CONTRIBUTION OF COLOR TO STEREOSCOPIC STEPS FOR ROAD-OBSTACLE DETECTION

In this article, we present a color stereo vision system conceived to detect road obstacle. And, we highlight the contribution of color by comparing the performance of color-based stereoscopic steps with corresponding gray level based steps. The first step extracts vertical edges points using the operator color declivity. Then, vertical edges points are associated using dynamic programming based on geometric, non-reversal, uniqueness and color photometric constraints. Finally, 3D edges of obstacle are extracted. Performance of segmentation, matching, extraction of 3D edges of obstacle are discussed. Experimental results are shown.