the use of this method, all necessary computations have been implemented into an R package ( SeedSorter ) that is freely available online at https://github.com/aleMorales/SeedSorter .Open asset ↗aleMorales/SeedSorterlines:76-82Code · publicThe R scripts and data required to reproduce these results can be obtained at https://github.com/aleMorales/SeedSorterPaper .Open asset ↗aleMorales/SeedSorterPaperlines:120-135Code / dataset availability confirmedOpenAlex · Crossref · Europe PMC · checked 9 Sept 2026
Image-based plant phenotyping has been steadily growing and this has steeply increased the need for more efficient image analysis techniques capable of evaluating multiple plant traits. Deep learning has shown its potential in a multitude of visual tasks in plant phenotyping, such as segmentation and counting. Here, we show how different phenotyping traits can be extracted simultaneously from plant images, using Multi-Task Learning (MTL). MTL leverages information contained in the training images of related tasks to improve overall generalization and learns models with fewer labels. We present a Multi-Task Deep Learning framework for plant phenotyping, able to infer three traits simultaneously: (i) leaf count; (ii) projected leaf area (PLA); and (iii) genotype classification. We adopted a modified ResNet50 as a feature extractor, trained end-to-end to predict multiple traits. We also leverage MTL to show that through learning from more easily obtainable annotations (such as PLA and genotype) we can predict a better leaf count (harder to obtain annotation). We evaluate our findings on several publicly available datasets of top-view images of Arabidopsis thaliana. Experimental results show that the proposed MTL method improves the leaf count Mean Squared Error (MSE) by more than 40 %, compared to a single task network on the same dataset. We also show that our MTL framework can be trained with up to 75 % fewer leaf count annotations without significantly impacting performance, whereas a single task model shows a steady decline when fewer annotations are available.
Why it matches plant phenotyping methods植物画像から複数形質を同時推定するマルチタスク深層学習手法の開発・評価が中心であり、明確な植物フェノタイピング方法論研究である。
abstractWe present a Multi-Task Deep Learning framework for plant phenotyping, able to infer three traits simultaneously: (i) leaf count; (ii) projected leaf area (PLA); and (iii) genotype classification.
Reproduction assets foundThe paper's authors provide public analysis code (MTL phenotyping framework) on GitHub, and the study analyzes publicly available CVPPP plant image datasets (Ara2013, A1, A4) hosted on plant-phenotyping.org. Both are paper-specific, public, and actionable.Code · publicCode available at https://github.com/andobrescu/Multi_task_plant_phenotyping .Open asset ↗andobrescu/Multi_task_plant_phenotypinglines:224-295Dataset · publicPublicly available datasets were analyzed in this study. This data can be found here: https://www.plant-phenotyping.org/CVPPP2017-challenge .Open asset ↗lines:607-694Code / dataset availability confirmedEurope PMC · checked 9 Sept 2026
Background Grain yield of wheat is greatly associated with the population of wheat spikes, i.e., s p i k e n u m b e r m - 2 . To obtain this index in a reliable and efficient way, it is necessary to count wheat spikes accurately and automatically. Currently computer vision technologies have shown great potential to automate this task effectively in a low-end manner. In particular, counting wheat spikes is a typical visual counting problem, which is substantially studied under the name of object counting in Computer Vision. TasselNet, which represents one of the state-of-the-art counting approaches, is a convolutional neural network-based local regression model, and currently benchmarks the best record on counting maize tassels. However, when applying TasselNet to wheat spikes, it cannot predict accurate counts when spikes partially present. Results In this paper, we make an important observation that the counting performance of local regression networks can be significantly improved via adding visual context to the local patches. Meanwhile, such context can be treated as part of the receptive field without increasing the model capacity. We thus propose a simple yet effective contextual extension of TasselNet-TasselNetv2. If implementing TasselNetv2 in a fully convolutional form, both training and inference can be greatly sped up by reducing redundant computations. In particular, we collected and labeled a large-scale wheat spikes counting (WSC) dataset, with 1764 high-resolution images and 675,322 manually-annotated instances. Extensive experiments show that, TasselNetv2 not only achieves state-of-the-art performance on the WSC dataset ( 91.01 % counting accuracy) but also is more than an order of magnitude faster than TasselNet (13.82 fps on 912 × 1216 images). The generality of TasselNetv2 is further demonstrated by advancing the state of the art on both the Maize Tassels Counting and ShanghaiTech Crowd Counting datasets. Conclusions This paper describes TasselNetv2 for counting wheat spikes, which simultaneously addresses two important use cases in plant counting: improving the counting accuracy without increasing model capacity , and improving efficiency without sacrificing accuracy . It is promising to be deployed in a real-time system with high-throughput demand. In particular, TasselNetv2 can achieve sufficiently accurate results when training from scratch with small networks, and adopting larger pre-trained networks can further boost accuracy. In practice, one can trade off the performance and efficiency according to certain application scenarios. Code and models are made available at: https://tinyurl.com/TasselNetv2.
Why it matches plant phenotyping methodsコムギ穂数という植物形態形質を画像から自動計数する手法を開発し、精度・速度を評価するとともに大規模データセットを構築しており、植物フェノタイピング手法が中心である。
abstractWe thus propose a simple yet effective contextual extension of TasselNet-TasselNetv2.
Reproduction assets foundThe paper explicitly states that the WSC dataset (1764 images, 675,322 annotated wheat spikes) and code/models are made available online at the authors' public URL https://tinyurl.com/TasselNetv2.Dataset · publicThe WSC dataset and other supporting materials are made available online at: https://tinyurl.com/TasselNetv2 .Open asset ↗lines:205-231Code · publicCode and models are made available at: https://tinyurl.com/TasselNetv2 .Open asset ↗lines:1-72Code / dataset availability confirmedCrossref · Europe PMC · checked 9 Sept 2026
Abstract Background Plant population density is an important factor for agricultural production systems due to its substantial influence on crop yield and quality. Traditionally, plant population density is estimated by using either field assessment or a germination-test-based approach. These approaches can be laborious and inaccurate. Recent advances in deep learning provide new tools to solve challenging computer vision tasks such as object detection, which can be used for detecting and counting plant seedlings in the field. The goal of this study was to develop a deep-learning-based approach to count plant seedlings in the field. Results Overall, the final detection model achieved F1 scores of 0.727 (at $$IOU_{all}$$ I O U all ) and 0.969 (at $$IOU_{0.5}$$ I O U 0.5 ) on the $$Seedling_{All}$$ S e e d l i n g All testing set in which images had large variations, indicating the efficacy of the Faster RCNN model with the Inception ResNet v2 feature extractor for seedling detection. Ablation experiments showed that training data complexity substantially affected model generalizability, transfer learning efficiency, and detection performance improvements due to increased training sample size. Generally, the seedling counts by the developed method were highly correlated ( $$R^2$$ R 2 = 0.98) with that found through human field assessment for 75 test videos collected in multiple locations during multiple years, indicating the accuracy of the developed approach. Further experiments showed that the counting accuracy was largely affected by the detection accuracy: the developed approach provided good counting performance for unknown datasets as long as detection models were well generalized to those datasets. Conclusion The developed deep-learning-based approach can accurately count plant seedlings in the field. Seedling detection models trained in this study and the annotated images can be used by the research community and the cotton industry to further the development of solutions for seedling detection and counting.
