Online Tracking of People through a Camera Network

Tracking pedestrians through a network of cameras is a difficult and nuanced problem that is of significant interest in visual surveillance. This paper describes an online system for tracking multiple people as they move around a small camera network with partially-overlapping fields of view. Multi-object tracking is performed on each camera feed resulting in single-camera pedestrian tracks. Multi-camera tracking is then framed as an incremental data assignment of single-camera tracks to multi-camera tracks. Tracks are matched based on their visual similarity alone, a challenging task due to the high variability of a subject's appearance in different cameras. Results are presented on a ground truth data set.

[1]  Bernhard Rinner,et al.  Visual on-line learning in distributed camera networks , 2008, 2008 Second ACM/IEEE International Conference on Distributed Smart Cameras.

[2]  Rhys Hill,et al.  Tracking hand-off in large surveillance networks , 2009, 2009 24th International Conference Image and Vision Computing New Zealand.

[3]  Ramakant Nevatia,et al.  Inter-camera Association of Multi-target Tracks by On-Line Learned Appearance Affinity Models , 2010, ECCV.

[4]  Mubarak Shah,et al.  Modeling inter-camera space-time and appearance relationships for tracking across non-overlapping views , 2008, Comput. Vis. Image Underst..

[5]  Tieniu Tan,et al.  Continuously Tracking Objects Across Multiple Widely Separated Cameras , 2007, ACCV.

[6]  Mei Han,et al.  A detection-based multiple object tracking method , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[7]  M. Shah,et al.  KNIGHT M : A REAL TIME SURVEILLANCE SYSTEM FOR MULTIPLE OVERLAPPING AND NON-OVERLAPPING CAMERAS , 2003 .

[8]  Justin K. Romberg,et al.  Multi-camera tracking on a graph using Markov chain Monte Carlo , 2009, 2009 Third ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC).

[9]  N. Otsu A threshold selection method from gray level histograms , 1979 .

[10]  Ian D. Reid,et al.  Stable multi-target tracking in real-time surveillance video , 2011, CVPR 2011.

[11]  Ramin Zabih,et al.  Bayesian multi-camera surveillance , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[12]  Nicholas J. Redding,et al.  Cross-Matching via Feature Matching for Camera Handover with Non-overlapping Fields of View , 2008, 2008 Digital Image Computing: Techniques and Applications.

[13]  Amit K. Roy-Chowdhury,et al.  Robust Tracking in A Camera Network: A Multi-Objective Optimization Framework , 2008, IEEE Journal of Selected Topics in Signal Processing.

[14]  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).