Tracking Ground Vehicles in Heavy-traffic Video by Grouping Tracks of Vehicle Corners
Zuguang Yang, Huadong Meng, Yimin Wei, Hao Zhang, Xiqin Wang · 2007
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.