A sparsity constrained inverse problem to locate people in a network of cameras

A novel approach is presented to locate dense crowd of people in a network of fixed cameras given the severely degraded background subtracted silhouettes. The problem is formulated as a sparsity constrained inverse problem using an adaptive dictionary constructed on-line. The framework has no constraint on the number of cameras neither on the surface to be monitored. Even with a single camera, partially occluded and grouped people are correctly detected and segmented. Qualitative results are presented in indoor and outdoor scenes.

[1]  Volkan Cevher,et al.  Distributed target localization via spatial sparsity , 2008, 2008 16th European Signal Processing Conference.

[2]  P. L. Combettes,et al.  Solving monotone inclusions via compositions of nonexpansive averaged operators , 2004 .

[3]  Dmitry M. Malioutov,et al.  A sparse signal reconstruction perspective for source localization with sensor arrays , 2005, IEEE Transactions on Signal Processing.

[4]  Yoichi Muraoka,et al.  A panorama-based technique for annotation overlay and its real-time implementation , 2000, 2000 IEEE International Conference on Multimedia and Expo. ICME2000. Proceedings. Latest Advances in the Fast Changing World of Multimedia (Cat. No.00TH8532).

[5]  Mubarak Shah,et al.  A Homographic Framework for the Fusion of Multi-view Silhouettes , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[6]  Paolo Remagnino,et al.  A multi-agent framework for visual surveillance , 1999, Proceedings 10th International Conference on Image Analysis and Processing.

[7]  Mubarak Shah,et al.  A Multiview Approach to Tracking People in Crowded Scenes Using a Planar Homography Constraint , 2006, ECCV.

[8]  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).

[9]  Volkan Cevher,et al.  Compressed sensing for multi-view tracking and 3-D voxel reconstruction , 2008, 2008 15th IEEE International Conference on Image Processing.

[10]  Pascal Fua,et al.  Multicamera People Tracking with a Probabilistic Occupancy Map , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Denis Simakov,et al.  Feature-Based Sequence-to-Sequence Matching , 2006, International Journal of Computer Vision.

[12]  Bhaskar D. Rao,et al.  Sparse signal reconstruction from limited data using FOCUSS: a re-weighted minimum norm algorithm , 1997, IEEE Trans. Signal Process..

[13]  Fatih Murat Porikli,et al.  Achieving real-time object detection and tracking under extreme conditions , 2006, Journal of Real-Time Image Processing.

[14]  Shai Avidan,et al.  Ensemble Tracking , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Aljoscha Smolic,et al.  Multi-texture modeling of 3D traffic scenes , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[16]  Stephen P. Boyd,et al.  Enhancing Sparsity by Reweighted ℓ1 Minimization , 2007, 0711.1612.