Background Subtraction is one of the vital image handling steps for video surveillance and many computer vision difficulties such as recognition, classification, activity investigation &tracking. Detection of moving objects in video streams is the relevant step of info extraction in several 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 uses k-means comparison for frame change, Approximate Average and Combination 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. After detecting the moving object the Short Message Service (SMS) will send to owner’s mobile. The user can see the images on any remote computer.