A New Approach to Detect Anomalous Behaviour in ATMs

Abstract

An automated teller machine is an electronics telecommunications device which is utilized by people, mostly to withdraw money. In the present scenario, a fair amount of the population using an ATM machine to withdraw cash are facing a problem of robberies and theft due to lack of security guards. Surveillance cameras being used in the ATM cells, however monitoring capabilities of law enforcement agencies has not kept pace. So, in this system anomalous behavior is detected using CNN and LSTM on the surveillance videos. Accurate recognition of anomalous behavior at a point in time is the most challenging problem for systems. The anomaly as well as non anomaly dataset is fed to a machine and trained to identify abnormal behavior. Classifying the video is quite difficult as it contains spatial as well as temporal data. Remembering the temporal data is what is needed for the successful classification of videos. Previous research that had taken place were only on activity detection of humans and none were proposed for abnormal behaviors in ATMs. Therefore, this system has proposed a method to identify and classify whether it is abnormal behavior or not. As it is becoming very crucial for well beings of our society.