Camera-based visual sensing provides a non-destructive and scalable approach for monitoring strawberry diseases and pests in greenhouse environments. However, greenhouse images acquired under practical cultivation conditions often contain early-stage tiny lesions, complex leaf backgrounds, uneven target scales, illumination variations, and partial occlusions, making accurate and efficient visual detection challenging. To address these issues, this study proposes YOLOv8n-DSLW (YOLOv8n enhanced by Dense reuse, Shuffle attention, LSKA-LAMP lightweight modeling, and Wise-IoU optimization), an AI-enabled vision-sensing detection model based on YOLOv8n for tiny strawberry disease and pest detection. Specifically, Shrink Residual Dense Block (ShrinkRDB) dense connection blocks and the C2f with Shuffle Attention (C2fSA) module are introduced to preserve weak lesion textures and suppress background interference in greenhouse visual data. A high-resolution P2 detection layer combined with Wise-IoU (WioU) dynamic regression loss is further incorporated to enhance tiny-target perception and localization. In addition, the Spatial Pyramid Pooling-Fast with Large Separable Kernel Attention (SPPF-LSKA) module strengthens contextual modeling under occlusion and clutter, while Layer-Adaptive Magnitude-based Pruning (LAMP) is adopted to mitigate model redundancy and improve the accuracy-efficiency balance. Experiments on a self-collected greenhouse strawberry disease and pest dataset show that YOLOv8n-DSLW achieves a mean Average Precision at 0.5 IoU threshold (mAP@0.5) of 94.3% and a mAP@0.5:0.95 of 77.5%, outperforming the YOLOv8n baseline. The final model has a parameter count of 4.386 M and a computational cost of 27.6 GFLOPs, achieving a frame rate of 45 FPS on the test workstation. It shows application potential for real-time visual monitoring in greenhouses under controlled data acquisition conditions. The results demonstrate that the proposed method improves tiny lesion detection under dense targets, complex backgrounds, and leaf occlusions, providing an AI-enabled vision-sensing framework for automated strawberry health monitoring in greenhouses. Nevertheless, due to limitations associated with imaging equipment, dataset representativeness, and the inherent constraints of the algorithm, further optimization and validation are required to support large-scale field deployment.
Why it matches plant phenotyping methodsイチゴ葉の病斑を画像から検出・局在化する新規YOLOモデルを開発し、データセット上で性能評価しており、植物病害状態の画像ベース表現型取得が中心である。
abstractthis study proposes YOLOv8n-DSLW (YOLOv8n enhanced by Dense reuse, Shuffle attention, LSKA-LAMP lightweight modeling, and Wise-IoU optimization), an AI-enabled vision-sensing detection model based on YOLOv8n for tiny strawberry disease and pest detection.
Reproduction assets foundThe paper's self-collected greenhouse strawberry disease/pest image dataset (with COCO annotations and train/test splits) is explicitly stated as publicly deposited on GitHub at the allowed URL. No author analysis code or trained model checkpoint is mentioned as publicly available.Dataset · publicThe dataset used in this study, including the training and independent test subsets, has been uploaded to a GitHub repository for dataset verification and is available at: https://github.com/dataset-review-2026/strawberry-dataset (accessed on 26 July 2026).Open asset ↗dataset-review-2026/strawberry-datasetlines:111-131Code / dataset availability confirmedEurope PMC · checked 5 Sept 2026
Tomato leaf diseases pose significant threats to crop yield and food security. However, in real-world cultivation environments, factors such as fluctuating illumination, varying leaf occlusion, and ambiguous lesion morphology often compromise detection accuracy. This paper presents the Gradient-aware Bidirectional Retentive Detection Transformer (GBR-DETR), a model designed for high-precision, real-time disease detection. This model is composed of two network structures and a retentive feature aggregation module: (1) a Multi-scale Gradient-Aware Transfer Network (MGAT-Net) is designed to encode gradient information through the Sobel operator, thereby enhancing the localization stability for small and blurry lesions; (2) a Bidirectional Context Pyramid Network (BCPN) is proposed to enable bidirectional interactions among multi-level features through a top-down and a bottom-up pathway, thereby generating multi-scale lesion features and bridging cross-scale semantic gaps; and (3) a Retentive Feature Aggregation Module (RFAM) is used to suppress background noise and establish global feature correlations, thereby enhancing the overall representation capability for lesion recognition. Experiments on the Multi-scenario Tomato Leaf Disease (M-TLD) dataset show that GBR-DETR yields gains of 3.12, 4.88, and 3.41 percentage points in mAP 50-95 , mAP 50 , and mAP 75 , respectively, over the baseline RT-DETR, while also outperforming representative DETR-based and CNN-based detectors. The model demonstrates robust generalization on the PlantDoc cross-domain benchmark, achieving a 2.11% improvement in mAP 50 over the baseline. Deployed on the NVIDIA Jetson Orin Nano with TensorRT FP16, it achieves 54 ms latency, enabling real-time disease monitoring on edge devices. This solution provides effective technical support for real-time disease monitoring in smart agriculture.
Why it matches plant phenotyping methodsトマト葉の病斑・病害状態を画像から検出するモデルを開発し、複数データセットで比較検証、エッジデバイス実装まで評価しており、植物病害表現型の取得手法が中心である。
abstractThis paper presents the Gradient-aware Bidirectional Retentive Detection Transformer (GBR-DETR), a model designed for high-precision, real-time disease detection.
Reproduction assets foundThe paper's M-TLD tomato leaf disease dataset (2212 images, 6581 annotations) and the GBR-DETR implementation/training code are explicitly stated to be publicly available at the authors' GitHub repository.Dataset · publicThe M-TLD dataset and all annotation files are publicly available at https://github.com/zhuojiaxiong6/DETR (accessed on 29 April 2026) to facilitate reproducibility and future research.Open asset ↗zhuojiaxiong6/DETRlines:38-108Code · publicThe code and dataset used in this study are publicly available at the following GitHub repository: https://github.com/zhuojiaxiong6/DETR (accessed on 29 April 2026). This repository contains the implementation of GBR-DETR, a Detection Transformer variant developed for detecting tomato leaf diseases and pests. All relevant training scripts, configuration files, and instructions for dataset usage are provided in the repository.Open asset ↗zhuojiaxiong6/DETRlines:673-675Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Accurate and real-time detection of maize foliar diseases is important for field disease monitoring and yield protection. However, in complex natural field environments, different diseases often exhibit high visual similarity, and early weak lesions are easily confused with background elements such as dry leaves, soil, and shadows, leading to false positives and missed detections in existing models. To address these challenges, this study proposes an improved lightweight maize foliar disease detection model based on YOLO11, termed CKM-YOLO11. First, a mixed local channel attention mechanism is introduced and adapted to the task in the backbone to construct the C3k2-MLCA module, thereby enhancing joint modeling of local lesion textures, edge details, and global contextual information. Second, a lightweight residual attention module, named MLCA-HeadLite, is designed at the P5 layer of the neck/head to alleviate the suppression of weak lesion responses during deep feature fusion. Experimental results demonstrate that the proposed model achieves an mAP@50 of 81.5% on a self-constructed maize disease dataset with complex field backgrounds, improving mAP@50 and mAP@50-95 by 3.2 and 3.4 percentage points, respectively, compared with the baseline YOLO11, while maintaining a low parameter count and computational cost. Further analyses based on the confusion matrix, comparisons of detection results, and Grad-CAM visualizations indicate that the proposed model performs better in background suppression, retention of weak lesion responses, and robustness in complex scenes. This study provides a reference for the lightweight design of maize foliar disease detection models in complex field environments and their deployment on agricultural edge devices.
Why it matches plant phenotyping methodsトウモロコシ葉の病斑・病害状態を画像から検出する軽量モデルを開発し、データセット上で性能評価しているため、植物病害表現型の取得手法が中心である。
abstractthis study proposes an improved lightweight maize foliar disease detection model based on YOLO11, termed CKM-YOLO11.
Reproduction assets foundThe paper's maize foliar disease detection dataset is built from public image sources (CD&S Dataset from OpenDataLab and PlantDoc-Dataset corn rust leaf folders) that are explicitly cited with public URLs, qualifying as paper-specific public phenotype image inputs. The self-collected images and the authors' code/tranedDataset · publict was constructed using three public-data components together with a small number of self-collected maize leaf images. First, field-acquired maize disease images were obtained from the Corn Disease and Severity (CD&S) Dataset downloaded from OpenDataLab, and only the Dataset_Original folder in the raw dataset package was used ( https://opendatalab.com/OpenDataLab/CD_and_S/tree/main , accessed on 3 May 2026). Second, to supplement the leaf rust category, additional images were collected from the train/Corn rust leaf folder of the PlantDoc-Dataset GitHub repository ( https://github.com/pratikkayal/PlantDoc-Dataset/tree/master/train/Corn%20rust%20leaf , accessed on 3 May 2026). Third, leaf rustOpen asset ↗OpenDataLab/CD_and_Slines:38-47Dataset · publicOpenDataLab, and only the Dataset_Original folder in the raw dataset package was used ( https://opendatalab.com/OpenDataLab/CD_and_S/tree/main , accessed on 3 May 2026). Second, to supplement the leaf rust category, additional images were collected from the train/Corn rust leaf folder of the PlantDoc-Dataset GitHub repository ( https://github.com/pratikkayal/PlantDoc-Dataset/tree/master/train/Corn%20rust%20leaf , accessed on 3 May 2026). Third, leaf rust images from the test folder of the same PlantDoc-Dataset repository were also used ( https://github.com/pratikkayal/PlantDoc-Dataset/tree/master/test , accessed on 3 May 2026). In addition, a small number of self-collected maize leaf images Open asset ↗pratikkayal/PlantDoc-Datasetlines:38-47Dataset · public, additional images were collected from the train/Corn rust leaf folder of the PlantDoc-Dataset GitHub repository ( https://github.com/pratikkayal/PlantDoc-Dataset/tree/master/train/Corn%20rust%20leaf , accessed on 3 May 2026). Third, leaf rust images from the test folder of the same PlantDoc-Dataset repository were also used ( https://github.com/pratikkayal/PlantDoc-Dataset/tree/master/test , accessed on 3 May 2026). In addition, a small number of self-collected maize leaf images were included as negative samples and field-background supplements. Considering that the present study focuses on object detection under complex backgrounds rather than image-level classification under simple-backgOpen asset ↗pratikkayal/PlantDoc-Datasetlines:38-47Code / dataset availability confirmedEurope PMC · checked 5 Sept 2026
Protein content is an important quality trait in sorghum that influences breeding approaches, end-use applications, and market value. Influenced by genetic, agronomic, and environmental variability, sorghum is characterized by its wide variation in composition, which may also be evident in kernels from the same sample. This study developed and evaluated a method for a non-destructive and rapid prediction of protein content in individual sorghum kernels using single-kernel near-infrared spectroscopy (SKNIR). Applying different pre-processing techniques to the spectra collected from intact kernels, the calibration models were developed using partial least squares regression and the reference protein content values obtained from the LECO combustion method. The best model was obtained using multiplicative scatter correction as pre-processing, resulting in a standard error of prediction of 0.83% and a relative predictive determinant of 3.40. These were indicative of the good predictive ability of the model and the instrument to be applied in quality control and sorting applications. These results highlight the potential of SKNIR to capture the inter-kernel variability in sorghum protein content and enhance screening for grain quality in breeding and grain processing.
Why it matches plant phenotyping methods単一穀粒NIRによるソルガム種子のタンパク質含量推定法を開発・評価しており、植物器官の形質取得が研究の中心である。
abstractThis study developed and evaluated a method for a non-destructive and rapid prediction of protein content in individual sorghum kernels using single-kernel near-infrared spectroscopy (SKNIR).
Reproduction assets foundThe paper's Data Availability Statement deposits the original single-kernel NIR spectra and reference protein data openly in Ag Data Commons, a paper-specific public dataset directly reproducing this study's measurements.Dataset · publicThe original data presented in the study is openly available in Ag Data Commons [https://doi.org/10.15482/USDA.ADC/31316725].Open asset ↗Ag Data Commons · 10.15482/USDA.ADC/31316725html-lines:226-278Code / dataset availability confirmedEurope PMC · checked 5 Sept 2026
Accurate and timely diagnosis of rice leaf diseases is crucial for smart agriculture leveraging vision sensors. However, existing lightweight convolutional neural networks (CNNs) often struggle in complex field environments, where small lesions, cluttered backgrounds, and varying illumination complicate recognition. This paper presents I-GhostNetV3, an incrementally improved GhostNetV3-based network for RGB rice leaf disease recognition. I-GhostNetV3 introduces two modular enhancements with controlled overhead: (1) Adaptive Parallel Attention (APA), which integrates edge-guided spatial and channel cues and is selectively inserted to enhance lesion-related representations (at the cost of additional computation), and (2) Fusion Coordinate-Channel Attention (FCCA), a near-neutral SE replacement that enables efficient spatial-channel feature fusion to suppress background interference. Experiments on the Rice Leaf Bacterial and Fungal Disease (RLBF) dataset show that I-GhostNetV3 achieves 90.02% Top-1 accuracy with 1.831 million parameters and 248.694 million FLOPs, outperforming MobileNetV2 and EfficientNet-B0 under our experimental setup while remaining compact relative to the original GhostNetV3. In addition, evaluation on PlantVillage-Corn serves as a supplementary transfer sanity check; further validation on independent real-field target domains and on-device profiling will be explored in future work. These results indicate that I-GhostNetV3 is a promising efficient backbone for future edge deployment in precision agriculture.
Why it matches plant phenotyping methods画像からイネ葉の病徴を認識・分類する軽量深層学習手法を開発し、複数データセットで精度と計算量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 paper presents I-GhostNetV3, an incrementally improved GhostNetV3-based network for RGB rice leaf disease recognition.
Reproduction assets foundThe paper's phenotyping inputs are two publicly available plant image datasets explicitly linked by the authors: the RLBF rice leaf disease dataset on Mendeley Data (primary evaluation) and the PlantVillage-Corn dataset on GitHub (cross-domain transfer). No author analysis code or trained model checkpoints are stated.Dataset · publicThe Rice Leaf Bacterial and Fungal Disease Dataset can be accessed at https://data.mendeley.com/datasets/hx6f852hw4/2 (accessed on 20 July 2025)Open asset ↗hx6f852hw4lines:688-704Dataset · publicthe PlantVillage-Corn Dataset is available at https://github.com/gabrieldgf4/PlantVillage-Dataset (accessed on 27 August 2025)Open asset ↗github.com/gabrieldgf4/PlantVillage-Datasetlines:688-704Code / dataset availability confirmedEurope PMC · checked 5 Sept 2026
Digital agriculture and smart farming require crop health monitoring methods that balance detection accuracy with computational cost. Rice leaf diseases threaten yield, while field images often contain small multi-scale lesions, variable illumination and cluttered backgrounds. This paper investigates SCD-YOLOv11n, a lightweight detector designed with these constraints in mind. The model replaces the YOLOv11n backbone with a StarNet backbone and integrates a C3k2-Star module to enhance fine-grained, multi-scale feature extraction. A Detail-Strengthened Cross-scale Detection (DSCD) head is further introduced to improve localization of small lesions. On this architecture, we design a DepGraph-based mixed group-normalization pruning rule and apply channel-wise feature distillation to recover performance after pruning. Experiments on a public rice leaf disease dataset show that the compressed model requires 1.9 MB of storage, achieves 97.4% mAP@50 and 76.2% mAP@50:95, and attains a measured speed of 184 FPS under the tested settings. These results provide a quantitative reference for designing lightweight object detectors for rice disease monitoring in digital agriculture scenarios.
Why it matches plant phenotyping methodsイネ葉の病斑を画像から検出・局在化する軽量モデルを開発し、精度・圧縮性能・速度を評価しており、植物病害状態の取得手法が研究の中心である。
abstractThis paper investigates SCD-YOLOv11n, a lightweight detector designed with these constraints in mind.
Reproduction assets foundThe paper's rice leaf disease image dataset (6715 annotated images) is explicitly stated to be publicly available on Roboflow, and an MDPI supplementary file is provided with additional dataset information. No author analysis code or trained model checkpoints are publicly deposited.Dataset · publicThe rice disease detection dataset used in this study is publicly available at: https://universe.roboflow.com/dreamydaisy-cdagn/rice-dyl9n/dataset/4 (accessed on 10 December 2025).Open asset ↗dreamydaisy-cdagn/rice-dyl9n/dataset/4lines:480-547Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Traditional segmentation methods are slow and rely on manual annotations, which are labor-intensive. To address these limitations, we propose YOLO-SAM AgriScan, a unified framework that combines the fast object detection capabilities of YOLOv11 with the zero-shot segmentation power of the Segment Anything Model 2 (SAM2). Our approach adopts a hybrid paradigm for on-plant ripe strawberry segmentation, wherein YOLOv11 is fine-tuned using a few-shot learning strategy with minimal annotated samples, and SAM2 performs mask generation without additional supervision. This architecture eliminates the bottleneck of pixel-wise manual annotation and enables the scalable and efficient segmentation of strawberries in both controlled and natural farm environments. Experimental evaluations on two datasets, a custom-collected dataset and a publicly available benchmark, demonstrate strong detection and segmentation performance in both full-data and data-constrained scenarios. The proposed framework achieved a mean Dice score of 0.95 and an IoU of 0.93 on our collected dataset and maintained competitive performance on public data (Dice: 0.95, IoU: 0.92), demonstrating its robustness, generalizability, and practical relevance in real-world agricultural settings. Our results highlight the potential of combining few-shot detection and zero-shot segmentation to accelerate the development of annotation-light, intelligent phenotyping systems.
