Plant phenotyping methods.

A Novel Multi Class Real World Fruit and Leaf Disease Image Dataset for Crop Health Analysis →

Abstract Plant diseases affecting leaves and fruits cause substantial yield and economic losses worldwide, particularly in horticultural crops cultivated under diverse agro-climatic conditions. Early and accurate disease diagnosis is essential for effective crop management; however, manual inspection is time-consuming, subjective, and often infeasible at large scale. In this work, we present the Tomato–Chilli–Papaya (TCP) Fruit and Leaf Disease Dataset, a comprehensive multi-crop image dataset designed to support deep learning-based plant disease recognition. The dataset comprises labeled RGB images of healthy and diseased leaves and fruits from three economically important crops—tomato, chilli, and papaya—captured under real-field and semi-controlled environments, reflecting significant variability in illumination, background complexity, and disease severity. To demonstrate the applicability of the dataset, several commonly used convolutional neural network (CNN) architectures, including VGG, ResNet, DenseNet, MobileNet, and EfficientNet models, were trained and evaluated on the TCP dataset using transfer learning. Experimental results show that deep CNN models can effectively learn discriminative visual features corresponding to disease-specific patterns such as leaf spots, lesions, discoloration, curling, and fruit surface abnormalities. Lightweight models such as MobileNet achieve competitive performance with reduced computational cost, while deeper architectures provide improved accuracy at the expense of higher complexity. The results highlight the importance of dataset diversity for robust model generalization across multiple crops and plant organs. The TCP dataset provides a challenging benchmark for single-crop and multi-crop disease classification and supports the development of advanced deep learning, attention-based, and explainable AI models for precision agriculture. By enabling reproducible research and realistic performance evaluation, this dataset contributes toward scalable and practical AI-driven plant disease diagnosis systems aimed at reducing yield losses and supporting sustainable agriculture.

Why it matches plant phenotyping methods植物の葉・果実の病徴を画像から評価する大規模データセットとベンチマークを中心に扱っており、植物病害状態の画像ベース表現型解析に該当する。

abstractwe present the Tomato–Chilli–Papaya (TCP) Fruit and Leaf Disease Dataset, a comprehensive multi-crop image dataset designed to support deep learning-based plant disease recognition.

A Deep Learning Model for Chili Pepper Fruit Shape Classification Using DenseNet-121 and CBAM. →

Traditional manual grading of fresh chili peppers suffers from inconsistent quality control and low efficiency. To meet the demand for accurate fruit shape recognition during the post-harvest stage, this study proposes an intelligent recognition method based on an improved DenseNet-121 network. This approach facilitates the application of machine vision in agricultural sorting equipment. DenseNet-121 serves as the backbone network. The Convolutional Block Attention Module (CBAM) is introduced to enhance feature focus on fruit shapes. A regularization strategy (Dropout = 0.3, weight decay = 1 × 10 -4 ) and a cross-entropy loss function with label smoothing (LS = 0.1) are integrated to optimize decision boundaries. These configurations prevent the model from overfitting to hard training labels and yield a robust classification architecture. Experimental results demonstrate that the proposed model achieves a precision of 90.09%, a recall of 89.60%, an F1-score (the harmonic mean of precision and recall) of 89.53%, and an overall accuracy of 89.74%. The model contains 7.09 M parameters and requires a single-frame inference time of 7.35 ms. Comprehensive evaluations indicate that the proposed model achieves an optimal balance among environmental noise robustness, prediction accuracy, and computational efficiency. Consequently, by maintaining high fine-grained classification accuracy alongside a low memory footprint and rapid inference speed, the model demonstrates strong potential for real-time deployment on resource-constrained edge devices within actual agricultural optical sorting equipment.

Why it matches plant phenotyping methodsチリペッパー果実の形状という植物器官形質を画像から分類する深層学習手法の開発・評価が中心であり、単なる品質測定ではない。

abstractExperimental results demonstrate that the proposed model achieves a precision of 90.09%, a recall of 89.60%, an F1-score (the harmonic mean of precision and recall) of 89.53%, and an overall accuracy of 89.74%.

Longitudinal multispectral image dataset for ToBRFV disease detection in tomato and pepper plants. →

ToBRFV is a major threat to tomato and pepper crops because it spreads quickly and survives for a long time in the environment. Since there are few ways to control it after infection, early detection before symptoms are visible is crucial. Yet, only limited public datasets are available for this research. We present one of the first openly accessible, longitudinal multispectral image dataset dedicated to ToBRFV detection. In this study, two tomato cultivars and two pepper cultivars, all of which are commercially important and widely cultivated in greenhouses, were selected. Using these plants ensures that the dataset reflects real-world agricultural practices and captures variability across commercially grown types. Both healthy and ToBRFV-inoculated plants from each cultivar were included in the imaging process. All plants were cultivated under fully controlled greenhouse conditions in Adana Province, Türkiye. Healthy and infected tomato plants were grown in two separate greenhouses to prevent cross-contamination. Imaging was conducted over a 29-day period using Red-Green-Blue (RGB) and Visible Near Infrared (VNIR) cameras, including narrowband captures at 800 nm and 1000 nm, from multiple viewing angles. Infection status was confirmed via Reverse Transcription quantitative Polymerase Chain Reaction (RT-qPCR) analysis at multiple time points. The dataset is organized into four clean, labelled subsets and released under a CC BY 4.0 license. This resource provides unique opportunities for developing and benchmarking computer vision and machine learning approaches for pre-symptomatic plant disease detection, spectral feature analysis, and integration into precision agriculture systems. By combining controlled experimental design, spectral diversity, and open access, it establishes a robust foundation for cross-disciplinary research in plant pathology, agricultural engineering, and artificial intelligence.

Why it matches plant phenotyping methods植物病害状態を対象にした縦断マルチスペクトル画像データセットであり、公開データセットとして開発・ベンチマーク利用を目的とするため、表現型取得が中心です。

abstractWe present one of the first openly accessible, longitudinal multispectral image dataset dedicated to ToBRFV detection.

Optimizing CNN-Based Transfer Learning through Fine-Tuning and Adaptive Augmentation for Chili Plant Disease Detection →

Chili peppers (Capsicum annuum L.) are a strategic horticultural commodity in Indonesia, but their productivity is often hampered by pathogen infections that cause leaf diseases such as anthracnose, leaf spot, and yellow virus. Early detection by farmers is still dominated by subjective visual observation and prone to misdiagnosis due to the similarity of symptoms between diseases. Although Deep Learning technology through Convolutional Neural Networks (CNN) offers an automated solution, implementation in real-world conditions still faces significant challenges such as lighting variations, complex backgrounds, and limited local datasets. This often leads to a drastic decrease in model performance compared to testing in a controlled environment. To address these issues, this study proposes an optimization of the transfer learning strategy on the MobileNetV2 architecture by integrating progressive layer-wise fine-tuning and adaptive data augmentation techniques. The fine-tuning method is carried out gradually on the pre-trained model layers, while adaptive augmentation dynamically manipulates images based on environmental characteristics to improve model robustness. The results of this study, which include multi-class classification on cross-location image data, are projected to be able to boost the accuracy and generalization ability of the model in heterogeneous field conditions. Practically, this research provides a framework for a more precise and robust disease detection system to accelerate the implementation of precision agriculture in the future.

Why it matches plant phenotyping methods植物葉の病徴を画像から分類するCNN手法の改良が研究の中心であり、病害状態の表現型推定に該当する。転移学習のファインチューニングと適応的画像拡張、異なる圃場条件での頑健性評価を扱っている。

abstractThe results of this study, which include multi-class classification on cross-location image data, are projected to be able to boost the accuracy and generalization ability of the model in heterogeneous field conditions.

Multispectral imaging for zeaxanthin content in the exocarp of chili peppers. →

This study developed a model to predict zeaxanthin content in peppers using multispectral imaging and chemical data. A one-dimensional convolutional neural network (1D CNN) model was identified as the optimal single-modal model after comparing four machine learning algorithms. On the prediction dataset, the model achieved a determination coefficient ( Rp 2 ) of 0.7639. Building upon the 1D CNN framework, a multimodal feature fusion model (MCSF) was constructed by integrating the chemical measurements of capsanthin and total carotenoid contents using a multilayer perceptron. This enhanced model demonstrated excellent predictive accuracy and robustness, with Rp 2 values of 0.9318 and 0.9211 across different spectral ranges. For high-throughput detection purposes, a simplified model that replaced measured capsanthin with a comprehensive red index still performed well, with an Rp 2 of 0.8912 and an RPD of 3.11. This strategy provides a new solution for the efficient spectral detection of plant chemicals affected by multicollinearity in their absorption spectra.

