Automated traffic surveillance using fusion of Doppler radar and video information

摘要

Current Continuous Wave (CW) Doppler radar speed measurement systems lack the ability to distinguish multiple targets. Most systems can only identify the strongest (closest) target or the fastest target. In this paper, a traffic surveillance system is presented that is capable of automatically monitoring all vehicle speeds on roadways using sensor fusion on data acquired from a video camera and a CW Doppler radar. First, a higher time-frequency resolution of the radar signal (than a standard FFT) is obtained by employing the method of time-frequency reassignment. Then, the 3D tracking information obtained from the calibrated video camera is fused with the more accurate information from the Doppler radar to produce a position and velocity track of the targets within the surveillance region.