YOLO-based deep learning framework for real-time multi-class plant health monitoring in precision agriculture.

Abstract

Real-time, accurate assessment of crop conditions is key to effective decision-making in precision agriculture. This study proposes an enhanced deep-learning framework that jointly investigates YOLOv8 and the newly released YOLOv11 object-detection architectures for multi-class leaf-health monitoring. A curated dataset of 5000 high-resolution images annotated as healthy, stressed, or damaged was collected across diverse species, growth stages, and lighting conditions. An end-to-end training pipeline was developed featuring extensive geometric, colour, cut-out, and mosaic augmentations; transfer-learning from COCO weights; and GPU-accelerated fine-tuning for 50 epochs. To underpin reproducibility, we provide a compact mathematical formulation (15 equations) that details bounding-box prediction, objectness scoring, class-probability estimation, and the composite CIoU-based loss. On the held-out test set YOLOv11 achieves a mean Average Precision of 93.3% (mAP@0.5) and 76.5% (mAP@0.5:0.95), surpassing YOLOv8 (92.0%/75.2%). Precision–Recall AUC improves from 0.931 to 0.947, while small-object recall rises by 3.4 pp. Inference latency is 15 ms per image on an RTX 3060 (YOLOv11) versus 12 ms for YOLOv8, maintaining real-time throughput (> 60 FPS). An ablation study confirms that full augmentation yields an additional + 1.3 pp mAP gain. Qualitative analyses illustrate tighter bounding boxes and fewer misclassifications between stressed and damaged classes with YOLOv11. These findings demonstrate that YOLOv11’s architectural refinements deliver measurable accuracy gains with only a modest computational overhead, making it preferable where detection fidelity is paramount. Remaining challenges occlusions, visually ambiguous symptoms, and domain shift are analysed, and mitigation strategies (multi-spectral inputs, temporal modelling, and edge-side quantisation) are proposed. The proposed framework, validated with meticulous metrics and consistent mathematical approaches, this framework creates a dependable baseline for AI-driven plant health monitoring in advanced agricultural ecosystems.

Plant phenotyping relevance

植物の葉の健康状態（healthy、stressed、damaged）を画像から推定するYOLOベースの手法を開発・比較し、データセット、学習パイプライン、精度、速度、アブレーションで技術評価しているため、植物フェノタイピング手法が中心である。

Code and data availability

The supplied blocks describe a curated 50,000-image plant health dataset and YOLO training pipeline, but contain no public deposit, repository, or availability statement for the dataset, annotations, code, or trained models. The only URL present is the Creative Commons license notice, which is not a paper-specific phen

No evidence-backed public reproduction asset is currently recorded.