A vision-based vehicle matching system

This paper describes a machine vision system that is able to match vehicles based on their color and shape (edge) attributes. The matching results enable the authors to estimate the travel time between two points on a road network. The system was tested on real video data that was collected in Michigan. The authors show that the travel time estimates obtained by their vision system are comparable to results that were obtained by a manual review of the video tapes.

[1]  George C. Stockman,et al.  Object recognition and localization via pose clustering , 1987, Comput. Vis. Graph. Image Process..

[2]  Anil K. Jain,et al.  A modified Hausdorff distance for object matching , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[3]  Y. Tanaka.  Travel-time data provision system using vehicle license number recognition devices , 1992, Proceedings of the Intelligent Vehicles `92 Symposium.

[4]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Anil K. Jain,et al.  2D matching of 3D moving objects in color outdoor scenes , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Paul W. Shuldiner,et al.  USING VIDEO TECHNOLOGY TO CONDUCT 1991 BOSTON REGION EXTERNAL CORDON SURVEY , 1993 .