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 confirmedEurope PMC · checked 5 Sept 2026
Low temperature stress severely restricts the cultivation and distribution of pear ( Pyrus L.) germplasms, frequently resulting in frost injury and yield reduction. To accurately evaluate the cold resistance of pear germplasm resources, this study investigates the physiological and biochemical responses of one-year-old branches to different degrees of low-temperature stress, as well as differences in the tissue structure of these pear germplasms after low-temperature stress. In this study, 122 pear germplasms were classified into high (HR), medium (MR), and low (LR) cold-tolerance categories based on their semi-lethal temperature (LT 50 ). Further analysis of pear germplasms with different levels of cold resistance revealed that, with decreasing temperature, HR germplasms exhibited smaller increases in relative electrolyte conductivity (REC) and malondialdehyde (MDA) content and higher accumulation of proline (Pro), soluble proteins (SP), soluble sugars (SS), and peroxidase activity compared with LR germplasms. In addition, the peak values of these indicators generally occurred at lower temperatures in HR germplasms. A correlation analysis and principal component analysis indicated that physiological indices, including REC, bound water/free water ratio, SS, and MDA, as well as branch anatomical traits related to xylem and cortex proportions, were closely associated with variation in LT 50 . An integrated assessment using membership function analysis produced rankings consistent with LT 50 -based clustering, supporting the reliability of the multivariate evaluation framework. Overall, this study establishes an integrated, indicator-based approach for evaluating cold resistance in pear germplasm by integrating physiological, biochemical, and anatomical characteristics. These results provide a theoretical basis and methodological reference for screening cold resistance germplasms.
Why it matches plant phenotyping methods生理・生化学・解剖学的形質を統合し、LT50と多変量評価によってナシ遺伝資源の耐寒性を分類・スクリーニングする評価フレームワークが研究の中心である。
abstractTo accurately evaluate the cold resistance of pear germplasm resources, this study investigates the physiological and biochemical responses of one-year-old branches to different degrees of low-temperature stress, as well as differences in the tissue structure of these pear germplasms after low-temperature stress.
Reproduction assets foundThe article's Data Availability statement links a public Zenodo deposit containing the paper's raw phenotyping data (LT50, physiological/biochemical and anatomical measurements for pear germplasms). Supplemental files also contain germplasm characteristics and LT50 comparisons, but the Zenodo raw-data deposit is the明确,Dataset · publicThe data is available at Zenodo: liu186253. (2025). liu186253/Data: raw data (Version V11). Zenodo. https://doi.org/10.5281/zenodo.17524773 .Open asset ↗Zenodo · 10.5281/zenodo.17524773lines:636-710Code / dataset availability confirmedOpenAlex · Crossref · checked 15 Sept 2026
LeafScans-Orchard is a curated, multi-year RGB image dataset of orchard plant leaves designed to support research in computer vision, machine learning, and plant phenotyping. The dataset comprises 9708 high-quality leaf scans acquired during collection campaigns conducted between 2015 and 2025, covering seven orchard crop species: apple, pear, sweet cherry, sour cherry, plum, peach, and apricot. In total, the dataset includes 67 cultivar labels. All samples were acquired using flatbed scanning under controlled conditions on a uniform background, ensuring high visual consistency and minimal background variability. The original scans were captured at 1200 dpi and subsequently converted into a public release format at 300 dpi, stored as lossless TIFF images to preserve morphological and textural details. Each image corresponds to a single leaf and is organized in a hierarchical directory structure by species, cultivar, and acquisition year, accompanied by image-level metadata and aggregated species–cultivar–year counts. LeafScans-Orchard is suitable for plant species classification, cultivar recognition, leaf morphology analysis, texture analysis, and general visual feature extraction. In addition to the main release, a representative subset of 300 original 1200 dpi scans is provided to support high-resolution analyses. The dataset is particularly suited for fine-grained classification, morphology-driven analysis, and methodological studies under controlled imaging conditions.
