Preceding Vehicle Visual Detection and Tracking Based on Template and Shadow Feature
Xiao Hui Zhang, Qing Liu, Yun Hou · Advanced materials research · 2012
As to the vehicle visual detection and tracking problem in IDASWs (Intelligent Driver-Assistance and Safety Warning System), this paper proposed a way of a good effect. Firstly use vehicle’s bottom shadow feature and identified lane result to determine the searching region. Then use template matching algorithm based on vehicle’s tail shape to realize detecting and tracking. Experimental results show that the algorithm can effectively detect and track the preceding vehicle from the video sequence, reaching robust and real-time requirements