Tracking Pedestrians Under Occlusion Using Multiple Cameras

This paper presents a integrated solution to track multiple non-rigid objects (pedestrians) in a multiple cameras system with ground-plane trajectory prediction and occlusion modelling. The resulting system is able to maintain the tracking of pedestrians before, during and after occlusion. Pedestrians are detected and segmented using a dynamic background model combined with motion detection and brightness and color distortion analysis. Two levels of tracking have been implemented: the image level tracking and the ground-plane level tracking. Several target cues are used to disambiguate between possible candidates of correspondence in the tracking process: spacial and temporal estimation, color and object height. A simple and robust solution for image occlusion monitoring and grouping management is described. Experiments in tracking multiple pedestrians in a dual camera setup with common field of view are presented.

[1]  J. Crowley,et al.  Multi-Modal Tracking of Interacting Targets Using Gaussian Approximations , 2001 .

[2]  Larry S. Davis,et al.  Hydra: multiple people detection and tracking using silhouettes , 1999, Proceedings 10th International Conference on Image Analysis and Processing.

[3]  Anurag Mittal,et al.  Video Analysis under Severe Occlusions , 2002 .

[4]  Gideon P. Stein,et al.  Tracking from multiple view points: Self-calibration of space and time , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[5]  Michael J. Swain,et al.  Color indexing , 1991, International Journal of Computer Vision.

[6]  Leonidas J. Guibas,et al.  Counting people in crowds with a real-time network of simple image sensors , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[7]  Shaogang Gong,et al.  Tracking colour objects using adaptive mixture models , 1999, Image Vis. Comput..

[8]  Azriel Rosenfeld,et al.  Tracking Groups of People , 2000, Comput. Vis. Image Underst..

[9]  Shaogang Gong,et al.  Bayesian Modality Fusion for Tracking Multiple People with a Multi-Camera System , 2002 .

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

[11]  David Harwood.  A statistical approach for real time robust background subtraction , 1999 .

[12]  Tim J. Ellis,et al.  Multi camera image tracking , 2006, Image Vis. Comput..

[13]  Mubarak Shah,et al.  Human Tracking in Multiple Cameras , 2001, ICCV.

[14]  Gérard G. Medioni,et al.  Continuous tracking within and across camera streams , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[15]  Ramakant Nevatia,et al.  Segmentation and tracking of multiple humans in complex situations , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[16]  Y. Bar-Shalom.  Tracking and data association , 1988 .

[17]  Paolo Remagnino,et al.  Automated registration of surveillance data for multi-camera fusion , 2002, Proceedings of the Fifth International Conference on Information Fusion. FUSION 2002. (IEEE Cat.No.02EX5997).

[18]  Takeo Kanade,et al.  A System for Video Surveillance and Monitoring , 2000 .

[19]  Isaac Cohen,et al.  Continuous multi-views tracking using tensor voting , 2002, Workshop on Motion and Video Computing, 2002. Proceedings..

[20]  Jake K. Aggarwal,et al.  Automatic tracking of human motion in indoor scenes across multiple synchronized video streams , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[21]  François Brémond,et al.  Tracking multiple nonrigid objects in video sequences , 1998, IEEE Trans. Circuits Syst. Video Technol..