Why it matches plant phenotyping methodsイチゴ果実の検出・セグメンテーションを行う画像ベース手法を開発し、複数データセットで性能評価している。単なる収穫対象の位置特定ではなく、果実マスク抽出を行うため、植物表現型取得手法が中心である。
abstractOur approach adopts a hybrid paradigm for on-plant ripe strawberry segmentation
Reproduction assets foundThe paper uses a public Roboflow Universe strawberry segmentation dataset (D2) directly for its detection/segmentation experiments, which qualifies as a paper-specific public asset. The authors' custom greenhouse dataset (D1) is only available upon request, and no authors' analysis code is deposited (Ultralytics is a CDataset · public3007-022-00866-2.
22. Song Y., Wang T., Cai P., Mondal S.K., Sahoo J.P. A comprehensive survey of few-shot learning: Evolution, applications, challenges, and opportunities. ACM Comput. Surv. 2023;55:1–40. doi: 10.1145/3582688.
23. Objectdetection Strawberry Seg Dataset. 2024. [(accessed on 10 September 2025)]. Available online: https://universe.roboflow.com/objectdetection-mnlwg/strawberry_seg-zkh1y .
24. Sekachev B., Manovich N., Zhiltsov M., Zhavoronkov A., Kalinin D., Hoff B., TOsmanov, Kruchinin D., Zankevich A., DmitriySidnev, et al. opencv/cvat: V1.1.0. 2020. [(accessed on 13 April 2025)]. Available online: https://zenodo.org/records/4009388 .
25. Ronneberger O., Fischer P., Brox T. U-Open asset ↗strawberry_seg-zkh1ylines:316-338Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Varieties show their unique characteristics in morphology, growth, and fruits. Tomato maturity is related to multiple dimensional characteristics including color, texture, smell, etc. An effective classification method of tomato variety and maturity is crucial for evaluating its growth and yield. However, due to the complex growth environment, some problems such as leaf occlusion and fruit shaded by each other make it difficult to accurately and efficiently identify them. To solve these problems, this study innovatively proposes a simultaneous detection model on tomato variety and maturity based on improved YOLOv8n, with the combination of frequency-adaptive dilated convolution (FADC) feature extraction module and the high-level screening-feature path aggregation network (HSPAN) with the aim of local and global feature fusion by the channel attention module and feature selection fusion mechanism. In addition, we use the Powerful-IoU (PIoU) loss function to replace the original Complete IoU (CIoU) to enhance the accuracy of bounding boxes. We also introduce a dynamic detection head as the final output of the model, which can adaptively adjust the focus of feature extraction according to the color and size of tomato fruits, thereby improving the recognition accuracy. Experimental results show that our model with better global perception capability achieves the highest detection accuracy and lower computation complexity among the comparative models.
Why it matches plant phenotyping methodsトマト果実の成熟度という観察可能な植物状態を画像から推定する検出モデルを開発しており、特徴抽出・検出ヘッド・損失関数の改良と比較評価が研究の中心である。
abstractthis study innovatively proposes a simultaneous detection model on tomato variety and maturity based on improved YOLOv8n
Reproduction assets foundThe paper's tomato variety/maturity detection experiments are built on the public Laboro Tomato dataset, which is explicitly cited with a public GitHub URL. No author analysis code, trained models, or supplementary assets are reported as available.Dataset · publicThe constructed dataset in this study is based on the Laboro Tomato open-access dataset [ 24 ], which is an image dataset of tomatoes with different maturity collected in a greenhouse in winter (15 December 2019).Open asset ↗lines:33-42Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
In this study, we propose a multi-scale feature fusion network based on an improved RT-DETR model for the efficient detection of tomato leaf disease. Our model combines the multi-scale extended residual module by capturing contextual information at various scales and the multi-scale feature pyramid network by integrating feature information from different levels, which improves feature extraction capability and reduces the interference of complex backgrounds on feature extraction, thereby improving information transmission efficiency and the accuracy of the model. In addition, the novel loss function called adaptive focal loss (AFL) was used, which is based on traditional focal loss with the introduction of attenuation factors to focus the model's attention to high-loss features to alleviate overfitting and of dynamic weight adjustment mechanisms to focus on the more important features during the training process to improve the overall learning performance. Another significant advantage of AFL is that it can more efficiently improve the detection accuracy on imbalanced datasets than on balanced datasets. These innovations optimized the learning strategy of the model, making AP@0.50 up to 97.9% on detecting the categories of tomato diseases. In addition, this model also achieves the high detection accuracy of 85.4% on other crop diseases. These results provide valuable references for agriculture applications.
Why it matches plant phenotyping methodsトマト葉の病害状態を画像から検出する深層学習手法を提案・改良しており、植物病害表現型の抽出法が研究の中心である。
abstractwe propose a multi-scale feature fusion network based on an improved RT-DETR model for the efficient detection of tomato leaf disease.
Reproduction assets foundThe paper constructs its LAB and ENV tomato leaf disease detection datasets by selecting and adjusting samples from two public Roboflow Universe datasets (cited as refs 30 and 31), which are public image inputs directly underlying this paper's phenotyping measurements. Both Roboflow URLs are given in the reference listDataset · public7-024-01188-1
38725014
PMC11080254
29.
Sun H.
Fu R.
Wang X.
Wu Y.
Al-Absi M.A.
Cheng Z.
Chen Q.
Sun Y.
Efficient Deep Learning-Based Tomato Leaf Disease Detection through Global and Local Feature Fusion
BMC Plant Biol. 2025 25 311
10.1186/s12870-025-06247-w
40069604
PMC11895386
30.
Sujansurya
Roboflow Universe
Available online: https://universe.roboflow.com/sujansurya/tomato_object (accessed on 15 August 2024)
31.
Roboflow Universe
Available online: https://universe.roboflow.com/classificationwithyolov8/tomato-leaf-diseases-4xa5i-3ajin-kyo9w (accessed on 15 August 2024)
32.
Singh D.
Jain N.
Jain P.
Kayal P.
Kumawat S.
Batra N.
PlantDoc: A Dataset for Visual Plant Disease Detection
ProceedingOpen asset ↗Roboflow Universelines:265-465Dataset · publicng-Based Tomato Leaf Disease Detection through Global and Local Feature Fusion
BMC Plant Biol. 2025 25 311
10.1186/s12870-025-06247-w
40069604
PMC11895386
30.
Sujansurya
Roboflow Universe
Available online: https://universe.roboflow.com/sujansurya/tomato_object (accessed on 15 August 2024)
31.
Roboflow Universe
Available online: https://universe.roboflow.com/classificationwithyolov8/tomato-leaf-diseases-4xa5i-3ajin-kyo9w (accessed on 15 August 2024)
32.
Singh D.
Jain N.
Jain P.
Kayal P.
Kumawat S.
Batra N.
PlantDoc: A Dataset for Visual Plant Disease Detection
Proceedings of the Proceedings of the 7th ACM IKDD CoDS and 25th COMAD Hyderabad, India 5–7 January 2020
ACM
New York, NY, USA
2020 24Open asset ↗Roboflow Universelines:265-465Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
Field / plotClassificationDisease symptoms / severity
The accurate identification of crop pests and diseases is critical for global food security, yet the development of robust deep learning models is hindered by the limitations of existing datasets. To address this gap, we introduce DLCPD-25, a new large-scale, diverse, and publicly available benchmark dataset. We constructed DLCPD-25 by integrating 221,943 images from both online sources and extensive field collections, covering 23 crop types and 203 distinct classes of pests, diseases, and healthy states. A key feature of this dataset is its realistic complexity, including images from uncontrolled field environments and a natural long-tail class distribution, which contrasts with many existing datasets collected under controlled conditions. To validate its utility, we pre-trained several state-of-the-art self-supervised learning models (MAE, SimCLR v2, MoCo v3) on DLCPD-25. The learned representations, evaluated via linear probing, demonstrated strong performance, with the SimCLR v2 framework achieving a top accuracy of 72.1% and an F1 score (Macro F1) of 71.3% on a downstream classification task. Our results confirm that DLCPD-25 provides a valuable and challenging resource that can effectively support the training of generalizable models, paving the way for the development of comprehensive, real-world agricultural diagnostic systems.
Why it matches plant phenotyping methods作物の病害・健全状態を画像で認識する大規模公開ベンチマークデータセットを構築・評価しており、植物状態の画像ベース表現型解析基盤が中心です。害虫認識も含まれますが、病害・健全状態の評価は植物フェノタイピングに該当します。
abstractwe introduce DLCPD-25, a new large-scale, diverse, and publicly available benchmark dataset.
Reproduction assets foundThe paper introduces DLCPD-25, a public crop pest/disease image dataset (221,943 images, 203 classes), with an explicit Data Availability Statement pointing to the authors' GitHub repository containing all image data and documentation.Dataset · publicThe DLCPD-25 dataset introduced and analyzed in this study is publicly available at: https://github.com/hwzhanng/DLCPD-25-Dataset (accessed on 20 October 2025). The repository provides access to all image data, and relevant documentation used in this research.Open asset ↗https://github.com/hwzhanng/DLCPD-25-Dataset · DLCPD-25lines:141-207Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
In the arid cultivation region of Xinjiang, China, shrinkage disease severely compromises the quality, yield, and market value of jujube. Published research has achieved high accuracy in detecting larger lesions using RGB imaging and hyperspectral imaging (HSI). However, these methods lack sensitivity in detecting early and subtle symptoms of disease. In this study, a multi-source data fusion strategy combining RGB imaging and HSI was proposed for non-destructive and high-precision detection of early-stage jujube shrinkage disease. Firstly, a total of 317 fruits of the 'Junzao' cultivar were collected during multiple stages of natural infection, covering early-stage shrinkage disease detection across different growth stages, including both green and mature red fruits. Secondly, morphological features were extracted from RGB images in multiple dimensions, while a three-stage feature selection strategy combining Principal Component Analysis (PCA), the Successive Projections Algorithm (SPA), and the Genetic Algorithm (GA) was implemented to identify four key wavelengths from HSI. Thirdly, a hybrid convolutional neural network-multilayer perceptron (CNN-MLP) architecture was constructed, with dynamic feature weighting employed to achieve effective multimodal fusion and optimize detection performance. Experimental results demonstrated that compared to the MLP and CNN models, the proposed method achieved approximately 8.0% and 5.4% improvements in accuracy and 38.6% and 32.4% improvements in F1 scores, respectively. It offers a robust and scalable solution for early disease detection and postharvest quality assessment in jujube production.
Why it matches plant phenotyping methodsRGB画像・HSIから果実の病斑形態と分光特徴を抽出し、マルチモーダル深層学習で植物病害状態を検出する手法の開発・性能評価が中心であるため。
abstracta multi-source data fusion strategy combining RGB imaging and HSI was proposed for non-destructive and high-precision detection of early-stage jujube shrinkage disease.
Reproduction assets foundThe paper's Data Availability Statement points to a public GitHub repository containing the study's dataset (RGB images and hyperspectral data of jujube fruits). No separate analysis code availability is stated, but the deposited dataset is a paper-specific, publicly actionable asset.Dataset · publicThe data from this study are publicly available. The dataset is available at https://github.com/2484733079/Early-detection-of-Jujube-Shrinkage-Disease-by-Multi-source-Data-on-Multi-task-Deep-Network.git (accessed on 13 October 2025).Open asset ↗2484733079/Early-detection-of-Jujube-Shrinkage-Disease-by-Multi-source-Data-on-Multi-task-Deep-Networklines:365-367Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
In the context of global agricultural modernization, the early and accurate detection of sugarcane leaf diseases is critical for ensuring stable sugar production. However, existing deep learning models still face significant challenges in complex field environments, such as blurred lesion edges, scale variation, and limited generalization capability. To address these issues, this study constructs an efficient recognition model for sugarcane disease detection, named CaneFocus-Net, specifically designed for precise identification of sugarcane leaf diseases. Based on a single-stage detection architecture, the model introduces a lightweight cross-stage feature fusion module (CP) to optimize feature transfer efficiency. It also designs a module combining a channel-spatial adaptive calibration mechanism with multi-scale pooling aggregation to enhance the backbone network's ability to extract multi-scale lesion features. Furthermore, by expanding the high-resolution shallow feature layer to enhance sensitivity toward small-sized targets and adopting a phased adaptive nonlinear optimization strategy, detection and localization accuracy along with convergence efficiency have been further improved. Test results on public datasets demonstrate that this method significantly enhances recognition performance for fuzzy lesions and multi-scale targets while maintaining high inference speed. Compared to the baseline model, precision, recall, and mean average precision (mAP50 and mAP50-95) improved by 1.9%, 4.6%, 1.5%, and 1.4%, respectively, demonstrating strong generalization capabilities and practical application potential. This provides reliable technical support for intelligent monitoring of sugarcane diseases in the field.
Why it matches plant phenotyping methodsサトウキビ葉の病斑を画像から検出・局在化する深層学習モデルを開発しており、植物の病害状態を直接推定する手法が研究の中心である。
abstractthis study constructs an efficient recognition model for sugarcane disease detection, named CaneFocus-Net
Reproduction assets foundThe paper's sugarcane leaf disease dataset (9100 images, five classes) is publicly available on Roboflow Universe, with an explicit Data Availability Statement providing the exact URL. No author analysis code or trained model checkpoints are stated as available.Dataset · publicData Availability Statement: The data presented in this study are openly available at Roboflow.
The website is: https://universe.roboflow.com/sugarcaneleaf/sugarcaneleaf-w0mto/dataset/2 (ac-
cessed on 23 July 2025).Open asset ↗Roboflow · sugarcaneleaf-w0mtopdf-page:26 lines:1-59Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
This research presents a fully automated two-step method for segmenting rice seedlings and assessing their health by integrating spectral, morphological, and textural features. Driven by the global need for increased food production, the proposed method enhances monitoring and control in agricultural processes. Seedling locations are first identified by the excess green minus excess red index, which enables automated point-prompt inputs for the segment anything model to achieve precise segmentation and masking. Morphological features are extracted from the generated masks, while spectral and textural features are derived from corresponding red-green-blue imagery. Health assessment is conducted through anomaly detection using a one-class support vector machine, which identifies seedlings exhibiting abnormal morphology or spectral signatures suggesting stress. The proposed method is validated by visual inspection and Silhouette score, confirming effective separation of anomalies. For segmentation, the proposed method achieved mean dice scores ranging from 72.6 to 94.7. For plant health assessment, silhouette scores ranged from 0.31 to 0.44 across both datasets and various growth stages. Applied across three consecutive rice growth stages, the framework facilitates temporal monitoring of seedling health. The findings highlight the potential of advanced segmentation and anomaly detection techniques to support timely interventions, such as pruning or replacing unhealthy seedlings, to optimize crop yield.
Why it matches plant phenotyping methodsイネ幼苗の画像セグメンテーションと形態・スペクトル・テクスチャ特徴に基づく健康状態推定を中心とする手法開発・検証研究であり、植物表現型の取得と異常判定が中核です。
abstractThis research presents a fully automated two-step method for segmenting rice seedlings and assessing their health by integrating spectral, morphological, and textural features.
Reproduction assets foundThe paper uses two publicly available rice seedling image datasets as its phenotyping inputs: the Taiwan UAV Rice Seedling Dataset (GitHub) and the Heilongjiang seedling image dataset (Science Data Bank). No author analysis code, models, or checkpoints are reported as publicly available.Dataset · publicThe first dataset used in this study was obtained from Rice Seedling Dataset repository, originally published in “A UAV Open Dataset of Rice Paddies for Deep Learning Practice” by Yang et al., 2021 [ 7 ]. The dataset is publicly available in a GitHub repository and can be accessed at the following link: https://github.com/aipal-nchu/RiceSeedlingDatasetOpen asset ↗aipal-nchu/RiceSeedlingDatasetlines:130-332Dataset · publicThe second dataset was obtained from repository of “Image Dataset of Wheat, Corn, and Rice Seedlings in Heilongjiang Province”, originally published in 2022 by Qin Jia Le and Guo Leifeng [ 46 ]. The dataset is publicly available in the Science Data Bank repository and can be accessed at the following link: https://www.scidb.cn/en/detail?dataSetId=a511f28b23444235b5378953c76c47c6#p4Open asset ↗lines:130-332Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Computer vision is of wide interest to perform the phenotyping of horticultural crops such as apple trees at high throughput. In orchards specially constructed for variety testing or breeding programs, computer vision tools should be able to extract phenotypical information form each tree separately. We focus on segmenting individual apple trees as the main task in this context. Segmenting individual apple trees in dense orchard rows is challenging because of the complexity of outdoor illumination and intertwined branches. Traditional methods rely on supervised learning, which requires a large amount of annotated data. In this study, we explore an alternative approach using prompt engineering with the Segment Anything Model and its variants in a zero-shot setting. Specifically, we first detect the trunk and then position a prompt (five points in a diamond shape) located above the detected trunk to feed to the Segment Anything Model. We evaluate our method on the apple REFPOP, a new large-scale European apple tree dataset and on another publicly available dataset. On these datasets, our trunk detector, which utilizes a trained YOLOv11 model, achieves a good detection rate of 97% based on the prompt located above the detected trunk, achieving a Dice score of 70% without training on the REFPOP dataset and 84% without training on the publicly available dataset.We demonstrate that our method equals or even outperforms purely supervised segmentation approaches or non-prompted foundation models. These results underscore the potential of foundational models guided by well-designed prompts as scalable and annotation-efficient solutions for plant segmentation in complex agricultural environments.
