Traffic Parameters Detection Based on Video Virtual-loop Technologies

摘要

Traffic parameters are critical for traffic management system and traffic control. This paper is focused on developing a flexible and reliable system to detect the traffic parameters through image sequences. Image data are converted to digital string signals by virtual-loops. Through detecting and tracking the digital strings, vehicle's spatial-temporal features are extracted. In the end, multiple criteria and multistage decision are used to report the parameters of traffic load, traffic velocity and vehicle classification. The real-time prototype system is implemented on a computer. Experimental results illustrate the detection accuracy.