Radar-Vision Fusion for Correcting the Position of Target Vehicles

Calculation of the exact coordinate of the target position is a crucial problem in the field of vehicle detection. This paper describes a vehicle detection system fusing radar and vision data which improve the accuracy of positioning. Firstly the calibration problem is introduced which consists of the alignment of time and space. Secondly, we address the problem of object correspondence between vision and radar data. Lastly, the accurately angle difference and distance data between the target vehicle and host vehicle are calculated by vision and radar data, respectively. Experiment results are presented to illustrate the performance of this approach.