Why it matches plant phenotyping methodsリンゴ樹を個体別に画像分割し、育種・品種試験向けの表現型情報抽出を可能にする手法を開発・評価しており、植物フェノタイピング手法が中心である。
abstractComputer vision is of wide interest to perform the phenotyping of horticultural crops such as apple trees at high throughput.
Reproduction assets foundThe paper's apple REFPOP image dataset (RGB orchard images with manual tree/trunk annotations used for the phenotyping segmentation task) is publicly deposited on Zenodo via DOI 10.57745/DZBMAM, stated in both the Supplementary Materials and Data Availability Statement. Other URLs (Ultralytics, FrontVeg, arXiv) are forDataset · publicon.
Grouding approach
Approach linking text as a prompt or description to localize
objects or regions in an image.
Latent embedding
Low-dimensional vector representation at the end of a neural
network that captures the key features of input data.
Supplementary Materials
The following supporting information can be downloaded at: https://doi.org/10.57745/DZBMAM , https://www.napari-hub.org/plugins/frontveg (accessed on 10 July 2025).
Author Contributions
H.M.: Conceptualization, Methodology, Software, Investigation, Data Curation, Writing—Original Draft, Writing—Review and Editing. D.R.: Conceptualization, Writing—Review and Editing, Supervision, Administration. P.R., J.L. and H.D.: SOpen asset ↗10.57745/DZBMAMlines:536-601Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
Chlorophyll levels are a key indicator of plant nitrogen status, which plays a critical role in optimizing agricultural yields. This study evaluated the performance of three low-cost multi-spectral sensors, AS7262, AS7263, and AS7265x, for non-destructive chlorophyll measurement. Measurements were taken from a diverse set of five leaf types, including smooth, uniform leaves (banana and mango), textured leaves (jasmine and sugarcane), and narrow leaves (rice). Partial least squares regression models were used to fit sensor spectra to chlorophyll levels, using nested cross-validation to ensure robust model evaluation. Sensor performance was assessed using R2 and mean absolute error (MAE) scores. The AS7265x demonstrated the best performance on smooth, uniform leaves with validation R2 scores of 0.96-0.95. Its performance decreased for the other leaves, with R2 scores of 0.75-0.85. The AS7262 and AS7263 sensors, while slightly less accurate, achieved reasonable R2 scores ranging from 0.93 to 0.86 for smooth leaves, and from 0.85 to 0.73 for the other leaves. All sensors, particularly the AS7265x, show potential for non-destructive chlorophyll measurement in agricultural applications. Their low cost and reasonable accuracy make them suitable for agricultural applications such as monitoring plant nitrogen levels.
Why it matches plant phenotyping methods低コストマルチスペクトルセンサーによる葉のクロロフィル測定法を評価・比較し、交差検証で性能を検証しているため、植物フェノタイピング手法が中心です。
abstractThis study evaluated the performance of three low-cost multi-spectral sensors, AS7262, AS7263, and AS7265x, for non-destructive chlorophyll measurement.
Reproduction assets foundThe authors publicly release raw sensor data, analysis scripts, firmware, and GUI in the GitHub repository KyleLopin/asm_chloro_test, plus supplementary information including extracted chlorophyll reference measurements (S2) at the MDPI supplement URL.Code · publicRaw data, scripts to generate the data and figures used in the manuscript, programs to run the sensors, and GUI used to collect the data are available at https://github.com/KyleLopin/asm_chloro_test (accessed on 25 March 2025).Open asset ↗KyleLopin/asm_chloro_test · KyleLopin/asm_chloro_testlines:187-200Code · publicThe microcontroller code to operate the sensor and a GUI for data collection are available at https://github.com/KyleLopin/asm_chloro_test/tree/master/source (accessed on 25 March 2025).Open asset ↗KyleLopin/asm_chloro_test · KyleLopin/asm_chloro_testlines:155-167Supplement · publicThe following supporting information can be downloaded at: https://www.mdpi.com/article/10.3390/s25072198/s1 . Supplementary Information S1: Device Electrical Characterization. Supplementary Information S2: Extracted Chlorophyll Reference Measurements.Open asset ↗lines:176-186Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
In agricultural production, lettuce growth, yield, and quality are impacted by nutrient deficiencies caused by both environmental and human factors. Traditional nutrient detection methods face challenges such as long processing times, potential sample damage, and low automation, limiting their effectiveness in diagnosing and managing crop nutrition. To address these issues, this study developed a lettuce nutrient deficiency detection system using multi-dimensional image analysis and Field-Programmable Gate Arrays (FPGA). The system first applied a dynamic window histogram median filtering algorithm to denoise captured lettuce images. An adaptive algorithm integrating global and local contrast enhancement was then used to improve image detail and contrast. Additionally, a multi-dimensional image analysis algorithm combining threshold segmentation, improved Canny edge detection, and gradient-guided adaptive threshold segmentation enabled precise segmentation of healthy and nutrient-deficient tissues. The system quantitatively assessed nutrient deficiency by analyzing the proportion of nutrient-deficient tissue in the images. Experimental results showed that the system achieved an average precision of 0.944, a recall rate of 0.943, and an F1 score of 0.943 across different lettuce growth stages, demonstrating significant improvements in automation, accuracy, and detection efficiency while minimizing sample interference. This provides a reliable method for the rapid diagnosis of nutrient deficiencies in lettuce.
Why it matches plant phenotyping methodsレタスの栄養欠乏組織を画像から分割・定量するシステムの開発が中心であり、植物状態の画像ベース表現型計測に該当する。
abstractthis study developed a lettuce nutrient deficiency detection system using multi-dimensional image analysis and Field-Programmable Gate Arrays (FPGA).
Reproduction assets foundThe paper's Data Availability Statement explicitly states that the original data, implementation code, and sample data are openly available on the authors' GitHub (https://github.com/lvss88), which matches an allowed URL. This qualifies as a paper-specific public asset covering the lettuce nutrient-deficiency image-d分析Code · publicData Availability Statement: The original data, including implementation code and sample data, pre-
sented in the study are openly available at https://github.com/lvss88 (accessed on 23 January 2025).Open asset ↗lvss88pdf-page:24 lines:1-59Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
This study proposes an advanced plant disease classification framework leveraging the Attention Score-Based Multi-Vision Transformer (Multi-ViT) model. The framework introduces a novel attention mechanism to dynamically prioritize relevant features from multiple leaf images, overcoming the limitations of single-leaf-based diagnoses. Building on the Vision Transformer (ViT) architecture, the Multi-ViT model aggregates diverse feature representations by combining outputs from multiple ViTs, each capturing unique visual patterns. This approach allows for a holistic analysis of spatially distributed symptoms, crucial for accurately diagnosing diseases in trees. Extensive experiments conducted on apple, grape, and tomato leaf disease datasets demonstrate the model's superior performance, achieving over 99% accuracy and significantly improving F 1 scores compared to traditional methods such as ResNet, VGG, and MobileNet. These findings underscore the effectiveness of the proposed model for precise and reliable plant disease classification.
Why it matches plant phenotyping methods植物葉の画像から病徴・病害状態を分類する新規Vision Transformer手法を開発し、複数データセットと既存モデルで性能比較しているため、植物フェノタイピング手法が中心です。
abstractThis study proposes an advanced plant disease classification framework leveraging the Attention Score-Based Multi-Vision Transformer (Multi-ViT) model.
Reproduction assets foundThe paper's plant disease classification experiments use a publicly available Kaggle leaf image dataset, explicitly named in the Data Availability Statement. No author code or model checkpoints are disclosed.Dataset · publicThe data that support the findings of this study are available in the
“New Plant Diseases Dataset” at Kaggle, accessible through https://www.kaggle.com/datasets/Open asset ↗New Plant Diseases Datasetpdf-page:13 lines:1-58Code / dataset availability confirmedEurope PMC · checked 7 Sept 2026
Automating pruning tasks entails overcoming several challenges, encompassing not only robotic manipulation but also environment perception and detection. To achieve efficient pruning, robotic systems must accurately identify the correct cutting points. A possible method to define these points is to choose the cutting location based on the number of nodes present on the targeted cane. For this purpose, in grapevine pruning, it is required to correctly identify the nodes present on the primary canes of the grapevines. In this paper, a novel method of node detection in grapevines is proposed with four distinct state-of-the-art versions of the YOLO detection model: YOLOv7, YOLOv8, YOLOv9 and YOLOv10. These models were trained on a public dataset with images containing artificial backgrounds and afterwards validated on different cultivars of grapevines from two distinct Portuguese viticulture regions with cluttered backgrounds. This allowed us to evaluate the robustness of the algorithms on the detection of nodes in diverse environments, compare the performance of the YOLO models used, as well as create a publicly available dataset of grapevines obtained in Portuguese vineyards for node detection. Overall, all used models were capable of achieving correct node detection in images of grapevines from the three distinct datasets. Considering the trade-off between accuracy and inference speed, the YOLOv7 model demonstrated to be the most robust in detecting nodes in 2D images of grapevines, achieving F1-Score values between 70% and 86.5% with inference times of around 89 ms for an input size of 1280 × 1280 px. Considering these results, this work contributes with an efficient approach for real-time node detection for further implementation on an autonomous robotic pruning system.
Why it matches plant phenotyping methodsブドウの節という明示的な植物器官形質をYOLO画像解析で検出する手法を開発・比較検証し、異なる品種・環境で評価しているため、フェノタイピング手法が中心である。
abstractIn this paper, a novel method of node detection in grapevines is proposed with four distinct state-of-the-art versions of the YOLO detection model: YOLOv7, YOLOv8, YOLOv9 and YOLOv10.
Reproduction assets foundThe paper's authors created and openly released a paper-specific grapevine node-detection image dataset (Dão and Douro vineyard images) on Zenodo, cited in the Data Availability Statement.Dataset · publicThe data presented in this study are openly available in the digital repository Zenodo: Douro & Dão Grapevines Dataset for Node Detection— https://doi.org/10.5281/zenodo.10991688 .Open asset ↗Zenodo · 10.5281/zenodo.10991688lines:552-565Code / dataset availability confirmedEurope PMC · checked 7 Sept 2026
Accurate crop disease classification is crucial for ensuring food security and enhancing agricultural productivity. However, the existing crop disease classification algorithms primarily focus on a single image modality and typically require a large number of samples. Our research counters these issues by using pre-trained Vision-Language Models (VLMs), which enhance the multimodal synergy for better crop disease classification than the traditional unimodal approaches. Firstly, we apply the multimodal model Qwen-VL to generate meticulous textual descriptions for representative disease images selected through clustering from the training set, which will serve as prompt text for generating classifier weights. Compared to solely using the language model for prompt text generation, this approach better captures and conveys fine-grained and image-specific information, thereby enhancing the prompt quality. Secondly, we integrate cross-attention and SE (Squeeze-and-Excitation) Attention into the training-free mode VLCD(Vision-Language model for Crop Disease classification) and the training-required mode VLCD-T (VLCD-Training), respectively, for prompt text processing, enhancing the classifier weights by emphasizing the key text features. The experimental outcomes conclusively prove our method's heightened classification effectiveness in few-shot crop disease scenarios, tackling the data limitations and intricate disease recognition issues. It offers a pragmatic tool for agricultural pathology and reinforces the smart farming surveillance infrastructure.
Why it matches plant phenotyping methods植物病害画像から病気状態を推定する分類手法の開発が中心であり、VLM、プロンプト生成、注意機構を組み込んだ具体的な解析ワークフローを提案・評価している。
abstractOur research counters these issues by using pre-trained Vision-Language Models (VLMs), which enhance the multimodal synergy for better crop disease classification than the traditional unimodal approaches.
Reproduction assets foundThe paper's Data Availability Statement provides a public Google Drive link to the authors' combined plant leaf disease image dataset used for their few-shot crop disease classification experiments. No code or model checkpoints are explicitly deposited.Dataset · publicData Availability Statement: The data utilized in this study are composed of several publicly
available datasets, which have been combined to form a new dataset. The combined dataset is
available at the following link: https://drive.google.com/drive/data/Plant_leave_diseases_datasetOpen asset ↗pdf-page:20 lines:1-57Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
The widespread use of IoT devices has led to the generation of a huge amount of data and driven the need for analytical solutions in many areas of human activities, such as the field of smart agriculture. Continuous monitoring of crop growth stages enables timely interventions, such as control of weeds and plant diseases, as well as pest control, ensuring optimal development. Decision-making systems in smart agriculture involve image analysis with the potential to increase productivity, efficiency and sustainability. By applying Convolutional Neural Networks (CNNs), state recognition and classification can be performed based on images from specific locations. Thus, we have developed a solution for early problem detection and resource management optimization. The main concept of the proposed solution relies on a direct connection between Cloud and Edge devices, which is achieved through Fog computing. The goal of our work is creation of a deep learning model for image classification that can be optimized and adapted for implementation on devices with limited hardware resources at the level of Fog computing. This could increase the importance of image processing in the reduction of agricultural operating costs and manual labor. As a result of the off-load data processing at Edge and Fog devices, the system responsiveness can be improved, the costs associated with data transmission and storage can be reduced, and the overall system reliability and security can be increased. The proposed solution can choose classification algorithms to find a trade-off between size and accuracy of the model optimized for devices with limited hardware resources. After testing our model for tomato disease classification compiled for execution on FPGA, it was found that the decrease in test accuracy is as small as 0.83% (from 96.29% to 95.46%).
Why it matches plant phenotyping methodsトマト病害を画像から分類する深層学習モデルを開発し、Fog/FPGA向けに最適化・精度検証しており、植物の病害状態推定が中心的な方法貢献である。
abstractThe goal of our work is creation of a deep learning model for image classification that can be optimized and adapted for implementation on devices with limited hardware resources at the level of Fog computing.
Reproduction assets foundThe paper's smart-agriculture image classification analysis (tomato disease, pest, and weed classification, with FPGA deployment) is built on three public Kaggle image datasets cited by the authors as the data sources. No authors' analysis code or trained model repository is disclosed; the other URLs are generic tools/Dataset · public7–19 December 2021
SPIE
Bellingham, WA, USA
2022 Volume 12174 194 201
57.
Maurício J.
Domingues I.
Bernardino J.
Comparing Vision Transformers and Convolutional Neural Networks for Image Classification: A Literature Review
Appl. Sci. 2023 13 5521
10.3390/app13095521
58.
Tomato Leaf Disease Image Classification
Available online: https://kaggle.com/code/rohanpatnaik/tomato-leaf-disease-image-classification (accessed on 7 June 2024)
59.
Pest Dataset
Available online: https://www.kaggle.com/datasets/simranvolunesia/pest-dataset (accessed on 7 June 2024)
60.
Weed-Classification
Available online: https://www.kaggle.com/datasets/aminelaatam/weed-classification (accessed on 7 June 2024)
61.
Pang B.
Open asset ↗kagglelines:611-800Dataset · publicers and Convolutional Neural Networks for Image Classification: A Literature Review
Appl. Sci. 2023 13 5521
10.3390/app13095521
58.
Tomato Leaf Disease Image Classification
Available online: https://kaggle.com/code/rohanpatnaik/tomato-leaf-disease-image-classification (accessed on 7 June 2024)
59.
Pest Dataset
Available online: https://www.kaggle.com/datasets/simranvolunesia/pest-dataset (accessed on 7 June 2024)
60.
Weed-Classification
Available online: https://www.kaggle.com/datasets/aminelaatam/weed-classification (accessed on 7 June 2024)
61.
Pang B.
Nijkamp E.
Wu Y.N.
Deep Learning with TensorFlow: A Review
J. Educ. Behav. Stat. 2020 45 227 248
10.3102/1076998619872761
62.
TensorFlow
AvOpen asset ↗kagglelines:611-800Dataset · public8.
Tomato Leaf Disease Image Classification
Available online: https://kaggle.com/code/rohanpatnaik/tomato-leaf-disease-image-classification (accessed on 7 June 2024)
59.
Pest Dataset
Available online: https://www.kaggle.com/datasets/simranvolunesia/pest-dataset (accessed on 7 June 2024)
60.
Weed-Classification
Available online: https://www.kaggle.com/datasets/aminelaatam/weed-classification (accessed on 7 June 2024)
61.
Pang B.
Nijkamp E.
Wu Y.N.
Deep Learning with TensorFlow: A Review
J. Educ. Behav. Stat. 2020 45 227 248
10.3102/1076998619872761
62.
TensorFlow
Available online: https://www.tensorflow.org/ (accessed on 10 June 2024)
63.
TensorFlow Lite | ML for Mobile and Edge Devices
AvailOpen asset ↗kagglelines:611-800Code / dataset availability confirmedEurope PMC · checked 7 Sept 2026
Biological nitrogen fixation (BNF) by symbiotic bacteria plays a vital role in sustainable agriculture. However, current quantification methods are often expensive and impractical. This study explores the potential of Raman spectroscopy, a non-invasive technique, for rapid assessment of BNF activity in soybeans. Raman spectra were obtained from soybean plants grown with and without rhizobia bacteria to identify spectral signatures associated with BNF. δN 15 isotope ratio mass spectrometry (IRMS) was used to determine actual BNF percentages. Partial least squares regression (PLSR) was employed to develop a model for BNF quantification based on Raman spectra. The model explained 80% of the variation in BNF activity. To enhance the model's specificity for BNF detection regardless of nitrogen availability, a subsequent elastic net (Enet) regularisation strategy was implemented. This approach provided insights into key wavenumbers and biochemicals associated with BNF in soybeans.
