Automated traffic surveillance using fusion of Doppler radar and video information

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.

[1]  Sharath Pankanti,et al.  Appearance models for occlusion handling , 2006, Image Vis. Comput..

[2]  Chandrika Kamath,et al.  Robust techniques for background subtraction in urban traffic video , 2004, IS&T/SPIE Electronic Imaging.

[3]  François Auger,et al.  Time-Frequency Reassignment: From Principles to Algorithms , 2018, Applications in Time-Frequency Signal Processing.

[4]  Patrick Flandrin,et al.  Improving the readability of time-frequency and time-scale representations by the reassignment method , 1995, IEEE Trans. Signal Process..

[5]  Sean A. Fulop,et al.  A Unified Theory of Time-Frequency Reassignment , 2009, ArXiv.

[6]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Greg Welch,et al.  An Introduction to Kalman Filter , 1995, SIGGRAPH 2001.

[8]  K. Kodera,et al.  Analysis of time-varying signals with small BT values , 1978 .

[9]  R. E. Kalman,et al.  A New Approach to Linear Filtering and Prediction Problems , 2002 .

[10]  P.D. Fisher.  Improving on police radar , 1992, IEEE Spectrum.

[11]  Lang Hong,et al.  Fusion of Doppler Radar and video information for automated traffic surveillance , 2009, 2009 12th International Conference on Information Fusion.

[12]  Jitendra Malik,et al.  Traffic Surveillance And Detection Technology Development: New Traffic Sensor Technology Final Report , 1997 .

[13]  H. Opower.  Multiple view geometry in computer vision , 2002 .

[14]  Deepak Gopalakrishna,et al.  ADVANCES IN TRAFFIC DATA COLLECTION AND MANAGEMENT. REV. , 2003 .

[15]  Daniel J. Dailey,et al.  An algorithm to estimate vehicle speed using uncalibrated cameras , 1999, Proceedings 199 IEEE/IEEJ/JSAI International Conference on Intelligent Transportation Systems (Cat. No.99TH8383).

[16]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[17]  Malcolm D. Macleod,et al.  Time Frequency Reassignment: A Review and Analysis , 2003 .

[18]  Shrinivas J. Pundlik,et al.  Vehicle segmentation and tracking from a low-angle off-axis camera , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).