Why it matches plant phenotyping methods圃場画像から植物個体数（苗立ち密度）を検出・計数する深層学習手法を開発し、人手評価および複数年・地点のデータで検証しており、植物表現型取得が中心である。
abstractThe goal of this study was to develop a deep-learning-based approach to count plant seedlings in the field.
Reproduction assets foundThe paper's availability statement explicitly archives original images and annotations, source code, and testing videos in a public GitHub repository, along with pretrained models for seedling detection and counting — directly reproducing this paper's phenotyping measurements and analysis.Code · publicOriginal images and annotations, source code, and testing videos are archived in a GitHub repository ( https://github.com/UGA-BSAIL/deepseedling ) along with the instruction to run pretrained models for seedling detection and counting.Open asset ↗UGA-BSAIL/deepseedlinglines:190-267Code / dataset availability confirmedCrossref · Europe PMC · checked 15 Sept 2026
The production of banana-one of the highly consumed fruits-is highly affected due to loss of certain number of banana plants in an early phase of vegetation. This affects the ability of farmers to forecast and estimate the production of banana. In this paper, we propose a deep learning (DL) based method to precisely detect and count banana plants on a farm exclusive of other plants, using high resolution RGB aerial images collected from Unmanned Aerial Vehicle (UAV). An attempt to detect the plants on the normal RGB images resulted less than 78.8% recall for our sample images of a commercial banana farm in Thailand. To improve this result, we use three image processing methods-Linear Contrast Stretch, Synthetic Color Transform and Triangular Greenness Index-to enhance the vegetative properties of orthomosaic, generating multiple variants of orthomosaic. Then we separately train a parameter-optimized Convolutional Neural Network (CNN) on manually interpreted banana plant samples seen on each image variants, to produce multiple results of detection on our region of interest. 96.4%, 85.1% and 75.8% of plants were correctly detected on three of our dataset collected from multiple altitude of 40, 50 and 60 meters, of same farm. Further discussion on results obtained from combination of multiple altitude variants are also discussed later in the research, in an attempt to find better altitude combination for data collection from UAV for the detection of banana plants. The results showed that merging the detection results of 40 and 50 meter dataset could detect the plants missed by each other, increasing recall upto 99%.
Why it matches plant phenotyping methodsUAV RGB画像からバナナ個体を検出・計数する画像解析手法の開発と性能評価が研究の中心であり、植物個体数という観測可能な植物形質を抽出している。
abstractwe propose a deep learning (DL) based method to precisely detect and count banana plants on a farm exclusive of other plants, using high resolution RGB aerial images collected from Unmanned Aerial Vehicle (UAV).
Reproduction assets foundThe paper's Data Availability statement deposits the paper-specific UAV-collected banana plant image datasets (the phenotyping inputs used for detection/counting) in a public Figshare repository with an authors' URL, making it directly actionable.Dataset · publichas-pdf yes pmc-prop-has-supplement no pmc-prop-pdf-only no pmc-prop-suppress-copyright no pmc-prop-is-real-version no pmc-prop-is-scanned-article no pmc-prop-preprint no pmc-prop-in-epmc yes pmc-license-ref CC BY Data Availability Data available from the Figshare Repository (DOIs: 10.6084/m9.figshare.7981547 ), and the URL is: https://figshare.com/s/62e391492b1be99515b4 .
Data Availability
Data available from the Figshare Repository (DOIs: 10.6084/m9.figshare.7981547 ), and the URL is: https://figshare.com/s/62e391492b1be99515b4 .
Introduction
Significance of counting banana plantsOpen asset ↗Figshare · 10.6084/m9.figshare.7981547lines:1-36Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
The soybean cyst nematode (SCN), Heterodera glycines, is the most damaging pathogen of soybeans in the United States. To assess the severity of nematode infestations in the field, SCN egg population densities are determined. Cysts (dead females) of the nematode must be extracted from soil samples and then ground to extract the eggs within. Sucrose centrifugation commonly is used to separate debris from suspensions of extracted nematode eggs. We present a method using OptiPrep as a density gradient medium with improved separation and recovery of extracted eggs compared to the sucrose centrifugation technique. Also, computerized methods were developed to automate the identification and counting of nematode eggs from the processed samples. In one approach, a high-resolution scanner was used to take static images of extracted eggs and debris on filter papers, and a deep learning network was trained to identify and count the eggs among the debris. In the second approach, a lensless imaging setup was developed using off-the-shelf components, and the processed egg samples were passed through a microfluidic flow chip made from double-sided adhesive tape. Holographic videos were recorded of the passing eggs and debris, and the videos were reconstructed and processed by custom software program to obtain egg counts. The performance of the software programs for egg counting was characterized with SCN-infested soil collected from two farms, and the results using these methods were compared with those obtained through manual counting.
