Connexity based fronto-parallel plane detection for stereovision obstacle segmentation

Progress in hardware makes it possible to compute dense disparity maps in real-time. This work describes a suitable obstacle segmentation method for these dense disparity maps. The method analyses the connexity of the disparity map in order to extract fronto-parallel planes by means of a suitable depth constraint. This pragmatic geometrical approach reduces the number of detection parameters. As a consequence it is easy and intuitive without requiring expert knowledge of the segmentation algorithm. The target application field is Advanced Driving Assistance Systems (ADAS). The performance of the method is illustrated by various results on real image sequences in the context of pedestrian detection.