Background Subtraction Based on Threshold Detection Using Modified K-means Algorithm

In video surveillance systems, background subtraction is the first processing stage and it is used to determine the objects in a particular scene. It is a general term for a process which aims to separate foreground objects from a relatively stationary background. It should be processed in real time. It is obtained in human detection system by computing the variation, pixel-by-pixel, between the current frame and the image of the background, followed by an automatic threshold. This paper proposed a K means based background subtraction for real time video processing in video surveillance. We have analyzed and evaluate the performance of the proposed method, with standard K-means and other background subtractions algorithms. The experimental results showed that the proposed method provides better output.