Monocular video foreground/background segmentation by tracking spatial-color Gaussian mixture models

Ting Yu*, Cha Zhang, Michael Cohen, Yong Rui, Ying Wu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

68 Scopus citations

Abstract

This paper presents a new approach to segmenting monocular videos captured by static or hand-held cameras filming large moving non-rigid foreground objects. The foreground and background objects are modeled using spatialcolor Gaussian mixture models (SCGMM), and segmented using the graph cut algorithm, which minimizes a Markov random field energy function containing the SCGMM models. In view of the existence of a modeling gap between the available SCGMMs and segmentation task of a new frame, one major contribution of our paper is the introduction of a novel foreground/background SCGMM joint tracking algorithm to bridge this space, which greatly improves the segmentation performance in case of complex or rapid motion. Specifically, we propose to combine the two SCGMMs into a generative model of the whole image, and maximize the joint data likelihood using a constrained Expectation-Maximization (EM) algorithm. The effectiveness of the proposed algorithm is demonstrated on a variety of sequences.

Original languageEnglish (US)
Title of host publication2007 IEEE Workshop on Motion and Video Computing, WMVC 2007
DOIs
StatePublished - Aug 1 2007
Event2007 IEEE Workshop on Motion and Video Computing, WMVC 2007 - Austin, TX, United States
Duration: Feb 23 2007Feb 24 2007

Publication series

Name2007 IEEE Workshop on Motion and Video Computing, WMVC 2007

Other

Other2007 IEEE Workshop on Motion and Video Computing, WMVC 2007
CountryUnited States
CityAustin, TX
Period2/23/072/24/07

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Signal Processing
  • Software

Fingerprint Dive into the research topics of 'Monocular video foreground/background segmentation by tracking spatial-color Gaussian mixture models'. Together they form a unique fingerprint.

Cite this