IoT-Based Pest Detection in Agriculture Using Raspberry Pi and YOLOv10m for Precision Farming

Abstract

The agricultural sector confronts challenges arising from climate change and evolving global trade, emphasizing the critical need for effective pest management to sustain crop yields. This study introduces an innovative pest detection and monitoring approach, centering on the Codling Moth (Cydia pomonella) as a model insect. The system seamlessly integrates a Raspberry Pi-based trap, the YOLOv10m (You Only Look Once) deep learning model, and the Ubidots IoT platform. The YOLOv10m model, renowned for its real-time object detection capabilities, undergoes training to identify Codling Moths in images captured by the trap. Subsequently, the model-generated data is transmitted to the Ubidots platform, facilitating remote real-time monitoring. The Ubidots dashboard encompasses features like data analysis, historical trends, and notification alerts for elevated pest densities. Results underscore the YOLOv10m model’s impressive 89% confidence level in detecting Codling Moths. The Ubidots platform enhances overall system performance, enabling farmers to monitor pest activity and intervene promptly. This integrated system fosters informed decision-making, curtails excessive pesticide use, and advocates sustainable farming practices. Ultimately, this research makes a substantial contribution to precision agriculture by harnessing the synergies of deep learning and IoT technologies, delivering a dependable and cost-effective solution for managing pest populations in agriculture.