Stereo vision-based road estimation assisted by efficient planar patch calculation

A robust and accurate road model estimation algorithm can greatly improve the performance of many Advanced Driver Assistance Systems (ADAS) applications such as lane detection, obstacle detection and road marking recognition. To estimate the road model, the proposed algorithm employs a stereo vision camera system. In this paper, local planar patches are efficiently estimated in the disparity domain rather than conventionally in the Euclidean domain. Then, the estimated planar patch orientations are integrated to the fitting stage and orientation differences are minimized along with height differences. Moreover, patch orientation differences are exploited for weighting data points. Thus, outliers become insignificant in the fitting stage and the road model is estimated robustly and accurately without any prior knowledge of any extrinsic camera parameters. Experiments have been carried out for a free space calculation application and the road is segmented with a True Positive Rate (TPR) of 88%.