Why it matches plant phenotyping methods果樹葉のRGBスキャン画像を収録した公開データセットで、植物フェノタイピングおよび葉形態解析を目的とする。標準化された画像取得と再利用可能なデータ構成が中心であり、フェノタイピング用データセットとして適格。
abstractLeafScans-Orchard is a curated, multi-year RGB image dataset of orchard plant leaves designed to support research in computer vision, machine learning, and plant phenotyping.
Reproduction assets foundThe paper's core asset is the LeafScans-Orchard dataset itself (9708 RGB leaf scans, 300 dpi TIFF release plus 1200 dpi subset, image-level metadata and summary counts), openly deposited on Zenodo with an explicit DOI and CC BY 4.0 license. This is a paper-specific, public, actionable phenotyping image dataset. No codeDataset · publicthe published version of the manuscript.
Funding: This research received no external funding.
Institutional Review Board Statement: Not applicable.
Informed Consent Statement: Not applicable.
Data Availability Statement: The dataset described in this article is openly available in Zenodo
as LeafScans-Orchard Dataset (v1.0.0) at https://doi.org/10.5281/zenodo.20187966 (accessed on
10 May 2026). The repository includes the 300 dpi image release, the 1200 dpi high-resolution subset,
image-level metadata, aggregated species–cultivar–year counts, and supporting documentation. The
complete archive of original 1200 dpi scans is retained locally by the authors but is not included in
the current pubOpen asset ↗Zenodo · 10.5281/zenodo.20187966pdf-raw-page:12 lines:1-46Code / dataset availability confirmedEurope PMC · checked 5 Sept 2026
The growing global demand for food production, coupled with the increasing threat of plant diseases, necessitates advanced and automated solutions for crop health monitoring. Among various crops, pome fruits such as apples and pears are widely cultivated yet highly susceptible to multiple diseases that can significantly reduce yield and quality. Existing approaches for disease detection and severity classification are often limited by their dependency on manual inspection and their inability to handle complex real-world imagery, especially when multiple diseases coexist on a single leaf. To address these limitations, this research introduces a novel dual-model deep learning framework for multi-disease severity detection and classification in pome fruit leaves. A fine-tuned MobileNetV2 backbone is employed to extract high-level discriminative features from a specialized pome leaf dataset annotated with multiple disease types and severity levels. The proposed system integrates a lightweight Lite-U-Net for semantic segmentation to isolate diseased regions and an enhanced Lite-YOLACT for instance segmentation using a linear combination of prototype masks and mask coefficients. Moreover, a new multi-disease severity scale is proposed to quantify the impact of multiple coexisting infections on a single leaf, an aspect not addressed in previous studies. To enhance interpretability, an improved Grad-CAM technique generates visual heatmaps highlighting the most influential regions in the model's decision-making process, providing transparency and validation for agricultural experts. Experimental evaluations demonstrate that the proposed framework achieves 95% accuracy in disease severity estimation, effectively identifying and grading multiple infections simultaneously. This study represents a significant step forward in precision agriculture, offering an efficient, interpretable, and scalable deep learning solution for real-world crop health monitoring and management. The source code and trained models are publicly available at: https://github.com/mqasim0787/Multi-Disease-Severity .
Why it matches plant phenotyping methods果樹葉の病斑領域を画像から分割し、複数病害の重症度を定量推定する深層学習フレームワークが研究の中心であり、植物状態の画像ベース表現型計測に該当する。
abstractthis research introduces a novel dual-model deep learning framework for multi-disease severity detection and classification in pome fruit leaves.
