Exploitation of multi-camera configurations for visual surveillance

In this paper, we propose novel methods for background modeling, occlusion handling and event recognition by using multi-camera configurations. Homography-related positions are utilized to construct a mixture of multivariate Gaussians to generate a background model for each pixel of the reference camera. Occlusion handling is achieved by generation of the top-view via trifocal tensors, as a result of matching over-segmented regions instead of pixels. The resulting graph is segmented into objects after determining the minimum spanning tree of this graph. Tracking of multiview data is obtained by utilizing measurements across the views in case of occlusions. Finally, the resulting trajectories are classified by GM-HMMs, yielding better results for using all different trajectories of the same object together.

[1]  L. Davis,et al.  M2Tracker: A Multi-View Approach to Segmenting and Tracking People in a Cluttered Scene , 2003, International Journal of Computer Vision.

[2]  Jitendra Malik,et al.  A real-time computer vision system for measuring traffic parameters , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  Larry S. Davis,et al.  Unified multi-camera detection and tracking using region-matching , 2001, Proceedings 2001 IEEE Workshop on Multi-Object Tracking.

[4]  Michael Harville,et al.  Adaptive video background modeling using color and depth , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[5]  A. Murat Tekalp,et al.  Tracking multiple objects in the presence of articulated and occluded motion , 2000, Proceedings Workshop on Human Motion.

[6]  Dan Schonfeld,et al.  HMM-based motion recognition system using segmented PCA , 2005, IEEE International Conference on Image Processing 2005.

[7]  James Black,et al.  Multi view image surveillance and tracking , 2002, Workshop on Motion and Video Computing, 2002. Proceedings..

[8]  F. Porikli,et al.  Traffic congestion estimation using HMM models without vehicle tracking , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[9]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[10]  Larry S. Davis,et al.  M2Tracker: A Multi-view Approach to Segmenting and Tracking People in a Cluttered Scene Using Region-Based Stereo , 2002, ECCV.

[11]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[12]  Marcus A. Magnor,et al.  Joint 3D-reconstruction and background separation in multiple views using graph cuts , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[13]  Larry S. Davis,et al.  Fast illumination-invariant background subtraction using two views: error analysis, sensor placement and applications , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[14]  Larry S. Davis,et al.  W4: Real-Time Surveillance of People and Their Activities , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  David Eppstein,et al.  Spanning Trees and Spanners , 2000, Handbook of Computational Geometry.

[16]  W. Eric L. Grimson,et al.  Learning Patterns of Activity Using Real-Time Tracking , 2000, IEEE Trans. Pattern Anal. Mach. Intell..