Why it matches plant phenotyping methodsマルチスペクトル画像と機械学習を用いて、トウガラシ果皮のゼアキサンチン含量という植物器官の形質を非破壊・高スループット推定する手法を開発・評価しており、フェノタイピング手法が中心である。

abstractThis study developed a model to predict zeaxanthin content in peppers using multispectral imaging and chemical data.

DeepGreen: a real-time deep learning system for smart agriculture monitoring. →

Plant diseases are a major problem for farmers around the world, reducing crop yields. The absence of expertise makes plant disease detection difficult and complicated. Plant disease detection is made easier by deep learning algorithms; however, they are computationally demanding and need huge training datasets. This research work proposes a novel Conv-7 DCNN model with modified ParNet attention layer to classify plant leaves into distinct categories with improved accuracy. Because of its architecture, the proposed network can identify leaf diseases with more accuracy by extracting the wider range of features from the images. The proposed Conv-7 DCNN model classifies the leaf diseases of three plants such as tomato, potato, and pepper-bell into fifteen categories. The CNN model is trained using publicly accessible Kaggle dataset, utilising image augmentation techniques. It is evident from the simulation results that the proposed model outperforms several pre-trained, and other trending deep learning models. Proposed model achieves 99.18% classification accuracy with an average precision of 99.17% and area under the curve (AUC) of 1, making this model highly effective in leaf diseases detection. Additionally, Conv-7 DCNN achieved high FPS of 112.49, low inference time of 18.34 s, and low GFLOPS of 13.98, making it suitable for real-time applications in smart agriculture systems.

Why it matches plant phenotyping methods植物葉画像から病害状態を推定する深層学習モデルを開発・比較しており、病害表現型の取得・分類手法が研究の中心である。

abstractThis research work proposes a novel Conv-7 DCNN model with modified ParNet attention layer to classify plant leaves into distinct categories with improved accuracy.

A Comparative Study of Deep Transfer Learning Architectures for Multi-Class Plant Leaf Disease Detection →

Plant Leaf Diseases represent a significant risk to global agricultural production. Crops ranging from Peppers and Tomatoes to Potatoes are affected by these diseases. Traditional methods of identifying leaf diseases based primarily on visual inspection have historically been slow and relatively inaccurate. A deep learning-based solution for the automated identification of plant leaf diseases utilizes Convolutional Neural Networks (CNNs) as the primary methodology. To identify leaf images into 15 disease categories, both pre-trained models such as VGG16, EfficientNetB3, Inception V3 and a custom CNN model were used. Using pre-trained models to allow for the use of Transfer Learning helps to mitigate some of the issues associated with computational resource limitations and data limitations in providing faster convergence rates and higher accuracy when compared to training a model from scratch. The Plant Village image collection which contains over 20,000 images of different plant leaf diseases was utilized for training and testing purposes. Each model's performance was evaluated based on its accuracy, loss and generalization capabilities. Additionally, each model was fine-tuned through hyperparameter optimization. As a result, the model that achieved the highest validation accuracy rate of 95% was the EfficientNetB3 model while the second highest accuracy rate was achieved by the Inception V3 model at 92%. This methodology provides an excellent answer to addressing early disease detection, enabling farmers to take the necessary actions quickly to reduce their losses and maximize their harvest.

Why it matches plant phenotyping methods植物葉画像から病害状態を推定する深層学習手法を比較・評価しており、病害フェノタイピングと手法検証が研究の中心です。

abstractA deep learning-based solution for the automated identification of plant leaf diseases utilizes Convolutional Neural Networks (CNNs) as the primary methodology.

Pepper-4D: Spatiotemporal 3D Pepper Crop Dataset for Phenotyping →

Pepper (Capsicum annuum) is a globally significant horticultural crop cultivated for its culinary, medicinal, and economic value. Traditional approaches for boosting the agricultural production of pepper, notably, expanding farmland, have become increasingly unsustainable. Recent advancements in artificial intelligence and 3D computer vision have started to transform crop cultivation and phenotyping, which has shed new light on increasing production by advanced breeding. However, currently, the field still lacks 3D pepper data that contains enough detail for organ-level analysis. Therefore, we propose Pepper-4D, a new, high-precision 4D point cloud dataset that records both the spatial structure and temporal development of pepper plants across various continuous growth stages. Our dataset is divided into three subsets, including a total of 916 individual point clouds from 29 indoor-cultivated pepper plant samples. Our dataset provides manual annotations at both the plant-level and organ-level, supporting phenotyping tasks such as pepper growth status classification, organ semantic segmentation, organ instance segmentation, organ growth tracking, new organ detection, and even the generation of synthetic 3D pepper plants.

Why it matches plant phenotyping methods植物の器官レベル表現型解析を支援する4D点群データセットを構築し、成長状態分類・器官分割・追跡などを可能にする研究であり、フェノタイピング用データ基盤が中心です。

abstractPepper-4D, a new, high-precision 4D point cloud dataset that records both the spatial structure and temporal development of pepper plants across various continuous growth stages.

VGG-EffAttnNet: Hybrid Deep Learning Model for Automated Chili Plant Disease Classification Using VGG16 and EfficientNetB0 With Attention Mechanism. →

Chili plant diseases significantly impact global agriculture, necessitating accurate and rapid classification for effective management. The study introduces VGG-EffAttnNet, a hybrid deep learning model combining VGG16 and EfficientNetB0 with attention mechanisms and Monte Carlo Dropout (MCD) for robust chili plant disease classification. VGG16 captures spatial and hierarchical features, while EfficientNetB0 ensures efficient, high-accuracy learning. Attention enhances focus on disease-relevant areas, and MCD improves robustness by estimating uncertainty. The study utilizes a chili plant disease dataset sourced from Kaggle, comprising 5000 images across five classes: Healthy, Leaf Curl, Leaf Spot, Whitefly, and Yellowish, after extensive data augmentation techniques, including rotation, flipping, zooming, and brightness adjustment, to improve model generalization. Feature extraction is performed using VGG16 and EfficientNetB0, followed by concatenation and refinement through attention mechanisms, enabling the model to focus on disease-relevant features while suppressing background noise. MCD is integrated to estimate model uncertainty and mitigate overfitting. Experimental results demonstrate the superior performance of the proposed hybrid model. The concatenated VGG16 and EfficientNetB0 model achieved a classification accuracy of 99%, precision, and recall of 99%, surpassing individual model performances (VGG16: 96.8%, EfficientNetB0: 96.5%, and attention-integrated variants reached up to 98%). The F1-score reached 99% across all disease categories, ensuring high precision and recall. Compared to state-of-the-art models like InceptionV3 (98.83%) and MobileNet (97.18%), the proposed hybrid model demonstrates improved classification accuracy and robustness. The study underscores the potential of deep learning-based automated disease classification in precision agriculture, enabling early intervention and reducing reliance on chemical treatments. Future work aims to extend the approach to real-time deployment on mobile and edge devices, integrate explainability techniques for enhanced interpretability, and explore federated learning for decentralized agricultural diagnostics.

Why it matches plant phenotyping methods植物画像から病徴・健全状態を分類する深層学習手法が研究の中心であり、植物病害状態の画像ベース表現型推定に該当する。

abstractThe study introduces VGG-EffAttnNet, a hybrid deep learning model combining VGG16 and EfficientNetB0 with attention mechanisms and Monte Carlo Dropout (MCD) for robust chili plant disease classification.

An advanced deep learning method for pepper diseases and pests detection. →

Despite the significant progress in deep learning-based object detection, existing models struggle to perform optimally in complex agricultural environments. To address these challenges, this study introduces YOLO-Pepper, an enhanced model designed specifically for greenhouse pepper disease and pest detection, overcoming three key obstacles: small target recognition, multi-scale feature extraction under occlusion, and real-time processing demands. Built upon YOLOv10n, YOLO-Pepper incorporates four major innovations: (1) an Adaptive Multi-Scale Feature Extraction (AMSFE) module that improves feature capture through multi-branch convolutions; (2) a Dynamic Feature Pyramid Network (DFPN) enabling context-aware feature fusion; (3) a specialized Small Detection Head (SDH) tailored for minute targets; and (4) an Inner-CIoU loss function that enhances localization accuracy by 18% compared to standard CIoU. Evaluated on a diverse dataset of 8046 annotated images, YOLO-Pepper achieves state-of-the-art performance, with 94.26% mAP@0.5 at 115.26 FPS, marking an 11.88 percentage point improvement over YOLOv10n (82.38% mAP@0.5) while maintaining a lightweight structure (2.51 M parameters, 5.15 MB model size) optimized for edge deployment. Comparative experiments highlight YOLO-Pepper's superiority over nine benchmark models, particularly in detecting small and occluded targets. By addressing computational inefficiencies and refining small object detection capabilities, YOLO-Pepper provides robust technical support for intelligent agricultural monitoring systems, making it a highly effective tool for early disease detection and integrated pest management in commercial greenhouse operations.

