Background modeling in video surveillance by using parallel computing

Abstract

In the last years, the research of extraction the movable object from video sequence in application of computer vision become wide spread and well-known . in this paper the extraction of background model by using parallel computing is done by two steps : the first one using non-linear buffer to extraction frame from video sequence depending on the number of frame whether it is even or odd . the goal of this step is obtaining initial background when over half of training sequence contains foreground object . in the second step , The execution time of the traditional K-mean has been improved to obtain initial background through perform the k-mean by using parallel computing where the time has been minimized to 50% of the conventional time of k-mean .