Real-time, GPU-based pose estimation of a UAV for autonomous takeoff and landing

Abstract

This paper proposes a real-time system for pose estimation of an Unmanned Aerial Vehicle (UAV) using parallel image processing of a known marker. The system exploits the capabilities of a high-performance CPU/GPU embedded system in order to provide on-board high-frequency pose estimation, eliminating the need for transmitting the video stream off-board, and enabling autonomous takeoff and landing. The system is evaluated extensively with lab and field tests on board a small quadrotor. The results show that the proposed system is able to provide precise pose estimation with a framerate of at least 30 fps and an image resolution of 640×480 pixels. The use of the GPU for image filtering and marker detection provides an upper bound on the required computation time regardless of the complexity of the image thereby allowing for robust marker detection even in cluttered environments.