Why it matches plant phenotyping methodsコショウの病害を画像から検出する深層学習手法を開発し、注釈画像データセットと複数モデルで性能比較・検証しており、植物の病害状態の取得方法が中心です。害虫検出も含みますが、病害検出の技術的貢献が明確なため採用します。

abstractthis study introduces YOLO-Pepper, an enhanced model designed specifically for greenhouse pepper disease and pest detection

Enhanced Plant Leaf Disease Detection Using Modified Logistic Regression for Sustainable Agriculture Practices →

Abstract Pepper, Hibiscus, and Basil are medicinal plants with a rich history in traditional medicine and health benefits. They are essential in culinary and medicinal applications, contributing to natural health solutions. Disease detection is crucial to protect their agricultural, economic, and medicinal value. Early detection minimizes crop losses, maintains plant health, and ensures plant availability for traditional medicine and culinary uses. This promotes sustainable and eco-friendly agricultural practices. Traditional logistic regression for plant leaf disease detection struggles with imbalanced data and a fixed linear decision boundary, making it less effective in capturing complex disease patterns. The modified logistic regression model with the One Half Constant improves performance metrics and handling intricate features of leaf images by addressing class imbalance more effectively. It adjusts the decision boundary to handle imbalanced datasets, enhancing classification accuracy for minority classes while maintaining simplicity and interpretability. This study uses a dataset collected from Kaggle and surrounding of Kadapa district AP, India. For the evaluation of the proposed model in disease detection, the traditional logistic regression and other machine learning algorithms were used, and the corresponding key metrics of accuracy, precision, recall, false positive rate (FPR) and F-Measure were assessed. A comparison with existing methods show overwhelming improvement of 32.94% in accuracy, 17.64% in precision, 33.6% in recall, 86.91% in FPR improvement, 34.6% in F-Measure. The proposed approach seeks to improve overall diagnostic accuracy, thereby providing a reliable tool for early detection and treatment planning in clinical sectors.

Why it matches plant phenotyping methods植物葉画像から病害状態を推定する分類手法を改良し、既存手法との性能比較で検証しているため、植物フェノタイピング手法が中心である。

titleEnhanced Plant Leaf Disease Detection Using Modified Logistic Regression for Sustainable Agriculture Practices

Diagnosis Anthracnose of Chili Pepper Using Convolutional Neural Networks Based Deep Learning Models. →

Chili pepper (Capsicum annuum L.), one of the most economically important vegetable crops globally, faces significant economic risks from anthracnose, leading to yield losses of 10% as well as decreasing marketability. Early and accurate detection is essential for mitigating these effects. Recent advancements in deep learning, particularly in image recognition, offer promising solutions for plant disease detection. This study applies deep learning models-MobileNet, ResNet50v2, and Xception-using transfer learning to diagnose anthracnose in chili peppers. A key challenge is the need for large, labeled datasets, which are costly to obtain. The study aims to identify the minimum dataset size required for accurate and efficient disease diagnosis using limited data. Performance metrics, including precision, recall, F1-score, and accuracy, were evaluated across different dataset sizes (500, 1,000, 2,000, 3,000, and 4,000 samples). Results indicated that model performance improves with larger datasets, with ResNet50v2 and Xception requiring more data to achieve optimal accuracy, while MobileNet showed strong generalization even with smaller datasets. These findings underscore the effectiveness of transfer learning-based models in plant disease detection, offering practical guidelines for balancing data availability and model performance in agricultural applications. Source code available at https://github.com/smart-able/Anthracnose.git.

Why it matches plant phenotyping methods唐辛子の病徴を画像から診断する深層学習モデルを比較し、データセット規模と性能の関係を評価しており、植物病害状態の取得・推定手法が中心である。

abstractThis study applies deep learning models-MobileNet, ResNet50v2, and Xception-using transfer learning to diagnose anthracnose in chili peppers.

ANFIS Fuzzy convolutional neural network model for leaf disease detection →

Leaf disease detection is critical in agriculture, as it directly impacts crop health, yield, and quality. Early and accurate detection of leaf diseases can prevent the spread of infections, reduce the need for chemical treatments, and minimize crop losses. This not only ensures food security but also supports sustainable farming practices. Effective leaf disease detection systems empower farmers with the knowledge to take timely actions, leading to healthier crops and more efficient resource management. In an era of increasing global food demand and environmental challenges, advanced leaf disease detection technologies are indispensable for modern agriculture. This study presents an innovative approach for detecting pepper bell leaf disease using an ANFIS Fuzzy convolutional neural network (CNN) integrated with local binary pattern (LBP) features. Experiments involve using the models without LBP, as well as, with LBP features. For both sets of experiments, the proposed ANFIS CNN model performs superbly. It shows an accuracy score of 0.8478 without using LBP features while its precision, recall, and F1 scores are 0.8959, 0.9045, and 0.8953, respectively. Incorporating LBP features, the proposed model achieved exceptional performance, with accuracy, precision, recall, and an F1 score of higher than 99%. Comprehensive comparisons with state-of-the-art techniques further highlight the superiority of the proposed method. Additionally, cross-validation was applied to ensure the robustness and reliability of the results. This approach demonstrates a significant advancement in agricultural disease detection, promising enhanced accuracy and efficiency in real-world applications.

Why it matches plant phenotyping methods画像からコショウ葉の病害状態を推定するCNN手法を開発・比較・検証しており、植物病害フェノタイピング手法が中心です。

abstractThis study presents an innovative approach for detecting pepper bell leaf disease using an ANFIS Fuzzy convolutional neural network (CNN) integrated with local binary pattern (LBP) features.

Comparative Investigation of Deep Convolutional Networks in Detection of Plant Diseases →

Abstract: Preserving plant health and early detection of diseases are crucial in modern agriculture. Artificial intelligence techniques, particularly deep learning networks, are employed for this purpose. In this study, disease recognition was conducted using leaf images from various plant species. The study encompassed important agricultural products such as apples, strawberries, grapes, corn, peppers, and potatoes among the plant species considered. Among the deep learning networks, popular architectures like AlexNet, Vgg16, MobileNetV2, and Inception were compared. The Inception V3 model achieved the highest success rate of 92%, followed by the AlexNet architecture with a success rate of 91%. Among these networks, the InceptionV3 model yielded the best results. The InceptionV3 model effectively learned from plant leaf images and accurately distinguished between diseased and healthy leaves. These findings demonstrate that AI-based systems can be efficiently utilized for disease recognition and prevention in the agriculture sector. In this study, the performance of the InceptionV3 model in disease recognition on plant leaves was analyzed in detail, emphasizing the role of deep learning networks in agricultural applications.

Why it matches plant phenotyping methods植物葉画像から健全・罹病状態を推定する深層学習手法を比較・評価しており、植物病害表現型の取得・分類が研究の中心です。

abstractIn this study, disease recognition was conducted using leaf images from various plant species.

CF-PRNet: Coarse-to-Fine Prototype Refining Network for Point Cloud Completion and Reconstruction →

In modern agriculture, precise monitoring of plants and fruits is crucial for tasks such as high-throughput phenotyping and automated harvesting. This paper addresses the challenge of reconstructing accurate 3D shapes of fruits from partial views, which is common in agricultural settings. We introduce CF-PRNet, a coarse-to-fine prototype refining network, leverages high-resolution 3D data during the training phase but requires only a single RGB-D image for real-time inference. Our approach begins by extracting the incomplete point cloud data that constructed from a partial view of a fruit with a series of convolutional blocks. The extracted features inform the generation of scaling vectors that refine two sequentially constructed 3D mesh prototypes - one coarse and one fine-grained. This progressive refinement facilitates the detailed completion of the final point clouds, achieving detailed and accurate reconstructions. CF-PRNet demonstrates excellent performance metrics with a Chamfer Distance of 3.78, an F1 Score of 66.76%, a Precision of 56.56%, and a Recall of 85.31%, and win the first place in the Shape Completion and Reconstruction of Sweet Peppers Challenge.

