Current studentsExisting staffContact us
 

Smooth foreground-background segmentation for video processing

Simple item page
dc.contributor.authorSchindler, K.
dc.contributor.authorWang, H.
dc.contributor.conferenceAsian Conference on Computer Vision (7th : 2006 : Hyderabad, India)
dc.date.issued2006
dc.description© Springer-Verlag Berlin Heidelberg 2006
dc.description.abstractWe propose an efficient way to account for spatial smoothness in foreground-background segmentation of video sequences. Most statistical background modeling techniques regard the pixels in an image as independent and disregard the fundamental concept of smoothness. In contrast, we model smoothness of the foreground and background with a Markov random field, in such a way that it can be globally optimized at video frame rate. As a background model, the mixture-of-Gaussian (MOG) model is adopted and enhanced with several improvements developed for other background models. Experimental results show that the MOG model is still competitive, and that segmentation with the smoothness prior outperforms other methods.
dc.description.statementofresponsibilityKonrad Schindler and Hanzi Wang
dc.identifier.citationComputer Vision – ACCV 2006: 7th Asian Conference on Computer Vision Hyderabad, India, January 13-16, 2006, Proceedings, Part II / P.J. Narayanan, Shree K. Nayar, Heung-Yeung Shum (eds.), pp.581-590
dc.identifier.doi10.1007/11612704_58
dc.identifier.isbn3540312196
dc.identifier.isbn9783540312444
dc.identifier.issn0302-9743
dc.identifier.issn1611-3349
dc.identifier.urihttp://hdl.handle.net/2440/56254
dc.language.isoen
dc.publisherSpringer
dc.publisher.placeBerlin
dc.relation.ispartofseriesLecture Notes in Computer Science, 2006; 3851: 581-590
dc.source.urihttp://dx.doi.org/10.1007/11612704_58
dc.titleSmooth foreground-background segmentation for video processing
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Computer Science publications