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.


Publié dans:
16th International Conference on Digital Signal Processing
Présenté à:
16th International Conference on Digital Signal Processing, Aegean island of Santorini, Greece, July 5-7, 2009
Année
2009
Publisher:
Aegean island of Santorini, Greece
Mots-clefs:
Laboratoires:




 Notice créée le 2009-02-18, modifiée le 2019-03-16

n/a:
dsp09 - Télécharger le documentPDF
atoms - Télécharger le documentJPG
Lien externe:
Télécharger le documentURL
Évaluer ce document:

Rate this document:
1
2
3
 
(Pas encore évalué)