Why it matches plant phenotyping methodsラマン分光によるダイズの生物的窒素固定活性の非侵襲的定量法を開発し、IRMSで検証しているため、植物生理状態の取得手法が中心である。
abstractThis study explores the potential of Raman spectroscopy, a non-invasive technique, for rapid assessment of BNF activity in soybeans.
Reproduction assets foundThe paper's Data Availability Statement explicitly deposits the original Raman spectra/BNF measurement data on FigShare, a public, paper-specific asset directly reproducing the study's phenotyping measurements.Dataset · publicData Availability Statement: The original data presented in the study are openly available in FigShare
at https://figshare.com/articles/dataset/dx_doi_org_10_6084_m9_figshare_25909780/25909780 (ac-
cessed on 28 May 2024).Open asset ↗FigSharepdf-page:13 lines:1-60Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Chlorophyll fluorescence is a well-established method to estimate chlorophyll content in leaves. A popular fluorescence-based meter, the Opti-Sciences CCM-300 Chlorophyll Content Meter (CCM-300), utilizes the fluorescence ratio F735/F700 and equations derived from experiments using broadleaf species to provide a direct, rapid estimate of chlorophyll content used for many applications. We sought to quantify the performance of the CCM-300 relative to more intensive methods, both across plant functional types and years of use. We linked CCM-300 measurements of broadleaf, conifer, and graminoid samples in 2018 and 2019 to high-performance liquid chromatography (HPLC) and/or spectrophotometric (Spec) analysis of the same leaves. We observed a significant difference between the CCM-300 and HPLC/Spec, but not between HPLC and Spec. In comparison to HPLC, the CCM-300 performed better for broadleaves (r = 0.55, RMSE = 154.76) than conifers (r = 0.52, RMSE = 171.16) and graminoids (r = 0.32, RMSE = 127.12). We observed a slight deterioration in meter performance between years, potentially due to meter calibration. Our results show that the CCM-300 is reliable to demonstrate coarse variations in chlorophyll but may be limited for cross-plant functional type studies and comparisons across years.
Why it matches plant phenotyping methodsCCM-300による葉のクロロフィル含量測定法を、HPLCおよび分光測定と比較して信頼性・校正性能を検証しており、植物表現型取得法が研究の中心である。
abstractWe sought to quantify the performance of the CCM-300 relative to more intensive methods, both across plant functional types and years of use.
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/s24154784/s1 , Figure S1: HPLC measurements from the UW-Madison dataset ( n = 26).Open asset ↗lines:262-279Code / dataset availability confirmedEurope PMC · checked 7 Sept 2026
This paper proposes a workflow to assess the uncertainty of the Normalized Difference Vegetation Index (NDVI), a critical index used in precision agriculture to determine plant health. From a metrological perspective, it is crucial to evaluate the quality of vegetation indices, which are usually obtained by processing multispectral images for measuring vegetation, soil, and environmental parameters. For this reason, it is important to assess how the NVDI measurement is affected by the camera characteristics, light environmental conditions, as well as atmospheric and seasonal/weather conditions. The proposed study investigates the impact of atmospheric conditions on solar irradiation and vegetation reflection captured by a multispectral UAV camera in the red and near-infrared bands and the variation of the nominal wavelengths of the camera in these bands. Specifically, the study examines the influence of atmospheric conditions in three scenarios: dry-clear, humid-hazy, and a combination of both. Furthermore, this investigation takes into account solar irradiance variability and the signal-to-noise ratio (SNR) of the camera. Through Monte Carlo simulations, a sensitivity analysis is carried out against each of the above-mentioned uncertainty sources and their combination. The obtained results demonstrate that the main contributors to the NVDI uncertainty are the atmospheric conditions, the nominal wavelength tolerance of the camera, and the variability of the NDVI values within the considered leaf conditions (dry and fresh).
Why it matches plant phenotyping methodsUAVマルチスペクトル画像から植物状態を示すNDVIを取得する測定ワークフローについて、不確かさ評価・感度分析を中心に扱っており、測定法の技術的検証が主題である。
abstractThis paper proposes a workflow to assess the uncertainty of the Normalized Difference Vegetation Index (NDVI), a critical index used in precision agriculture to determine plant health.
Reproduction assets foundThe paper's Monte Carlo NDVI uncertainty analysis relies on two public datasets: the ORNL Visible and Near-Infrared Leaf Reflectance Spectra (1992–1993), which provide the dry/fresh leaf reflectance inputs underlying the NDVI variability analysis, and the NASA GES DISC TSIS-1 Level 3 Solar Spectral Irradiance 24-Hour VDataset · public43. Richard E. TSIS SIM Level 3 Solar Spectral Irradiance 24-Hour Means V09. Goddard Earth Sciences Data and Information Services Center (GES DISC); Greenbelt, MD, USA: 2022. [(accessed on 23 April 2024)]. Available online: https://disc.gsfc.nasa.gov/datasets/TSIS_SSI_L3_24HR_12/summary .Open asset ↗GES DISC · TSIS SIM Level 3 Solar Spectral Irradiance 24-Hour Means V09lines:687-687Code / 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 confirmedEurope PMC · checked 15 Sept 2026
The primary objective of this study is to develop an advanced, automated system for the early detection and classification of leaf diseases in potato plants, which are among the most cultivated vegetable crops worldwide. These diseases, notably early and late blight caused by Alternaria solani and Phytophthora infestans , significantly impact the quantity and quality of global potato production. We hypothesize that the integration of Vision Transformer (ViT) and ResNet-50 architectures in a new model, named EfficientRMT-Net, can effectively and accurately identify various potato leaf diseases. This approach aims to overcome the limitations of traditional methods, which are often labor-intensive, time-consuming, and prone to inaccuracies due to the unpredictability of disease presentation. EfficientRMT-Net leverages the CNN model for distinct feature extraction and employs depth-wise convolution (DWC) to reduce computational demands. A stage block structure is also incorporated to improve scalability and sensitive area detection, enhancing transferability across different datasets. The classification tasks are performed using a global average pooling layer and a fully connected layer. The model was trained, validated, and tested on custom datasets specifically curated for potato leaf disease detection. EfficientRMT-Net's performance was compared with other deep learning and transfer learning techniques to establish its efficacy. Preliminary results show that EfficientRMT-Net achieves an accuracy of 97.65% on a general image dataset and 99.12% on a specialized Potato leaf image dataset, outperforming existing methods. The model demonstrates a high level of proficiency in correctly classifying and identifying potato leaf diseases, even in cases of distorted samples. The EfficientRMT-Net model provides an efficient and accurate solution for classifying potato plant leaf diseases, potentially enabling farmers to enhance crop yield while optimizing resource utilization. This study confirms our hypothesis, showcasing the effectiveness of combining ViT and ResNet-50 architectures in addressing complex agricultural challenges.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から分類する深層学習手法を開発・検証しており、植物病害表現型の取得・推定が研究の中心である。
abstractdevelop an advanced, automated system for the early detection and classification of leaf diseases in potato plants
Reproduction assets foundThe paper uses the public PlantVillage leaf image dataset (hosted on Mendeley Data) to train and evaluate EfficientRMT-Net; no author code or trained model is released.Dataset · publichave read and agreed to the published version of the manuscript.
Institutional Review Board Statement
Not applicable.
Informed Consent Statement
Not applicable.
Data Availability Statement
A standard online dataset, PlantVillage [ 32 ], is utilized in this paper to evaluate the EfficientRMT-Net model. It can be downloaded from https://data.mendeley.com/datasets/tywbtsjrjv/1 (accessed on 12 July 2023).
Conflicts of Interest
The authors declare no conflict of interest.
Funding Statement
This work was supported and funded by the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University (IMSIU) (grant number IMSIU-RP23063).
Footnotes
Disclaimer/Publisher’s Note: The statementsOpen asset ↗tywbtsjrjv/1lines:683-710Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
The occurrence of tomato diseases has substantially reduced agricultural output and financial losses. The timely detection of diseases is crucial to effectively manage and mitigate the impact of episodes. Early illness detection can improve output, reduce chemical use, and boost a nation's economy. A complete system for plant disease detection using EfficientNetV2B2 and deep learning (DL) is presented in this paper. This research aims to develop a precise and effective automated system for identifying several illnesses that impact tomato plants. This will be achieved by analyzing tomato leaf photos. A dataset of high-resolution photographs of healthy and diseased tomato leaves was created to achieve this goal. The EfficientNetV2B2 model is the foundation of the deep learning system and excels at picture categorization. Transfer learning (TF) trains the model on a tomato leaf disease dataset using EfficientNetV2B2's pre-existing weights and a 256-layer dense layer. Tomato leaf diseases can be identified using the EfficientNetV2B2 model and a dense layer of 256 nodes. An ideal loss function and algorithm train and tune the model. Next, the concept is deployed in smartphones and online apps. The user can accurately diagnose tomato leaf diseases with this application. Utilizing an automated system facilitates the rapid identification of diseases, assisting in making informed decisions on disease management and promoting sustainable tomato cultivation practices. The 5-fold cross-validation method achieved 99.02% average weighted training accuracy, 99.22% average weighted validation accuracy, and 98.96% average weighted test accuracy. The split method achieved 99.93% training accuracy and 100% validation accuracy. Using the DL approach, tomato leaf disease identification achieves nearly 100% accuracy on a test dataset.
Why it matches plant phenotyping methodsトマト葉の画像から病害状態を推定する深層学習・スマートフォンシステムの開発と検証が研究の中心であり、植物病害フェノタイピング手法に該当する。
abstractA complete system for plant disease detection using EfficientNetV2B2 and deep learning (DL) is presented in this paper.
Reproduction assets foundThe authors publicly deposited their main tomato leaf image dataset and smartphone application (.apk) on Zenodo, and deployed a live web application for tomato leaf disease detection on Streamlit. Both are paper-specific, public, and actionable. The Kaggle and Mendeley datasets are third-party source datasets cited as输Dataset · publicmatoleaf (accessed on 30 June 2023). This research also used the plant village dataset for comparison and collected only tomato leaves. The dataset was collected from https://data.mendeley.com/datasets/tywbtsjrjv/1 (accessed on 30 June 2023). The main dataset and smartphone application (.apk file) of this study are available at https://zenodo.org/record/8311631 (accessed on 2 September 2023).
Conflicts of Interest
The authors declare that they have no conflict of interest.
Funding Statement
The researchers would like to acknowledge the deanship of Scientific Research, Taif University, for funding this project.
Footnotes
Disclaimer/Publisher’s Note: The statements, opinions and data coOpen asset ↗zenodo · 8311631lines:464-502Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Defect segmentation of apples is an important task in the agriculture industry for quality control and food safety. In this paper, we propose a deep learning approach for the automated segmentation of apple defects using convolutional neural networks (CNNs) based on a U-shaped architecture with skip-connections only within the noise reduction block. An ad-hoc data synthesis technique has been designed to increase the number of samples and at the same time to reduce neural network overfitting. We evaluate our model on a dataset of multi-spectral apple images with pixel-wise annotations for several types of defects. In this paper, we show that our proposal outperforms in terms of segmentation accuracy general-purpose deep learning architectures commonly used for segmentation tasks. From the application point of view, we improve the previous methods for apple defect segmentation. A measure of the computational cost shows that our proposal can be employed in real-time (about 100 frame-per-second on GPU) and in quasi-real-time (about 7/8 frame-per-second on CPU) visual-based apple inspection. To further improve the applicability of the method, we investigate the potential of using only RGB images instead of multi-spectral images as input images. The results prove that the accuracy in this case is almost comparable with the multi-spectral case.
Why it matches plant phenotyping methodsリンゴ果実の欠陥を画像から画素単位で抽出する深層学習手法を開発・評価しており、植物器官の状態（欠陥）取得が中心的な方法論的貢献である。
abstractwe propose a deep learning approach for the automated segmentation of apple defects using convolutional neural networks (CNNs)
Reproduction assets foundThe paper's authors publicly release the analysis code for their apple defect segmentation experiments via a GitHub repository, explicitly stated in the text. The apple image dataset itself is cited prior work (Kleynen et al.) and no separate dataset deposit by these authors is stated.Code · publicwe investigate the feasibility of using RGB images exclusively as input data instead of multi-spectral images. Encouragingly, the results show that the accuracy achieved in this scenario is nearly comparable to the multi-spectral approach. The experiments can be reproduced using the code made available at the following address: https://github.com/cimice15/Quasi_real-time_apple_defect_segmentation (accessed on 8 September 2023).
The paper is organized as follows: Section 2 presents related works, Section 3 presents the database used in our experiments and the method we propose. Section 4 presents evaluation metrics and experimental setups. Finally Section 5 discusses results of the proposed mOpen asset ↗cimice15/Quasi_real-time_apple_defect_segmentationlines:40-49Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
The Segment Anything Model (SAM) is a versatile image segmentation model that enables zero-shot segmentation of various objects in any image using prompts, including bounding boxes, points, texts, and more. However, studies have shown that the SAM performs poorly in agricultural tasks like crop disease segmentation and pest segmentation. To address this issue, the agricultural SAM adapter (ASA) is proposed, which incorporates agricultural domain expertise into the segmentation model through a simple but effective adapter technique. By leveraging the distinctive characteristics of agricultural image segmentation and suitable user prompts, the model enables zero-shot segmentation, providing a new approach for zero-sample image segmentation in the agricultural domain. Comprehensive experiments are conducted to assess the efficacy of the ASA compared to the default SAM. The results show that the proposed model achieves significant improvements on all 12 agricultural segmentation tasks. Notably, the average Dice score improved by 41.48% on two coffee-leaf-disease segmentation tasks.
Why it matches plant phenotyping methods農業画像から作物病害を分割・推定するモデルアダプターを開発し、複数タスクで性能検証しているため、植物病害状態の画像ベース表現型計測が中心である。
abstractthe agricultural SAM adapter (ASA) is proposed, which incorporates agricultural domain expertise into the segmentation model through a simple but effective adapter technique.
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。Dataset · publicThese data can be
downloaded from https://doi.org/10.17632/yy2k5y8mxg.1Open asset ↗10.17632/yy2k5y8mxg.1pdf-page:15 lines:1-59Dataset · publicdownloaded from https://doi.org/10.17632/yy2k5y8mxg.1 and https://data.mendeley.com/datasetsOpen asset ↗pdf-page:15 lines:1-59Code / dataset availability confirmedEurope PMC · OpenAlex · checked 13 Sept 2026
Tree height is a crucial structural parameter in forest inventory as it provides a basis for evaluating stock volume and growth status. In recent years, close-range photogrammetry based on smartphone has attracted attention from researchers due to its low cost and non-destructive characteristics. However, such methods have specific requirements for camera angle and distance during shooting, and pre-shooting operations such as camera calibration and placement of calibration boards are necessary, which could be inconvenient to operate in complex natural environments. We propose a tree height measurement method based on three-dimensional (3D) reconstruction. Firstly, an absolute depth map was obtained by combining ARCore and MidasNet. Secondly, Attention-UNet was improved by adding depth maps as network input to obtain tree mask. Thirdly, the color image and depth map were fused to obtain the 3D point cloud of the scene. Then, the tree point cloud was extracted using the tree mask. Finally, the tree height was measured by extracting the axis-aligned bounding box of the tree point cloud. We built the method into an Android app, demonstrating its efficiency and automation. Our approach achieves an average relative error of 3.20% within a shooting distance range of 2-17 m, meeting the accuracy requirements of forest survey.
Why it matches plant phenotyping methodsスマートフォン画像・深度情報と3D再構成を用いて樹高という植物構造形質を自動測定する手法を開発し、誤差評価とAndroidアプリ化まで行っているため、植物フェノタイピング手法が中心である。
abstractWe propose a tree height measurement method based on three-dimensional (3D) reconstruction.
Reproduction assets foundThe paper's Data Availability Statement explicitly provides two paper-specific public assets: the source code of the TreeHeight prototype app on GitHub and the authors' annotated tree image dataset (300 annotated images augmented to 1000 pairs of color images, relative depth maps, and tree masks) on Google Drive. Both,Code · publicThe source code of the prototype app is publicly available on GitHub at https://github.com/LisaShen0509/Tree_Height_Measurement (accessed on 27 July 2023).Open asset ↗LisaShen0509/Tree_Height_Measurementlines:432-615Dataset · publicTree image dataset is available at https://drive.google.com/file/d/1kG6LWMOAiA2KvGF_suZ5cG_4C-udUV0m/view?usp=sharing (accessed on 27 July 2023).Open asset ↗lines:432-615Code / 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 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 14 Sept 2026
A framework combining two powerful tools of hyperspectral imaging and deep learning for the processing and classification of hyperspectral images (HSI) of rice seeds is presented. A seed-based approach that trains a three-dimensional convolutional neural network (3D-CNN) using the full seed spectral hypercube for classifying the seed images from high day and high night temperatures, both including a control group, is developed. A pixel-based seed classification approach is implemented using a deep neural network (DNN). The seed and pixel-based deep learning architectures are validated and tested using hyperspectral images from five different rice seed treatments with six different high temperature exposure durations during day, night, and both day and night. A stand-alone application with Graphical User Interfaces (GUI) for calibrating, preprocessing, and classification of hyperspectral rice seed images is presented. The software application can be used for training two deep learning architectures for the classification of any type of hyperspectral seed images. The average overall classification accuracy of 91.33% and 89.50% is obtained for seed-based classification using 3D-CNN for five different treatments at each exposure duration and six different high temperature exposure durations for each treatment, respectively. The DNN gives an average accuracy of 94.83% and 91% for five different treatments at each exposure duration and six different high temperature exposure durations for each treatment, respectively. The accuracies obtained are higher than those presented in the literature for hyperspectral rice seed image classification. The HSI analysis presented here is on the Kitaake cultivar, which can be extended to study the temperature tolerance of other rice cultivars.
