Efficient and effective automated surveillance agents using kernel tricks

This article was published in the SIMULATION [© 2012 The Society for Modeling and Simulation International.] and the definite version is available at: http://doi.org/10.1177/0037549712460908 The Article's website is at: http://sim.sagepub.com/content/89/5/562

Sonraí bibleagrafaíochta
Príomhchruthaitheoirí:	Ahmed, Tarem, Pathan, Al-Sakib Khan, Ahmed, Supriyo Sabbir, Wei, Xianglin
Rannpháirtithe:	Department of Electrical and Electronic Engineering, BRAC University
Formáid:	Alt
Teanga:	English
Foilsithe / Cruthaithe:	© 2012 The Society for Modeling and Simulation International. 2016
Ábhair:	Agent Automated Camera Intrusion Kernel Surveillance
Rochtain ar líne:	http://hdl.handle.net/10361/7204 http://doi.org/10.1177/0037549712460908

id	10361-7204
record_format	dspace
spelling	10361-72042016-12-12T06:57:18Z Efficient and effective automated surveillance agents using kernel tricks Ahmed, Tarem Pathan, Al-Sakib Khan Ahmed, Supriyo Sabbir Wei, Xianglin Department of Electrical and Electronic Engineering, BRAC University Agent Automated Camera Intrusion Kernel Surveillance This article was published in the SIMULATION [© 2012 The Society for Modeling and Simulation International.] and the definite version is available at: http://doi.org/10.1177/0037549712460908 The Article's website is at: http://sim.sagepub.com/content/89/5/562 Many schemes have been presented over the years to develop automated visual surveillance systems. However, these schemes typically need custom equipment, or involve significant complexity and storage requirements. In this paper we present three software-based agents built using kernel machines to perform automated, real-time intruder detection in surveillance systems. Kernel machines provide a powerful data mining technique that may be used for pattern matching in the presence of complex data. They work by first mapping the raw input data onto a (often much) higher-dimensional feature space, and then clustering in the feature space instead. The reasoning is that mapping onto the (higher-dimensional) feature space enables the comparison of additional, higher-order correlations in determining patterns between the raw data points. The agents proposed here have been built using algorithms that are adaptive, portable, do not require any expensive or sophisticated components, and are lightweight and efficient having run times of the order of hundredths of a second. Through application to real image streams from a simple, run-of-the-mill closed-circuit television surveillance system, and direct quantitative performance comparison with some existing schemes, we show that it is possible to easily obtain high detection accuracy with low computational and storage complexities. Published 2016-12-12T06:55:19Z 2016-12-12T06:55:19Z 2012 Article Ahmed, T., Pathan, A. -. K., Ahmed, S., & Wei, X. (2013). Efficient and effective automated surveillance agents using kernel tricks. Simulation, 89(5), 562-577. doi:10.1177/0037549712460908 00375497 http://hdl.handle.net/10361/7204 http://doi.org/10.1177/0037549712460908 en http://sim.sagepub.com/content/89/5/562 © 2012 The Society for Modeling and Simulation International.
institution	Brac University
collection	Institutional Repository
language	English
topic	Agent Automated Camera Intrusion Kernel Surveillance
spellingShingle	Agent Automated Camera Intrusion Kernel Surveillance Ahmed, Tarem Pathan, Al-Sakib Khan Ahmed, Supriyo Sabbir Wei, Xianglin Efficient and effective automated surveillance agents using kernel tricks
description	This article was published in the SIMULATION [© 2012 The Society for Modeling and Simulation International.] and the definite version is available at: http://doi.org/10.1177/0037549712460908 The Article's website is at: http://sim.sagepub.com/content/89/5/562
author2	Department of Electrical and Electronic Engineering, BRAC University
author_facet	Department of Electrical and Electronic Engineering, BRAC University Ahmed, Tarem Pathan, Al-Sakib Khan Ahmed, Supriyo Sabbir Wei, Xianglin
format	Article
author	Ahmed, Tarem Pathan, Al-Sakib Khan Ahmed, Supriyo Sabbir Wei, Xianglin
author_sort	Ahmed, Tarem
title	Efficient and effective automated surveillance agents using kernel tricks
title_short	Efficient and effective automated surveillance agents using kernel tricks
title_full	Efficient and effective automated surveillance agents using kernel tricks
title_fullStr	Efficient and effective automated surveillance agents using kernel tricks
title_full_unstemmed	Efficient and effective automated surveillance agents using kernel tricks
title_sort	efficient and effective automated surveillance agents using kernel tricks
publisher	© 2012 The Society for Modeling and Simulation International.
publishDate	2016
url	http://hdl.handle.net/10361/7204 http://doi.org/10.1177/0037549712460908
work_keys_str_mv	AT ahmedtarem efficientandeffectiveautomatedsurveillanceagentsusingkerneltricks AT pathanalsakibkhan efficientandeffectiveautomatedsurveillanceagentsusingkerneltricks AT ahmedsupriyosabbir efficientandeffectiveautomatedsurveillanceagentsusingkerneltricks AT weixianglin efficientandeffectiveautomatedsurveillanceagentsusingkerneltricks
_version_	1814307395844702208

Efficient and effective automated surveillance agents using kernel tricks

Míreanna comhchosúla