Why it matches plant phenotyping methods植物病害状態（線虫卵密度・感染重症度）の定量を目的に、画像取得、深層学習およびレンズレス撮像・画像処理による自動計数法を開発し、手動計数と比較検証しているため、方法が中心である。
abstractcomputerized methods were developed to automate the identification and counting of nematode eggs from the processed samples.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicData Availability: All software files are available through gitHub. ( https://github.com/ukalwa/nematode_egg_counting ).Open asset ↗ukalwa/nematode_egg_countinglines:133-142Code / dataset availability confirmedEurope PMC · checked 9 Sept 2026
Crop yield is an essential measure for breeders, researchers, and farmers and is composed of and may be calculated by the number of ears per square meter, grains per ear, and thousand grain weight. Manual wheat ear counting, required in breeding programs to evaluate crop yield potential, is labor-intensive and expensive; thus, the development of a real-time wheat head counting system would be a significant advancement. In this paper, we propose a computationally efficient system called DeepCount to automatically identify and count the number of wheat spikes in digital images taken under natural field conditions. The proposed method tackles wheat spike quantification by segmenting an image into superpixels using simple linear iterative clustering (SLIC), deriving canopy relevant features, and then constructing a rational feature model fed into the deep convolutional neural network (CNN) classification for semantic segmentation of wheat spikes. As the method is based on a deep learning model, it replaces hand-engineered features required for traditional machine learning methods with more efficient algorithms. The method is tested on digital images taken directly in the field at different stages of ear emergence/maturity (using visually different wheat varieties), with different canopy complexities (achieved through varying nitrogen inputs) and different heights above the canopy under varying environmental conditions. In addition, the proposed technique is compared with a wheat ear counting method based on a previously developed edge detection technique and morphological analysis. The proposed approach is validated with image-based ear counting and ground-based measurements. The results demonstrate that the DeepCount technique has a high level of robustness regardless of variables, such as growth stage and weather conditions, hence demonstrating the feasibility of the approach in real scenarios. The system is a leap toward a portable and smartphone-assisted wheat ear counting systems, results in reducing the labor involved, and is suitable for high-throughput analysis. It may also be adapted to work on Red; Green; Blue (RGB) images acquired from unmanned aerial vehicle (UAVs).
Why it matches plant phenotyping methodsコムギ穂数という植物形質を圃場画像から自動抽出・計数する手法を開発し、比較検証・地上測定による妥当性確認まで行っており、フェノタイピング手法が研究の中心である。
abstractwe propose a computationally efficient system called DeepCount to automatically identify and count the number of wheat spikes in digital images taken under natural field conditions.
Reproduction assets foundThe paper provides an authors' public code URL (GitHub profile of the first author) for the DeepCount wheat spike counting model, and a data availability statement directing to the public DFW repository (ckan.grassroots.tools) and supplementary files for the datasets generated in this study.Code · publicThe code can be found at https://github.com/pouriast .Open asset ↗https://github.com/pouriastlines:557-572Code / dataset availability confirmedEurope PMC · Crossref · bioRxiv · checked 15 Sept 2026
ABSTRACT Automatically scoring plant traits using a combination of imaging and deep learning holds promise to accelerate data collection, scientific inquiry, and breeding progress. However, applications of this approach are currently held back by the availability of large and suitably annotated training datasets. Early training datasets targeted arabidopsis or tobacco. The morphology of these plants quite different from that of grass species like maize. Two sets of maize training data, one real-world and one synthetic were generated and annotated for late vegetative stage maize plants using leaf count as a model trait. Convolutional neural networks (CNNs) trained on entirely synthetic data provided predictive power for scoring leaf number in real-world images. This power was less than CNNs trained with equal numbers of real-world images, however, in some cases CNNs trained with larger numbers of synthetic images outperformed CNNs trained with smaller numbers of real-world images. When real-world training images were scarce, augmenting real-world training data with synthetic data provided improved prediction accuracy. Quantifying leaf number over time can provide insight into plant growth rates and stress responses, and can help to parameterize crop growth models. The approaches and annotated training data described here may help future efforts to develop accurate leaf counting algorithms for maize.
Why it matches plant phenotyping methodsトウモロコシの葉数という植物形質を対象に、合成・実画像データセットとCNNによる画像ベース計測手法を開発・評価しており、フェノタイピング手法が中心である。
abstractTwo sets of maize training data, one real-world and one synthetic were generated and annotated for late vegetative stage maize plants using leaf count as a model trait.
Reproduction assets foundThe paper deposits its phenotyping analysis scripts/source code in a public GitHub repository and used a public Zooniverse project to crowd-score the real-world maize leaf-count images; both are paper-specific, public, and actionable.Code · publicAdditional Information
The scripts and source code employed in this study have been deposited at https://github.com/freemao/MaizeLeafCounting.Images and annotations used in this study have been deposited with CyVerse [27].
The authors declare no competing interests.
References
1. Houle, D., Govindaraju, D. R. & Omholt, S. Phenomics: the next challenge. Nat. reviews genetics 11, 855 (2010).
2. Furbank, R. T. & Tester, M. Phenomics–technologies to relieve the phenotyping bottOpen asset ↗freemao/MaizeLeafCounting.Imagespdf-raw-page:9 lines:1-56Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
The yield of cereal crops such as sorghum ( Sorghum bicolor L. Moench) depends on the distribution of crop-heads in varying branching arrangements. Therefore, counting the head number per unit area is critical for plant breeders to correlate with the genotypic variation in a specific breeding field. However, measuring such phenotypic traits manually is an extremely labor-intensive process and suffers from low efficiency and human errors. Moreover, the process is almost infeasible for large-scale breeding plantations or experiments. Machine learning-based approaches like deep convolutional neural network (CNN) based object detectors are promising tools for efficient object detection and counting. However, a significant limitation of such deep learning-based approaches is that they typically require a massive amount of hand-labeled images for training, which is still a tedious process. Here, we propose an active learning inspired weakly supervised deep learning framework for sorghum head detection and counting from UAV-based images. We demonstrate that it is possible to significantly reduce human labeling effort without compromising final model performance ( R 2 between human count and machine count is 0.88) by using a semitrained CNN model (i.e., trained with limited labeled data) to perform synthetic annotation. In addition, we also visualize key features that the network learns. This improves trustworthiness by enabling users to better understand and trust the decisions that the trained deep learning model makes.
Why it matches plant phenotyping methodsUAV画像からソルガム穂数を検出・計数する弱教師あり深層学習手法を開発し、人的計数との性能も検証しており、植物表現型取得が研究の中心です。
abstractHere, we propose an active learning inspired weakly supervised deep learning framework for sorghum head detection and counting from UAV-based images.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicThe codes used for generating results and reproducing the results presented in this work are available at DeepSorghumHead ( https://github.com/oceam/DeepSorghumHead ).Open asset ↗DeepSorghumHeadlines:66-80Code / dataset availability confirmedEurope PMC · checked 9 Sept 2026
: Pre-harvest fruit yield estimation is useful to guide harvesting and marketing resourcing, but machine vision estimates based on a single view from each side of the tree ("dual-view") underestimates the fruit yield as fruit can be hidden from view. A method is proposed involving deep learning, Kalman filter, and Hungarian algorithm for on-tree mango fruit detection, tracking, and counting from 10 frame-per-second videos captured of trees from a platform moving along the inter row at 5 km/h. The deep learning based mango fruit detection algorithm, MangoYOLO, was used to detect fruit in each frame. The Hungarian algorithm was used to correlate fruit between neighbouring frames, with the improvement of enabling multiple-to-one assignment. The Kalman filter was used to predict the position of fruit in following frames, to avoid multiple counts of a single fruit that is obscured or otherwise not detected with a frame series. A "borrow" concept was added to the Kalman filter to predict fruit position when its precise prediction model was absent, by borrowing the horizontal and vertical speed from neighbouring fruit. By comparison with human count for a video with 110 frames and 192 (human count) fruit, the method produced 9.9% double counts and 7.3% missing count errors, resulting in around 2.6% over count. In another test, a video (of 1162 frames, with 42 images centred on the tree trunk) was acquired of both sides of a row of 21 trees, for which the harvest fruit count was 3286 (i.e., average of 156 fruit/tree). The trees had thick canopies, such that the proportion of fruit hidden from view from any given perspective was high. The proposed method recorded 2050 fruit (62% of harvest) with a bias corrected Root Mean Square Error (RMSE) = 18.0 fruit/tree while the dual-view image method (also using MangoYOLO) recorded 1322 fruit (40%) with a bias corrected RMSE = 21.7 fruit/tree. The video tracking system is recommended over the dual-view imaging system for mango orchard fruit count.
