Terminal Phase Vision-Based Target Recognition and 3D Pose Estimation for a Tail-Sitter, Vertical Takeoff and Landing Unmanned Air Vehicle

摘要

This paper presents an approach to accurately identify landing targets and obtain 3D pose estimates for vertical takeoff and landing unmanned air vehicles via computer vision methods. The objective of this paper is to detect and recognize a pre-known landing target and from that landing target obtain the 3D attitude information of the flight vehicle with respect to the landing target using a single image. The Hu's invariant moments' theorem is used for target identification and parallel lines of the target shape are investigated to obtain the flight vehicle orientation. Testing of the proposed methods is carried out on flight images obtained from a camera onboard a tail-sitter, vertical takeoff and landing unmanned air vehicle.