Runway extraction method based on rotating projection for UAV

Abstract

We bring out a runway extraction method based on rotating projection in this paper, which is consisted of three steps, locating the Region of interest (ROI), edge extraction and line detection. Firstly we employed template matching to locate the ROI which contains the runway area. Then we use Sobel operator to extract edges. The rotating projection algorithm is proposed to seek the potential straights in ROI, which will be integrated into the real straights by means of improved K-means clustering method. Simulations are carried out in the end, and results show that the algorithm proposed in this paper can extract the four boundaries of the runway effectively, while it can reduce 50% of computing time compared with Hough transform.