A New Video-Based Approach to Extract Traffic State Parameters for Traffic Surveillance

Vision-based sensors for traffic surveillance have attracted more attention because of their area sensing ability and flexibility. Conventional methods can be implemented into three steps: selection of regions of interesting (ROI), vehicle detection and vehicle tracking. Possible questions brought by these methods are time costuming and lack of robustness. Different from previous research, a new method based on wavelet transform is proposed. One dimension data set is generated from ROI of one frame in video. Vehicle edge is acquired from characterization of signals from wavelet transform. Then combined geometry characterization and a dynamic criterion using histogram-based method are proposed to eliminate all unwanted shadow. Speed of vehicles is obtained based on detective lines and minimum boundary rectangle (MBR). Experimental results show that the proposed method is more robust and accurate than traditional methods.