A Sparsity Constrained Inverse Problem to Locate People in a Network of Cameras

Alahi, AlexandreBoursier, YannickJacques, LaurentVandergheynst, Pierre2009-02-182009-02-182009-02-18200910.1109/ICDSP.2009.5201223https://infoscience.epfl.ch/handle/20.500.14299/35474WOS:000276494500006A 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.Inverse problemSparsityPeople detectionlts2lts4A Sparsity Constrained Inverse Problem to Locate People in a Network of Camerastext::conference output::conference proceedings::conference paper