Real-time, GPU-based pose estimation of a UAV for autonomous takeoff and landing
Authors:
- 1 May 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3463-3470
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.Keywords
This publication has 16 references indexed in Scilit:
- A mobile self-leveling landing platform for VTOL UAVs2015
- Autonomous landing system for aerial mobile robot cooperation2014
- Autonomous navigation, landing and recharge of a quadrotor using artificial vision2014
- A survey of autonomous landing techniques for UAVs2014
- Camera tracking using concentric circle markers: Paradigms and algorithms2012
- A GPU accelerated real-time self-contained visual navigation system for UAVs2012
- Height estimation via stereo vision system for unmanned helicopter autonomous landing2010
- A Robust Circular Fiducial Detection Technique and Real-Time 3D Camera TrackingJournal of Multimedia, 2008
- Parallel Tracking and Mapping for Small AR Workspaces2007
- Landing on a Moving Target Using an Autonomous Helicopter2006