Practical mixtures of Gaussians with brightness monitoring
Stefan Atev, Osama Masoud, Nikos Papanikolopoulos · 2005
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.