Motion detection is the first essential process in the extraction of information regarding moving objects and makes use of stabilization in functional areas, such as patient monitoring, & so on. Automatic detection of patient monitoring are the fundamental tasks of video-based surveillance systems. Higher level patient monitoring procedures based upon these essential video analysis tasks. Video analysis task is essential in order to save the memory size of the recorded video in database which becomes a problem due to it large size in the previous generation of video surveillance system. The purpose of this project is to design a surveillance system which would detect motion in a live video feed and record the video feed only at the moment where the motion was detected based on background subtraction using video surveillance. The movement of patient is identified using the image subtraction method. The background image is subtracted from the foreground image. From that the moving object is derived. This software was connected to the USB web camera to receive the live feed video.