ATM Intelligent Surveillance Based on Omni-directional Vision

This paper discusses a new intelligently monitoring system for the automatic teller machine (ATM) by using an omni-directional vision sensor (ODVS) and the computer vision technology. It uses ODVS to acquire the omni-directional image. By using perspective algorithm it unwrap the omni-directional image into several separated key surveillance sections and by using the Gaussian skin-color model of face detection algorithm and the Kalman filter of face tracking algorithm it detect the ATM userspsila faces and the suspected behavior of the voyeur who behind the ATM user. To improve the search efficiency and minimize the storage and data transmission, this paper combines the ATM userpsilas face image with the time and location information of certain activities. In additional, this paper designs a visualized omni-directional vibration perception device which can recognize the malicious violent behaviors by detecting whether the vibration ball under the irregular outside force or not. The experimental results show that the system has the advantages of widely detecting range, high-level intelligence, high-efficiency storage and searching and high robustness. So it provides a new way for preventing financial crimes.