Ego-Vehicle Corridors for Vision-Based Driver Assistance

摘要

Improving or generalizing lane detection solutions on curved roads with possibly broken lane marks is still a challenging task. This paper proposes a concept of a (virtual) corridor for modeling the space an ego-vehicle is able to drive through, using available (but often incomplete, e.g., due to occlusion, road conditions, or road intersections) information about the lane marks but also about the motion and relative position (with respect to the road) of the ego-vehicle. A corridor is defined in this paper by special features, such as two fixed starting points, a constant width, and a unique relationship with visible lane marks. Robust corridor detection is possible by hypothesis testing based on maximum a posterior (MAP) estimation, followed by boundary selection, and road patch extension. Obstacles are explicitly considered. A corridor tracking method is also discussed. Experimental results are provided.