Computer vision based real-time information acquisition for transport traffic

This paper presents a low-cost computer vision system for real time traffic monitoring. The prototype built up simply consists of a PC (or a laptop) and a web-cam camera. The hardware configuration, the software structure and the basic image processing algorithms are presented. The prototype was tested in real scene under different nature lighting conditions and showed reasonable results. After an evaluation on the results obtained, the further work needed to improve the robustness of the system is given.