The function of the video capture section is to take input video data from the individual cameras connected in the local area network and each of the cameras is accessed through the different IP address. So, this part basically tells whether the captured video is corrected or any failure in the video capture process. The image analysis part contains all processing tasks related to the image within the captured video to fetch some important information such as motion detection, tracking, classification etc. The image understanding section contains the artificial intelligence techniques for finding out the meaning of the scene among its tasks such as detecting abnormal behavior of human and other moving objects in the scene. The next section is Event generator which receives the abnormal behavior and blows an alarm and helps the image analysis part to tune the image processing tasks to increase the behavior for easier perception and monitoring. The events which are detected and which are based on the abnormal behavior are modeled and stored in the field experience section for easy access and for detection for future [5].