Why it matches plant phenotyping methods果実の部分RGB-D画像から3D形状を再構成する手法を開発・評価しており、植物器官の形態形質取得が研究の中心である。

abstractThis paper addresses the challenge of reconstructing accurate 3D shapes of fruits from partial views

PLANesT-3D: A new annotated dataset for segmentation of 3D plant point clouds →

Creation of new annotated public datasets is crucial in helping advances in 3D computer vision and machine learning meet their full potential for automatic interpretation of 3D plant models. Despite the proliferation of deep neural network architectures for segmentation and phenotyping of 3D plant models in the last decade, the amount of data, and diversity in terms of species and data acquisition modalities are far from sufficient for evaluation of such tools for their generalization ability. To contribute to closing this gap, we introduce PLANesT-3D; a new annotated dataset of 3D color point clouds of plants. PLANesT-3D is composed of 34 point cloud models representing 34 real plants from three different plant species: \textit{Capsicum annuum}, \textit{Rosa kordana}, and \textit{Ribes rubrum}. Both semantic labels in terms of "leaf" and "stem", and organ instance labels were manually annotated for the full point clouds. PLANesT-3D introduces diversity to existing datasets by adding point clouds of two new species and providing 3D data acquired with the low-cost SfM/MVS technique as opposed to laser scanning or expensive setups. Point clouds reconstructed with SfM/MVS modality exhibit challenges such as missing data, variable density, and illumination variations. As an additional contribution, SP-LSCnet, a novel semantic segmentation method that is a combination of unsupervised superpoint extraction and a 3D point-based deep learning approach is introduced and evaluated on the new dataset. The advantages of SP-LSCnet over other deep learning methods are its modular structure and increased interpretability. Two existing deep neural network architectures, PointNet++ and RoseSegNet, were also tested on the point clouds of PLANesT-3D for semantic segmentation.

Why it matches plant phenotyping methods3D植物点群の注釈付きデータセットを構築し、植物器官のセマンティック・インスタンス分割手法を開発・評価しており、植物フェノタイピング手法が中心である。

abstractwe introduce PLANesT-3D; a new annotated dataset of 3D color point clouds of plants.

A Dataset and Benchmark for Shape Completion of Fruits for Agricultural Robotics →

As the world population is expected to reach 10 billion by 2050, our agricultural production system needs to double its productivity despite a decline of human workforce in the agricultural sector. Autonomous robotic systems are one promising pathway to increase productivity by taking over labor-intensive manual tasks like fruit picking. To be effective, such systems need to monitor and interact with plants and fruits precisely, which is challenging due to the cluttered nature of agricultural environments causing, for example, strong occlusions. Thus, being able to estimate the complete 3D shapes of objects in presence of occlusions is crucial for automating operations such as fruit harvesting. In this paper, we propose the first publicly available 3D shape completion dataset for agricultural vision systems. We provide an RGB-D dataset for estimating the 3D shape of fruits. Specifically, our dataset contains RGB-D frames of single sweet peppers in lab conditions but also in a commercial greenhouse. For each fruit, we additionally collected high-precision point clouds that we use as ground truth. For acquiring the ground truth shape, we developed a measuring process that allows us to record data of real sweet pepper plants, both in the lab and in the greenhouse with high precision, and determine the shape of the sensed fruits. We release our dataset, consisting of almost 7,000 RGB-D frames belonging to more than 100 different fruits. We provide segmented RGB-D frames, with camera intrinsics to easily obtain colored point clouds, together with the corresponding high-precision, occlusion-free point clouds obtained with a high-precision laser scanner. We additionally enable evaluation of shape completion approaches on a hidden test set through a public challenge on a benchmark server.

Why it matches plant phenotyping methods果実の3D形状という植物器官の形態形質を対象に、RGB-D画像・高精度点群・評価用ベンチマークを構築しており、形状取得と推定の方法論が中心である。

abstractWe provide an RGB-D dataset for estimating the 3D shape of fruits.

PC4C_CAPSI: Image data of capsicum plant growth in protected horticulture. →

Feeding the increasing global population and reducing the carbon footprint of agricultural activities are two critical challenges of our century. Growing crops under protected horticulture and precise crop monitoring have emerged to address these challenges. Crop monitoring in commercial protected facilities remains mostly manual and labour intensive. Using computer vision to solve specific problems in image-based crop monitoring in these compact and complex growth environments is currently hindered by the scarcity of available data. We collected an RGBD dataset for vertically supported, hydroponically-grown capsicum plants in a commercial-scale glasshouse facility to fill this gap. Data were collected weekly using a single top-angled stereo camera mounted on a mobile platform running between the hydroponic gutters. The RGBD streams covered 80 % of the crop growing season in three different light conditions. The metadata include camera configurations and light condition information. Manually measured plant heights of ten selected plants per gutter are provided as ground truth. The images covered the whole plants and focused on the top third. This dataset will support research on plant height estimation, plant organ identification, object segmentation, organ measurements, 3D reconstruction, 3D data processing, and depth noise reduction. The usability of the dataset has been successfully demonstrated in a previously published study on plant height estimation using machine learning and 3D point cloud.

Why it matches plant phenotyping methods植物の草丈推定や器官計測を目的としたRGBD画像データセットを構築し、地上真値も提供しているため、植物フェノタイピング手法・データセットが中心です。

abstractWe collected an RGBD dataset for vertically supported, hydroponically-grown capsicum plants in a commercial-scale glasshouse facility to fill this gap.

MCCM: multi-scale feature extraction network for disease classification and recognition of chili leaves. →

Currently, foliar diseases of chili have significantly impacted both yield and quality. Despite effective advancements in deep learning techniques for the classification of chili leaf diseases, most existing classification models still face challenges in terms of accuracy and practical application in disease identification. Therefore, in this study, an optimized and enhanced convolutional neural network model named MCCM (MCSAM-ConvNeXt-MSFFM) is proposed by introducing ConvNeXt. The model incorporates a Multi-Scale Feature Fusion Module (MSFFM) aimed at better capturing disease features of various sizes and positions within the images. Moreover, adjustments are made to the positioning, activation functions, and normalization operations of the MSFFM module to further optimize the overall model. Additionally, a proposed Mixed Channel Spatial Attention Mechanism (MCSAM) strengthens the correlation between non-local channels and spatial features, enhancing the model's extraction of fundamental characteristics of chili leaf diseases. During the training process, pre-trained weights are obtained from the Plant Village dataset using transfer learning to accelerate the model's convergence. Regarding model evaluation, the MCCM model is compared with existing CNN models (Vgg16, ResNet34, GoogLeNet, MobileNetV2, ShuffleNet, EfficientNetV2, ConvNeXt), and Swin-Transformer. The results demonstrate that the MCCM model achieves average improvements of 3.38%, 2.62%, 2.48%, and 2.53% in accuracy, precision, recall, and F1 score, respectively. Particularly noteworthy is that compared to the original ConvNeXt model, the MCCM model exhibits significant enhancements across all performance metrics. Furthermore, classification experiments conducted on rice and maize disease datasets showcase the MCCM model's strong generalization performance. Finally, in terms of application, a chili leaf disease classification website is successfully developed using the Flask framework. This website accurately identifies uploaded chili leaf disease images, demonstrating the practical utility of the model.