Reproduction assets foundThe paper's authors publicly release source code and trained models on GitHub, and the study analyzes two public Kaggle plant-image datasets (DiaMOS Plant and PlantVillage) used directly for the multi-disease severity phenotyping experiments.Code · publicThe source code and trained models are publicly available at: https://github.com/mqasim0787/Multi-Disease-Severity .Open asset ↗https://github.com/mqasim0787/Multi-Disease-Severity · mqasim0787/Multi-Disease-Severitylines:1-23Dataset · publicThe datasets analyzed during the current study are available publicly in the Kaggle repository, DiaMOS dataset (1) and PlantVillage Dataset (2) 0.1. [https://www.kaggle.com/datasets/alexandraneagu101/diamos-plant-dataset]Open asset ↗https://www.kaggle.com/datasets/alexandraneagu101/diamos-plant-dataset · diamos-plant-datasetlines:964-977Code / dataset availability confirmedEurope PMC · OpenAlex · checked 15 Sept 2026
Fruit growth has long been described using single- or double-sigmoid curves; however, these temporal models cannot fully capture the spatial heterogeneity that ultimately shapes a fruit. Here, we present a three-dimensional analysis pipeline that non-destructively tracks spatial fruit growth dynamics from field-collected imagery. Surface landmarks were drawn, and video recordings were taken throughout development for three pome fruits, apple ( Malus × domestica ), Japanese pear ( Pyrus pyrifolia ) and European pear ( Pyrus communis ), and two drupe fruits, peach ( Prunus persica ) and Japanese apricot ( Prunus mume ), to track their motion. Using 3D Gaussian splatting, we successfully reconstructed 3D models of the fruits, and the landmark displacement could be measured with high accuracy, with R 2 ≥ 0.98 when compared to manual recordings. We found a common spatial growth gradient in the longitudinal growth shared in the pomes and drupes of the Rosaceae; proximal (stem-end) regions exhibited more pronounced growth than the distal (stylar) end. An exception was found in European pear 'Bartlett,' which showed relatively vigorous growth in the distal region, explaining its distinct shape with expanded distal end. Transverse expansion varied far less than longitudinal expansion, with a possible association with initial fruit morphology. Inter-fruit growth variability peaked in the fastest-growing regions, particularly in the distal area of the European pear, highlighting the link between growth vigor and phenotypic variance. These results provide foundational insights into the developmental dynamics of both pome and drupe fruits of the Rosaceae family, contributing to the optimization of fruit size, shape, and uniformity.
Why it matches plant phenotyping methods3D画像解析パイプラインと3D Gaussian Splattingを用いて果実の空間的成長を非破壊計測し、手動記録との精度比較で検証しているため、植物表現型取得法が中心である。
abstractHere, we present a three-dimensional analysis pipeline that non-destructively tracks spatial fruit growth dynamics from field-collected imagery.
Reproduction assets foundThe authors deposited a subset of the 3DGS-reconstructed fruit models (the paper's phenotyping outputs) on Figshare with a public DOI; additional data only on request. No author analysis code or raw imagery deposit is stated.Dataset · publicFootnotes
Appendix A
Supplementary data to this article can be found online at https://doi.org/10.1016/j.plaphe.2026.100166 .
Appendix A.
Supplementary data
The following is the Supplementary data to this article:
Multimedia component 1
Multimedia component 1
Data availability
A subset of the generated 3D models is available at https://doi.org/10.6084/m9.figshare.30854579 , where the quality of the 3DGS reconstructions and the marking/measurement procedure can be examined. Additional data may be provided upon reasonable request to the corresponding author.
