International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 02 | Feb 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 1272 Trajectory Movement Detection on ATM Survillance Suraj Kumble 1 , Pratik Phirke 2 , Vaibhav Tyagi 3 , Prof Smita Khairnar 4 1,2,3 Department of Computer Engineering, Pimpri Chinchwad of Engineering, Pune, Maharashtra, India 4 Prof Smita Khairnar, Dept. of Computer Engineering, Pimpri Chinchwad College of Engineering, Pune, Maharashtra, India ---------------------------------------------------------------------***---------------------------------------------------------------------- Abstract - Video surveillance is an important application that helps in monitoring different areas which require high security, thus video surveillance is a very important concept which plays a vital role in safety and security. Video surveillance system is used in detecting, analyzing, and tracking any unusual activity also it is used for public safety and other highly security needed areas. Many times there are cases of burglary in ATMs and the current video surveillance system is incapable of tracking such activities and is just for the recording purpose mainly. Therefore, to overcome the incapability’s of the existing system a system is proposed, which is going to track the trajectory of the user in the ATM using the background subtraction algorithm. Along with that there will be some prohibited areas declared by us for the user to enter. In case someone tries to enter prohibited area a message will be sent to the administrator the ATM. There will also be a feature of human face detection; in case the user’s face is covered s carf or helmet the ATM will not be accessed by the user until the face is uncovered. Key Words: Video Surveillance, Motion History Images, Classification, Background subtraction Algorithm, haar Classification. 1. INTRODUCTION Surveillance technology ordinance and its installation are increasingly being used in public facilities and organizations, to the common places of criminal acts. The environments monitoring has been expanded to protect residents in places, such as elementary schools and other care facilities, city parks and ATM system. The installation of the Smart surveillance technology helps prevent crime and may aid in the solution of cases. This Project is fundamentally for the ATMs surveillance. Currently, the video surveillance in ATMs is just for the purpose of capturing the video or recording only. They lack the ability to detect and analyze the activities performed by the user inside the ATMs. Due to which they the security of the ATM is limited. The system proposed by us will be programmed to overcome all those shortcoming of the current video surveillance. 2. MOTIVATION The motivation towards implementation towards the idea is to prevent the malicious activity happening in ATM system, provide a reliable and user friendly and secured ATM to improve the standards of the security. Along with that, it will also be helpful in tracing the culprit in case of a burglary. 3. LITERARTURE SURVEY The authors Sambarta Ray, Souvik Das, Dr. Anindya Sen in the paper[1] presents an automated Currently, a camera attached with the ATM unit, records and transmits the video feed to the main server of the bank. Around the clock, this manual surveillance utilizes a lot of bandwidth for transmission. According to the paper it is possible to detect whether a person is wearing a mask or not. The proposed system is also capable of counting the number of people present inside the ATM kiosk and generate a warning signal, thereby removes a constant human supervision. The authors A K Singh Kushwaha, Maheshkumar H Kolekar, A Khare, [2] paper presents an algorithm for real-time object classification and human activity recognition which can help to made intelligent video surveillance systems for human behavior analysis. The proposed method makes use of object silhouettes to classify objects and activity of humans present in a scene monitored by a dynamic camera. Astatically background subtraction method is used for object segmentation. The matching templates are constructed using the motion history images for classify objects into classes like human, human group and vehicle; and object shape information for different human activities in a video. Experimental results demonstrate that the proposed method can recognize these activities accurately. The idea proposed in paper[3] improve the security in ATMs, they have come up with various techniques which combined together to give a better result .The purpose of this paper is to present a survey about different techniques used for ATM security purpose and about confrontations facing in it. Various types of attacks on ATM are discussed in the paper which