Road detection based on region similarity analysis

Drivable space detection is a key component for autonomous driving and robot road-following. In this paper, we propose a visual-based approach to detect road region in a dynamic environment from a moving camera. In the approach, a free road region candidates are estimated first based on intensity similarity search which using statistical feature analysis (SFA) combined with a breadth-first search (BFS) algorithm to segment different intensity similarity regions in a road image. Then, the similarity between a prior road model by drivers selected and the road region candidates is expressed by a metric derived from the Bhattacharyya distance. Finally, the road region can be identified by voting scores for these similarity measures. The experimental results have shown that the proposed approach can detect road regions in real road scenes.