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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Practical mixtures of Gaussians with brightness monitoring


    Contributors:


    Publication date :

    2004-01-01


    Size :

    449843 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Density Estimation Using Mixtures of Mixtures of Gaussians

    Abd-Almageed, Wael / Davis, Larry S. | Springer Verlag | 2006

    Free access

    Density Estimation Using Mixtures of Mixtures of Gaussians

    Abd-Almageed, W. / Davis, L. S. | British Library Conference Proceedings | 2006


    A novel robust scene change detection algorithm for autonomous robots using mixtures of gaussians

    Manso, Luis / Núñez, Pedro / Silva, Sidnei da et al. | BASE | 2014

    Free access

    Bounding Multiple Gaussians Uncertainty with Application to Object Tracking

    Zhang, B. / Perina, A. / Li, Z. et al. | British Library Online Contents | 2016


    GOLD: Gaussians of Local Descriptors for image representation

    Serra, G. / Grana, C. / Manfredi, M. et al. | British Library Online Contents | 2015