抽象的

Vehicle Speed Estimation Using Headlight Trajectory Information in Night Time

Cindia V Anand, V. Janani

Traffic surveillance plays an important role in computer vision and intelligent transportation systems. However most of the methods concentrate on the day time traffic monitoring. This paper gets a night time traffic surveillance image as its input. The night time traffic surveillance system consists of headlight detection, headlight tracking and pairing, and camera calibration and vehicle speed estimation. First, the headlight detection is done by extracting two features reflection intensity map and reflection suppressed map based on the analysis of light attenuation model. Second, the headlight is tacked and paired using yet effective bidirectional reasoning algorithm. Finally, the trajectory of vehicles headlight is employed to calibrate the surveillance camera and computes the vehicle’s speed. The proposed method can robustly detect and pair the vehicles headlight in night scene and the speed of the vehicle can also be calibrated.