Real-Time Crop Health Monitoring Using AI-Based Drone Surveillance and YOLOv12

Abstract

Early crop disease detection remains challenging for precision agriculture. This research presents an AI-drone surveillance system using YOLOv12 deep learning model to automatically identify diseases for real-time monitoring in potato, banana, and cotton crops. The complete pipeline includes automated image acquisition, intelligent preprocessing, and real-time analysis. Compared to traditional manual inspection, this approach reduces diagnosis time from days to minutes while improving reliability. Key innovations include optimized model architectures for resource-limited environments and multi-spectral disease pattern recognition. Field tests confirm the system's robustness across varying weather conditions and growth stages. Proposed method processes the drone-captured images through Raspberry Pi edge computing, achieving 99.5%, 98.1%, and 89.7% detection accuracy of potato, banana, and cotton crops respectively. The lightweight YOLO-Nano variants enable efficient field deployment while maintaining precision. A merged dataset across 28 disease classes demonstrates 91.8% overall accuracy through comprehensive validation metrics. Farmers receive immediate alerts for targeted treatment, reducing pesticide use by 30-45% in trial implementations. This scalable solution outperforms existing methods in both speed (4.2ms per image) and accuracy. Results demonstrate practical potential for transforming global agricultural monitoring through accessible AI technology.

Plant phenotyping relevance

植物の病害状態をドローン画像から推定するYOLOベースの取得・解析パイプラインを開発し、圃場で検証しており、表現型取得法が研究の中心である。

Code and data availability

The paper describes crop disease image datasets assembled via Roboflow and YOLOv12 training, but provides no public dataset URL, code repository, model checkpoint deposit, or data availability statement. Supplementary Materials are 'Not applicable.' No paper-specific public asset is actionable.

No evidence-backed public reproduction asset is currently recorded.