Current studentsExisting staffContact us
 

Robust Foreground Segmentation Based on Two Effective Background Models

Simple item page
dc.contributor.authorLi, X.
dc.contributor.authorHu, W.
dc.contributor.authorZhang, Z.
dc.contributor.authorZhang, X.
dc.contributor.conferenceACM International Conference on Multimedia Information Retrieval (1st : 2008 : Vancouver, Canada)
dc.date.issued2008
dc.description.abstractForeground segmentation is a common foundation for many computer vision applications such as tracking and behavior analysis. Most existing algorithms for foreground segmentation learn pixel-based statistical models, which are sensitive to dynamic scenes such as illumination change, shadow movement, and swaying trees. In order to address this problem, we propose two block-based background models using the recently developed incremental rank-(R1, R2, R3) tensor-based subspace learning algorithm (referred to as IRTSA [1]). These two IRTSA-based background models (i.e., IRTSAGBM and IRTSA-CBM respectively for grayscale and color images) incrementally learn low-order tensor-based eigenspace representations to fully capture the intrinsic spatio-temporal characteristics of a scene, leading to robust foreground segmentation results. Theoretic analysis and experimental evaluations demonstrate the promise and effectiveness of the proposed background models.
dc.description.statementofresponsibilityXi Li, Weiming Hu, Zhongfei Zhang, Xiaoqin Zhang
dc.description.urihttp://press.liacs.nl/mir2008/index.html
dc.identifier.citationMM’08 : Proceedings of the 2008 ACM International Conference on Multimedia, with co-located Symposium & Workshops Vancouver, BC, Canada, October 27–31, 2008 / pp.223-228
dc.identifier.doi10.1145/1460096.1460133
dc.identifier.isbn9781605583129
dc.identifier.urihttp://hdl.handle.net/2440/67306
dc.language.isoen
dc.publisherACM Press
dc.publisher.placeNew York
dc.rightsCopyright 2008 ACM
dc.source.urihttps://doi.org/10.1145/1460096.1460133
dc.subjectVideo surveillance
dc.subjectobject detection
dc.titleRobust Foreground Segmentation Based on Two Effective Background Models
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Computer Science publications