Wasp-Hive Candidate Site Search System Using a Small Drone

Abstract

Early detection of wasp hives is crucial for mitigating their impact on native species, preventing agricultural damage, and improving pest control strategies. Traditional detection methods rely on ground surveys and sensor-based tracking of individual insects, which are often labor-intensive, time-consuming, and prone to errors because of environmental constraints. The integration of artificial intelligence and drone-based imaging has the potential to revolutionize ecological monitoring by providing scalable, efficient, and noninvasive methods for detecting wasp hives. However, research on AI-assisted hive detection remains limited, with most studies focusing on large-scale wildlife monitoring rather than small-object localization. Therefore, we propose a system for searching the candidate site of a wasp hive using a small drone. In the proposed system, a small drone is equipped with a camera and takes aerial images of the error range. Subsequently, three-dimensional (3D) modeling is performed on the captured images using a 3D surveying toolkit, and deep learning–based hive detection is performed on the completed 3D model to extract the GPS information of the detected target.