A Data-Driven Monitoring System for the Early Pest Detection in the Precision Agriculture of Hazelnut Orchards

Abstract

Identifying pests and treating them in a timely manner is a crucial aspect of the Precision Agriculture (PA) paradigm. Driven by the needs of the H2020 European Project Pantheon, focused on precision farming in hazelnut orchards, we propose a pest management system for gall-mites, which cause severe symptoms on generative and vegetative buds. We develop a data-driven monitoring system based on You Only Look Once (YOLO) framework enabling the early detection of the pest infestation with mean average precision of 86.7% on a holdout dataset. We perform a thorough analysis on its performance using several data augmentation methods as well as validate its real-time computation capability on a NVIDIA Jetson Xavier, which can be easily integrated into any robotic platform. Finally, we contextualize the role of the proposed detection framework in a comprehensive pest management system.