Learning based obstacle detection with uncalibrated cameras

In this paper, we present a simple method to detect obstacles, which is qualitative in that it returns only yes/no answers regarding the presence of obstacles in the field of view. The method is based on the difference of disparity between the ground plane and non-ground plane. The two main features of the method are: neither the camera internal parameters nor the external calibration information is required; and does not need to find the corresponding point in the stereo pair images. Some constructive results are presented.