Road boundary detection using segmentation on stereo images

Abstract

In this paper, a road detection method based on an  image segmentation and stereo vision is presented. Road detection process is a key issue for an autonomous  driving system in urban environment. Image-based road detection algorithm is applied on sources of visual information recorded by stereo cameras when our car is running on road. Our method combines a posteriori probability and visual information for image segmentation. The depth map in stereo camera is calculated on real time by a circuit board and it is utilized to rectify the boundary on left and right side of road. The method is composed of threesteps.  Firstly, a road identifier is trained with supervised learning algorithm. Secondly, road regions are detected  by combining a posteriori probability and visual information using image  segmentation  algorithm.  In  the  last step,  the  segmentation  result  is  combined  with the depth-map image to correct the boundary. Experimental results are presented for video sequences of road in urban areas.