ReferencesOpen asset ↗figshare · 10.6084/m9.figshare.30854579lines:151-171Code / 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 confirmedEurope PMC · checked 6 Sept 2026
The comprehensive understanding of the dormant pruning patterns in pear trees, along with the accurate identification of shoots suitable for pruning, is essential for implementing automated pruning and fruit production. Due to the complexity of tree architecture, previous descriptions of pruning strategies were qualitative summaries based on experience. In this study, we proposed a high-precision shoot extraction pipeline through point cloud alignment at different times, enabling a quantitative analysis of the pruning patterns. The structural parameters of 126 full bearing period pear trees, encompassing two cultivars and three architectures, were characterized, including the shoot number, single shoot angle and length, as well as shoot length density. The validation results demonstrated that the method attained an R 2 of 0.82, 0.92, and 0.85 for shoot number, single shoot angle and length, respectively, with mean absolute error of 18.72, 6.08°, and 0.13 m. The findings indicate that tree architecture exerts a greater influence on pruning compared to cultivar, particularly in Cuiguan, where significant differences were observed across diverse tree architectures. The characters of the corresponding annual (one-year-old) shoots (AS) and pruned shoots (PS) exhibit similar distribution. The AS, constituted 78.62% of the PS number, and 94.90% of length of AS were pruned, indicating that dormant pruning in full bearing period pear tree primarily targets at the annual shoots, and the pruning of annual shoots is mainly by thinning. This study could help the automatic pruning system make pruning decisions and promotes the development of fine orchard management.
Why it matches plant phenotyping methodsナシ樹のシュート形態を点群アライメントで抽出・定量化する手法を開発し、精度検証まで行っており、植物フェノタイピング手法が中心です。
abstractwe proposed a high-precision shoot extraction pipeline through point cloud alignment at different times, enabling a quantitative analysis of the pruning patterns.
Reproduction assets foundThe paper's Data availability statement explicitly provides authors' source code and point cloud samples at a public GitHub repository, matching an allowed URL.Code · publicThe source code and point clouds samples used in this study are publicly available at: https://github.com/Lixiao-bai/Pear_branch_seg_and_analysis .Open asset ↗Lixiao-bai/Pear_branch_seg_and_analysislines:227-309Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
The PlantCity dataset addresses significant agricultural yield losses in Pakistan from plant diseases. It provides 10,667 high-resolution images of leaves from 12 key crops: apple, apricot, bean, cherry, maize, fig, grape, loquat, pear, tomato, walnut, and persimmon. The images are organized into 52 classes (41 diseased and 11 healthy) and augmented to a total of 52,273 images. Data was collected in real-field conditions in Charsadda (34.15°N, 71.74°E, typical temperature 40-44 °C) and Chitral (35.85°N, 71.79°E, typical temperature 25-30 °C) from April to July 2023-2024. The dataset enables the development of deep learning models for automated disease classification and captures a range of environmental factors, including high temperatures that can exacerbate disease symptoms. It utilizes smartphone-based computer vision to facilitate early disease identification, thereby supporting precision farming and sustainable agriculture in Pakistan.
Why it matches plant phenotyping methods植物葉の病害状態を画像から分類するデータセットが研究の中心であり、植物病害フェノタイピング用の画像データセットとして適格です。
abstractThe PlantCity dataset addresses significant agricultural yield losses in Pakistan from plant diseases.
Reproduction assets foundThe paper is a Data in Brief article describing the PlantCity plant leaf image dataset (10,667 original images, 52 classes, 12 crops, collected in Pakistan). The dataset itself is the paper's core phenotyping asset and is publicly deposited on Mendeley Data with a direct URL provided in the article.Dataset · publicon of diseases, pests, or environmental stress in plant leaves.
