Road Segmentation Supervised by an Extended V-Disparity Algorithm for Autonomous Navigation

This paper presents an original approach of road segmentation supervised by stereovision. It deals with free space estimation by stereovision and road detection by color segmentation. The v-disparity algorithm is extended to provide a reliable and precise road profile on all types of roads. The free space is estimated by classifying the pixels of the disparity map. This classification is performed by using the road profile and the u-disparity image. Then a color segmentation is performed on the free space. Here is the supervision. Each stage of the algorithm is presented and experimental results are shown.