Why it matches plant phenotyping methodsトウガラシ葉の病徴を画像から分類する深層学習手法を開発・比較評価しており、植物の病害状態を推定するフェノタイピング手法が中心である。

abstractan optimized and enhanced convolutional neural network model named MCCM (MCSAM-ConvNeXt-MSFFM) is proposed

AMS-MLP: Adaptive Multi-Scale MLP Network with Multi-Scale Context Relation Decoder for Pepper Leaf Segmentation →

Pepper leaf segmentation plays a crucial role in monitoring pepper leaf diseases in various backgrounds and ensuring the healthy growth of peppers. However, existing transformer-based segmentation methods suffer from computational inefficiency, excessive parameterization, and limited utilization of edge information. To tackle these challenges, we propose an adaptive multi-scale MLP framework, named AMS-MLP, which combines the multi-path aggregation module (MPAM) and the multi-scale context relation mask module (MCRD) to refine the object boundaries in pepper leaf segmentation. AMS-MLP consists of an encoder-based network, an adaptive multi-scale MLP (AM-MLP) module, and a decoder network. In the encoder network, the MPAM module effectively fuses five-scale features to generate a single-channel mask, improving the accuracy of pepper leaf boundary extraction. The AM-MLP module divides the input features into two branches: the global multi-scale MLP branch captures long-range dependencies between image information, while the local multi-scale MLP branch focuses on extracting local feature maps. Adaptive attention mechanism is designed to dynamically adjust the weights of global and local features. The decoder network incorporates the MCRD module into the convolutional layer, enhancing the extraction of boundary features. To verify the performance of the proposed method, we conducted extensive experiments on three pepper leaf datasets with different backgrounds. The results demonstrate mIoU scores of 97.39%, 96.91%, and 97.91%, as well as F1 scores of 98.29%, 97.86%, and 98.51%, respectively. Comparative analysis with U-Net and state-of-the-art models reveals that the proposed method dramatically improves the accuracy and efficiency of pepper leaf image segmentation.

Why it matches plant phenotyping methodsコショウ葉の画像から葉領域・境界を抽出するセグメンテーション手法を開発し、複数データセットで性能検証しているため、植物表現型取得法が中心である。

abstractwe propose an adaptive multi-scale MLP framework, named AMS-MLP, which combines the multi-path aggregation module (MPAM) and the multi-scale context relation mask module (MCRD) to refine the object boundaries in pepper leaf segmentation.

Temporal forecasting of plant height and canopy diameter from RGB images using a CNN-based regression model for ornamental pepper plants (Capsicum spp.) growing under high-temperature stress →

Abstract Being capable of accurately predicting morphological parameters of the plant weeks before achieving fruit maturation is of great importance in the production and selection of suitable ornamental pepper plants. The objective of this article is evaluating the feasibility and assessing the performance of CNN-based models using RGB images as input to forecast two morphological parameters: plant height and canopy diameter. To this end, four CNN-based models are proposed to predict these morphological parameters in four different scenarios: first, using as input a single image of the plant; second, using as input several images from different viewpoints of the plant acquired on the same date; third, using as input two images from two consecutive weeks; and fourth, using as input a set of images consisting of one image from each week up to the current date. The results show that it is possible to accurately predict both plant height and canopy diameter. The RMSE for a forecast performed 6 weeks in advance to the actual measurements was below 4.5 cm and 4.2 cm, respectively. When information from previous weeks is added to the model, better results can be achieved and as the prediction date gets closer to the assessment date the accuracy improves as well.

Why it matches plant phenotyping methodsRGB画像からCNNで植物体高と樹冠径を予測し、予測精度を評価する手法開発・検証が研究の中心であるため。

abstractThe objective of this article is evaluating the feasibility and assessing the performance of CNN-based models using RGB images as input to forecast two morphological parameters: plant height and canopy diameter.

Maturity Recognition and Fruit Counting for Sweet Peppers in Greenhouses Using Deep Learning Neural Networks →

This study presents an approach to address the challenges of recognizing the maturity stage and counting sweet peppers of varying colors (green, yellow, orange, and red) within greenhouse environments. The methodology leverages the YOLOv5 model for real-time object detection, classification, and localization, coupled with the DeepSORT algorithm for efficient tracking. The system was successfully implemented to monitor sweet pepper production, and some challenges related to this environment, namely occlusions and the presence of leaves and branches, were effectively overcome. We evaluated our algorithm using real-world data collected in a sweet pepper greenhouse. A dataset comprising 1863 images was meticulously compiled to enhance the study, incorporating diverse sweet pepper varieties and maturity levels. Additionally, the study emphasized the role of confidence levels in object recognition, achieving a confidence level of 0.973. Furthermore, the DeepSORT algorithm was successfully applied for counting sweet peppers, demonstrating an accuracy level of 85.7% in two simulated environments under challenging conditions, such as varied lighting and inaccuracies in maturity level assessment.

Why it matches plant phenotyping methods深層学習による果実の成熟段階認識と計数が研究の中心であり、植物器官の状態（成熟度）を画像から抽出・評価しているため、植物フェノタイピング手法として含める。

abstractThis study presents an approach to address the challenges of recognizing the maturity stage and counting sweet peppers of varying colors

Automatic Root Length Estimation from Images Acquired In Situ without Segmentation. →

Image-based root phenotyping technologies, including the minirhizotron (MR), have expanded our understanding of the in situ root responses to changing environmental conditions. The conventional manual methods used to analyze MR images are time-consuming, limiting their implementation. This study presents an adaptation of our previously developed convolutional neural network-based models to estimate the total (cumulative) root length (TRL) per MR image without requiring segmentation. Training data were derived from manual annotations in Rootfly, commonly used software for MR image analysis. We compared TRL estimation with 2 models, a regression-based model and a detection-based model that detects the annotated points along the roots. Notably, the detection-based model can assist in examining human annotations by providing a visual inspection of roots in MR images. The models were trained and tested with 4,015 images acquired using 2 MR system types (manual and automated) and from 4 crop species (corn, pepper, melon, and tomato) grown under various abiotic stresses. These datasets are made publicly available as part of this publication. The coefficients of determination ( R 2 ), between the measurements made using Rootfly and the suggested TRL estimation models were 0.929 to 0.986 for the main datasets, demonstrating that this tool is accurate and robust. Additional analyses were conducted to examine the effects of (a) the data acquisition system and thus the image quality on the models' performance, (b) automated differentiation between images with and without roots, and (c) the use of the transfer learning technique. These approaches can support precision agriculture by providing real-time root growth information.

Why it matches plant phenotyping methods画像から根長という植物形質を推定するCNN手法を開発し、複数データセットで精度・頑健性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 presents an adaptation of our previously developed convolutional neural network-based models to estimate the total (cumulative) root length (TRL) per MR image without requiring segmentation.

A novel smartphone application for early detection of habanero disease. →

Habanero plant diseases can significantly reduce crop yield and quality, making early detection and treatment crucial for farmers. In this study, we discuss the creation of a modified VGG16 (MVGG16) Deep Transfer Learning (DTL) model-based smartphone app for identifying habanero plant diseases. With the help of the smartphone application, growers can quickly diagnose the health of a habanero plant by taking a photo of one of its leaves. We trained the DTL model on a dataset of labelled images of healthy and infected habanero plants and evaluated its performance on a separate test dataset. The MVGG16 DTL algorithm had an accuracy, precision, f1-score, recall and AUC of 98.79%, 97.93%, 98.44%, 98.95 and 98.63%, respectively, on the testing dataset. The MVGG16 DTL model was then integrated into a smartphone app that enables users to upload photographs, get diagnosed, and explore a history of earlier diagnoses. We tested the software on a collection of photos of habanero plant leaves and discovered that it was highly accurate at spotting infected plants. The smartphone software can boost early identification and treatment of habanero plant diseases, resulting in higher crop output and higher-quality harvests.

Why it matches plant phenotyping methods葉画像から感染状態を推定する深層学習モデルとスマートフォンアプリの開発・評価が研究の中心であり、植物病害状態の表現型計測に該当する。

abstractcreation of a modified VGG16 (MVGG16) Deep Transfer Learning (DTL) model-based smartphone app for identifying habanero plant diseases

Rapid spatial assessment of leaf-absorbed irradiance. →

Image-based high-throughput phenotyping promises the rapid determination of functional traits in large plant populations. However, interpretation of some traits - such as those related to photosynthesis or transpiration rates - is only meaningful if the irradiance absorbed by the measured leaves is known, which can differ greatly between different parts of the same plant and within canopies. No feasible method currently exists to rapidly measure absorbed irradiance in three-dimensional plants and canopies. We developed a method and protocols to derive absorbed irradiance at any visible part of a canopy with a thermal camera, by fitting a leaf energy balance model to transient changes in leaf temperature. Leaves were exposed to short light pulses (30 s) that were not long enough to trigger stomatal opening but strong enough to induce transient changes in leaf temperature that was proportional to the absorbed irradiance. The method was successfully validated against point measurements of absorbed irradiance in plant species with relatively simple architecture (sweet pepper, cucumber, tomato, and lettuce). Once calibrated, the model was used to produce absorbed irradiance maps from thermograms. Our method opens new avenues for the interpretation of plant responses derived from imaging techniques and can be adapted to existing high-throughput phenotyping platforms.

