INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
Detection of Suspicious Behaviour In ATM Site using Computer Vision Techniques
Authors Name:
Sharath babu CG
, Dr. Anitha Devi.M.D , Dr.M Z Kurian
Unique Id:
IJSDR2302049
Published In:
Volume 8 Issue 2, February-2023
Abstract:
Many individuals find that using an automated teller machine (ATM) provides them with a great deal of convenience since it enables them to do bank transactions and cash withdrawals in a much shorter amount of time. However, if an ATM is left unattended outside of normal business hours or on a public holiday, it leaves itself open to the possibility of being attacked. In recent months, it has been reported that a number of automated teller machines have been stolen from their locations or deliberately destroyed in order to get access to the cash they contain. Because of this, many automated teller machine locations actually have video surveillance systems installed to keep an eye on the surrounding area and deter criminal activity. When there are a large number of surveillance cameras, however, it becomes more difficult for security officers to locate the location of an ongoing crime in real time. The goal of this research is to build real-time video analysis algorithms based on computer vision methods and deep learning technologies for artificial neural networks, with the goal of recognizing anomalous human behavior near essential facilities, such as automated teller machines.In this article, a real-time security expert video surveillance system that utilises image processing methods to identify suspicious behaviour was presented as a means of combating the problem. The paper begins with a discussion of the typical approach to the detection and recognition of suspicious activity. The supervised and unsupervised machine learning approaches, which are generally based on SVM, HMM, and ANN classifiers, are then summarised. These methodologies were adopted by the researchers in the past, and they range from modelling single human behaviour to modelling crowded scenes.
Keywords:
ATM surveillance, Deep Learning, Machine Learning, Computer Vision
Cite Article:
"Detection of Suspicious Behaviour In ATM Site using Computer Vision Techniques", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.8, Issue 2, page no.282 - 286, February-2023, Available :http://www.ijsdr.org/papers/IJSDR2302049.pdf
Downloads:
000337212
Publication Details:
Published Paper ID: IJSDR2302049
Registration ID:203930
Published In: Volume 8 Issue 2, February-2023
DOI (Digital Object Identifier):
Page No: 282 - 286
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn