Real time moving object extraction based on area filling

Abstract

Moving object extraction is the first task for motion detection and recognition. It usually is performed from several frames to distinguish foreground from the background. In this paper we developed a simple extraction method which was suitable for real time application. First, we performed moving object detection by using frames subtraction. This yielded edge label in the motion area. This edge label couldn't extract the whole moving object. To extract the whole moving object, we performed filling operation followed by intersection and union operation to fill the area within the label. The experimental result, our system can extract the moving object in computation time of 116–296 ms, video rate of 15 frames per second (fps) and image frame size of 640×480 pixels, which is suitable for real time application.