Data source location
Charsadda (Village Sarki) chosen for tomato and Chitral (Village Danin) for the other 11 crops, Khyber Pakhtunkhwa, Pakistan
Data accessibility
Repository name: Mendeley Data
Data identification number: 10.17632/w8kh2xkspx.2
Direct URL to data: https://data.mendeley.com/datasets/w8kh2xkspx/1
Related research article
None
1
Value of the Data
•
The PlantCity dataset is comprehensive, consisting of 10,667 high-resolution images across 52 classes (41 diseased, 11 healthy) from 12 crop species, collected from Charsadda (tomato disease symptoms) and Danin Chitral (selected for its agro-climatic suitability for fruOpen asset ↗Mendeley Data · 10.17632/w8kh2xkspx.2lines:1-48Code / dataset availability confirmedEurope PMC · bioRxiv · OpenAlex · checked 15 Sept 2026
Fruit growth has long been described using single- or double-sigmoid curves; however, these temporal models cannot fully capture the spatial heterogeneity that ultimately shapes a fruit. Here, we present a three-dimensional analysis pipeline that non-destructively tracks spatial fruit growth dynamics from field-collected imaginary. Surface landmarks were drawn, and video recordings were taken throughout development for three pome fruits, apple ( Malus × domestica ), Japanese pear ( Pyrus pyrifolia ) and European pear ( Pyrus communis ), and two drupe fruits, peach ( Prunus persica ) and Japanese apricot ( Prunus mume ), to track their motion. Using 3D Gaussian Splatting, we successfully reconstructed 3D models of the fruits, and the landmark displacement could be measured with high accuracy, with R 2 ≥ 0.98 when compared to manual recordings. We found a common spatial growth gradient in the longitudinal growth shared in the pomes and drupes of the Rosaceae; proximal (stem-end) regions exhibited more pronounced growth than the distal (stylar) end. An exception was found in European pear ‘Bartlett,’ which showed relatively vigorous growth in the distal region, explaining its distinct shape with expanded distal end. Transverse expansion varied far less than longitudinal expansion, with a possible association with initial fruit morphology. Inter-fruit growth variability peaked in the fastest-growing regions, particularly in the distal area of the European pear, highlighting the link between growth vigor and phenotypic variance. These results provide foundational insights into the developmental dynamics of both pome and drupe fruits of the Rosaceae family, contributing to the optimization of fruit size, shape, and uniformity.
Why it matches plant phenotyping methods3D Gaussian Splattingを用いて果実の3D再構成と空間的成長形質の非破壊計測パイプラインを開発し、手動記録との精度比較で検証しているため、フェノタイピング手法が中心である。
abstractHere, we present a three-dimensional analysis pipeline that non-destructively tracks spatial fruit growth dynamics
Reproduction assets foundThe paper's data availability statement deposits a subset of the generated 3DGS fruit reconstruction models (the paper's phenotyping outputs) on Figshare with a public DOI; additional data is request-only. No author analysis code is explicitly deposited.Dataset · publicFootnotes
Appendix A
Supplementary data to this article can be found online at https://doi.org/10.1016/j.plaphe.2026.100166 .
Appendix A.
Supplementary data
The following is the Supplementary data to this article:
Multimedia component 1
Multimedia component 1
Data availability
A subset of the generated 3D models is available at https://doi.org/10.6084/m9.figshare.30854579 , where the quality of the 3DGS reconstructions and the marking/measurement procedure can be examined. Additional data may be provided upon reasonable request to the corresponding author.
ReferencesOpen asset ↗figshare · 10.6084/m9.figshare.30854579lines:151-171Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
The evaluation of fruit genetic resources regarding a resistance to pathogens is an essential basis for subsequent selection in fruit breeding. Both genetic analysis and phenotyping of defined traits are important tools and provide decision data in the evaluation process. However, the phenotyping of plants is often carried out 'by hand' and remains the bottleneck in fruit breeding and fruit growing. The development of a digital and UAV (unmanned aerial vehicle)-based phenotyping method for the assessment of genotype-specific susceptibility or resistance against diseases in orchards would significantly increase the efficiency of plant breeding. In this framework, a workflow for drone-based monitoring of pathogens in orchards was developed using the European pear rust ( Gymnosporangium sabinae ) as model pathogen. Pear rust is widespread in orchards and causes conspicuous, clearly visible, yellow to orange-colored disease symptoms. In this paper, we provide a dataset with expert-annotated high-resolution RGB images with pear rust symptoms. For data collection, ten UAV-flight campaigns were realized between 2021 and 2023 under various weather conditions and with different flight parameters in the experimental orchard of the Julius Kühn-Institute for Breeding Research on Fruit Crops in Dresden-Pillnitz (Germany). 1394 images were captured of different pear genotypes, including varieties, wild species and progeny from breeding. The dataset contains manually labelled images with a size of 768 × 768 pixels of leaves infected with pear rust at different stages of development, labelled as class GYMNSA, as well as background images without symptoms. Each leaf with pear rust symptoms was annotated with the drawing method by two points (bounding boxes) using the Computer Vision Annotation Tool (CVAT, v1.1.0) [1] and presented in YOLO 1.1 file format (.txt files). A total of 584 annotated images and 162 background images, organized into a training and validation set, are included in the GYMNSA dataset. This GYMNSA dataset can be used as a resource for researchers and developers working on drone-based plant disease monitoring systems.
