论文信息 - The Research of Red Light Runners Video Detection Based on Analysis of Tracks of Vehicles

The Research of Red Light Runners Video Detection Based on Analysis of Tracks of Vehicles

The research of red light runners video detecting algorithm is an important research field in computer vision applications. This paper proposes a novel method for red light runners video detecting based on analysis of tracks of vehicles. This method including two steps: obtaining and fit for tracks of vehicles and analysis of red light runners. Our method is simple and effective, as while as can be solved the problem of undetected and error-detected in existing algorithms.

[1] Derek R. Magee,et al. Tracking multiple vehicles using foreground, background and motion models , 2004, Image Vis. Comput..

[2] Larry S. Davis,et al. A Robust Background Subtraction and Shadow Detection , 1999 .

[3] David Beymer,et al. A real-time computer vision system for vehicle tracking and traffic surveillance , 1998 .

[4] Larry S. Davis,et al. Non-parametric Model for Background Subtraction , 2000, ECCV.

[5] N. H. C. Yung,et al. An effective video analysis method for detecting red light runners , 2001, IEEE Trans. Veh. Technol..

[6] Roger D. Boyle,et al. Tracking multiple sports players through occlusion, congestion and scale , 2001, BMVC.

[7] W. Eric L. Grimson,et al. Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[8] Kai-Kuang Ma,et al. A new diamond search algorithm for fast block-matching motion estimation , 2000, IEEE Trans. Image Process..