Why it matches plant phenotyping methodsハイパースペクトル画像からイネ種子の温度処理状態を分類する深層学習手法を開発・検証し、校正・前処理・分類用GUIも提供しており、種子表現型の取得・抽出方法が中心である。
abstractA framework combining two powerful tools of hyperspectral imaging and deep learning for the processing and classification of hyperspectral images (HSI) of rice seeds is presented.
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 for the DL framework for hyperspectral seed image calibration, preprocessing, segmentation, and classification are available at: https://gitfront.io/r/vido6/vC64GLsxCDZx/classificationRice/ , accessed on 23 March 2023.Open asset ↗classificationRicelines:95-200Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Tomato leaf diseases can incur significant financial damage by having adverse impacts on crops and, consequently, they are a major concern for tomato growers all over the world. The diseases may come in a variety of forms, caused by environmental stress and various pathogens. An automated approach to detect leaf disease from images would assist farmers to take effective control measures quickly and affordably. Therefore, the proposed study aims to analyze the effects of transformer-based approaches that aggregate different scales of attention on variants of features for the classification of tomato leaf diseases from image data. Four state-of-the-art transformer-based models, namely, External Attention Transformer (EANet), Multi-Axis Vision Transformer (MaxViT), Compact Convolutional Transformers (CCT), and Pyramid Vision Transformer (PVT), are trained and tested on a multiclass tomato disease dataset. The result analysis showcases that MaxViT comfortably outperforms the other three transformer models with 97% overall accuracy, as opposed to the 89% accuracy achieved by EANet, 91% by CCT, and 93% by PVT. MaxViT also achieves a smoother learning curve compared to the other transformers. Afterwards, we further verified the legitimacy of the results on another relatively smaller dataset. Overall, the exhaustive empirical analysis presented in the paper proves that the MaxViT architecture is the most effective transformer model to classify tomato leaf disease, providing the availability of powerful hardware to incorporate the model.
Why it matches plant phenotyping methodsトマト葉画像から病害状態を分類する画像解析手法を複数のTransformerで比較・検証しており、植物の病害表現型の取得が研究の中心である。
abstractanalyze the effects of transformer-based approaches that aggregate different scales of attention on variants of features for the classification of tomato leaf diseases from image data
Reproduction assets foundThe paper used two public plant-image datasets for tomato leaf disease classification, both explicitly linked in the Data Availability Statement: a Kaggle tomato disease dataset (20,000 images, 11 classes) and a Mendeley/PlantVillage-derived dataset (4,972 images, 6 classes). No author analysis code or trained model isDataset · publicsupervision, A.C. and Y.J.J.; funding acquisition, A.C. and Y.J.J. All authors 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
This dataset was collected from Kaggle, this can be found at https://www.kaggle.com/datasets/cookiefinder/tomato-disease-multiple-sources (accessed on 2 January 2023). This dataset was collected from Mendeley, this can be found at https://data.mendeley.com/datasets/ngdgg79rzb/1 (accessed on 17 March 2023).
Conflicts of Interest
The authors declare no conflict of interest.
Funding Statement
This research was funded in part by theOpen asset ↗Kaggle · cookiefinder/tomato-disease-multiple-sourceslines:335-374Dataset · publicd Statement
Not applicable.
Informed Consent Statement
Not applicable.
Data Availability Statement
This dataset was collected from Kaggle, this can be found at https://www.kaggle.com/datasets/cookiefinder/tomato-disease-multiple-sources (accessed on 2 January 2023). This dataset was collected from Mendeley, this can be found at https://data.mendeley.com/datasets/ngdgg79rzb/1 (accessed on 17 March 2023).
Conflicts of Interest
The authors declare no conflict of interest.
Funding Statement
This research was funded in part by the National Research Foundation of Korea (grant no. NRF-2020R1A2C1008753).
Footnotes
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publicOpen asset ↗Mendeley · ngdgg79rzblines:335-374Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Fusarium head blight (FHB) is a disease of small grains caused by the fungus Fusarium graminearum . In this study, we explored the use of hyperspectral imaging (HSI) to evaluate the damage caused by FHB in wheat kernels. We evaluated the use of HSI for disease classification and correlated the damage with the mycotoxin deoxynivalenol (DON) content. Computational analyses were carried out to determine which machine learning methods had the best accuracy to classify different levels of damage in wheat kernel samples. The classes of samples were based on the DON content obtained from Gas Chromatography-Mass Spectrometry (GC-MS). We found that G-Boost, an ensemble method, showed the best performance with 97% accuracy in classifying wheat kernels into different severity levels. Mask R-CNN, an instance segmentation method, was used to segment the wheat kernels from HSI data. The regions of interest (ROIs) obtained from Mask R-CNN achieved a high mAP of 0.97. The results from Mask R-CNN, when combined with the classification method, were able to correlate HSI data with the DON concentration in small grains with an R 2 of 0.75. Our results show the potential of HSI to quantify DON in wheat kernels in commercial settings such as elevators or mills.
Why it matches plant phenotyping methods小麦粒のFHB損傷・重症度をハイパースペクトル画像と機械学習で分類・定量する手法が研究の中心であり、Mask R-CNNによる抽出と精度評価も含むため、植物病害表現型の方法研究として適格。
abstractwe explored the use of hyperspectral imaging (HSI) to evaluate the damage caused by FHB in wheat kernels.
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 Statement: The codes and the data are available at Li lab GitHub repository at
https://github.com/LiLabAtVT/WheatHyperSpectral (accessed on 1 March 2023).Open asset ↗LiLabAtVT/WheatHyperSpectralpdf-page:11 lines:1-60Code / dataset availability confirmedEurope PMC · checked 7 Sept 2026
The rapidly changing climate affects an extensive spectrum of human-centered environments. The food industry is one of the affected industries due to rapid climate change. Rice is a staple food and an important cultural key point for Japanese people. As Japan is a country in which natural disasters continuously occur, using aged seeds for cultivation has become a regular practice. It is a well-known truth that seed quality and age highly impact germination rate and successful cultivation. However, a considerable research gap exists in the identification of seeds according to age. Hence, this study aims to implement a machine-learning model to identify Japanese rice seeds according to their age. Since agewise datasets are unavailable in the literature, this research implements a novel rice seed dataset with six rice varieties and three age variations. The rice seed dataset was created using a combination of RGB images. Image features were extracted using six feature descriptors. The proposed algorithm used in this study is called Cascaded-ANFIS. A novel structure for this algorithm is proposed in this work, combining several gradient-boosting algorithms such as XGBoost, CatBoost, and LightGBM. The classification was conducted in two steps. First, the seed variety was identified. Then, the age was predicted. As a result, seven classification models were implemented. The performance of the proposed algorithm was evaluated against 13 state-of-the-art algorithms. Overall, the proposed algorithm has a higher accuracy, precision, recall, and F1-score than the others. For the classification of variety, the proposed algorithm scored 0.7697, 0.7949, 0.7707, and 0.7862, respectively. The results of this study confirm that the proposed algorithm can be employed in the successful age classification of seeds.
Why it matches plant phenotyping methodsRGB画像からコメ種子の品種・年齢を抽出する機械学習手法を開発し、新規データセットを構築して複数手法と性能比較しているため、種子状態の画像ベース表現型解析が中心である。
abstractthis study aims to implement a machine-learning model to identify Japanese rice seeds according to their age
Reproduction assets foundThe paper's authors constructed a novel rice seed image dataset (six varieties, three harvest ages) and explicitly state it is publicly available on Kaggle under the author's account, matching an allowed URL. No code or model release is stated.Dataset · publicgle data repository accessed on 15 January 2023 (https://www.kaggle.com/datasets/namalrathnayake1Open asset ↗Kagglepdf-page:16 lines:1-60Code / dataset availability confirmedEurope PMC · OpenAlex · checked 15 Sept 2026
Smart farming (SF) applications rely on robust and accurate computer vision systems. An important computer vision task in agriculture is semantic segmentation, which aims to classify each pixel of an image and can be used for selective weed removal. State-of-the-art implementations use convolutional neural networks (CNN) that are trained on large image datasets. In agriculture, publicly available RGB image datasets are scarce and often lack detailed ground-truth information. In contrast to agriculture, other research areas feature RGB-D datasets that combine color (RGB) with additional distance (D) information. Such results show that including distance as an additional modality can improve model performance further. Therefore, we introduce WE3DS as the first RGB-D image dataset for multi-class plant species semantic segmentation in crop farming. It contains 2568 RGB-D images (color image and distance map) and corresponding hand-annotated ground-truth masks. Images were taken under natural light conditions using an RGB-D sensor consisting of two RGB cameras in a stereo setup. Further, we provide a benchmark for RGB-D semantic segmentation on the WE3DS dataset and compare it with a solely RGB-based model. Our trained models achieve up to 70.7% mean Intersection over Union (mIoU) for discriminating between soil, seven crop species, and ten weed species. Finally, our work confirms the finding that additional distance information improves segmentation quality.
Why it matches plant phenotyping methods植物種の画素単位セグメンテーション用RGB-Dデータセットとベンチマークを構築し、植物識別・分離という表現型取得ワークフローを中心的に評価しているため。
abstractwe introduce WE3DS as the first RGB-D image dataset for multi-class plant species semantic segmentation in crop farming.
Reproduction assets foundThe paper's WE3DS RGB-D image dataset (2568 annotated images) and the authors' modified ESANet analysis code are publicly deposited on Zenodo (DOI 10.5281/zenodo.7457983), as stated in the experiments section. The MDPI supplementary file contains only tables (species list, depth accuracy, confusion matrices), not the影像Dataset · public024 × 512
20.6
27.0
37.7 †
34.2
11.5
RGB
1024 × 512
52.4
22.2
39.2 †
38.4
11.5
RGB-D
1024 × 512
59.1
19.2
85.8
55.3
18.5
D
1280 × 960
48.5
11.3
154.1
37.0
27.1
RGB
1280 × 960
70.1
11.0
156.1
46.8
27.1
RGB-D
1280 × 960
70.7
8.6
240.3
66.6
43.4
Information on the dataset and modified code of the ESANet can be found on our website https://doi.org/10.5281/zenodo.7457983 (accessed on 18 December 2022).
4.4. ResultsOpen asset ↗Zenodo · 10.5281/zenodo.7457983lines:69-146Code / dataset availability confirmedEurope PMC · checked 7 Sept 2026
In this paper, we present a direct drive brush-shaped tool developed for the use of robotic vine suckering. Direct drive design philosophy allows for precise and high bandwidth control of the torque exerted by the brush. Besides limiting the torque exerted onto the plant, this kind of design philosophy allows the brush to be used as a torque sensor. High bandwidth torque feedback from the tool is used to enable a position controlled robot arm to perform the suckering task without knowing the exact position and shape of the trunk of the vine. An experiment was conducted to investigate the dependency of the applied torque on the overlap between the brush and the obstacle. The results of the experiment indicate a quadratic relationship between torque and overlap. This quadratic function is estimated and used for compliant trunk shape following. A trunk shape following experiment demonstrates the utility of the presented tool to be used as a sensor for compliant robot arm control. The shape of the trunk is estimated by tracking the motion of the robot arm during the experiment.
Why it matches plant phenotyping methodsブドウ樹の幹形状をトルクセンサ付きロボット工具で推定する手法を開発・実験検証しており、植物形状の取得が中心的である。
abstractDirect drive design philosophy allows for precise and high bandwidth control of the torque exerted by the brush. Besides limiting the torque exerted onto the plant, this kind of design philosophy allows the brush to be used as a torque sensor.
Reproduction assets foundThe paper's authors explicitly state that their implementation of the prioritized task-space control algorithm (used for the compliant trunk shape following experiments) is publicly available on GitHub. No phenotype/trait datasets or image/sensor data deposits are mentioned; the video link is supplementary footage of aCode · publicThis implementation of the prioritized task-space control
algorithm is available on GitHub (https://github.com/ivatavuk/ptsc_eigen, accessed on
29 November 2022).Open asset ↗github.com/ivatavuk/ptsc_eigen · ivatavuk/ptsc_eigenpdf-page:10 lines:1-29Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Crop pests and diseases have been the main cause of reduced food production and have seriously affected food security. Therefore, it is very urgent and important to solve the pest problem efficiently and accurately. While traditional neural networks require complete processing of data when processing data, by compressed sensing, only one part of the data needs to be processed, which greatly reduces the amount of data processed by the network. In this paper, a combination of compressed perception and neural networks is used to classify and identify pest images in the compressed domain. A network model for compressed sampling and classification, CSBNet, is proposed to enable compression in neural networks instead of the sensing matrix in conventional compressed sensing (CS). Unlike traditional compressed perception, no reduction is performed to reconstruct the image, but recognition is performed directly in the compressed region, while an attention mechanism is added to enhance feature strength. The experiments in this paper were conducted on different datasets with various sampling rates separately, and our model was substantially less accurate than the other models in terms of trainable parameters, reaching a maximum accuracy of 96.32%, which is higher than the 93.01%, 83.58%, and 87.75% of the other models at a sampling rate of 0.7.
Why it matches plant phenotyping methods圧縮センシングとニューラルネットワークを用いた葉画像の病害・害虫分類手法を開発しており、植物の病害状態を画像から推定する技術が研究の中心である。
abstractIn this paper, a combination of compressed perception and neural networks is used to classify and identify pest images in the compressed domain.
Reproduction assets foundThe paper uses publicly available PlantVillage maize leaf images (4142 images, 4 classes) for its classification experiments and provides an authors' public GitHub repository with the source code implementing the proposed CSBNet/CS-Block method. Both are paper-specific, public, and actionable.Code · publicInformed Consent Statement
Not applicable.
Data Availability Statement
Publicly available datasets were analyzed in this study. These data can be found here: ( https://plantvillage.psu.edu/ , accessed on 12 April 2016). The source code implementing the proposed method in this paper is available in the url: ( https://github.com/zt0528/CS-Block-model , accessed on 19 November 2022).
Conflicts of Interest
The authors declare no conflict of interest.
Funding Statement
This research was funded by the National Natural Science Foundation of China (Grant Nos.61861021). Jiangxi Natural Science Foundation (Grant Nos.20224BAB202038). National Natural Science Foundation of China(GranOpen asset ↗CS-Block-modellines:390-416Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Plant diseases are a major cause of reduction in agricultural output, which leads to severe economic losses and unstable food supply. The citrus plant is an economically important fruit crop grown and produced worldwide. However, citrus plants are easily affected by various factors, such as climate change, pests, and diseases, resulting in reduced yield and quality. Advances in computer vision in recent years have been widely used for plant disease detection and classification, providing opportunities for early disease detection, and resulting in improvements in agriculture. Particularly, the early and accurate detection of citrus diseases, which are vulnerable to pests, is very important to prevent the spread of pests and reduce crop damage. Research on citrus pest disease is ongoing, but it is difficult to apply research results to cultivation owing to a lack of datasets for research and limited types of pests. In this study, we built a dataset by self-collecting a total of 20,000 citrus pest images, including fruits and leaves, from actual cultivation sites. The constructed dataset was trained, verified, and tested using a model that had undergone five transfer learning steps. All models used in the experiment had an average accuracy of 97% or more and an average f1 score of 96% or more. We built a web application server using the EfficientNet-b0 model, which exhibited the best performance among the five learning models. The built web application tested citrus pest disease using image samples collected from websites other than the self-collected image samples and prepared data, and both samples correctly classified the disease. The citrus pest automatic diagnosis web system using the model proposed in this study plays a useful auxiliary role in recognizing and classifying citrus diseases. This can, in turn, help improve the overall quality of citrus fruits.
Why it matches plant phenotyping methods柑橘の葉・果実画像から病害状態を分類するデータセット、深層学習モデル、診断Webシステムを構築・検証しており、植物状態の取得・推定手法が中心である。
abstractIn this study, we built a dataset by self-collecting a total of 20,000 citrus pest images, including fruits and leaves, from actual cultivation sites.
Reproduction assets foundThe authors explicitly state they published their self-collected citrus pest image dataset (20,000 images, six classes) free of charge at their public GitHub repository, which is a paper-specific, publicly actionable asset. No code availability statement was found for the analysis scripts or trained models.Dataset · publicrus images that are either infected or non-infected by pests in Jeju Island, South Korea, in 2021. The constructed dataset provides a total of 20,000 high-quality images with a resolution of 1920 × 1090. Currently, Citrus Open Datasets are either low resolution or paid. We published the datasets used in the study free of charge https://github.com/LeeSaeBom/citrus (accessed on 19 August 2022). A detailed description of the dataset is provided in Section 5 .
We use EfficientNet and ViT models, which are the latest algorithms in this area, including VGGNet, ResNet, and DenseNet models, which are commonly used for the classification and detection of plant pests and diseases [ 21 , 22 , 23 ]Open asset ↗LeeSaeBom/citruslines:28-38Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Rust is a common disease in wheat that significantly impacts its growth and yield. Stem rust and leaf rust of wheat are difficult to distinguish, and manual detection is time-consuming. With the aim of improving this situation, this study proposes a method for identifying wheat rust based on ensemble learning (WR-EL). The WR-EL method extracts and integrates multiple convolutional neural network (CNN) models, namely VGG, ResNet 101, ResNet 152, DenseNet 169, and DenseNet 201, based on bagging, snapshot ensembling, and the stochastic gradient descent with warm restarts (SGDR) algorithm. The identification results of the WR-EL method were compared to those of five individual CNN models. The results show that the identification accuracy increases by 32%, 19%, 15%, 11%, and 8%. Additionally, we proposed the SGDR-S algorithm, which improved the f1 scores of healthy wheat, stem rust wheat and leaf rust wheat by 2%, 3% and 2% compared to the SGDR algorithm, respectively. This method can more accurately identify wheat rust disease and can be implemented as a timely prevention and control measure, which can not only prevent economic losses caused by the disease, but also improve the yield and quality of wheat.
