Local Search as a Tool for Horizon Line Matching.

Abstract : A robust and general local search matching algorithm is used match fragmentary horizon lines. A horizon line model is extracted from a rendered terrain map and is then matched to features extracted from CCD imagery. Such matching is one means of automating vehicle orientation correction: a problem of practical significance for the UGV program. Currently, final orientation correction relating vehicle co-ordinates to terrain map coordinates must be performed manually. Results are presented for actual terrain and image data collected at the UGV Demo C test site.

[1]  Allen R. Hanson,et al.  Extracting Straight Lines , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Tod S. Levitt,et al.  Qualitative Landmark-based Path Planning and Following , 1987, AAAI.

[3]  William Grimson,et al.  Object recognition by computer - the role of geometric constraints , 1991 .

[4]  R. Weiss,et al.  Combinatorial optimization applied to variable scale 2D model matching , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[5]  Gérard G. Medioni,et al.  Map-based localization using the panoramic horizon , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[6]  W. Thompson.  Vision-Based Navigation , 1993 .

[7]  J. Beveridge.  Local search algorithms for geometric object recognition: optimal correspondence and pose , 1993 .

[8]  Carolyn M. Valiquette,et al.  Vision-Based Localization , 1993 .

[9]  William B. Thompson,et al.  Localizing in unstructured environments: dealing with the errors , 1994, IEEE Trans. Robotics Autom..

[10]  J. Beveridge,et al.  Demonstrating polynomial run-time growth for local search matching , 1995, Proceedings of International Symposium on Computer Vision - ISCV.

[11]  J. Beveridge,et al.  Optimal geometric model matching under full 3D perspective , 1995, Proceedings of 1994 IEEE 2nd CAD-Based Vision Workshop.

[12]  Paul S. Schenker,et al.  Sensor Fusion and Networked Robotics VIII , 1995 .

[13]  Allen R. Hanson,et al.  Model-based fusion of FLIR, color, and ladar , 1995, Other Conferences.