Autonomous indoor object tracking with the Parrot AR.Drone

摘要

This article presents an image-based visual servoing system for indoor visual tracking of 3D moving objects by an Unmanned Aerial Vehicle. This system autonomously follows a 3D moving target object, maintaining it with a fixed distance and centered on its image plane. The initial setup is tested in a detailed simulation environment. The system is then validated on flights in indoor scenarios using the Parrot AR.Drone and the CMT tracker, demonstrating the robustness of the system to differences in object features, environmental clutter, and target trajectory. The obtained results indicate that the proposed system is suitable for complex controls task, such object surveillance and pursuit.