Implementation of Abandoned Object detection System using Frame Differencing

Nireshwalya, Sumith and Bijur, Gururaj (2009) Implementation of Abandoned Object detection System using Frame Differencing. In: IEEE-DSCE Explore -09 , 7th-9th November 2009, Dayanand Sagar College of Engg., Bangalore .

[img] PDF
7-Implementation of Abandoned Object detection.pdf - Published Version
Restricted to Registered users only

Download (352kB) | Request a copy

Abstract

The increased interest in public safety after recent terrorist activities has caused a rapid growth in the number of surveillance cameras. Traditional operator-based surveillance of public spaces is very labor intensive, due to the number of people involved in analyzing the recorder video material on- and off line. Up to now video surveillance has been used as forensic tool, to obtain knowledge about what has happened. Therefore a fully automated surveillance system seems desirable in order to provide continuous analysis of people’s behaviors, discover potential threats in time and eventually prevent dangerous situations. This is not an easy task, as the system has to deal with large crowds resulting in severe occlusion, difficult and fast changing lighting situations, and views that are very narrow or too wide. In this paper we present a system for identifying abandoned objects in public places based on frame differencing approach . In the present work the concepts of dynamic frame differencing have been used to implement a robust automated abandoned object detection system. Using frame differencing on frame-by-frame basis an abandoned object, if any, is detected with high accuracy and efficiency

Item Type: Conference or Workshop Item (Paper)
Subjects: Engineering > MIT Manipal > Computer Science and Engineering
Depositing User: MIT Library
Date Deposited: 10 Jan 2014 06:10
Last Modified: 10 Jan 2014 06:21
URI: http://eprints.manipal.edu/id/eprint/138312

Actions (login required)

View Item View Item