A Novel Vision-based Method for Real-time Extracting Vehicle Flow Information on a Road

Abstract

A novel vision-based method for real time extracting vehicle flow information on a road is proposed in this paper. Two new vision parameters, called as the contrast and luminance distortion ones respectively, are defined and employed to extract the vehicle flow information on the road. The analytical results show that the contrast distortion parameter of a video sequence can restrain the effects of the shadow interferences on the vehicle flow measurements, while the luminance distortion parameter is good for real-time background updating and supplement in order to enhance the accuracy of the measurements. In addition, the unsolved problem of the traditional vision-based methods, failing to distinguish two close consecutive vehicles, can be relaxed to a large extent by combining information from such two parameters. The experimental results from the different roads and vehicle flows under the different whether conditions show that the measurement accuracy of the proposed method is 97.27%.