A Method of Vision-Based State Estimation of an Unmanned Helicopter

This paper presents a real-time algorithm of accurately identifying helipad and estimating the state information for landing an unmanned aerial helicopter autonomously via computer vision. The algorithm estimates the instantaneous attitude and position parameters of the helicopter relative to the helipad from continuously tracked points using the optical flow method. The vision system, consisting of a calibrated monocular camera, a helipad and an experiment platform, can perform image processing, helipad recognition, feature extraction, target tracking and motion estimation. The experimental results show that the algorithm is accuracy, robust and fast.