Real-time traffic parameter extraction using entropy

A vision-based traffic monitoring system that can perform real-time traffic parameter extraction is proposed. The entropy measurement, which is commonly adopted as an important feature to describe the degree of disorder in thermodynamics, is used as an underlying feature in this work. Based on an entropy measurement, a number of important traffic parameters, such as traffic flow, space mean speed and traffic queue, can be determined in real time. The experimental results clearly show that the proposed system is highly effective.