Why it matches plant phenotyping methodsナシさび病の植物症状をUAV画像から検出するための注釈付きデータセットを提供しており、植物病害状態の画像ベース表現型取得・解析ワークフローが中心的です。
abstractThe development of a digital and UAV (unmanned aerial vehicle)-based phenotyping method for the assessment of genotype-specific susceptibility or resistance against diseases in orchards would significantly increase the efficiency of plant breeding.
Reproduction assets foundThe paper's GYMNSA dataset — annotated UAV RGB images of pear rust symptoms with YOLO labels — is publicly deposited on Mendeley Data under DOI 10.17632/44kjgc4gkc.1, directly reproducing the paper's phenotyping measurements.Dataset · publicl orchard of the Julius Kühn-Institute (JKI - Federal Research Centre for Cultivated Plants) at the Institute for Breeding Research on Fruit Crops located in Dresden-Pillnitz (Germany) [51°00ʹ01"N 13°53ʹ12"E].
Data accessibility
Repository name: Mendeley Data
Data identification number: 10.17632/44kjgc4gkc.1
Direct URL to data: https://data.mendeley.com/datasets/44kjgc4gkc/1
1.
Value of the Data
•
These data were collected on an approximately 1.6 ha experimental field with over 1000 different pear genotypes (breeding material and genetic resources of pear varieties and species) and presents a wide spectrum of phenotypic characteristics of pear rust infections at different stages of developmeOpen asset ↗Mendeley Data · 10.17632/44kjgc4gkc.1lines:43-69Code / dataset availability confirmedOpenAlex · Crossref · checked 8 Sept 2026
Computer vision techniques offer promising tools for disease detection in orchards and can enable effective phenotyping for the selection of resistant cultivars in breeding programmes and research. In this study, a digital phenotyping system for disease detection and monitoring was developed using drones, object detection and photogrammetry, focusing on European pear rust (Gymnosporangium sabinae) as a model pathogen. High-resolution RGB images from ten low-altitude drone flights were collected in 2021, 2022 and 2023. A total of 16,251 annotations of leaves with pear rust symptoms were created on 584 images using the Computer Vision Annotation Tool (CVAT). The YOLO algorithm was used for the automatic detection of symptoms. A novel photogrammetric approach using Agisoft’s Metashape Professional software ensured the accurate localisation of symptoms. The geographic information system software QGIS calculated the infestation intensity per tree based on the canopy areas. This drone-based phenotyping system shows promising results and could considerably simplify the tasks involved in fruit breeding research.
