Automated Soybean Crop Health Evaluation from UAV Images Using Patch Level CNNs

Abstract

Abstract - The rapid advancement of unmanned aerial vehicles (UAVs) and deep learning techniques has significantly transformed crop monitoring and precision agriculture. Among various crops, soybean plays a crucial role in global food and oilseed production, making timely and accurate crop health assessment essential. This review presents a comprehensive analysis of UAV-based soybean crop health evaluation methods, with a particular focus on image-based disease detection and stress monitoring using deep learning models. Recent progress in convolutional neural networks, patch-level image analysis, attention mechanisms, and lightweight architectures is systematically examined. The paper discusses commonly used UAV imaging modalities, preprocessing strategies, model architectures, and evaluation practices reported in the literature. Furthermore, existing challenges such as environmental variability, computational complexity, data imbalance, and real-world deployment constraints are critically analyzed. Based on the reviewed studies, potential research directions are identified, emphasizing efficient patch-level learning, interpretable health mapping, and scalable field-level assessment. This review aims to provide researchers and practitioners with a clear understanding of current trends, limitations, and future opportunities in UAV-assisted soybean crop health monitoring. Key Words: - Unmanned Aerial Vehicles (UAVs), Soybean Crop Health Monitoring, Precision Agriculture, Deep Learning

Plant phenotyping relevance

UAV画像と深層学習によるダイズの病害・ストレス評価手法を体系的にレビューしており、植物状態の画像ベース取得・推定方法が中心である。

Code and data availability

This is a review-style paper describing a proposed UAV/patch-level CNN framework for soybean crop health assessment. No public phenotype/trait datasets, UAV images, author analysis code, trained models, or supplements with such assets are mentioned. All datasets and methods referenced are cited prior work, and no data-

No evidence-backed public reproduction asset is currently recorded.