Recent Advanced Statistical Background Modeling for Foreground Detection - A Systematic Survey

Author(s): Thierry Bouwmans.

Journal Name: Recent Patents on Computer Science

Volume 4 , Issue 3 , 2011

Become EABM
Become Reviewer


Background modeling is currently used to detect moving objects in video acquired from static cameras. Numerous statistical methods have been developed over the recent years. The aim of this paper is firstly to provide an extended and updated survey of the recent researches and patents which concern statistical background modeling and secondly to achieve a comparative evaluation. For this, we firstly classified the statistical methods in terms of category. Then, the original methods are reminded and discussed following the challenges met in video sequences. We classified their respective improvements in terms of strategies used. Furthermore, we discussed them in terms of the critical situations they claim to handle. Finally, we conclude with several promising directions for future research. The survey also discussed relevant patents.

Keywords: Background modeling, Kernel Density Estimation, Mixture of Gaussians, Single Gaussian, Subspace Learning, Foreground Detection, Background Clustering, Background Maintenance, MOG Versions, Background Initialization

Rights & PermissionsPrintExport Cite as

Article Details

Year: 2011
Page: [147 - 176]
Pages: 30
DOI: 10.2174/2213275911104030147
Price: $58

Article Metrics

PDF: 4