Tracking Ground Vehicles in Heavy-traffic Video by Grouping Tracks of Vehicle Corners

Tracking vehicles in heavy-traffic video is a challenging problem. It is hard for algorithms based on background extraction to work well. We propose an algorithm that does not need background information. In this algorithm, vehicle corners are detected and tracked, and then grouped into vehicles. Experiments show the effectiveness of the proposed algorithm under heavy congestion.

[1]  Luigi di Stefano,et al.  Occlusion Robust Vehicle Tracking based on SOM (Self-Organizing Map) , 2005, 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1.

[2]  Shrinivas J. Pundlik,et al.  Vehicle segmentation and tracking from a low-angle off-axis camera , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[3]  Wayne A Sarasua,et al.  Vehicle Segmentation and Tracking in the Presence of Occlusions , 2006 .

[4]  Yo-Sung Ho,et al.  A Feature-Based Vehicle Tracking System in Congested Traffic Video Sequences , 2001, IEEE Pacific Rim Conference on Multimedia.

[5]  Luigi di Stefano,et al.  Using local and global object's information to track vehicles in urban scenes , 2005, IEEE Conference on Advanced Video and Signal Based Surveillance, 2005..

[6]  Jitendra Malik,et al.  A real-time computer vision system for measuring traffic parameters , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.