Landmark identification based on projective and permutation invariant vectors

We address the issue of environment representation for navigational tasks by using reference scene patterns, the so-called landmarks, to adequately describe the robot's workspace. Mathematical tools from projective geometry are employed for landmark identification. A complete framework is presented for landmark extraction and recognition based on projective and point-permutation invariant vectors.

[1]  Kenichi Kanatani,et al.  Computational projective geometry , 1991, CVGIP Image Underst..

[2]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Ezio Biglieri,et al.  Some properties of singular value decomposition and their applications to digital signal processing , 1989 .

[4]  Russell Greiner,et al.  Learning to Select Useful Landmarks , 1994, AAAI.

[5]  Reiner Lenz,et al.  Efficient Invariant Representations , 1998, International Journal of Computer Vision.

[6]  Panos E. Trahanias,et al.  Visual Recognition of Workspace Landmarks for Topological Navigation , 1999, Auton. Robots.