Why it matches plant phenotyping methods熱画像と葉エネルギーバランスモデルにより、植物キャノピー内の吸収光量を迅速に推定・可視化するフェノタイピング手法を開発し、点測定で検証しているため。

abstractWe developed a method and protocols to derive absorbed irradiance at any visible part of a canopy with a thermal camera, by fitting a leaf energy balance model to transient changes in leaf temperature.

An effective approach for plant leaf diseases classification based on a novel DeepPlantNet deep learning model →

Introduction Recently, plant disease detection and diagnosis procedures have become a primary agricultural concern. Early detection of plant diseases enables farmers to take preventative action, stopping the disease's transmission to other plant sections. Plant diseases are a severe hazard to food safety, but because the essential infrastructure is missing in various places around the globe, quick disease diagnosis is still difficult. The plant may experience a variety of attacks, from minor damage to total devastation, depending on how severe the infections are. Thus, early detection of plant diseases is necessary to optimize output to prevent such destruction. The physical examination of plant diseases produced low accuracy, required a lot of time, and could not accurately anticipate the plant disease. Creating an automated method capable of accurately classifying to deal with these issues is vital. Method This research proposes an efficient, novel, and lightweight DeepPlantNet deep learning (DL)-based architecture for predicting and categorizing plant leaf diseases. The proposed DeepPlantNet model comprises 28 learned layers, i.e., 25 convolutional layers (ConV) and three fully connected (FC) layers. The framework employed Leaky RelU (LReLU), batch normalization (BN), fire modules, and a mix of 3×3 and 1×1 filters, making it a novel plant disease classification framework. The Proposed DeepPlantNet model can categorize plant disease images into many classifications. Results The proposed approach categorizes the plant diseases into the following ten groups: Apple_Black_rot (ABR), Cherry_(including_sour)_Powdery_mildew (CPM), Grape_Leaf_blight_(Isariopsis_Leaf_Spot) (GLB), Peach_Bacterial_spot (PBS), Pepper_bell_Bacterial_spot (PBBS), Potato_Early_blight (PEB), Squash_Powdery_mildew (SPM), Strawberry_Leaf_scorch (SLS), bacterial tomato spot (TBS), and maize common rust (MCR). The proposed framework achieved an average accuracy of 98.49 and 99.85in the case of eight-class and three-class classification schemes, respectively. Discussion The experimental findings demonstrated the DeepPlantNet model's superiority to the alternatives. The proposed technique can reduce financial and agricultural output losses by quickly and effectively assisting professionals and farmers in identifying plant leaf diseases.

Why it matches plant phenotyping methods葉画像から植物病害状態を分類する深層学習手法を開発しており、植物の病徴・病害状態の取得と推定が研究の中心であるため。

abstractThis research proposes an efficient, novel, and lightweight DeepPlantNet deep learning (DL)-based architecture for predicting and categorizing plant leaf diseases.

Pretrained CNN Architectures: A Detailed Analysis Using Bell Pepper Image Datasets →

In the era of artificial intelligence, automation is becoming popular in every sector. The primary sector includes the agriculture sector. Farmers are facing problems such as the identification of diseases in their plants, lack of proper treatment for the disease, climatic changes that affect their yield, and low price for their crops. In this paper, we are mainly focusing on the disease identification of bell pepper plants using deep learning architectures such as Alex Net, google net, ResNet (18,50,101), and Vgg (16,19). We also focus on the detailed study of different pre-trained CNN architectures to analyze their performance and identify which architecture is more suitable for disease classification in bell pepper. This paper also helps bell pepper farmers to identify the disease with high accuracy compared to the traditional methods of disease identification. The new automation concept helps bell pepper framers to identify diseases with less time and effort, which makes their work easier. The identification of disease at an early stage with less effort will help the farmer to increase their yield. The paper will help to understand the performance of different pre-trained convolutional neural network architectures with and without augmentation of images and also compare the performance of the architectures. Based on these comparisons, it could find out that google net is more suitable for the classification of images in bell pepper as compared to other architectures with augmentation, and vgg19 was observed to be best for the classification of images without augmentation.

Why it matches plant phenotyping methodsベルペッパー植物の画像から病害を分類するCNN手法を複数比較し、データ拡張の有無を含めて性能評価しているため、植物病害フェノタイピング手法が研究の中心である。

abstractwe are mainly focusing on the disease identification of bell pepper plants using deep learning architectures such as Alex Net, google net, ResNet (18,50,101), and Vgg (16,19).

Leaf Disease Classification in Bell Pepper Plant using VGGNet →

In the era of artificial intelligence, deep learning, and computer vision play a vital role in leaf-based disease identification and categorization. Leaf diseases are the most dangerous calamity that has direct detrimental effects on farmers’ lives, and consequently on gross yield production and the world economy. Nutritious food for all is a great challenge faced by the farmer and agricultural research community. Bell peppers can be categorized as fruit or vegetable that is universally available and full of various nutrients like carbs, vitamins, and fat. Leaves of bell pepper plants infected by bacterial spot diseases affect their yield significantly. The aim of this study is to classify bacterial spots and healthy images of bell peppers’ leaf images taken from the PlantVillage dataset using CNN-based pre-trained architecture. Two CNN architectures, i.e., VGG16 and VGG19 are applied through transfer learning in the binary classification of leaf-based disease. A total of 2475 images are used for training, validation, and testing purposes, with 1478 healthy images and 997 images with bacterial disease spots. Although both VGG16 and VGG19 achieved good performances, VGG16 architecture performs slightly better than VGG19.

Why it matches plant phenotyping methodsベルペッパー葉の病斑という植物の病態を画像から分類するCNN手法が研究の中心であり、植物病害フェノタイピングの方法適用に該当する。

abstractThe aim of this study is to classify bacterial spots and healthy images of bell peppers’ leaf images taken from the PlantVillage dataset using CNN-based pre-trained architecture.

BAF-Net: Bidirectional attention fusion network via CNN and transformers for the pepper leaf segmentation. →

The segmentation of pepper leaves from pepper images is of great significance for the accurate control of pepper leaf diseases. To address the issue, we propose a bidirectional attention fusion network combing the convolution neural network (CNN) and Swin Transformer, called BAF-Net, to segment the pepper leaf image. Specially, BAF-Net first uses a multi-scale fusion feature (MSFF) branch to extract the long-range dependencies by constructing the cascaded Swin Transformer-based and CNN-based block, which is based on the U-shape architecture. Then, it uses a full-scale feature fusion (FSFF) branch to enhance the boundary information and attain the detailed information. Finally, an adaptive bidirectional attention module is designed to bridge the relation of the MSFF and FSFF features. The results on four pepper leaf datasets demonstrated that our model obtains F1 scores of 96.75%, 91.10%, 97.34% and 94.42%, and IoU of 95.68%, 86.76%, 96.12% and 91.44%, respectively. Compared to the state-of-the-art models, the proposed model achieves better segmentation performance. The code will be available at the website: https://github.com/fangchj2002/BAF-Net.

Why it matches plant phenotyping methodsペッパー葉画像から葉領域を抽出する画像解析手法を開発・検証しており、植物器官の形態状態取得が研究の中心である。

abstractwe propose a bidirectional attention fusion network combing the convolution neural network (CNN) and Swin Transformer, called BAF-Net, to segment the pepper leaf image.

Tracing Back the History of Pepper (Capsicum annuum) in the Iberian Peninsula from a Phenomics Point of View →

The Iberian Peninsula was the place where pepper (Capsicum annuum) entered Europe and dispersed to other continents but was also an important secondary center for its diversification. The current work evaluated the phenotypic diversity existing in this region and investigated how that evolved from Capsicum native areas (Mexico and Andean Region). For that purpose, the high-throughput phenotyping tool Tomato Analyzer was employed. Descriptors related to size and shape were the most distinctive among fruit types, reflecting a broad diversity for Iberian peppers. These traits likely reflected those suffering from more intensive human selections, driving the worldwide expansion of C. annuum. Iberian peppers maintained close proximity to the American accessions in terms of fruit phenomics. The highest similarities were observed for those coming from the southeastern edge of the Peninsula, while northwestern accessions displayed more significant differences. Common fruit traits (small, conical) suggested that Portuguese and Spanish landraces may have arisen from an ancient American population that entered the south of Spain and promptly migrated to the central and northern territories, giving rise to larger, elongated, and blocky pods. Such lineages would be the result of adaptations to local soil–climate factors prevailing in different biogeographic provinces.

