Investigation of mixture of Gaussians method for background subtraction in traffic surveillance
Boris Nikolov, Nikolay Kostov, Slava Yordanova · International Journal of Reasoning-based Intelligent Systems · 2013
Many background subtraction techniques have been developed in the past years to improve the precision of motion detection in video surveillance systems. Separating the moving objects from the background is a goal in every modern video surveillance system. Mixture of Gaussians (MoG) is one of the most complex methods used for motion detection in video sequences. This paper further investigates the MoG method. The algorithm is implemented in MATLAB and a typical traffic video is estimated. The accuracy of the algorithm is measured as a function of each variable parameter. An optimal set of parameters along with a filter are proposed in order to increase the performance.