Airport runway recognition in complex infrared image using contextual information

Airport runway recognition is of great significance in fields like remote sensing, navigation and traffic monitoring. An airport runway recognition method using the “hypothesize-and-verify” paradigm is proposed. Firstly, local line segments of runway contour are extracted in complex infrared image. Secondly, basing on a new Line Segment Hough Transform, local line segments vote fuzzily in the parameter space to obtain global line segment clustering, and then parallel straight lines are extracted on the basis of parameter space to form hypotheses of potential airport runways. Finally, using contextual information of airport constructions, hypotheses disambiguation and verification of runway is accomplished primarily by extraction of runway markings and segmentation of transportation network, i.e. taxiways and apron. Experimental results demonstrate the good performance of our method on a variety of complex scenes.