Why it matches plant phenotyping methods小麦葉・茎さび病という植物の病徴状態を画像から分類する手法を開発・比較しており、病害フェノタイピング手法が中心である。
abstractthis study proposes a method for identifying wheat rust based on ensemble learning (WR-EL).
Reproduction assets foundThe paper's wheat rust classification uses the public ICLR Workshop/CGIAR crop disease image dataset (healthy, stem rust, leaf rust wheat images from Ethiopia and Tanzania), which the authors explicitly state is downloadable from the Zindi competition page. No author code or trained models are stated as available (DataDataset · publict.
Figure 1
Workflow of this study.
Figure 2 is based on the dataset used in this research, which includes the three categories of healthy wheat, leaf rust wheat, and stem rust wheat, with image data from farm sites in Ethiopia and Tanzania, and from public images on Google Maps. The dataset can be obtain in the following link: https://zindi.africa/competitions/iclr-workshop-challenge-1-cgiar-computer-vision-for-crop-disease/data (accessed on 16 July 2022). Leaf rust occurs mainly on the leaf area, but it can also arise on the stem, and stem rust occurs mostly on the stem, but it may also appear on the leaf area. Therefore, it is important to judge not only the location of the disease but alOpen asset ↗Zindi · iclr-workshop-challenge-1-cgiar-computer-vision-for-crop-diseaselines:29-38Code / dataset availability confirmedEurope PMC · checked 8 Sept 2026
Strawberries are sensitive fruits that are afflicted by various pests and diseases. Therefore, there is an intense use of agrochemicals and pesticides during production. Due to their sensitivity, temperatures or humidity at extreme levels can cause various damages to the plantation and to the quality of the fruit. To mitigate the problem, this study developed an edge technology capable of handling the collection, analysis, prediction, and detection of heterogeneous data in strawberry farming. The proposed IoT platform integrates various monitoring services into one common platform for digital farming. The system connects and manages Internet of Things (IoT) devices to analyze environmental and crop information. In addition, a computer vision model using Yolo v5 architecture searches for seven of the most common strawberry diseases in real time. This model supports efficient disease detection with 92% accuracy. Moreover, the system supports LoRa communication for transmitting data between the nodes at long distances. In addition, the IoT platform integrates machine learning capabilities for capturing outliers in collected data, ensuring reliable information for the user. All these technologies are unified to mitigate the disease problem and the environmental damage on the plantation. The proposed system is verified through implementation and tested on a strawberry farm, where the capabilities were analyzed and assessed.
Why it matches plant phenotyping methodsイチゴ病害を画像からリアルタイム検出するコンピュータビジョン手法をIoTプラットフォームの中心機能として開発・実装し、農場で評価しているため、植物病害状態のフェノタイピング手法に該当する。
abstracta computer vision model using Yolo v5 architecture searches for seven of the most common strawberry diseases in real time.
Reproduction assets foundThe paper provides an authors' public GitHub repository for the proposed IoT/edge phenotyping platform (sensor collection, YOLO v5 disease detection, Isolation Forest ML) and points to a public Kaggle strawberry disease detection dataset used for the computer vision model.Dataset · publicPublicly available datasets were analyzed in this study. This data can be found here: https://www.kaggle.com/datasets/usmanafzaal/strawberry-disease-detection-dataset (accessed on 14 June 2022).Open asset ↗https://www.kaggle.com/datasets/usmanafzaal/strawberry-disease-detection-datasetlines:394-409Code / dataset availability confirmedEurope PMC · OpenAlex · checked 13 Sept 2026
Growth indices can quantify crop productivity and establish optimal environmental, nutritional, and irrigation control strategies. A convolutional neural network (CNN)-based model is presented for estimating various growth indices (i.e., fresh weight, dry weight, height, leaf area, and diameter) of four varieties of greenhouse lettuce using red, green, blue, and depth (RGB-D) data obtained using a stereo camera. Data from an online autonomous greenhouse challenge (Wageningen University, June 2021) were employed in this study. The data were collected using an Intel RealSense D415 camera. The developed model has a two-stage CNN architecture based on ResNet50V2 layers. The developed model provided coefficients of determination from 0.88 to 0.95, with normalized root mean square errors of 6.09%, 6.30%, 7.65%, 7.92%, and 5.62% for fresh weight, dry weight, height, diameter, and leaf area, respectively, on unknown lettuce images. Using red, green, blue (RGB) and depth data employed in the CNN improved the determination accuracy for all five lettuce growth indices due to the ability of the stereo camera to extract height information on lettuce. The average time for processing each lettuce image using the developed CNN model run on a Jetson SUB mini-PC with a Jetson Xavier NX was 0.83 s, indicating the potential for the model in fast real-time sensing of lettuce growth indices.
Why it matches plant phenotyping methodsRGB-D画像とCNNを用いてレタスの複数の生育形質を推定する手法を開発・検証しており、表現型取得が研究の中心である。
abstractA convolutional neural network (CNN)-based model is presented for estimating various growth indices (i.e., fresh weight, dry weight, height, leaf area, and diameter) of four varieties of greenhouse lettuce using red, green, blue, and depth (RGB-D) data obtained using a stereo camera.
Reproduction assets foundThe paper's phenotyping inputs (388 RGB-D lettuce image pairs with destructive growth-index measurements from the Third Autonomous Greenhouse Challenge) are a third-party public dataset explicitly stated to be publicly available at 4TU.ResearchData, with the DOI 10.4121/15023088.v1 cited in the text and figure captionsDataset · publicThe dataset is available in online: https://doi.org/10.4121/15023088.v1 [ 30 ].Open asset ↗10.4121/15023088.v1lines:518-697Code / 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
Agricultural industry is facing a serious threat from plant diseases that cause production and economic losses. Early information on disease development can improve disease control using suitable management strategies. This study sought to detect downy mildew ( Peronospora ) on grapevine ( Vitis vinifera ) leaves at early stages of development using thermal imaging technology and to determine the best time during the day for image acquisition. In controlled experiments, 1587 thermal images of grapevines grown in a greenhouse were acquired around midday, before inoculation, 1, 2, 4, 5, 6, and 7 days after an inoculation. In addition, images of healthy and infected leaves were acquired at seven different times during the day between 7:00 a.m. and 4:30 p.m. Leaves were segmented using the active contour algorithm. Twelve features were derived from the leaf mask and from meteorological measurements. Stepwise logistic regression revealed five significant features used in five classification models. Performance was evaluated using K-folds cross-validation. The support vector machine model produced the best classification accuracy of 81.6%, F1 score of 77.5% and area under the curve (AUC) of 0.874. Acquiring images in the morning between 10:40 a.m. and 11:30 a.m. resulted in 80.7% accuracy, 80.5% F1 score, and 0.895 AUC.
Why it matches plant phenotyping methods熱画像と画像解析・分類モデルを用いてブドウ葉の病害状態を早期推定する手法を開発・評価しており、植物病害表現型の取得が中心です。
abstractThis study sought to detect downy mildew ( Peronospora ) on grapevine ( Vitis vinifera ) leaves at early stages of development using thermal imaging technology
Reproduction assets foundThe paper's Data Availability Statement explicitly deposits the authors' phenotyping datasets (thermal-image-derived leaf temperature features, meteorological measurements, and disease severity labels) as Excel files in two public GitHub repositories, both listed in allowed_urls. These directly reproduce the paper's 1,Dataset · publicThe datasets generated and analyzed during the current study are available in GitHub: Data sets (Excel): https://github.com/BarCohenBGU/database.git (29 September 2021). ‘All data new’—the classification dataset included 1403 records.Open asset ↗BarCohenBGU/databaselines:635-637Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Seed vigor is an important index to evaluate seed quality in plant species. How to evaluate seed vigor quickly and accurately has always been a serious problem in the seed research field. As a new physical testing method, multispectral technology has many advantages such as high sensitivity and accuracy, nondestructive and rapid application having advantageous prospects in seed quality evaluation. In this study, the morphological and spectral information of 19 wavelengths (365, 405, 430, 450, 470, 490, 515, 540, 570, 590, 630, 645, 660, 690, 780, 850, 880, 940, 970 nm) of alfalfa seeds with different level of maturity and different harvest periods (years), representing different vigor levels and age of seed, were collected by using multispectral imaging. Five multivariate analysis methods including principal component analysis (PCA), linear discriminant analysis (LDA), support vector machine (SVM), random forest (RF) and normalized canonical discriminant analysis (nCDA) were used to distinguish and predict their vigor. The results showed that LDA model had the best effect, with an average accuracy of 92.9% for seed samples of different maturity and 97.8% for seed samples of different harvest years, and the average sensitivity, specificity and precision of LDA model could reach more than 90%. The average accuracy of nCDA in identifying dead seeds with no vigor reached 93.3%. In identifying the seeds with high vigor and predicting the germination percentage of alfalfa seeds, it could reach 95.7%. In summary, the use of Multispectral Imaging and multivariate analysis in this experiment can accurately evaluate and predict the seed vigor, seed viability and seed germination percentages of alfalfa, providing important technical methods and ideas for rapid non-destructive testing of seed quality.
Why it matches plant phenotyping methodsマルチスペクトル画像と多変量解析により、アルファルファ種子の活力・生存性・発芽率を非破壊推定する手法が研究の中心であるため。
abstractAs a new physical testing method, multispectral technology has many advantages such as high sensitivity and accuracy, nondestructive and rapid application having advantageous prospects in seed quality evaluation.
Reproduction assets foundThe authors provide a public Google Drive supplement containing the paper's own multispectral imaging data: mean reflectance at 19 wavelengths for all seeds (Table S1), morphological feature data for all seeds (Table S2), and multispectral images of the alfalfa seed samples (Figures S1–S6). These directly reproduce theDataset · publicThe following are available online at https://drive.google.com/file/d/13CXchEm81qnbIZCXLqdvupDPib7BS8FM/view?usp=sharing , Table S1: Mean reflectance of 19 wavelengths in all seeds, Table S2: Data of morphological feature in all seeds. Figure S1: Multispectral image of seeds harvested in 2004. Figure S2: Multispectral image of seeds harvested in 2008. Figure S3: Multispectral image of seeds harvested in 2019. Figure S4: Multispectral image of seeOpen asset ↗lines:79-239Code / dataset availability confirmedEurope PMC · OpenAlex · checked 8 Sept 2026
This work focuses on the problem of non-contact measurement for vegetables in agricultural automation. The application of computer vision in assisted agricultural production significantly improves work efficiency due to the rapid development of information technology and artificial intelligence. Based on object detection and stereo cameras, this paper proposes an intelligent method for vegetable recognition and size estimation. The method obtains colorful images and depth maps with a binocular stereo camera. Then detection networks classify four kinds of common vegetables (cucumber, eggplant, tomato and pepper) and locate six points for each object. Finally, the size of vegetables is calculated using the pixel position and depth of keypoints. Experimental results show that the proposed method can classify four kinds of common vegetables within 60 cm and accurately estimate their diameter and length. The work provides an innovative idea for solving the vegetable's non-contact measurement problems and can promote the application of computer vision in agricultural automation.
Why it matches plant phenotyping methods野菜の長さ・直径という植物器官形質を、ステレオカメラ、深度画像、キーポイント検出で非接触推定する手法が研究の中心であるため。
abstractThis work focuses on the problem of non-contact measurement for vegetables in agricultural automation.
Reproduction assets foundThe authors publicly released both the vegetable keypoint dataset (1600 COCO-format images with ROI boxes and six keypoints) and the implementation code for their size estimation method on GitHub. Labelme is a generic third-party annotation tool and is excluded.Code · publicThe implementation code of our size estimation method can be accessed on https://github.com/BourneZ130/VegetableDetection , accessed on 15 February 2022.Open asset ↗BourneZ130/VegetableDetectionlines:76-141Code / dataset availability confirmedEurope PMC · checked 8 Sept 2026
The scarcity of water for agricultural use is a serious problem that has increased due to intense droughts, poor management, and deficiencies in the distribution and application of the resource. The monitoring of crops through satellite image processing and the application of machine learning algorithms are technological strategies with which developed countries tend to implement better public policies regarding the efficient use of water. The purpose of this research was to determine the main indicators and characteristics that allow us to discriminate the phenological stages of maize crops ( Zea mays L.) in Sentinel 2 satellite images through supervised classification models. The training data were obtained by monitoring cultivated plots during an agricultural cycle. Indicators and characteristics were extracted from 41 Sentinel 2 images acquired during the monitoring dates. With these images, indicators of texture, vegetation, and colour were calculated to train three supervised classifiers: linear discriminant (LD), support vector machine (SVM), and k-nearest neighbours (kNN) models. It was found that 45 of the 86 characteristics extracted contributed to maximizing the accuracy by stage of development and the overall accuracy of the trained classification models. The characteristics of the Moran's I local indicator of spatial association (LISA) improved the accuracy of the classifiers when applied to the L*a*b* colour model and to the near-infrared (NIR) band. The local binary pattern (LBP) increased the accuracy of the classification when applied to the red, green, blue (RGB) and NIR bands. The colour ratios, leaf area index (LAI), RGB colour model, L*a*b* colour space, LISA, and LBP extracted the most important intrinsic characteristics of maize crops with regard to classifying the phenological stages of the maize cultivation. The quadratic SVM model was the best classifier of maize crop phenology, with an overall accuracy of 82.3%.
Why it matches plant phenotyping methods衛星画像からトウモロコシの生育段階（植物状態）を抽出・分類する画像解析および機械学習手法が研究の中心であり、特徴量比較と分類精度評価も実施している。
abstractThe purpose of this research was to determine the main indicators and characteristics that allow us to discriminate the phenological stages of maize crops ( Zea mays L.) in Sentinel 2 satellite images through supervised classification models.
Reproduction assets foundThe paper's supplement (Table S1) publicly lists the 41 Sentinel-2 satellite images analyzed for maize phenology classification, hosted on MDPI. No author analysis code or trained models are stated as publicly available; MATLAB scripts are described but no deposit/URL is given.Dataset · publicThe following are available online at https://www.mdpi.com/article/10.3390/s22010094/s1 , Table S1: The sentinel 2 satellite images analyzed in this research work.Open asset ↗MDPI · 10.3390/s22010094/s1lines:453-471Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
High-throughput, nondestructive, and precise measurement of seeds is critical for the evaluation of seed quality and the improvement of agricultural productions. To this end, we have developed a novel end-to-end platform named HyperSeed to provide hyperspectral information for seeds. As a test case, the hyperspectral images of rice seeds are obtained from a high-performance line-scan image spectrograph covering the spectral range from 600 to 1700 nm. The acquired images are processed via a graphical user interface (GUI)-based open-source software for background removal and seed segmentation. The output is generated in the form of a hyperspectral cube and curve for each seed. In our experiment, we presented the visual results of seed segmentation on different seed species. Moreover, we conducted a classification of seeds raised in heat stress and control environments using both traditional machine learning models and neural network models. The results show that the proposed 3D convolutional neural network (3D CNN) model has the highest accuracy, which is 97.5% in seed-based classification and 94.21% in pixel-based classification, compared to 80.0% in seed-based classification and 85.67% in seed-based classification from the support vector machine (SVM) model. Moreover, our pipeline enables systematic analysis of spectral curves and identification of wavelengths of biological interest.
Why it matches plant phenotyping methods種子のハイパースペクトル画像取得、セグメンテーション、スペクトル解析を一体化したプラットフォームとソフトウェアを開発しており、植物形質取得法が中心である。
abstractwe have developed a novel end-to-end platform named HyperSeed to provide hyperspectral information for seeds.
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 software and data for testing is accessible in Github: https://github.com/tgaochn/HyperSeed (accessed on 3 December 2021).Open asset ↗tgaochn/HyperSeedlines:168-188Code / dataset availability confirmedEurope PMC · checked 9 Sept 2026
This study tested whether machine learning (ML) methods can effectively separate individual plants from complex 3D canopy laser scans as a prerequisite to analyzing particular plant features. For this, we scanned mung bean and chickpea crops with PlantEye (R) laser scanners. Firstly, we segmented the crop canopies from the background in 3D space using the Region Growing Segmentation algorithm. Then, Convolutional Neural Network (CNN) based ML algorithms were fine-tuned for plant counting. Application of the CNN-based (Convolutional Neural Network) processing architecture was possible only after we reduced the dimensionality of the data to 2D. This allowed for the identification of individual plants and their counting with an accuracy of 93.18% and 92.87% for mung bean and chickpea plants, respectively. These steps were connected to the phenotyping pipeline, which can now replace manual counting operations that are inefficient, costly, and error-prone. The use of CNN in this study was innovatively solved with dimensionality reduction, addition of height information as color, and consequent application of a 2D CNN-based approach. We found there to be a wide gap in the use of ML on 3D information. This gap will have to be addressed, especially for more complex plant feature extractions, which we intend to implement through further research.
Why it matches plant phenotyping methods3Dレーザースキャンから個体植物を分離・計数する画像解析手法を開発し、CNNの精度評価とフェノタイピングパイプラインへの統合を行っており、植物表現型取得が研究の中心である。
abstractThis study tested whether machine learning (ML) methods can effectively separate individual plants from complex 3D canopy laser scans as a prerequisite to analyzing particular plant features.
