Intruder detection in camera networks using the one-class neighbor machine

Ahmed, Tarem Ozair and Wei, Xianglin and Ahmed, Supriyo and Pathan, Al-Sakib Khan (2011) Intruder detection in camera networks using the one-class neighbor machine. In: Networking and Electronic Commerce Research Conference 2011 (NAEC 2011), October 13-16, 2011, Riva del Garda, Italy. (In Press)

PDF (Accepted and To Appear (Intruder Detection in Camera Networks)) - Accepted Version Restricted to Registered users only Download (281kB) | Request a copy

Abstract

We propose a new algorithm based on machine learning techniques for automatic intruder detection in surveillance networks. The algorithm is theoretically founded on the concept of minimum volume sets. Through application to real images from an example, simple closed-circuit television system and comparison with some existing algorithms, we show that it is possible to easily obtain high detection accuracy with low false alarm rates.

Item Type:	Conference or Workshop Item (Full Paper)
Additional Information:	6841/1417 (BRACU Project in which Dr. Al-Sakib Khan Pathan is a collaborator. Accepted paper and to appear in the proceedings of NAEC 2011 conference. Tarem Ozair Ahmed is also under the processing of Ph.D. transfer from McGill University to IIUM DCS, KICT.)
Uncontrolled Keywords:	One-Class Neighbor Machine, Principal Component Analysis, Normalized Compression Distance
Subjects:	Q Science > Q Science (General)
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Information and Communication Technology > Department of Computer Science Kulliyyah of Information and Communication Technology > Department of Computer Science
Depositing User:	Dr. Al-Sakib Khan Pathan
Date Deposited:	25 Aug 2011 14:19
Last Modified:	25 Aug 2011 14:19
URI:	http://irep.iium.edu.my/id/eprint/1417

Actions (login required)

View Item