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.


Published in:
16th International Conference on Digital Signal Processing
Presented at:
16th International Conference on Digital Signal Processing, Aegean island of Santorini, Greece, July 5-7, 2009
Year:
2009
Publisher:
Aegean island of Santorini, Greece
Keywords:
Laboratories:




 Record created 2009-02-18, last modified 2018-03-18

n/a:
dsp09 - Download fulltextPDF
atoms - Download fulltextJPG
External link:
Download fulltextURL
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)