Reproduction assets foundThe paper's plant detection/counting pipeline source code is explicitly published on the authors' GitHub repository, stated in both the Conclusions and Data Availability Statement. No public phenotype dataset or trained model deposit is stated.Code · publicSource code of the proposed pipeline and plant detection, including the following updates, has been published in the following Github repositoriy https://github.com/serkankartal/Machine_Learning_Based_Plant_Detection_on_3D_Canopy_scansOpen asset ↗https://github.com/serkankartal/Machine_Learning_Based_Plant_Detection_on_3D_Canopy_scanslines:101-111Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Tomato is one of the most essential and consumable crops in the world. Tomatoes differ in quantity depending on how they are fertilized. Leaf disease is the primary factor impacting the amount and quality of crop yield. As a result, it is critical to diagnose and classify these disorders appropriately. Different kinds of diseases influence the production of tomatoes. Earlier identification of these diseases would reduce the disease's effect on tomato plants and enhance good crop yield. Different innovative ways of identifying and classifying certain diseases have been used extensively. The motive of work is to support farmers in identifying early-stage diseases accurately and informing them about these diseases. The Convolutional Neural Network (CNN) is used to effectively define and classify tomato diseases. Google Colab is used to conduct the complete experiment with a dataset containing 3000 images of tomato leaves affected by nine different diseases and a healthy leaf. The complete process is described: Firstly, the input images are preprocessed, and the targeted area of images are segmented from the original images. Secondly, the images are further processed with varying hyper-parameters of the CNN model. Finally, CNN extracts other characteristics from pictures like colors, texture, and edges, etc. The findings demonstrate that the proposed model predictions are 98.49% accurate.
Why it matches plant phenotyping methodsトマト葉の病害状態を画像から分類するCNN手法が研究の中心であり、植物の病徴を直接推定する画像ベース表現型解析に該当する。
titleEarly Detection and Classification of Tomato Leaf Disease Using High-Performance Deep Neural Network.
Reproduction assets foundThe paper's tomato leaf disease classification experiments were performed on a publicly available Kaggle dataset (PlantVillage), explicitly cited by the authors with a public URL. No author analysis code, trained models, or supplementary data deposits are reported; the Data Availability Statement says 'Not applicable.'Dataset · publicence (CCDC); Hefei, China. 22–24 August 2020; pp. 1446–1450.
30. Agarwal M., Gupta S.K., Biswas K.K. Development of Efficient CNN model for Tomato crop disease identification. Sustain. Comput. Inform. Syst. 2020;28:100407–100421. doi: 10.1016/j.suscom.2020.100407.
31. PlantVillege. [(accessed on 3 July 2021)]. Available online: https://www.kaggle.com/emmarex/plantdisease .
32. Kaur P., Gautam V. Research patterns and trends in classification of biotic and abiotic stress in plant leaf. Mater. Today Proc. 2021;45:4377–4382. doi: 10.1016/j.matpr.2020.11.198.
33. Kaur P., Gautam V. Plant Biotic Disease Identification and Classification Based on Leaf Image: A Review; Proceedings of the 3rd InternOpen asset ↗Kaggle · emmarex/plantdiseaselines:257-279Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Monitoring fruit growth is useful when estimating final yields in advance and predicting optimum harvest times. However, observing fruit all day at the farm via RGB images is not an easy task because the light conditions are constantly changing. In this paper, we present CROP (Central Roundish Object Painter). The method involves image segmentation by deep learning, and the architecture of the neural network is a deeper version of U-Net. CROP identifies different types of central roundish fruit in an RGB image in varied light conditions, and creates a corresponding mask. Counting the mask pixels gives the relative two-dimensional size of the fruit, and in this way, time-series images may provide a non-contact means of automatically monitoring fruit growth. Although our measurement unit is different from the traditional one (length), we believe that shape identification potentially provides more information. Interestingly, CROP can have a more general use, working even for some other roundish objects. For this reason, we hope that CROP and our methodology yield big data to promote scientific advancements in horticultural science and other fields.
Why it matches plant phenotyping methodsRGB画像から果実をセグメンテーションし、画素数で果実サイズと成長を時系列推定する手法開発が中心である。
abstractIn this paper, we present CROP (Central Roundish Object Painter). The method involves image segmentation by deep learning, and the architecture of the neural network is a deeper version of U-Net.
Reproduction assets foundThe authors explicitly state that their trained CROP neural network dictionaries and related programs are publicly available on GitHub. The paper's image datasets (Data_Fruit from Pixabay, farm pear images) are described but the annotations/datasets themselves are not deposited at a public URL; the USDA ARS image and CCode · publicthors have read and agreed to the 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
Our trained neural network CROP and the related programs are available on GitHub ( https://github.com/MotohisaFukuda/CROP , accessed on 20 October 2021). Some of the images used for the qualitative analysis in this paper came from the image gallery organized by United States Department of Agriculture, Agricultural Research Service ( https://www.ars.usda.gov/oc/images/image-gallery , accessed on 20 October 2021). Data_Fruit the training dataset inOpen asset ↗MotohisaFukuda/CROPlines:95-151Code / dataset availability confirmedEurope PMC · checked 9 Sept 2026
Decrease in crop yield and degradation in product quality due to plant diseases such as rust and blast in pearl millet is the cause of concern for farmers and the agriculture industry. The stipulation of expert advice for disease identification is also a challenge for the farmers. The traditional techniques adopted for plant disease detection require more human intervention, are unhandy for farmers, and have a high cost of deployment, operation, and maintenance. Therefore, there is a requirement for automating plant disease detection and classification. Deep learning and IoT-based solutions are proposed in the literature for plant disease detection and classification. However, there is a huge scope to develop low-cost systems by integrating these techniques for data collection, feature visualization, and disease detection. This research aims to develop the 'Automatic and Intelligent Data Collector and Classifier' framework by integrating IoT and deep learning. The framework automatically collects the imagery and parametric data from the pearl millet farmland at ICAR, Mysore, India. It automatically sends the collected data to the cloud server and the Raspberry Pi. The 'Custom-Net' model designed as a part of this research is deployed on the cloud server. It collaborates with the Raspberry Pi to precisely predict the blast and rust diseases in pearl millet. Moreover, the Grad-CAM is employed to visualize the features extracted by the 'Custom-Net'. Furthermore, the impact of transfer learning on the 'Custom-Net' and state-of-the-art models viz. Inception ResNet-V2, Inception-V3, ResNet-50, VGG-16, and VGG-19 is shown in this manuscript. Based on the experimental results, and features visualization by Grad-CAM, it is observed that the 'Custom-Net' extracts the relevant features and the transfer learning improves the extraction of relevant features. Additionally, the 'Custom-Net' model reports a classification accuracy of 98.78% that is equivalent to state-of-the-art models viz. Inception ResNet-V2, Inception-V3, ResNet-50, VGG-16, and VGG-19. Although the classification of 'Custom-Net' is comparable to state-of-the-art models, it is effective in reducing the training time by 86.67%. It makes the model more suitable for automating disease detection. This proves that the proposed model is effective in providing a low-cost and handy tool for farmers to improve crop yield and product quality.
Why it matches plant phenotyping methods画像とIoTデータから作物病害を推定する低コストの収集・分類フレームワークを開発し、モデル性能と特徴抽出を評価しており、植物病態の表現型取得が中心である。
abstractTherefore, there is a requirement for automating plant disease detection and classification.
Reproduction assets foundThe authors explicitly state that the pearl millet blast/rust image dataset collected as part of this research is publicly available on Kaggle, making it a paper-specific, publicly actionable phenotype image dataset. No author analysis code or trained model checkpoints are reported as publicly available.Dataset · publicData prepared as a part of this research is available at https://www.kaggle.com/kalpitgupta/blast-and-rust-compressed . The researchers who wish to use the dataset available at the above link must cite this article.Open asset ↗Kaggle · kalpitgupta/blast-and-rust-compressedlines:417-422Code / dataset availability confirmedEurope PMC · checked 9 Sept 2026
Traditional methods to measure spatio-temporal variations in above-ground biomass dynamics (AGBD) predominantly rely on the extraction of several vegetation-index features highly associated with AGBD variations through the phenological crop cycle. This work presents a comprehensive comparison between two different approaches for feature extraction for non-destructive biomass estimation using aerial multispectral imagery. The first method is called GFKuts, an approach that optimally labels the plot canopy based on a Gaussian mixture model, a Montecarlo-based K-means, and a guided image filtering for the extraction of canopy vegetation indices associated with biomass yield. The second method is based on a Graph-Based Data Fusion (GBF) approach that does not depend on calculating vegetation-index image reflectances. Both methods are experimentally tested and compared through rice growth stages: vegetative, reproductive, and ripening. Biomass estimation correlations are calculated and compared against an assembled ground-truth biomass measurements taken by destructive sampling. The proposed GBF-Sm-Bs approach outperformed competing methods by obtaining biomass estimation correlation of 0.995 with R2=0.991 and RMSE=45.358 g. This result increases the precision in the biomass estimation by around 62.43% compared to previous works.
Why it matches plant phenotyping methodsイネの地上部バイオマスという植物形質を、航空マルチスペクトル画像から抽出・推定する特徴抽出手法を開発し、比較検証しているため、フェノタイピング手法が中心です。
abstractThis work presents a comprehensive comparison between two different approaches for feature extraction for non-destructive biomass estimation using aerial multispectral imagery.
Reproduction assets foundThe paper's multispectral UAV imagery and ground-truth biomass measurements are deposited on OSF (via a view-only link, which is nonetheless publicly reachable with the URL), and the crop-monitoring protocol is on protocols.io. No author analysis code repository is stated.Dataset · publicDatasets supporting the experimental results presented in Figure 4 , Figure 5 and Figure 6 are available at the Open Science Framework: https://osf.io/cde6h/?view_only=1c4e5e03b9a34d3b96736ad8ab1b2774 folder Raw Data—MDPI Sensors.Open asset ↗Open Science Frameworklines:197-212Code / dataset availability confirmedEurope PMC · checked 9 Sept 2026
PeachChlorophyll fluorescenceFruitClassificationGrowth / development / phenologyPigment / colour / senescence
Technology for rapid, non-invasive and accurate determination of fruit maturity is increasingly sought after in horticultural industries. This study investigated the ability to predict fruit maturity of yellow peach cultivars using a prototype non-destructive fluorescence spectrometer. Collected spectra were analysed to predict flesh firmness (FF), soluble solids concentration (SSC), index of absorbance difference (I AD ), skin and flesh colour attributes (i.e., a* and H°) and maturity classes (immature, harvest-ready and mature) in four yellow peach cultivars-'August Flame', 'O'Henry', 'Redhaven' and 'September Sun'. The cultivars provided a diverse range of maturity indices. The fluorescence spectrometer consistently predicted I AD and skin colour in all the cultivars under study with high accuracy (Lin's concordance correlation coefficient > 0.85), whereas flesh colour's estimation was always accurate apart from 'Redhaven'. Except for 'September Sun', good prediction of FF and SSC was observed. Fruit maturity classes were reliably predicted with a high likelihood ( F1 -score = 0.85) when samples from the four cultivars were pooled together. Further studies are needed to assess the performance of the fluorescence spectrometer on other fruit crops. Work is underway to develop a handheld version of the fluorescence spectrometer to improve the utility and adoption by fruit growers, packhouses and supply chain managers.
Why it matches plant phenotyping methods蛍光分光計を用いてモモ果実の成熟度や品質関連形質を非破壊推定し、複数品種で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す。
abstractusing a prototype non-destructive fluorescence spectrometer
Reproduction assets foundThe paper reports peach fluorescence-spectra phenotyping and PLS/LDA modelling. The only qualifying paper-specific public asset is the authors' sample analysis code (simulated annealing wavelength band selection with PLS), explicitly stated as freely available as a Jupyter Notebook. No public phenotype dataset, spectraCode · publicSample scripts of the algorithms are freely available as a Project Jupyter Notebook [ 45 ].Open asset ↗lines:45-57Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Wildfires are an increasing problem worldwide, with their number and intensity predicted to rise due to climate change. When fires occur close to vineyards, this can result in grapevine smoke contamination and, subsequently, the development of smoke taint in wine. Currently, there are no in-field detection systems that growers can use to assess whether their grapevines have been contaminated by smoke. This study evaluated the use of near-infrared (NIR) spectroscopy as a chemical fingerprinting tool, coupled with machine learning, to create a rapid, non-destructive in-field detection system for assessing grapevine smoke contamination. Two artificial neural network models were developed using grapevine leaf spectra (Model 1) and grape spectra (Model 2) as inputs, and smoke treatments as targets. Both models displayed high overall accuracies in classifying the spectral readings according to the smoking treatments (Model 1: 98.00%; Model 2: 97.40%). Ultraviolet to visible spectroscopy was also used to assess the physiological performance and senescence of leaves, and the degree of ripening and anthocyanin content of grapes. The results showed that chemical fingerprinting and machine learning might offer a rapid, in-field detection system for grapevine smoke contamination that will enable growers to make timely decisions following a bushfire event, e.g., avoiding harvest of heavily contaminated grapes for winemaking or assisting with a sample collection of grapes for chemical analysis of smoke taint markers.
Why it matches plant phenotyping methodsブドウ葉・果実のNIRスペクトルと機械学習により煙汚染状態を非破壊推定する検出システムを開発しており、植物状態の取得・推定手法が研究の中心である。
abstractThis study evaluated the use of near-infrared (NIR) spectroscopy as a chemical fingerprinting tool, coupled with machine learning, to create a rapid, non-destructive in-field detection system for assessing grapevine smoke contamination.
Reproduction assets foundThe article's supplementary materials link (MDPI) hosts Table S1 with the paper's own smoke-taint chemical measurements (volatile phenol concentrations in grape juice and glycoconjugates in grape homogenate). No public code, model checkpoints, or raw spectral/image datasets are described; the ANN code is only describedSupplement · publicw.arcwinecentre.org.au ), which is funded as part of the ARC’s Industrial Transformation Research Program (Project No. ICI70100008), with support from Wine Australia and industry partners. The authors greatly acknowledge the Digital Agriculture, Food, and Wine Group.
Supplementary Materials
The following are available online at https://www.mdpi.com/1424-8220/20/18/5099/s1 , Table S1: Concentrations of volatile phenols in grape juice (µg/L) and their glycoconjugates in grape homogenate (µg/kg) one hour after smoke treatments.
Click here for additional data file.
Author Contributions
Conceptualization, V.S., and S.F.; data curation, V.S., C.G.V., and S.F.; formal analysis, V.S.; funding acquisOpen asset ↗lines:87-170Code / dataset availability confirmedEurope PMC · checked 9 Sept 2026
Due to the rich vitamin content in citrus fruit, citrus is an important crop around the world. However, the yield of these citrus crops is often reduced due to the damage of various pests and diseases. In order to mitigate these problems, several convolutional neural networks were applied to detect them. It is of note that the performance of these selected models degraded as the size of the target object in the image decreased. To adapt to scale changes, a new feature reuse method named bridge connection was developed. With the help of bridge connections, the accuracy of baseline networks was improved at little additional computation cost. The proposed BridgeNet-19 achieved the highest classification accuracy (95.47%), followed by the pre-trained VGG-19 (95.01%) and VGG-19 with bridge connections (94.73%). The use of bridge connections also strengthens the flexibility of sensors for image acquisition. It is unnecessary to pay more attention to adjusting the distance between a camera and pests and diseases.
Why it matches plant phenotyping methods柑橘の病害を画像から分類するCNN手法の改良と精度比較が中心であり、植物の病害状態を直接推定するフェノタイピング手法に該当する。
abstracta new feature reuse method named bridge connection was developed
Reproduction assets foundThe paper explicitly states that the implementation of the phenotyping/classification models (BridgeNet-19 and benchmark CNNs for citrus pest and disease image classification) is publicly available on the authors' GitHub repository. The image dataset itself is described but no separate public deposit URL is given in a Code · publicImplementation of models is available at https://github.com/xingshulicc/xingshulicc/tree/master/citrus_pest_Open asset ↗github.com/xingshulicc/xingshuliccpdf-page:11 lines:1-65Code / dataset availability confirmedEurope PMC · checked 9 Sept 2026
Rice lodging severely affects harvest yield. Traditional evaluation methods and manual on-site measurement are found to be time-consuming, labor-intensive, and cost-intensive. In this study, a new method for rice lodging assessment based on a deep learning UNet (U-shaped Network) architecture was proposed. The UAV (unmanned aerial vehicle) equipped with a high-resolution digital camera and a three-band multispectral camera synchronously was used to collect lodged and non-lodged rice images at an altitude of 100 m. After splicing and cropping the original images, the datasets with the lodged and non-lodged rice image samples were established by augmenting for building a UNet model. The research results showed that the dice coefficients in RGB (Red, Green and Blue) image and multispectral image test set were 0.9442 and 0.9284, respectively. The rice lodging recognition effect using the RGB images without feature extraction is better than that of multispectral images. The findings of this study are useful for rice lodging investigations by different optical sensors, which can provide an important method for large-area, high-efficiency, and low-cost rice lodging monitoring research.
Why it matches plant phenotyping methodsUAV画像とUNetによってイネの倒伏状態を抽出・評価する手法を開発し、RGBおよびマルチスペクトル画像で性能検証しているため、植物表現型取得が中心である。
abstracta new method for rice lodging assessment based on a deep learning UNet (U-shaped Network) architecture was proposed.