Why it matches plant phenotyping methodsTomato Analyzerを用いた高スループット表現型解析が、ペッパー果実のサイズ・形状多様性を評価する研究の中心であり、方法の実質的な適用に該当する。

abstractFor that purpose, the high-throughput phenotyping tool Tomato Analyzer was employed.

WITHDRAWN: Deep Learning Based Approach for Plant Disease Detection →

Abstract Plant disease detection has a huge impact on plant farming. Early diagnosis of plant illness can help control disease spread and reduce loss. It is a soil-borne disease that affects leaves of plants. In the current research, the emphasis is on the early diagnosis and prevention of plant leaf disease. In this paper, strawberry, tomato, pepper bell, and potato disease detection network (STPP- DDN) based on Faster R-CNN and multi-task learning. STPP-ddn is developed which leverages attention mechanisms in feature extraction. STPP-DDN detects disease based on plant symptoms. Unlike other approaches for diagnosing disease from the total plant look, the STPP-DDN automatically classifies the petioles and young leaves. A large dataset with number of photos divided into various groups is constructed to serve as a basis for analyzing and testing our proposed technique. Each image also includes a label that indicates whether or not the plants has been affected. With the proposed STPP-DDN, we achieved a mAP of 77:54% on object detection of 4 categories and 99:95% accuracy for strawberry verticillium wilt detection.

Why it matches plant phenotyping methods植物病徴を画像から検出・分類する深層学習手法を開発し、データセットと精度評価を提示しており、植物の疾病状態の表現型取得が中心です。撤回表示はあるものの、内容はスクリーニング対象に該当します。

abstractSTPP-DDN detects disease based on plant symptoms.

Non-Destructive Monitoring of Crop Fresh Weight and Leaf Area with a Simple Formula and a Convolutional Neural Network →

Crop fresh weight and leaf area are considered non-destructive growth factors due to their direct relation to vegetative growth and carbon assimilation. Several methods to measure these parameters have been introduced; however, measuring these parameters using the existing methods can be difficult. Therefore, a non-destructive measurement method with high versatility is essential. The objective of this study was to establish a non-destructive monitoring system for estimating the fresh weight and leaf area of trellised crops. The data were collected from a greenhouse with sweet peppers ( Capsicum annuum var. annuum ); the target growth factors were the crop fresh weight and leaf area. The crop fresh weight was estimated based on the total system weight and volumetric water content using a simple formula. The leaf area was estimated using top-view images of the crops and a convolutional neural network (ConvNet). The estimated crop fresh weight and leaf area exhibited average R 2 values of 0.70 and 0.95, respectively. The simple calculation was able to avoid overfitting with fewer limitations compared with the previous study. ConvNet was able to analyze raw images and evaluate the leaf area without additional sensors and features. As the simple calculation and ConvNet could adequately estimate the target growth factors, the monitoring system can be used for data collection in practice owing to its versatility. Therefore, the proposed monitoring system can be widely applied for diverse data analyses.

Why it matches plant phenotyping methods作物の生体重と葉面積を非破壊推定する計測システムの開発が中心であり、画像とCNNによる形質抽出および検証を行っている。

abstractTherefore, a non-destructive measurement method with high versatility is essential.

DIANA: A deep learning-based paprika plant disease and pest phenotyping system with disease severity analysis →

The emergence of deep neural networks has allowed the development of fully automated and efficient diagnostic systems for plant disease and pest phenotyping. Although previous approaches have proven to be promising, they are limited, especially in real-life scenarios, to properly diagnose and characterize the problem. In this work, we propose a framework which besides recognizing and localizing various plant abnormalities also informs the user about the severity of the diseases infecting the plant. By taking a single image as input, our algorithm is able to generate detailed descriptive phrases (user-defined) that display the location, severity stage, and visual attributes of all the abnormalities that are present in the image. Our framework is composed of three main components. One of them is a detector that accurately and efficiently recognizes and localizes the abnormalities in plants by extracting region-based anomaly features using a deep neural network-based feature extractor. The second one is an encoder-decoder network that performs pixel-level analysis to generate abnormality-specific severity levels. Lastly is an integration unit which aggregates the information of these units and assigns unique IDs to all the detected anomaly instances, thus generating descriptive sentences describing the location, severity, and class of anomalies infecting plants. We discuss two possible ways of utilizing the abovementioned units in a single framework. We evaluate and analyze the efficacy of both approaches on newly constructed diverse paprika disease and pest recognition datasets, comprising six anomaly categories along with 11 different severity levels. Our algorithm achieves mean average precision of 91.7% for the abnormality detection task and a mean panoptic quality score of 70.78% for severity level prediction. Our algorithm provides a practical and cost-efficient solution to farmers that facilitates proper handling of crops.

Why it matches plant phenotyping methods画像から植物病害・害虫の位置と重症度を推定する深層学習システムの開発・評価が研究の中心であり、植物の病害状態を直接定量化するため、植物フェノタイピング手法として含める。

abstractwe propose a framework which besides recognizing and localizing various plant abnormalities also informs the user about the severity of the diseases infecting the plant.

A pixel-level coarse-to-fine image segmentation labelling algorithm. →

Fine segmentation labelling tasks are time consuming and typically require a great deal of manual labor. This paper presents a novel method for efficiently creating pixel-level fine segmentation labelling that significantly reduces the amount of necessary human labor. The proposed method utilizes easily produced multiple and complementary coarse labels to build a complete fine label via supervised learning. The primary label among the coarse labels is the manual label, which is produced with simple contours or bounding boxes that roughly encompass an object. All others coarse labels are complementary and are generated automatically using existing algorithms. Fine labels can be rapidly created during the supervised learning of such coarse labels. In the experimental study, the proposed technique achieved a fine label IOU (intersection of union) of 92% in segmenting our newly constructed bean field dataset. The proposed method also achieved 95% and 92% mean IOU when tested on publicly available agricultural CVPPP and CWFID datasets, respectively. Our proposed method of segmentation also achieved a mean IOU of 81% when it was tested on our newly constructed paprika disease dataset, which includes multiple categories.

Why it matches plant phenotyping methods画素レベル画像セグメンテーション手法そのものを開発し、植物・農業およびパプリカ病害データセットで性能評価しているため、植物画像から状態・領域を抽出する方法研究として中心的です。

abstractThis paper presents a novel method for efficiently creating pixel-level fine segmentation labelling

Vegetable Size Measurement Based on Stereo Camera and Keypoints Detection →

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.

Analysis of New RGB Vegetation Indices for PHYVV and TMV Identification in Jalapeño Pepper ( Capsicum annuum ) Leaves Using CNNs-Based Model. →

Recently, deep-learning techniques have become the foundations for many breakthroughs in the automated identification of plant diseases. In the agricultural sector, many recent visual-computer approaches use deep-learning models. In this approach, a novel predictive analytics methodology to identify Tobacco Mosaic Virus (TMV) and Pepper Huasteco Yellow Vein Virus (PHYVV) visual symptoms on Jalapeño pepper ( Capsicum annuum L.) leaves by using image-processing and deep-learning classification models is presented. The proposed image-processing approach is based on the utilization of Normalized Red-Blue Vegetation Index (NRBVI) and Normalized Green-Blue Vegetation Index (NGBVI) as new RGB-based vegetation indices, and its subsequent Jet pallet colored version NRBVI-Jet NGBVI-Jet as pre-processing algorithms. Furthermore, four standard pre-trained deep-learning architectures, Visual Geometry Group-16 (VGG-16), Xception, Inception v3, and MobileNet v2, were implemented for classification purposes. The objective of this methodology was to find the most accurate combination of vegetation index pre-processing algorithms and pre-trained deep- learning classification models. Transfer learning was applied to fine tune the pre-trained deep- learning models and data augmentation was also applied to prevent the models from overfitting. The performance of the models was evaluated using Top-1 accuracy, precision , recall , and F1-score using test data. The results showed that the best model was an Xception-based model that uses the NGBVI dataset. This model reached an average Top-1 test accuracy of 98.3%. A complete analysis of the different vegetation index representations using models based on deep-learning architectures is presented along with the study of the learning curves of these deep-learning models during the training phase.

Why it matches plant phenotyping methods葉の可視症状をRGB画像処理と深層学習で識別する手法を開発・比較しており、植物病害状態の表現型推定が中心である。

abstracta novel predictive analytics methodology to identify Tobacco Mosaic Virus (TMV) and Pepper Huasteco Yellow Vein Virus (PHYVV) visual symptoms on Jalapeño pepper ( Capsicum annuum L.) leaves by using image-processing and deep-learning classification models is presented.

