Real time Background Subtraction techniques for detection of moving objects in video surveillance system

Background Subtraction is one of the important image processing steps for video surveillance and many computer vision problems such as recognition, classification, activity analysis & tracking. Detection of moving objects in video streams is the first relevant step of information extraction in many computer vision applications. This paper deals with the performance of different techniques of Background Subtraction. Mainly there are three features has been extracted from each moving objects such as centroid, area, average luminance. The proposed approach compare the Frame difference, Approximate Median and Mixture of Gaussian method and this attempt proves that the chosen method has good performance under dynamic circumstances for real time tracking. Finally the similarity function is applied to tracking.