Why it matches plant phenotyping methods動画画像と深層学習・追跡アルゴリズムを組み合わせ、樹上マンゴー果実数（収量関連形質）を推定する手法の開発・比較検証が中心である。
abstractA method is proposed involving deep learning, Kalman filter, and Hungarian algorithm for on-tree mango fruit detection, tracking, and counting
Reproduction assets foundThe paper states that the tree images and video used for the MangoYOLO–Kalman–Hungarian fruit tracking/counting analysis are available as a supplementary data file, and the Supplementary Materials section lists Video S1 (Fruit Tracking Count) at the MDPI supplementary URL. This is a paper-specific, publicly accessible,Supplement · publicThe images and video are available as a supplementary data file to this manuscript.Open asset ↗lines:34-41Code / dataset availability confirmedOpenAlex · arXiv · checked 15 Sept 2026
We present an approach to leaf level segmentation of images of Arabidopsis thaliana plants based upon detected edges. We introduce a novel approach to edge classification, which forms an important part of a method to both count the leaves and establish the leaf area of a growing plant from images obtained in a high-throughput phenotyping system. Our technique uses a relatively shallow convolutional neural network to classify image edges as background, plant edge, leaf-on-leaf edge or internal leaf noise. The edges themselves were found using the Canny edge detector and the classified edges can be used with simple image processing techniques to generate a region-based segmentation in which the leaves are distinct. This approach is strong at distinguishing occluding pairs of leaves where one leaf is largely hidden, a situation which has proved troublesome for plant image analysis systems in the past. In addition, we introduce the publicly available plant image dataset that was used for this work.
Why it matches plant phenotyping methods葉画像から葉数・葉面積を抽出するエッジ分類および画像分割手法を開発し、ハイスループット表現型解析で評価するとともにデータセットも公開しており、植物フェノタイピング手法が中心である。
abstractWe present an approach to leaf level segmentation of images of Arabidopsis thaliana plants based upon detected edges.
Reproduction assets foundThe paper introduces the Aberystwyth Leaf Evaluation Dataset (ALED), a public Zenodo deposit containing the Arabidopsis top-down plant images, hand-annotated ground truth, and segmentation evaluation software used directly in this work's leaf segmentation experiments.Dataset · publicArabidopsis plant image dataset
As part of this work we have generated a dataset of several thousand top
down images of growing Arabidopsis plants.
The data has been made available to the wider community as the Aberystwyth Leaf Evaluation Dataset (ALED)
1 1
1
The dataset is hosted at https://zenodo.org and it can be found from
https://doi.org/10.5281/zenodo.168158 .
The images were obtained
using the Photon Systems Instruments (PSI) PlantScreen plant scanner
[ 22 ] at the National Plant Phenomics Centre.
Alongside the images themselves are some ground truth hand-annotations and
software to evaluate leaf level segmentation against this ground truth.Open asset ↗zenodo · 10.5281/zenodo.168158lines:101-172Code / dataset availability confirmedEurope PMC · checked 10 Sept 2026
Sorghum ( Sorghum bicolor L. Moench) is a C4 tropical grass that plays an essential role in providing nutrition to humans and livestock, particularly in marginal rainfall environments. The timing of head development and the number of heads per unit area are key adaptation traits to consider in agronomy and breeding but are time consuming and labor intensive to measure. We propose a two-step machine-based image processing method to detect and count the number of heads from high-resolution images captured by unmanned aerial vehicles (UAVs) in a breeding trial. To demonstrate the performance of the proposed method, 52 images were manually labeled; the precision and recall of head detection were 0.87 and 0.98, respectively, and the coefficient of determination ( R 2 ) between the manual and new methods of counting was 0.84. To verify the utility of the method in breeding programs, a geolocation-based plot segmentation method was applied to pre-processed ortho-mosaic images to extract >1000 plots from original RGB images. Forty of these plots were randomly selected and labeled manually; the precision and recall of detection were 0.82 and 0.98, respectively, and the coefficient of determination between manual and algorithm counting was 0.56, with the major source of error being related to the morphology of plants resulting in heads being displayed both within and outside the plot in which the plants were sown, i.e., being allocated to a neighboring plot. Finally, the potential applications in yield estimation from UAV-based imagery from agronomy experiments and scouting of production fields are also discussed.
Why it matches plant phenotyping methodsUAV画像からソルガムの穂の外観と数を抽出する画像処理法を開発し、手動ラベルとの精度・再現性を検証しており、植物形質取得法が研究の中心である。
abstractWe propose a two-step machine-based image processing method to detect and count the number of heads from high-resolution images captured by unmanned aerial vehicles (UAVs) in a breeding trial.
