Motion estimation for human activity surveillance

Abstract

This paper represents the system is based on the identification of human body, object and suspicious activity detection. The survey of videos is important solution for people having priorities in market, buildings, train stations, courts, religious places and airport etc. Video provided as input then it converted into sequence of frames and these frames are used for the detection of object. The contributions for activity observation are proposed. It is challenging task for object tracking and video surveillance and because of illumination changes, quick variations in object appearance, similar non target objects in background and obstacle. The algorithm includes of different steps having video compression, object detection, and object localization. The main advantages of this algorithm are accurately moving object and doubtful activity recognition.