A vision-based autonomous detection scheme for obstacles on the runway

In order to detect obstacles on the runway without the ground obstacle detection system, a vision-based autonomous detection scheme is proposed in this paper. An algorithm based on adaptive singular value decomposition and reconstruction (AS VDR) is adopted to identify and segment the runway region accurately by combining Canny operator edge detection algorithm and Hough line detection algorithm. The useful information about the runway and the obstacle which is not on the same plane as the runway can be obtained by an algorithm based on optical flow field. A method based on mixed Gauss background model is used to evaluate the information of the optical flow field in the runway area, and then calculate the confidence level of the obstacle. Through these algorithms, it can put out the final decision of whether to land or not. The experimental results show that the difference of confidence level curves between the runway with obstacles and that without obstacles is large enough to determine whether there are obstacles. The accurate scaled model simulation results show that the scheme is feasible and accurate.