Reproduction assets foundThe paper's sorghum head detection/counting training data and manually labeled image datasets (Datasets 1 and 2) are explicitly stated to be available in the article's Supplementary Materials, hosted at the Frontiers supplementary-material URL. This is a paper-specific, publicly accessible asset containing the phenotypDataset · publicTo aid in this growth, datasets 1 and 2 along with the manual labeling used in this study are available in the Supplementary Materials .Open asset ↗lines:410-460Code / dataset availability confirmedOpenAlex · Europe PMC · checked 15 Sept 2026
Direct observation of morphological plant traits is tedious and a bottleneck for high-throughput phenotyping. Hence, interest in image-based analysis is increasing, with the requirement for software that can reliably extract plant traits, such as leaf count, preferably across a variety of species and growth conditions. However, current leaf counting methods do not work across species or conditions and therefore may lack broad utility. In this paper, we present Pheno-Deep Counter, a single deep network that can predict leaf count in two-dimensional (2D) plant images of different species with a rosette-shaped appearance. We demonstrate that our architecture can count leaves from multi-modal 2D images, such as visible light, fluorescence and near-infrared. Our network design is flexible, allowing for inputs to be added or removed to accommodate new modalities. Furthermore, our architecture can be used as is without requiring dataset-specific customization of the internal structure of the network, opening its use to new scenarios. Pheno-Deep Counter is able to produce accurate predictions in many plant species and, once trained, can count leaves in a few seconds. Through our universal and open source approach to deep counting we aim to broaden utilization of machine learning-based approaches to leaf counting. Our implementation can be downloaded at https://bitbucket.org/tuttoweb/pheno-deep-counter.
Why it matches plant phenotyping methods植物画像から葉数を抽出する汎用深層学習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。
abstractwe present Pheno-Deep Counter, a single deep network that can predict leaf count in two-dimensional (2D) plant images of different species with a rosette-shaped appearance.
Reproduction assets foundThe authors explicitly deposit their Pheno-Deep Counter source code and pre-trained model in a public Bitbucket repository; the plant image datasets used (CVPPP, Cruz et al., komatsuna, Aberystwyth) are cited prior-work datasets rather than paper-specific deposits.Code · publicinput/modalities without changing the overall architecture. This simplifies adoption and permits the sharing of model updates when new experiments have been made available on the basis of our architecture. Therefore, by placing our pre‐trained PhenoDC and source code (and instructions) into the publicly available repository at https://bitbucket.org/tuttoweb/pheno-deep-counter , we hope to accelerate the adoption of such methods in plant phenotyping analysis.Open asset ↗https://bitbucket.org/tuttoweb/pheno-deep-counterlines:340-387Code / dataset availability confirmedbioRxiv · Europe PMC · checked 14 Sept 2026
O_LIStomata fulfill an important physiological role and are often phenotyped by researchers in many fields. Currently, no fully automated method exists to perform this task. Researchers typically rely on manual counts of stomata, which is an error-prone method and difficult to reproduce.\nC_LIO_LIWe introduce StomataCounter, an automated stomata counting system using a deep convolutional neural network to identify pores in a variety of different microscopic images. We used a human-in-the-loop approach to train and refine a neural network on a large variety of microscopic images, which helps us achieve robust detection among a number of datasets.\nC_LIO_LIOur network achieves 98.1% identification accuracy on Ginkgo SEM micrographs, and 94.2% transfer accuracy when tested on untrained species.\nC_LIO_LITo facilitate adoption of the method, we make a web tool available under http://www.stomata.science/\nC_LI
Why it matches plant phenotyping methods気孔という植物形質の画像ベース自動同定・計数法を開発し、異なる画像・種で精度検証した研究であり、方法自体が中心です。
abstractWe introduce StomataCounter, an automated stomata counting system using a deep convolutional neural network to identify pores in a variety of different microscopic images.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · public125 codes for network training, as well as the webserver are available at http://stomata.science/source. To useOpen asset ↗pdf-page:5 lines:1-57Code / dataset availability confirmedOpenAlex · Crossref · Europe PMC · checked 15 Sept 2026
BACKGROUND: Image-based plant phenotyping facilitates the extraction of traits noninvasively by analyzing large number of plants in a relatively short period of time. It has the potential to compute advanced phenotypes by considering the whole plant as a single object (holistic phenotypes) or as individual components, i.e., leaves and the stem (component phenotypes), to investigate the biophysical characteristics of the plants. The emergence timing, total number of leaves present at any point of time and the growth of individual leaves during vegetative stage life cycle of the maize plants are significant phenotypic expressions that best contribute to assess the plant vigor. However, image-based automated solution to this novel problem is yet to be explored. RESULTS: A set of new holistic and component phenotypes are introduced in this paper. To compute the component phenotypes, it is essential to detect the individual leaves and the stem. Thus, the paper introduces a novel method to reliably detect the leaves and the stem of the maize plants by analyzing 2-dimensional visible light image sequences captured from the side using a graph based approach. The total number of leaves are counted and the length of each leaf is measured for all images in the sequence to monitor leaf growth. To evaluate the performance of the proposed algorithm, we introduce University of Nebraska-Lincoln Component Plant Phenotyping Dataset (UNL-CPPD) and provide ground truth to facilitate new algorithm development and uniform comparison. The temporal variation of the component phenotypes regulated by genotypes and environment (i.e., greenhouse) are experimentally demonstrated for the maize plants on UNL-CPPD. Statistical models are applied to analyze the greenhouse environment impact and demonstrate the genetic regulation of the temporal variation of the holistic phenotypes on the public dataset called Panicoid Phenomap-1. CONCLUSION: The central contribution of the paper is a novel computer vision based algorithm for automated detection of individual leaves and the stem to compute new component phenotypes along with a public release of a benchmark dataset, i.e., UNL-CPPD. Detailed experimental analyses are performed to demonstrate the temporal variation of the holistic and component phenotypes in maize regulated by environment and genetic variation with a discussion on their significance in the context of plant science.
Why it matches plant phenotyping methods画像系列から葉・茎を自動検出し、葉数・葉長などの表現型を抽出する手法の開発が中心で、ベンチマークデータセットも提供しているため。
abstractThe central contribution of the paper is a novel computer vision based algorithm for automated detection of individual leaves and the stem to compute new component phenotypes along with a public release of a benchmark dataset, i.e., UNL-CPPD.
Reproduction assets foundThe paper releases UNL-CPPD, a maize component plant phenotyping dataset with original images, ground truth, and annotated images, publicly downloadable from the authors' site. The paper's holistic phenotyping analysis also uses Panicoid Phenomap-1, available from the same authors' site. No author analysis code is madeDataset · publicmanuscript.
Acknowledgements
Authors appreciate Dipal Bhandari for his contributions in preparing the ground truth of the dataset.
Competing interests
The authors declare that they have no competing interests.
Availability of data and materials
UNL-CPPD public dataset is released with the paper and may be freely downloaded from http://plantvision.unl.edu/dataset . The dataset contains original images, ground truth and annotated images.
Consent for publication
Not applicable.
Ethics approval and consent to participate
Not applicable.
