Forward stereo obstacle detection with Weighted Hough Transform and local temporal correlation

In this paper, we propose a robust obstacle detection approach by leveraging Weighted Hough Transform (WHT) in combination with temporal information correlation from the stereo video sequences. First, to model the road surface or obstacles in the video, rather than using simple threshold from binarized frame sequence, we propose to adopt WHT to extract the linear relation from the v-disparity map. Second, we exploit the temporal correlation of the road surface profile in stereo video sequences to produce the stable road surface model by filtering out the unreliable road. Extensive experiments with comparisons to state-of-the-arts demonstrate the merit of the proposed approach.