Why it matches plant phenotyping methodsドローン画像、物体検出、写真測量を統合し、ナシ樹のさび病症状を検出・局在化して樹体ごとの感染強度を推定するデジタル表現型解析システムの開発が中心である。
abstracta digital phenotyping system for disease detection and monitoring was developed using drones, object detection and photogrammetry
Reproduction assets foundThe paper's Data Availability Statement explicitly deposits the annotated UAV image dataset on Mendeley Data and the trained model, detection workflow, and Metashape loading script on figshare, both with public URLs matching allowed entries.Dataset · publicsource repository Mendeley Data (https://data.mendeley.com/datasets/44kjgc4gkc/1, accessed on 8Open asset ↗Mendeley Data · 44kjgc4gkc/1pdf-page:15 lines:1-67Code · publicThe model, the detection workflow with instructions and the script for
loading the detections into Agisoft’s Metashape are available in the open-source figshare repository
(https://doi.org/10.6084/m9.figshare.27225312.v2, accessed on 28 October 2024).Open asset ↗figshare · 10.6084/m9.figshare.27225312.v2pdf-page:15 lines:1-67Code / 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 confirmedEurope PMC · checked 7 Sept 2026
A large number of countries worldwide depend on the agriculture, as agriculture can assist in reducing poverty, raising the country's income, and improving the food security. However, the plan diseases usually affect food crops and hence play a significant role in the annual yield and economic losses in the agricultural sector. In general, plant diseases have historically been identified by humans using their eyes, where this approach is often inexact, time-consuming, and exhausting. Recently, the employment of machine learning and deep learning approaches have significantly improved the classification and recognition accuracy for several applications. Despite the CNN models offer high accuracy for plant disease detection and classification, however, the limited available data for training the CNN model affects seriously the classification accuracy. Therefore, in this paper, we designed a Cycle Generative Adversarial Network (CycleGAN) to overcome the limitations of over-fitting and the limited size of the available datasets. In addition, we developed an efficient plant disease classification approach, where we adopt the CycleGAN architecture in order to enhance the classification accuracy. The obtained results showed an average enhancement of 7% in the classification accuracy.
Why it matches plant phenotyping methods植物病害を画像から分類するCycleGANベースの手法開発が研究の中心であり、植物の病害状態を直接推定するため、植物フェノタイピング手法として適格です。
abstractTherefore, in this paper, we designed a Cycle Generative Adversarial Network (CycleGAN) to overcome the limitations of over-fitting and the limited size of the available datasets.
Reproduction assets foundThe paper's Data availability statement explicitly points to the DiaMOS pear disease image dataset (the plant image dataset used for all classification and CycleGAN experiments) hosted publicly on Zenodo. No author analysis code, trained models, or generated CycleGAN image dataset is reported as publicly available.Dataset · publicData availability
The dataset that has been used in this study is available in https://zenodo.org/record/5557313.Open asset ↗zenodopdf-page:10 lines:1-64Code / dataset availability confirmedEurope PMC · checked 7 Sept 2026
A large number of countries worldwide depend on the agriculture, as agriculture can assist in reducing poverty, raising the country’s income, and improving the food security. However, the plan diseases usually affect food crops and hence play a significant role in the annual yield and economic losses in the agricultural sector. In general, plant diseases have historically been identified by humans using their eyes, where this approach is often inexact, time-consuming, and exhausting. Recently, the employment of machine learning and deep learning approaches have significantly improved the classification and recognition accuracy for several applications. Despite the CNN models offer high accuracy for plant disease detection and classification, however, the limited available data for training the CNN model affects seriously the classification accuracy. Therefore, in this paper, we employed a Cycle Generative Adversarial Network (CycleGAN) to overcome the limitations of over-fitting and the limited size of the available datasets. In addition, we developed an efficient plant disease classification approach, where we adopt the CycleGAN architecture in order to enhance the classification accuracy. The obtained results showed an average enhancement of 7% in the classification accuracy.
Why it matches plant phenotyping methods植物病害画像を対象に、CycleGANによるデータ拡張・分類手法を開発し、分類精度を評価しているため、病害状態の画像ベース表現型推定が中心です。
abstractwe employed a Cycle Generative Adversarial Network (CycleGAN) to overcome the limitations of over-fitting and the limited size of the available datasets.