Funding
The authors would like to thank the Agricultural Research Division in the Institute of Agriculture and Natural Resources of the UNL, USA, for proviOpen asset ↗plantvision.unl.edu · UNL-CPPDlines:1781-1890Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Background The formation of crossovers during meiosis is pivotal for the redistribution of traits among the progeny of sexually reproducing organisms. In plants the molecular mechanisms underlying the formation of crossovers have been well established, but relatively little is known about the factors that determine the exact location and the frequency of crossover events in the genome. In the model plant species Arabidopsis , research on these factors has been greatly facilitated by reporter lines containing linked fluorescence marker genes under control of promoters active in seeds or pollen, allowing for the visualization of crossover events by fluorescence microscopy. However, the usefulness of these reporter lines to screen for novel modulators of crossover frequency in a high throughput manner relies on the availability of programs that can accurately count fluorescent seeds. Such a program was previously not available in scientific literature. Results Here we present MeioSeed, a novel CellProfiler-based program that accurately counts GFP and RFP fluorescent Arabidopsis seeds with adjustable detection thresholds for fluorescence intensity, making use of a robust seed classifier which was trained by machine learning in Ilastik. Using the previously published reporter line Col3-4/20 as an example, we explain the use of MeioSeed and the steps taken to optimize the thresholding settings of the program to fit the published model for recombination frequency and transgene segregation. The use of MeioSeed is illustrated by investigating salt stress as a novel abiotic trigger for changes in crossover frequency in Col3-4/20 (♂) × Ler-0 (♀) F 1 hybrids. Salt stress was found to trigger increases in crossover frequency between the marker genes of up to 70% compared to the control treatment without salt stress. Genotyping of control and salt treated populations revealed that the changes in crossover frequency were not limited to the region between the marker genes, but that fluctuations in crossover frequency are likely to occur genome-wide after treatment with high salt concentrations. Conclusions MeioSeed allows for the high throughput recognition and counting of fluorescent Arabidopsis seeds and can facilitate the screening for novel abiotic and biotic modulators of crossover frequency using reporter lines in Arabidopsis .
Why it matches plant phenotyping methods蛍光種子を機械学習・画像解析で高スループットに認識・計数し、交差頻度という植物の遺伝的状態を推定するソフトウェア開発が中心であるため。
abstractHere we present MeioSeed, a novel CellProfiler-based program that accurately counts GFP and RFP fluorescent Arabidopsis seeds with adjustable detection thresholds for fluorescence intensity, making use of a robust seed classifier which was trained by machine learning in Ilastik.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicThe MeioSeed package is available at http://cellprofiler.org/examples/published_pipelines .Open asset ↗lines:44-51Code / dataset availability confirmedCrossref · OpenAlex · Europe PMC · checked 10 Sept 2026
BACKGROUND: Image-based plant phenotyping has become a powerful tool in unravelling genotype-environment interactions. The utilization of image analysis and machine learning have become paramount in extracting data stemming from phenotyping experiments. Yet we rely on observer (a human expert) input to perform the phenotyping process. We assume such input to be a 'gold-standard' and use it to evaluate software and algorithms and to train learning-based algorithms. However, we should consider whether any variability among experienced and non-experienced (including plain citizens) observers exists. Here we design a study that measures such variability in an annotation task of an integer-quantifiable phenotype: the leaf count. RESULTS: to measure intra- and inter-observer variability in a controlled study using specially designed annotation tools but also citizens using a distributed citizen-powered web-based platform. In the controlled study observers counted leaves by looking at top-view images, which were taken with low and high resolution optics. We assessed whether the utilization of tools specifically designed for this task can help to reduce such variability. We found that the presence of tools helps to reduce intra-observer variability, and that although intra- and inter-observer variability is present it does not have any effect on longitudinal leaf count trend statistical assessments. We compared the variability of citizen provided annotations (from the web-based platform) and found that plain citizens can provide statistically accurate leaf counts. We also compared a recent machine-learning based leaf counting algorithm and found that while close in performance it is still not within inter-observer variability. CONCLUSIONS: While expertise of the observer plays a role, if sufficient statistical power is present, a collection of non-experienced users and even citizens can be included in image-based phenotyping annotation tasks as long they are suitably designed. We hope with these findings that we can re-evaluate the expectations that we have from automated algorithms: as long as they perform within observer variability they can be considered a suitable alternative. In addition, we hope to invigorate an interest in introducing suitably designed tasks on citizen powered platforms not only to obtain useful information (for research) but to help engage the public in this societal important problem.
Why it matches plant phenotyping methods画像ベース植物フェノタイピングにおける葉数アノテーションの観察者間・内変動を、専用ツール、市民参加型基盤、機械学習アルゴリズムと比較検証しており、測定手法の技術的妥当性評価が中心である。
abstractHere we design a study that measures such variability in an annotation task of an integer-quantifiable phenotype: the leaf count.
Reproduction assets foundThe article states that the Arabidopsis image dataset used for the leaf-counting observer-variability study is publicly available at the plant-phenotyping.org datasets page, and the citizen-science annotations were collected via the authors' public Zooniverse 'Leaf Targeting' project. No author analysis code or trainedDataset · publicAvailability of data and materials
The image dataset used in this article is available at http://www.plant-phenotyping.org/datasets .Open asset ↗plant-phenotyping.orglines:307-379Dataset · publicThe A data (RPi) were included as part of a larger citizen-powered study (“Leaf Targeting”, available at https://www.zooniverse.org/projects/venchen/leaf-targeting ) built on ZooniverseOpen asset ↗Zooniverse · venchen/leaf-targetinglines:132-149Code / dataset availability confirmedOpenAlex · Crossref · Europe PMC · checked 10 Sept 2026
Deep learning presents many opportunities for image-based plant phenotyping. Here we consider the capability of deep convolutional neural networks to perform the leaf counting task. Deep learning techniques typically require large and diverse datasets to learn generalizable models without providing a priori an engineered algorithm for performing the task. This requirement is challenging, however, for applications in the plant phenotyping field, where available datasets are often small and the costs associated with generating new data are high. In this work we propose a new method for augmenting plant phenotyping datasets using rendered images of synthetic plants. We demonstrate that the use of high-quality 3D synthetic plants to augment a dataset can improve performance on the leaf counting task. We also show that the ability of the model to generate an arbitrary distribution of phenotypes mitigates the problem of dataset shift when training and testing on different datasets. Finally, we show that real and synthetic plants are significantly interchangeable when training a neural network on the leaf counting task.
Why it matches plant phenotyping methods合成植物画像によるデータセット拡張と深層学習を用いたロゼット植物の葉数推定手法が中心であり、植物表現型取得・推定の技術開発に該当する。
abstractDeep learning presents many opportunities for image-based plant phenotyping.
