Practical mixtures of gaussians with brightness monitoring

Stefan Atev, Osama Masoud, Nikolaos P Papanikolopoulos

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

29 Scopus citations

Abstract

We discuss some of the practical issues concerning the use of mixtures of Gaussians for background segmentation in outdoor scenes, including the choice of parameters. Different covariance representations and their performance impact are examined. In addition, we propose a simple, yet efficient method for coping with sudden global illumination changes based on smoothing brightness and contrast changes over time. All of the discussed methods are capable of running in real time at reasonable resolution on current generation PCs.

Original languageEnglish (US)
Title of host publicationProceedings - 7th International IEEE Conference on Intelligent Transportation Systems, ITSC 2004
Pages423-428
Number of pages6
StatePublished - Dec 1 2004
EventProceedings - 7th International IEEE Conference on Intelligent Transportation Systems, ITSC 2004 - Washington, DC, United States
Duration: Oct 3 2004Oct 6 2004

Other

OtherProceedings - 7th International IEEE Conference on Intelligent Transportation Systems, ITSC 2004
CountryUnited States
CityWashington, DC
Period10/3/0410/6/04

Keywords

  • Background segmentation
  • Illumination monitoring
  • Mixture models

Fingerprint Dive into the research topics of 'Practical mixtures of gaussians with brightness monitoring'. Together they form a unique fingerprint.

Cite this