Reproduction assets foundThe paper uses the public DiaMOS pear leaf/fruit image dataset as its phenotyping input and explicitly states its availability on Zenodo. No author analysis code, trained models, or generated CycleGAN image dataset is reported as publicly deposited.Dataset · publicData availability: The dataset that has been used in this study is available
in https://zenodo.org/record/5557313.Open asset ↗zenodo · 5557313pdf-page:15 lines:1-40Code / dataset availability confirmedCrossref · checked 13 Sept 2026
Over the last few years, the impact of climate change has increased rapidly. It is influencing all steps of plant production and forcing farmers to change and adapt their crop management practices using new technologies based on data analytics. This study aims to classify plant diseases based on images collected directly in the field using deep learning. To this end, an ensemble learning paradigm is investigated to build a robust network in order to predict four different pear leaf diseases. Several convolutional neural network architectures, named EfficientNetB0, InceptionV3, MobileNetV2 and VGG19, were compared and ensembled to improve the predictive performance by adopting the bagging strategy and weighted averaging. Quantitative experiments were conducted to evaluate the model on the DiaMOS Plant dataset, a self-collected dataset in the field. Data augmentation was adopted to improve the generalization of the model. The results, evaluated with a range of metrics, including accuracy, recall, precison and f1-score, showed that the proposed ensemble convolutional neural network outperformed the single convolutional neural network in classifying diseases in real field-condition with variation in brightness, disease similarity, complex background, and multiple leaves.
Why it matches plant phenotyping methodsナシ葉の画像から病害状態を推定する深層学習分類法の開発・比較が中心であり、植物病害表現型の取得・抽出手法に該当する。
abstractThis study aims to classify plant diseases based on images collected directly in the field using deep learning.
Reproduction assets foundThe paper's authors publicly released both the DiaMOS Plant dataset (field-collected pear leaf images used for all experiments, on Zenodo) and their analysis code as the LeafBox toolbox (website and GitHub repository), with explicit availability statements.Dataset · publicaMOS Plant dataset is available at https://doi.org/10.5281/zenodo.5557313, accessed on 16 JanuaryOpen asset ↗Zenodo · 10.5281/zenodo.5557313pdf-page:10 lines:1-59Code · publicThe source code is available at https://leafbox.francescamalloci.com/,
https://github.com/mallociFrancesca/leaf-disease-toolbox, accessed on 16 January 2023.Open asset ↗GitHub · mallociFrancesca/leaf-disease-toolboxpdf-page:10 lines:1-59Code / dataset availability confirmedCrossref · checked 9 Sept 2026
The classification and recognition of foliar diseases is an increasingly developing field of research, where the concepts of machine and deep learning are used to support agricultural stakeholders. Datasets are the fuel for the development of these technologies. In this paper, we release and make publicly available the field dataset collected to diagnose and monitor plant symptoms, called DiaMOS Plant, consisting of 3505 images of pear fruit and leaves affected by four diseases. In addition, we perform a comparative analysis of existing literature datasets designed for the classification and recognition of leaf diseases, highlighting the main features that maximize the value and information content of the collected data. This study provides guidelines that will be useful to the research community in the context of the selection and construction of datasets.
Why it matches plant phenotyping methods植物病徴を画像で診断・モニタリングする公開データセットの構築と既存データセット比較が中心であり、植物病害状態の画像ベース表現型解析に該当する。
abstractwe release and make publicly available the field dataset collected to diagnose and monitor plant symptoms, called DiaMOS Plant
Reproduction assets foundThe paper releases the DiaMOS Plant dataset (3505 field images of pear leaves/fruits with csv and YOLO annotations) on Zenodo, and the authors' LeafBox analysis code (used for the CNN classification benchmark) on GitHub. Both are paper-specific, public, and directly actionable.Dataset · publicThe dataset is freely available for
academic purposes from a repository at https://doi.org/10.5281/zenodo.5557313 (accessed
on 17 October 2021)Open asset ↗Zenodo · 10.5281/zenodo.5557313pdf-page:4 lines:1-46Code · publicThe source code is available
at https://github.com/mallociFrancesca/leaf-disease-toolbox, accessed on 17 October 2021.Open asset ↗GitHubpdf-page:12 lines:1-59