Reproduction assets foundThe paper publicly releases its generated/analysed leaf-counting datasets (including synthetic rosette images and real Ara2012/Ara2013-Canon subsets) via a figshare deposit with an explicit availability statement, and it uses the public IPPN PRL dataset as its real-plant phenotyping input. The L-system model code is inDataset · publicThe datasets generated and analysed during the current study are available for download at the following url: https://figshare.com/articles/SATLC-28-09-17_zip/5450080 .Open asset ↗figshare · SATLC-28-09-17_zip/5450080lines:221-323Dataset · publicwe use a publicly available plant phenotyping dataset from the International Plant Phenotyping Network (IPPN), Footnote 1 referred to by its authors as the PRL datasetOpen asset ↗International Plant Phenotyping Network (IPPN)lines:75-84Code / dataset availability confirmedEurope PMC · OpenAlex · checked 10 Sept 2026
Background Accurately counting maize tassels is important for monitoring the growth status of maize plants. This tedious task, however, is still mainly done by manual efforts. In the context of modern plant phenotyping, automating this task is required to meet the need of large-scale analysis of genotype and phenotype. In recent years, computer vision technologies have experienced a significant breakthrough due to the emergence of large-scale datasets and increased computational resources. Naturally image-based approaches have also received much attention in plant-related studies. Yet a fact is that most image-based systems for plant phenotyping are deployed under controlled laboratory environment. When transferring the application scenario to unconstrained in-field conditions, intrinsic and extrinsic variations in the wild pose great challenges for accurate counting of maize tassels, which goes beyond the ability of conventional image processing techniques. This calls for further robust computer vision approaches to address in-field variations. Results This paper studies the in-field counting problem of maize tassels. To our knowledge, this is the first time that a plant-related counting problem is considered using computer vision technologies under unconstrained field-based environment. With 361 field images collected in four experimental fields across China between 2010 and 2015 and corresponding manually-labelled dotted annotations, a novel Maize Tassels Counting ( MTC ) dataset is created and will be released with this paper. To alleviate the in-field challenges, a deep convolutional neural network-based approach termed TasselNet is proposed. TasselNet can achieve good adaptability to in-field variations via modelling the local visual characteristics of field images and regressing the local counts of maize tassels. Extensive results on the MTC dataset demonstrate that TasselNet outperforms other state-of-the-art approaches by large margins and achieves the overall best counting performance, with a mean absolute error of 6.6 and a mean squared error of 9.6 averaged over 8 test sequences. Conclusions TasselNet can achieve robust in-field counting of maize tassels with a relatively high degree of accuracy. Our experimental evaluations also suggest several good practices for practitioners working on maize-tassel-like counting problems. It is worth noting that, though the counting errors have been greatly reduced by TasselNet, in-field counting of maize tassels remains an open and unsolved problem.
Why it matches plant phenotyping methodsトウモロコシ雄穂数という植物形態形質を、圃場画像から推定する深層学習手法を開発・評価し、データセットも作成しているため、フェノタイピング手法が中心である。
abstractIn the context of modern plant phenotyping, automating this task is required to meet the need of large-scale analysis of genotype and phenotype.
Reproduction assets foundThe paper's MTC dataset (361 field images with manually-labelled dotted tassel annotations) is explicitly stated to be publicly released online at the authors' site.Dataset · publicThe MTC dataset and other supporting materials are available online at: https://sites.google.com/site/poppinace/ .Open asset ↗lines:1796-1869Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Background The spike of a cereal plant is the grain-bearing organ whose physical characteristics are proxy measures of grain yield. The ability to detect and characterise spikes from 2D images of cereal plants, such as wheat, therefore provides vital information on tiller number and yield potential. Results We have developed a novel spike detection method for wheat plants involving, firstly, an improved colour index method for plant segmentation and, secondly, a neural network-based method using Laws texture energy for spike detection. The spike detection step was further improved by removing noise using an area and height threshold. The evaluation results showed an accuracy of over 80% in identification of spikes. In the proposed method we also measure the area of individual spikes as well as all spikes of individual plants under different experimental conditions. The correlation between the final average grain yield and spike area is also discussed in this paper. Conclusions Our highly accurate yield trait phenotyping method for spike number counting and spike area estimation, is useful and reliable not only for grain yield estimation but also for detecting and quantifying subtle phenotypic variations arising from genetic or environmental differences.
Why it matches plant phenotyping methods小麦の穂数・穂面積を画像から抽出するニューラルネットワーク手法を開発・評価しており、植物表現型取得が研究の中心です。
abstractWe have developed a novel spike detection method for wheat plants involving, firstly, an improved colour index method for plant segmentation and, secondly, a neural network-based method using Laws texture energy for spike detection.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicThe Matlab programs and sample data are available from https://sourceforge.net/projects/spike-detection .Open asset ↗spike-detectionlines:189-225Code / dataset availability confirmedarXiv · OpenAlex · checked 15 Sept 2026
In recent years, there has been an increasing interest in image-based plant phenotyping, applying state-of-the-art machine learning approaches to tackle challenging problems, such as leaf segmentation (a multi-instance problem) and counting. Most of these algorithms need labelled data to learn a model for the task at hand. Despite the recent release of a few plant phenotyping datasets, large annotated plant image datasets for the purpose of training deep learning algorithms are lacking. One common approach to alleviate the lack of training data is dataset augmentation. Herein, we propose an alternative solution to dataset augmentation for plant phenotyping, creating artificial images of plants using generative neural networks. We propose the Arabidopsis Rosette Image Generator (through) Adversarial Network: a deep convolutional network that is able to generate synthetic rosette-shaped plants, inspired by DCGAN (a recent adversarial network model using convolutional layers). Specifically, we trained the network using A1, A2, and A4 of the CVPPP 2017 LCC dataset, containing Arabidopsis Thaliana plants. We show that our model is able to generate realistic 128x128 colour images of plants. We train our network conditioning on leaf count, such that it is possible to generate plants with a given number of leaves suitable, among others, for training regression based models. We propose a new Ax dataset of artificial plants images, obtained by our ARIGAN. We evaluate this new dataset using a state-of-the-art leaf counting algorithm, showing that the testing error is reduced when Ax is used as part of the training data.
Why it matches plant phenotyping methods植物表現型解析用の合成画像生成ネットワークを開発し、葉数を条件付けたデータセットを作成・評価しており、表現型取得・解析ワークフローの技術的貢献が中心である。
abstractWe propose a new Ax dataset of artificial plants images, obtained by our ARIGAN.
