A simple linear method to obtain height ordering of scene points

We present a novel algorithm to extract height ordering information for points relative to the ground plane. The ordering of scene points is obtained by exploiting the idea of linearly invariant representation of space points, image points, and the optical center of the camera, from which we derive a measure that is monotonic with respect to the height of points relative to the ground plane. We present results of the algorithm on data obtained from a mobile robot.

[1]  Andrew Blake,et al.  Quantitative planar region detection , 2004, International Journal of Computer Vision.

[2]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[3]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[4]  Ian D. Reid,et al.  Duality, Rigidity and Planar Parallax , 1998, ECCV.

[5]  O. Faugeras.  Three-dimensional computer vision: a geometric viewpoint , 1993 .

[6]  Stefan Carlsson,et al.  Duality of reconstruction and positioning from projective views , 1995, Proceedings IEEE Workshop on Representation of Visual Scenes (In Conjunction with ICCV'95).

[7]  Nicola J. Ferrier,et al.  Plane based relative structure recovery , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).