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.

[1]  Gianni Conte,et al.  Automatic Vehicle Guidance: the Experience of the ARGO Autonomous Vehicle , 1999 .

[2]  Allen R. Hanson,et al.  Qualitative obstacle detection , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Olivier Faugeras,et al.  Motion and Structure from Motion in a piecewise Planar Environment , 1988, Int. J. Pattern Recognit. Artif. Intell..

[4]  Allen R. Hanson,et al.  Obstacle Detection Based on Qualitative and Quantitative 3D Reconstruction , 1997, IEEE Trans. Pattern Anal. Mach. Intell..