Foreground detection of moving object using Gaussian mixture model

Abstract

The segmentation/Detection of a moving object is one of the important step in computer vision application, such as remote sensing, medical imaging, traffic surveillance, machine/robot vision, microscopic imaging etc. In this paper "Gaussian Mixture model" for background subtraction/foreground detection has been applied which computes a foreground mask on a moving object (which is either the color video frame or series of a gray scale image). The blob analyzer has also been used to calculate statistics of identified region in a binary image. The result shows that the proposed algorithm can detect the moving object effectively while occluded by the box.