Road tracking by Parallel Angular Texture Signature

Abstract

Road tracking is a promising technique to increase the efficiency of road mapping. In this paper, a new semi-automatic road tracker, parallel angular texture signature (PATS) is presented. The tracker is object-oriented in some sense, because it makes best use of the texture signature of road primitives on high-resolution remotely sensed imagery. Our tracker uses parabola to model the road trajectory and predict the position of next road centreline point. It employs parallel angular texture signature (PATS) to get the moving direction of current road centreline point, and it will move on one predefined step along the direction to reach a new position, and then it uses curvature change to verify the newly added road point. We also build compactness of Angular Texture Signature polygon to check whether the parallel angular texture signature (PATS) is suitable for tracking. Extensive experiments demonstrate that the proposed tracker reliably extracts ribbon roads from high resolution optical imagery even in very complex scenes.