Reproduction assets foundThe paper's authors publicly released the Ax dataset of 57 synthetic Arabidopsis plant images generated by ARIGAN (with leaf-count annotations in a CSV), which directly reproduces the paper's phenotyping data contribution. The CVPPP 2017 LCC dataset is the training input but is cited prior work, not a paper-specific.Dataset · publicr quantitative experiments show that the extension of the training dataset with the images in Ax improved the testing error and reduced overfitting. We run a 4-fold cross validation experiment on A4 dataset. Evaluation metrics of our experiments are reported in Table 1 . Our synthetic dataset Ax is available to download at \url http://www.valeriogiuffrida.academy/ax.
Acknowledgements
This work was supported by The Alan Turing Institute under the EPSRC grant EP/N510129/1, and also by the BBSRC grant BB/P023487/1.
References
[1]
F. Bastien, P. Lamblin, R. Pascanu, J. Bergstra, I. J. Goodfellow, A. Bergeron,
N. Bouchard, and Y. Bengio.
Theano: new features and speed improvements.
Deep LearninOpen asset ↗Axlines:101-153Code / dataset availability confirmedbioRxiv · Europe PMC · OpenAlex · checked 15 Sept 2026
In recent years, there has been an increasing interest in image-based plant phenotyping, applying state-of-the-art machine learning approaches to tackle challenging problems, such as leaf segmentation (a multi-instance problem) and counting. Most of these algorithms need labelled data to learn a model for the task at hand. Despite the recent release of a few plant phenotyping datasets, large annotated plant image datasets for the purpose of training deep learning algorithms are lacking. One common approach to alleviate the lack of training data is dataset augmentation. Herein, we propose an alternative solution to dataset augmentation for plant phenotyping, creating artificial images of plants using generative neural networks. We propose the Arabidopsis Rosette Image Generator (through) Adversarial Network: a deep convolutional network that is able to generate synthetic rosette-shaped plants, inspired by DC-GAN (a recent adversarial network model using convolutional layers). Specifically, we trained the network using A1, A2, and A4 of the CVPPP 2017 LCC dataset, containing Arabidopsis Thaliana plants. We show that our model is able to generate realistic 128 x 128 colour images of plants. We train our network conditioning on leaf count, such that it is possible to generate plants with a given number of leaves suitable, among others, for training regression based models. We propose a new Ax dataset of artificial plants images, obtained by our ARIGAN. We evaluate this new dataset using a state-of-the-art leaf counting algorithm, showing that the testing error is reduced when Ax is used as part of the training data.
Why it matches plant phenotyping methods植物フェノタイピング用の合成画像生成手法を開発し、葉数条件付き生成とデータセットの評価を行っており、表現型データ取得・解析基盤が研究の中心です。
abstractWe propose a new Ax dataset of artificial plants images, obtained by our ARIGAN.
Reproduction assets foundThe paper's authors publicly released their synthetic Ax dataset of 57 GAN-generated Arabidopsis plant images, with an explicit download URL stated in the paper. This is a paper-specific, publicly available asset directly tied to this paper's phenotyping analysis. No code or trained model availability is stated.Dataset · publicBatch normalization: Accelerating
Evaluation metrics of our experiments are reported in Ta- deep network training by reducing internal covariate shift.
In F. Bach and D. Blei, editors, Proceedings of the 32nd In-
ble 1. Our synthetic dataset Ax is available to download at
ternational Conference on Machine Learning, volume 37 of
http://www.valeriogiuffrida.academy/ax. Proceedings of Machine Learning Research, pages 448–456,
Lille, France, 07–09 Jul 2015. PMLR.
Acknowledgements [14] Y. LeCunn. The MNIST database of handwritten digits,
http://yann.lecun.com/exdb/mnist/.
This work was supported by The Alan Turing Institute un- [15] A. L. Maas, A. Y. Hannun, and A. Y. Ng. Rectifier non-
der theOpen asset ↗pdf-layout-page:7 lines:1-56Code / dataset availability confirmedarXiv · checked 10 Sept 2026
In this paper, we investigate the problem of counting rosette leaves from an RGB image, an important task in plant phenotyping. We propose a data-driven approach for this task generalized over different plant species and imaging setups. To accomplish this task, we use state-of-the-art deep learning architectures: a deconvolutional network for initial segmentation and a convolutional network for leaf counting. Evaluation is performed on the leaf counting challenge dataset at CVPPP-2017. Despite the small number of training samples in this dataset, as compared to typical deep learning image sets, we obtain satisfactory performance on segmenting leaves from the background as a whole and counting the number of leaves using simple data augmentation strategies. Comparative analysis is provided against methods evaluated on the previous competition datasets. Our framework achieves mean and standard deviation of absolute count difference of 1.62 and 2.30 averaged over all five test datasets.
Why it matches plant phenotyping methodsロゼット葉の画像から葉数を推定する深層学習手法を提案し、セグメンテーションと葉数カウントをデータセットで評価しており、植物表現型取得手法が中心である。
abstractcounting rosette leaves from an RGB image, an important task in plant phenotyping
Reproduction assets foundThe paper's authors explicitly state their leaf counting/segmentation code is publicly available on GitHub, and the CVPPP2017 Leaf Counting Challenge dataset used for all experiments is publicly hosted at plant-phenotyping.org.Code · publicCode is publicly available here. 1 1Open asset ↗lines:215-305Code / dataset availability confirmedCrossref · Europe PMC · OpenAlex · checked 14 Sept 2026
Plant phenomics has received increasing interest in recent years in an attempt to bridge the genotype-to-phenotype knowledge gap. There is a need for expanded high-throughput phenotyping capabilities to keep up with an increasing amount of data from high-dimensional imaging sensors and the desire to measure more complex phenotypic traits (Knecht et al., 2016). In this paper, we introduce an open-source deep learning tool called Deep Plant Phenomics. This tool provides pre-trained neural networks for several common plant phenotyping tasks, as well as an easy platform that can be used by plant scientists to train models for their own phenotyping applications. We report performance results on three plant phenotyping benchmarks from the literature, including state of the art performance on leaf counting, as well as the first published results for the mutant classification and age regression tasks for Arabidopsis thaliana .
Why it matches plant phenotyping methods植物フェノタイピング向けのオープンソース深層学習ツールを開発し、複数のベンチマークで性能評価しているため、表現型取得・解析手法が研究の中心です。
abstractwe introduce an open-source deep learning tool called Deep Plant Phenomics.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicDeep Plant Phenomics is available for download at https://github.com/usaskdapper/deepplantphenomics . Detailed documentation describing installation and usage of the platform is available in the software repository.Open asset ↗usaskdapper/deepplantphenomicslines:49-57