Stereovision-based Lane Detection and Tracking for Intelligent Vehicles

Abstract

Lane detection is one of the  key issues for intelligent vehicles. In this paper, we present a lane detection approach designed to navigate an autonomous vehicle through challenging traffic scenes based on stereo vision. In the method, both intensity and geometry cues of the road scenes are utilized and integrated for detecting and tracking the targets based on Hidden Markov Models to deal with challenging conditions and situations. It can capture both painted and physical lane boundaries. Furthermore, the geometry relationships between the stereo camera in the moving vehicle and the road are dynamically estimated and calibrated. Therefore, more accuracy and robustness can be expected in the proposed system. Experimental results in various real challenging traffic scenes show the effectiveness of the proposed system.