A Drone-based Automated Halyomorpha halys Scouting: A Case Study on Orchard Monitoring

This paper presents the results of a case study focusing on automating the monitoring process of Halyomorpha halys (HH) in smart agriculture. HH is an invasive global pest that causes significant economic damages to fruit orchards. Our study aims to address the challenges associated with HH scouting, which is traditionally a time-and labor-intensive task. The study concentrates on HALY. ID project achievements of 2022 campaign, where the image acquisition is performed using solely a drone, and exploiting an autonomous drone-based navigation protocol from the top of the orchard. The protocol for the drone involves flying through predefined waypoints and capturing pictures at various tree positions. Moreover, for the sake of simplicity we conducted the detection of HH class only. We performed analyses on the acquired images, including evaluations of both image blurriness and brightness. Then, we obtain encouraging results from YOLOV5 detection algorithms trained on the novel acquired dataset of images. These outcomes show promising potential for automating HH monitoring and mark a significant step towards enhancing smart agriculture practices.