Human Identification using Histogram of Oriented Gradients (HOG) and Non-Maximum Suppression (NMS) for ATM Video Surveillance

Abstract

Today video surveillance is the scorching topic in the research field of Computer Vision. Around 400 million surveillance cameras are used in various sectors which merely act as blind and record videos for post-incident analysis. With the increase in crimes around the world, video surveillance plays a key role in identifying anomaly activities in a day to day application. One such application is a robbery in Automated Teller Machine (ATM). Identifying and tracking unlawful human activities is a challenging task in the ATM video surveillance system. Thus, an effective Human detection method using computer vision and image processing is proposed to create phenomenal results. The proposed approach, incorporate the most acclaimed Histogram of Oriented Gradient (HOG)-Support Vector Machine (SVM) with a combination of Adaptive Background Generation Model and Non-Maximum Suppression (NMS) algorithm to detect human with appropriate results in a video sequence. The experimentation result of the proposed method is applied on ATM Video Surveillance, real-time dataset. The performance analysis is evaluated by considering the average value of metrics such as the number of an input frames, ground truth elements and frames with human identified which acquired 97% of accuracy.

Authors and Affiliations

Sanjeevkumar Angadi, Suvarna Nandyal

Keywords

Related Articles

Improvisation of Round Robin Algorithm

We are trying to improvise the existing Round Robin Algorithm and test its performance across host OS and VM as well. We would be testing the performance of the improvised algorithm on the Cent OS running on Virtual Box....

An Overview of the Green Internet of Things (IoT)

In line of the huge scope of the digital context, the number of subscribers of digital services, and the number of digital devices, levels of energy intake have reached alarming levels during the last decade. By 2020, th...

IoT and Wireless Communications: An Overview

The fundamental premise behind this notion is that the Internet is present all around us in the form of a variety of items or objects such as mobile phones, computers, and everyday goods such as refrigerators, TVs, and s...

A Review Study on Green Tea and Its Health Benefits

The Camellia sinensis plant conveys an extent of white, green, or dull teas. Tea is among the most notable beverages on earth, behind water similar to joy or clinical benefits. Green tea is more imperative than dull tea...

Implementation of UPFC, UPFC Along with PI and Fuzzy Based Controllers in Three Area Interconnected Power Systems for Load Frequency Control

In this paper, the author intends to present the application of Unified Power Factor Controllers (UPFC) to control the frequency of three area interdependent and interconnected reheat and hydro systems by controlling the...

Download PDF file
  • EP ID EP747323
  • DOI 10.21276/ijircst.2021.9.3.1
  • Views 1
  • Downloads 0

How To Cite

Sanjeevkumar Angadi, Suvarna Nandyal (2021). Human Identification using Histogram of Oriented Gradients (HOG) and Non-Maximum Suppression (NMS) for ATM Video Surveillance. International Journal of Innovative Research in Computer Science and Technology, 9(3), -. https://europub.co.uk/articles/-A-747323