Road Detection By Ransac On Randomly Sampled Patches With Slanted Plane Prior

In this paper, an efficient road detection algorithm is proposed. By exploiting the recent progress of fast stereo matching algorithms, the proposed road detection algorithm relies on the accurate semi-dense disparity map only. The RANSAC algorithm is used to compute road plane parameters on randomly sampled disparity patches. Unreliable patches are removed by introducing a road plane slope constraint, and the final road plane model is computed from pixels in a valid patch set. Experimental results show that the proposed method is robust to the illumination variations in real world urban road environments, and can mark road pixels accurately and efficiently on challenging datasets.