A New Background Subtraction Method in Video Sequences Based on Temporal Motion Windows

Background detection and removal in video sequences for tracking motion objects is an important part of tracking process. It's clear that removal static background leads to tracking motion object and analyzing their movements more accurately. Older techniques for background removal, only use spatial features of image and remove background by focusing on color, texture ..., but newer techniques improve results of background subtraction by using temporal features. In this paper we propose a novel method that uses combination of temporal and spatial features for background removal. In this method we reach to some motion windows by comparing and combining each frame with its neighbors, and obviously points out of these windows are parts of background. Then by other comparisons we detect static parts of motion windows and remove them. One advantage of this method is simplicity and the other is the ability of detection motion objects independent of their size and speed. Furthermore it has no noticeable overhead for real-time tracking process. Keywords– background subtraction, object tracking, temporal features.