Reproduction assets foundThe paper's UNet training/analysis code for rice lodging segmentation is explicitly stated to be publicly available at the authors' GitHub repository. No public dataset or image deposit is mentioned; the UAV imagery and annotations are not stated as shared.Code · publicThe UNet model training algorithm was implemented with Python 3.6 in Spyder software, and code can be found at the URL “ https://github.com/zhxsking/unet_on_jsj ”.Open asset ↗zhxsking/unet_on_jsjlines:38-45Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Precise sensor-based non-destructive estimation of crop nitrogen (N) status is essential for low-cost, objective optimization of N fertilization, as well as for early estimation of yield potential and N use efficiency. Several studies assessed the performance of spectral vegetation indices (SVI) for winter wheat ( Triticum aestivum L.), often either for conditions of low N status or across a wide range of the target traits N uptake (Nup), N concentration (NC), dry matter biomass (DM), and N nutrition index (NNI). This study aimed at a critical assessment of the estimation ability depending on the level of the target traits. It included seven years' data with nine measurement dates from early stem elongation until flowering in eight N regimes (0-420 kg N ha -1 ) for selected SVIs. Tested across years, a pronounced date-specific clustering was found particularly for DM and NC. While for DM, only the R900_970 gave moderate but saturated relationships (R 2 = 0.47, p 2 = 0.59, p NC ≈ DM. Depending on the number (n = 1-3) and characteristic of cultivars included, the relationships improved when testing within instead of across cultivars, with the relatively lowest cultivar effect on the estimation of DM and the strongest on NC. For assessing the trait estimation under conditions of high-excessive N fertilization, the range of the target traits was divided into two intervals with NNI values 0.8 (interval 2: high N status). Although better estimations were found in interval 1, useful relationships were also obtained in interval 2 from the best indices (DM: R780_740: average R 2 = 0.35, RMSE = 567 kg ha -1 ; NC: REIP: average R 2 = 0.40, RMSE = 0.25%; NNI: REIP: average R 2 = 0.46, RMSE = 0.10; Nup: REIP: average R 2 = 0.48, RMSE = 21 kg N ha -1 ). While in interval 1, all indices performed rather similarly, the three red edge-based indices were clearly better suited for the three N-related traits. The results are promising for applying SVIs also under conditions of high N status, aiming at detecting and avoiding excessive N use. While in canopies of lower N status, the use of simple NIR/VIS indices may be sufficient without losing much precision, the red edge information appears crucial for conditions of higher N status. These findings can be transferred to the configuration and use of simpler multispectral sensors under conditions of contrasting N status in precision farming.
Why it matches plant phenotyping methods冬コムギのスペクトル植生指数によるN状態・バイオマス等の非破壊推定性能を複数年・品種・施肥条件で批判的に評価しており、センサー型表現型計測と検証が中心である。
abstractPrecise sensor-based non-destructive estimation of crop nitrogen (N) status is essential
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 are available online at https://www.mdpi.com/1424-8220/19/17/3712/s1 , Supplementary Table S1: Treatment effects of main plot treatment factors; Supplementary Table S2: Treatment effects of N fertilization; Supplementary Table S3: RMSE and mean-normalized RMSE for regressions across main plots; Supplementary Table S4: Significant ( p < 0.05) coefficients of determination (R²) for the whole data and for data subsets; Supplementary Table S5: Index ranking by data and statistical approachOpen asset ↗lines:241-279Code / dataset availability confirmedEurope PMC · checked 9 Sept 2026
Pests and diseases can cause severe damage to citrus fruits. Farmers used to rely on experienced experts to recognize them, which is a time consuming and costly process. With the popularity of image sensors and the development of computer vision technology, using convolutional neural network (CNN) models to identify pests and diseases has become a recent trend in the field of agriculture. However, many researchers refer to pre-trained models of ImageNet to execute different recognition tasks without considering their own dataset scale, resulting in a waste of computational resources. In this paper, a simple but effective CNN model was developed based on our image dataset. The proposed network was designed from the aspect of parameter efficiency. To achieve this goal, the complexity of cross-channel operation was increased and the frequency of feature reuse was adapted to network depth. Experiment results showed that Weakly DenseNet-16 got the highest classification accuracy with fewer parameters. Because this network is lightweight, it can be used in mobile devices.
Why it matches plant phenotyping methods柑橘の病害・害虫を画像から認識するCNNモデルを開発し、分類精度とパラメータ効率を評価しているため、植物の病害状態を推定する方法が中心である。
titleCitrus Pests and Diseases Recognition Model Using Weakly Dense Connected Convolution Network.
Reproduction assets foundThe paper's citrus pest/disease image dataset is publicly hosted via the authors' mycloud link (Appendix B), and the models/code are publicly available on the authors' GitHub (Appendix C). Both are paper-specific, public, and actionable.Dataset · publicImage dataset is available at: https://files.mycloud.com/home.php?brand=webfiles#23a3c71/Open asset ↗pdf-page:16 lines:1-41Code · publicModels and code are available at: https://github.com/xingshulicc/xingshulicc/tree/master/citrus_Open asset ↗xingshulicc/xingshuliccpdf-page:16 lines:1-41Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Remote sensing (RS) is currently regarded as one of the standard tools used for mapping invasive and expansive plants for scientific purposes and it is increasingly widely used in nature conservation management. The applicability of RS methods is determined by its limitations and requirements. One of the most important limitations is the species percentage cover at which the classification result is correct and useful for nature conservation. The primary objective, carried out in 2017 in three areas of Poland, was to determine the minimum percentage cover from which it is possible to identify a target species by RS methods. A secondary objective of this research, related to the requirements of the method, was to optimize the set of training polygons for a target species in terms of the number of polygons and abundance percentage cover of the target species. Our method has to be easy to use, effective, and applicable, therefore the analysis was carried out using the basic set of rasters-the first 30 channels after the Minimum Noise Fraction (MNF) transformation (the mosaic of hyperspectral data from HySpex sensors with spectral range 0.4-2.5 µm) and commonly used Random Forest algorithm. The analysis used airborne hyperspectral data with a spatial resolution of 1 m to perform classification of one invasive and three expansive plants-two grasses and two large perennials. On-ground training and validation data sets were collected simultaneously with airborne data collection. When testing different classification scenarios, only the set of training polygons for a target species was changed. Classification results were evaluated based on three methods: accuracy measures (Kappa and F1), true-positive pixels in subclasses with different species cover and compatibility with field mapping. The classification results indicate that to classify the target plant species at the accepted level, the training dataset should contain polygons with a species cover ranging from 80-100%. Training performed only using polygons with a species characterized by a variable, but lower, cover (20-70%) and missing samples in the 80-100% range, led to a map which was not acceptable because of a high overestimation of target species. We achieved effective identification of species in areas where the species cover is above 50%, considering that ecosystems are heterogeneous. The results of these studies developed a methodology of field data acquisition and the necessity of synchronization in the acquisition of airborne data, and training and validation of on-ground sampling.
Why it matches plant phenotyping methods侵入・拡大型植物の種被覆率を航空ハイパースペクトル画像から推定する手法について、訓練データ要件、分類精度、現地データとの適合性を検証しており、植物状態の取得方法が研究の中心である。
abstractThe primary objective, carried out in 2017 in three areas of Poland, was to determine the minimum percentage cover from which it is possible to identify a target species by RS methods.
Reproduction assets foundThe article's Supplementary Materials (hosted at the MDPI supplement URL) are stated to include species spectral profiles and study-area materials tied directly to this paper's hyperspectral phenotyping/classification analysis. No author analysis code or raw dataset deposit is explicitly described beyond this; the VCS/Supplement · publichods. This problem results from the lack of the possibility of sufficiently dense background sampling for validations in large area with very heterogeneous ecosystems.
Acknowledgments
The authors thank William Oxford for the helpful comments and English proofreading.
Supplementary Materials
The following are available online at https://www.mdpi.com/1424-8220/19/13/2871/s1 .
Click here for additional data file.
Author Contributions
Conceptualization, A.H.-D. and D.K.; Funding acquisition, D.K.; Investigation, A.Z. and A.H.-D.; Methodology, A.H.-D. and D.K.; Project administration, D.K.; Resources, A.Z., A.H.-D., J.W. and J.N.; Software, A.K.; Supervision, A.K. and D.K.; Validation, D.K.; VisuOpen asset ↗lines:588-606Code / 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 confirmedEurope PMC · checked 15 Sept 2026
Accurate estimation of terrestrial photosynthesis has broad scientific and societal impacts. Measurements of photosynthesis can be used to assess plant health, quantify crop yield, and determine the largest CO₂ flux in the carbon cycle. Long-term and continuous monitoring of vegetation optical properties can provide valuable information about plant physiology. Recent developments of the remote sensing of solar-induced chlorophyll fluorescence (SIF) and vegetation spectroscopy have shown promising results in using this information to quantify plant photosynthetic activities and stresses at the ecosystem scale. However, there are few automated systems that allow for unattended observations over months to years. Here we present FluoSpec 2, an automated system for collecting irradiance and canopy radiance that has been deployed in various ecosystems in the past years. The instrument design, calibration, and tests are recorded in detail. We discuss the future directions of this field spectroscopy system. A network of SIF sensors, FluoNet, is established to measure the diurnal and seasonal variations of SIF in several ecosystems. Automated systems such as FluoSpec 2 can provide unique information on ecosystem functioning and provide important support to the satellite remote sensing of canopy photosynthesis.
Why it matches plant phenotyping methodsFluoSpec 2は植物キャノピーのSIF・光学特性を継続取得する自動センサーシステムであり、装置設計、校正、試験が論文の中心です。植物の光合成・生理状態を測定するフェノタイピング基盤に該当します。
abstractHere we present FluoSpec 2, an automated system for collecting irradiance and canopy radiance
Reproduction assets foundThe paper's acknowledgments explicitly state that source codes used to control the FluoSpec 2 system and for postprocessing are publicly available at two GitHub repositories (persl/SeaBreeze and zhangyaonju/seabreeze_control), both of which are in the allowed URL list. These are authors' public code assets directly支撑该仪Code · publicDong Yan, Xian Wang, and Matt Dannenberg for the help with the installation of FluoSpec 2. We also thank Christian Frankenberg, Ari Kornfeld, Joe Berry, Troy Magney, Lianhong Gu, and Jochen Stutz for providing important and useful feedbacks. Source codes that are used to control the system and for postprocesing can be found in https://github.com/persl/SeaBreeze and https://github.com/zhangyaonju/seabreeze_control .
Author Contributions
X.Y. designed the FluoSpec 2 system. X.Y., H.S., A.S. designed all the tests of FluoSpec 2 and installed three FluoSpec 2. All authors contributed to the improvement of FluoSpec 2 and the writing and editing of the manuscript.
FundingOpen asset ↗persl/SeaBreezelines:139-146Code · publicrg for the help with the installation of FluoSpec 2. We also thank Christian Frankenberg, Ari Kornfeld, Joe Berry, Troy Magney, Lianhong Gu, and Jochen Stutz for providing important and useful feedbacks. Source codes that are used to control the system and for postprocesing can be found in https://github.com/persl/SeaBreeze and https://github.com/zhangyaonju/seabreeze_control .
Author Contributions
X.Y. designed the FluoSpec 2 system. X.Y., H.S., A.S. designed all the tests of FluoSpec 2 and installed three FluoSpec 2. All authors contributed to the improvement of FluoSpec 2 and the writing and editing of the manuscript.
FundingOpen asset ↗zhangyaonju/seabreeze_controllines:139-146Code / dataset availability confirmedEurope PMC · OpenAlex · checked 10 Sept 2026
Non-destructive plant growth measurement is essential for plant growth and health research. As a 3D sensor, Kinect v2 has huge potentials in agriculture applications, benefited from its low price and strong robustness. The paper proposes a Kinect-based automatic system for non-destructive growth measurement of leafy vegetables. The system used a turntable to acquire multi-view point clouds of the measured plant. Then a series of suitable algorithms were applied to obtain a fine 3D reconstruction for the plant, while measuring the key growth parameters including relative/absolute height, total/projected leaf area and volume. In experiment, 63 pots of lettuce in different growth stages were measured. The result shows that the Kinect-measured height and projected area have fine linear relationship with reference measurements. While the measured total area and volume both follow power law distributions with reference data. All these data have shown good fitting goodness ( R ² = 0.9457-0.9914). In the study of biomass correlations, the Kinect-measured volume was found to have a good power law relationship ( R ² = 0.9281) with fresh weight. In addition, the system practicality was validated by performance and robustness analysis.
Why it matches plant phenotyping methodsKinectによる多視点3D再構成とアルゴリズムを用いて、植物の高さ・葉面積・体積・バイオマス関連形質を自動測定し、精度と頑健性も検証しているため、植物フェノタイピング手法が中心である。
abstractThe paper proposes a Kinect-based automatic system for non-destructive growth measurement of leafy vegetables.
Reproduction assets foundThe paper's Supplementary Materials, available at the MDPI s1 URL, explicitly contain the paper-specific phenotyping assets: point clouds and meshes shown in figures, the datasets used for the scatter plots of Kinect-measured growth parameters vs. reference measurements, and interactive MATLAB 3D scatter plots. No codeDataset · publicThe following are available online at http://www.mdpi.com/1424-8220/18/3/806/s1 . Supplementary data associated with this article have been provided. These data include the point clouds and meshes appeared in figures, the data sets used by scatter plots, and interactive MATLAB 3D scatter plots.Open asset ↗lines:114-135Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
We demonstrate that optical coherence tomography (OCT) is a plausible optical tool for in vivo detection of plant seeds and its morphological changes during growth. To investigate the direct impact of salt stress on seed germination, the experiment was conducted using Capsicum annuum seeds that were treated with different molar concentrations of NaCl. To determine the optimal concentration for the seed growth, the seeds were monitored for nine consecutive days. In vivo two-dimensional OCT images of the treated seeds were obtained and compared with the images of seeds that were grown using sterile distilled water. The obtained results confirm the feasibility of using OCT for the proposed application. Normalized depth profile analysis was utilized to support the conclusions.
Why it matches plant phenotyping methodsOCTを用いた種子の形態変化の非破壊・生体内モニタリング手法を開発・実証しており、植物表現型の取得方法が中心である。
abstractWe demonstrate that optical coherence tomography (OCT) is a plausible optical tool for in vivo detection of plant seeds and its morphological changes during growth.
Reproduction assets foundThe paper's supplementary material (Table S1) contains the paper-specific phenotyping measurements: seed weight and embryo thickness statistics for all NaCl-treated and control seed groups across the 9-day monitoring period, publicly available at the MDPI supplementary URL. No analysis code or image datasets are statedSupplement · publicugh Advanced Production Technology Development Program, funded by Ministry of Agriculture, Food and Rural Affairs (MAFRA) (No. 314031-3). Additionally, this study was also supported by the BK21 Plus project funded by the Ministry of Education, Korea (21A20131600011).
Supplementary Materials
The following are available online at http://www.mdpi.com/1424-8220/17/12/2887/s1 . Table S1, The average weight gain observed and the averaged embryo thickness values for each group, along with its standard deviation value and the maximum and minimum values of seeds in each group that was observed during the entire monitoring process.
Click here for additional data file.
Author Contributions
The experimeOpen asset ↗lines:63-81Code / dataset availability confirmedEurope PMC · checked 11 Sept 2026
CoffeeGrapevineLeafMorphology / geometry measurementPhysiological trait estimationLeaf traitsWater status / transpiration
Fresh water is a key natural resource for food production, sanitation and industrial uses and has a high environmental value. The largest water use worldwide (~70%) corresponds to irrigation in agriculture, where use of water is becoming essential to maintain productivity. Efficient irrigation control largely depends on having access to reliable information about the actual plant water needs. Therefore, fast, portable and non-invasive sensing techniques able to measure water requirements directly on the plant are essential to face the huge challenge posed by the extensive water use in agriculture, the increasing water shortage and the impact of climate change. Non-contact resonant ultrasonic spectroscopy (NC-RUS) in the frequency range 0.1-1.2 MHz has revealed as an efficient and powerful non-destructive, non-invasive and in vivo sensing technique for leaves of different plant species. In particular, NC-RUS allows determining surface mass, thickness and elastic modulus of the leaves. Hence, valuable information can be obtained about water content and turgor pressure. This work analyzes and reviews the main requirements for sensors, electronics, signal processing and data analysis in order to develop a fast, portable, robust and non-invasive NC-RUS system to monitor variations in leaves water content or turgor pressure. A sensing prototype is proposed, described and, as application example, used to study two different species: Vitis vinifera and Coffea arabica, whose leaves present thickness resonances in two different frequency bands (400-900 kHz and 200-400 kHz, respectively), These species are representative of two different climates and are related to two high-added value agricultural products where efficient irrigation management can be critical. Moreover, the technique can also be applied to other species and similar results can be obtained.
Why it matches plant phenotyping methods植物葉の水分量・膨圧を非接触超音波で測定するセンサー方式の要件分析、試作、応用を中心に扱っており、植物表現型取得法が明確に中心的である。
abstractThis work analyzes and reviews the main requirements for sensors, electronics, signal processing and data analysis in order to develop a fast, portable, robust and non-invasive NC-RUS system to monitor variations in leaves water content or turgor pressure.
Reproduction assets foundThe paper's inverse-problem analysis code for extracting leaf parameters (thickness, density, ultrasound velocity, attenuation) from measured resonance spectra is explicitly stated to be publicly available via the authors' GitHub repository and the US-BIOMAT resource page. No phenotype dataset deposit is mentioned.Code · publicUS-BIOMAT
Available online: https://us-biomat.com/resources/code-2/ or https://github.com/usbiomat/ultrasonic-thickness-resonance (accessed on 12 July 2016)Open asset ↗usbiomat/ultrasonic-thickness-resonancelines:327-413