Smoke detection using spatial and temporal analyses

Lee, CY; Lin, CT; Hong, CT; Su, MT

Smoke detection using spatial and temporal analyses

Lee, CY Lin, CT

Hong, CT Su, MT

Permalink

Publication Type:: Journal Article
Citation:: International Journal of Innovative Computing, Information and Control, 2012, 8 (7 A), pp. 4749 - 4770
Issue Date:: 2012-07-01

Closed Access

	Filename	Description	Size
	ijicic-11-03010.pdf	Published Version	2.56 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Lee, CY	en_US
dc.contributor.author	Lin, CT https://orcid.org/0000-0001-8371-8197	en_US
dc.contributor.author	Hong, CT	en_US
dc.contributor.author	Su, MT	en_US
dc.date.issued	2012-07-01	en_US
dc.identifier.citation	International Journal of Innovative Computing, Information and Control, 2012, 8 (7 A), pp. 4749 - 4770	en_US
dc.identifier.issn	1349-4198	en_US
dc.identifier.uri	http://hdl.handle.net/10453/115055
dc.description.abstract	Video-based fire detection is currently a fairly common application with the growth in the number of installed surveillance video systems. Moreover, the related processing units are becoming more powerful. Smoke is an early sign of most fires; therefore, selecting an appropriate smoke-detection method is essential. However, detecting smoke without creating a false alarm remains a challenging problem for open or large spaces with the disturbances of common moving objects, such as pedestrians and vehicles. This study proposes a novel video-based smoke-detection method that can be incorpora,ted into a surveillance system to provide early alerts. In this study, the process of extracting smoke features from Candidate regions was accomplished by analyzing the spatial and temporal characteristics of video sequences for three important features: edge blurring, gradual energy changes, and gradual chromatic configuration changes. The proposed spatial-temporal analysis technique improves the feature extraction of gradual energy changes. In order to make the video smoke-detection results more reliable, these three features were combined using a support vector machine (SVM) technique and a temporal-based alarm decision unit (ADU) was also introduced. The effectiveness of the proposed algorithm was evaluated on a PC with an Intel® Core™ 2 Duo CPU (2.2 GHz) and 2 GB RAM. The average processing time was 32.27 ms per frame; i.e., the proposed algorithm can process 30.98 frames per second. Experimental results showed that the proposed system can detect smoke effectively with a low false-alarm rate and a short reaction time in many real-world scenarios. © ICIC International 2012.	en_US
dc.relation.ispartof	International Journal of Innovative Computing, Information and Control	en_US
dc.subject.classification	Industrial Engineering & Automation	en_US
dc.title	Smoke detection using spatial and temporal analyses	en_US
dc.type	Journal Article
utslib.citation.volume	7 A	en_US
utslib.citation.volume	8	en_US
utslib.for	080109 Pattern Recognition and Data Mining	en_US
utslib.for	01 Mathematical Sciences	en_US
utslib.for	08 Information and Computing Sciences	en_US
utslib.for	09 Engineering	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	closed_access
pubs.issue	7 A	en_US
pubs.publication-status	Published	en_US
pubs.volume	8	en_US

Abstract:

Video-based fire detection is currently a fairly common application with the growth in the number of installed surveillance video systems. Moreover, the related processing units are becoming more powerful. Smoke is an early sign of most fires; therefore, selecting an appropriate smoke-detection method is essential. However, detecting smoke without creating a false alarm remains a challenging problem for open or large spaces with the disturbances of common moving objects, such as pedestrians and vehicles. This study proposes a novel video-based smoke-detection method that can be incorpora,ted into a surveillance system to provide early alerts. In this study, the process of extracting smoke features from Candidate regions was accomplished by analyzing the spatial and temporal characteristics of video sequences for three important features: edge blurring, gradual energy changes, and gradual chromatic configuration changes. The proposed spatial-temporal analysis technique improves the feature extraction of gradual energy changes. In order to make the video smoke-detection results more reliable, these three features were combined using a support vector machine (SVM) technique and a temporal-based alarm decision unit (ADU) was also introduced. The effectiveness of the proposed algorithm was evaluated on a PC with an Intel® Core™ 2 Duo CPU (2.2 GHz) and 2 GB RAM. The average processing time was 32.27 ms per frame; i.e., the proposed algorithm can process 30.98 frames per second. Experimental results showed that the proposed system can detect smoke effectively with a low false-alarm rate and a short reaction time in many real-world scenarios. © ICIC International 2012.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/115055