Improved prediction of potassium and nitrogen in dried bell pepper leaves with visible and near-infrared spectroscopy utilising wavelength selection techniques. →

Wet chemistry analysis of agricultural plant materials such as leaves is widely performed to quantify key chemical components to understand plant physiological status. Visible and near-infrared (Vis-NIR) spectroscopy is an interesting tool to replace the wet chemistry analysis, often labour intensive and time-consuming. Hence, this study accesses the potential of Vis-NIR spectroscopy to predict nitrogen (N) and potassium (K) concentration in bell pepper leaves. In the chemometrics perspective, the study aims to identify key Vis-NIR wavelengths that are most correlated to the N and K, and hence, improves the predictive performance for N and K in bell pepper leaves. For wavelengths selection, six different wavelength selection techniques were used. The performances of several wavelength selection techniques were compared to identify the best technique. As a baseline comparison, the partial least-square (PLS) regression analysis was used. The results showed that the Vis-NIR spectroscopy has the potential to predict N and K in pepper leaves with root mean squared error of prediction (RMSEP) of 0.28 and 0.44%, respectively. The wavelength selection in general improved the predictive performance of models for both K and N compared to the PLS regression. With wavelength selection, the RMSEP's were decreased by 19% and 15% for N and K, respectively, compared to the PLS regression. The results from the study can support the development of protocols for non-destructive prediction of key plant chemical components such as K and N without wet chemistry analysis.

Why it matches plant phenotyping methodsVis-NIR分光と波長選択・回帰モデルにより、ベル pepper葉のN・K濃度という植物形質を非破壊推定する方法の開発・比較検証が中心である。

abstractthis study accesses the potential of Vis-NIR spectroscopy to predict nitrogen (N) and potassium (K) concentration in bell pepper leaves.

Viewpoint Planning for Fruit Size and Position Estimation →

Modern agricultural applications require knowledge about the position and size of fruits on plants. However, occlusions from leaves typically make obtaining this information difficult. We present a novel viewpoint planning approach that builds up an octree of plants with labeled regions of interest (ROIs), i.e., fruits. Our method uses this octree to sample viewpoint candidates that increase the information around the fruit regions and evaluates them using a heuristic utility function that takes into account the expected information gain. Our system automatically switches between ROI targeted sampling and exploration sampling, which considers general frontier voxels, depending on the estimated utility. When the plants have been sufficiently covered with the RGB-D sensor, our system clusters the ROI voxels and estimates the position and size of the detected fruits. We evaluated our approach in simulated scenarios and compared the resulting fruit estimations with the ground truth. The results demonstrate that our combined approach outperforms a sampling method that does not explicitly consider the ROIs to generate viewpoints in terms of the number of discovered ROI cells. Furthermore, we show the real-world applicability by testing our framework on a robotic arm equipped with an RGB-D camera installed on an automated pipe-rail trolley in a capsicum glasshouse.

Why it matches plant phenotyping methods果実の位置・サイズという植物器官形質をRGB-Dセンサで取得・推定する視点計画法を開発し、シミュレーションと実環境で検証しており、フェノタイピング手法が中心である。

abstractWe present a novel viewpoint planning approach that builds up an octree of plants with labeled regions of interest (ROIs), i.e., fruits.

Modeling the Dynamic Response of Plant Growth to Root Zone Temperature in Hydroponic Chili Pepper Plant Using Neural Networks →

One of the essential factors in the root zone environment that affects plant growth is temperature. Determining the optimal root zone temperature condition in a hydroponic system during cultivation could lead to an improvement in plant growth. An optimal control strategy can be determined by identifying the eco-physiological process using a dynamic model. However, it is difficult to develop a dynamic model of the responses of plant growth to root zone temperature because the eco-physiological processes of plants are quite complicated. We propose an intelligent approach that can deal with this complex system. Non-linear autoregressive with exogenous input (NARX) neural networks were used to develop a dynamic model of the responses of plant growth to root zone temperature. The responses of chili pepper plant growth as affected by root zone temperature were measured during 60 days of cultivation inside a growth chamber using a non-destructive and continuous system based on a load cell. Five datasets of dynamic responses of plant growth were obtained for system identification. The results suggest that the application of a neural network is useful for modeling the dynamic response of plant growth to root zone temperature in hydroponic cultivation, with promising performance.

Why it matches plant phenotyping methods植物成長を連続・非破壊に測定するロードセル系と、成長応答を推定するNARXニューラルネットワーク動的モデルが研究の中心であり、植物成長という形質の取得・モデル化手法に該当する。

abstractWe propose an intelligent approach that can deal with this complex system. Non-linear autoregressive with exogenous input (NARX) neural networks were used to develop a dynamic model of the responses of plant growth to root zone temperature.

Large Scale Phenotyping Provides Insight into the Diversity of Vegetative and Reproductive Organs in a Wide Collection of Wild and Domesticated Peppers ( Capsicum spp.). →

In the past years, the diversity of Capsicum has been mainly investigated through genetics and genomics approaches, fewer efforts have been made in the field of plant phenomics. Assessment of crop traits with high-throughput methodologies could enhance the knowledge of the plant phenome, giving at the same time a key contribution to the understanding of the function of many genes. In this study, a wide germplasm collection of 307 accessions retrieved from 48 world regions, and belonging to nine Capsicum species was characterized for 54 plant, leaf, flower and fruit traits. Conventional descriptors and semi-automated tools based on image analysis and colour coordinate detection were used. Significant differences were found among accessions, between species and between sweet and spicy cultivated types, revealing a large diversity. The results highlighted how the domestication process and the continued selection have increased the variability of fruit shape and colour. Hierarchical clustering based on conventional and fruit morphological descriptors reflected the separation of species on the basis of their phylogenetic relationships. These observations suggested that the flow between distinct gene pools could have contributed to determine the similarity of the species on the basis of morphological plant and fruit parameters. The approach used represents the first high-throughput phenotyping effort in Capsicum spp. aimed at broadening the knowledge of the diversity of domesticated and wild peppers. The data could help to select best the candidates for breeding and provide new insight into the understanding of the genetic base of the fruit shape of pepper.

Why it matches plant phenotyping methods大規模な植物表現型解析を主題とし、半自動画像解析・色座標検出ツールを用いて植物、葉、花、果実の形質を高スループットに取得しているため、方法の実質的適用に該当する。

abstractAssessment of crop traits with high-throughput methodologies could enhance the knowledge of the plant phenome

Data synthesis methods for semantic segmentation in agriculture: A Capsicum annuum dataset →

This paper provides synthesis methods for large-scale semantic image segmentation datasets of agricultural scenes with the objective to bridge the gap between state-of-the art computer vision performance and that of computer vision in the agricultural robotics domain. We propose a novel methodology to generate renders of random meshes of plants based on empirical measurements, including the automated generation per-pixel class and depth labels for multiple plant parts. A running example is given of Capsicum annuum (sweet or bell pepper) in a high-tech greenhouse. A synthetic dataset of 10,500 images was rendered through Blender, using scenes with 42 procedurally generated plant models with randomised plant parameters. These parameters were based on 21 empirically measured plant properties at 115 positions on 15 plant stems. Fruit models were obtained by 3D scanning and plant part textures were gathered photographically. As reference dataset for modelling and evaluate segmentation performance, 750 empirical images of 50 plants were collected in a greenhouse from multiple angles and distances using image acquisition hardware of a sweet pepper harvest robot prototype. We hypothesised high similarity between synthetic images and empirical images, which we showed by analysing and comparing both sets qualitatively and quantitatively. The sets and models are publicly released with the intention to allow performance comparisons between agricultural computer vision methods, to obtain feedback for modelling improvements and to gain further validations on usability of synthetic bootstrapping and empirical fine-tuning. Finally, we provide a brief perspective on our hypothesis that related synthetic dataset bootstrapping and empirical fine-tuning can be used for improved learning.

Why it matches plant phenotyping methods植物部位のセマンティックセグメンテーション用の合成・実画像データセットと生成手法を開発し、性能比較・検証可能な形で公開しており、植物画像から部位を抽出する方法が中心である。

abstractWe propose a novel methodology to generate renders of random meshes of plants based on empirical measurements, including the automated generation per-pixel class and depth labels for multiple plant parts.

In Vivo Non-Destructive Monitoring of Capsicum Annuum Seed Growth with Diverse NaCl Concentrations Using Optical Detection Technique. →