Suspicious Motion Detection and Tracking Based on Histogram

Abstract

Video surveillance systems are becoming important for crime investigation and the number of cameras installed in public space is increasing. Detection of suspicious human behavior is of great practical importance. Due to irregular nature of human movements, reliable classification of distrustful human movements can be very difficult. Defining a way to the problem of automatically track down the people and detecting unusual or distrustful movements in Closed Circuit TV (CCTV) videos is our primary aim. We are proposing a system that works for close observation systems installed in indoor environments like entrances/exits of buildings, corridors, etc. Our work presents a structure that processes video data obtained from a CCTV camera fixed at a particular location. The development of an Android application which interprets the message a mobile device receives on possible interruption and subsequently a reply (Short Message Service) SMS which prompt an alarm/buzzer in the remote house making others aware of the possible interruption.  Using threshold value the detected pixel is recognized. Hence the movement of the object is identified exactly. After motion detection it will send GCM alert to the android mobile application.