Video based wildfire detection at night

Osman Günay; Kasim Taşdemir; B. Uǧur Töreyin; A. Enis Çetin

doi:10.1016/j.firesaf.2009.04.003

Video based wildfire detection at night

Osman Günay^*, Kasim Taşdemir, B. Uǧur Töreyin, A. Enis Çetin

^*Corresponding author for this work

Bilkent University

Research output: Contribution to journal › Article › peer-review

52 Citations (Scopus)

Abstract

There has been an increasing interest in the study of video based fire detection algorithms as video based surveillance systems become widely available for indoor and outdoor monitoring applications. A novel method explicitly developed for video based detection of wildfires at night (in the dark) is presented in this paper. The method comprises four sub-algorithms: (i) slow moving video object detection, (ii) bright region detection, (iii) detection of objects exhibiting periodic motion, and (iv) a sub-algorithm interpreting the motion of moving regions in video. Each of these sub-algorithms characterizes an aspect of fire captured at night by a visible range PTZ camera. Individual decisions of the sub-algorithms are combined together using a least-mean-square (LMS) based decision fusion approach, and fire/nofire decision is reached by an active learning method.

Original language	English
Pages (from-to)	860-868
Number of pages	9
Journal	Fire Safety Journal
Volume	44
Issue number	6
DOIs	https://doi.org/10.1016/j.firesaf.2009.04.003
Publication status	Published - Aug 2009
Externally published	Yes

Funding

This work was supported in part by the Scientific and Technical Research Council of Turkey, TUBITAK, with Grant nos. 106G126 and 105E191, and in part by European Commission 6th Framework Program with Grant no. FP6-507752 (MUSCLE Network of Excellence Project).

Funders	Funder number
European Commission 6th Framework Program	FP6-507752
TUBITAK	106G126, 105E191
Türkiye Bilimsel ve Teknolojik Araştirma Kurumu

Keywords

Active learning
Computer vision
Decision fusion
Fire detection
Least-mean-square methods
On-line learning

Access to Document

10.1016/j.firesaf.2009.04.003

Cite this

@article{a7a0cf1273614864802dd3b0b6edb62f,

title = "Video based wildfire detection at night",

abstract = "There has been an increasing interest in the study of video based fire detection algorithms as video based surveillance systems become widely available for indoor and outdoor monitoring applications. A novel method explicitly developed for video based detection of wildfires at night (in the dark) is presented in this paper. The method comprises four sub-algorithms: (i) slow moving video object detection, (ii) bright region detection, (iii) detection of objects exhibiting periodic motion, and (iv) a sub-algorithm interpreting the motion of moving regions in video. Each of these sub-algorithms characterizes an aspect of fire captured at night by a visible range PTZ camera. Individual decisions of the sub-algorithms are combined together using a least-mean-square (LMS) based decision fusion approach, and fire/nofire decision is reached by an active learning method.",

keywords = "Active learning, Computer vision, Decision fusion, Fire detection, Least-mean-square methods, On-line learning",

author = "Osman G{\"u}nay and Kasim Ta{\c s}demir and {Uǧur T{\"o}reyin}, B. and {Enis {\c C}etin}, A.",

year = "2009",

month = aug,

doi = "10.1016/j.firesaf.2009.04.003",

language = "English",

volume = "44",

pages = "860--868",

journal = "Fire Safety Journal",

issn = "0379-7112",

publisher = "Elsevier Ltd",

number = "6",

}

TY - JOUR

T1 - Video based wildfire detection at night

AU - Günay, Osman

AU - Taşdemir, Kasim

AU - Uǧur Töreyin, B.

AU - Enis Çetin, A.

PY - 2009/8

Y1 - 2009/8

N2 - There has been an increasing interest in the study of video based fire detection algorithms as video based surveillance systems become widely available for indoor and outdoor monitoring applications. A novel method explicitly developed for video based detection of wildfires at night (in the dark) is presented in this paper. The method comprises four sub-algorithms: (i) slow moving video object detection, (ii) bright region detection, (iii) detection of objects exhibiting periodic motion, and (iv) a sub-algorithm interpreting the motion of moving regions in video. Each of these sub-algorithms characterizes an aspect of fire captured at night by a visible range PTZ camera. Individual decisions of the sub-algorithms are combined together using a least-mean-square (LMS) based decision fusion approach, and fire/nofire decision is reached by an active learning method.

AB - There has been an increasing interest in the study of video based fire detection algorithms as video based surveillance systems become widely available for indoor and outdoor monitoring applications. A novel method explicitly developed for video based detection of wildfires at night (in the dark) is presented in this paper. The method comprises four sub-algorithms: (i) slow moving video object detection, (ii) bright region detection, (iii) detection of objects exhibiting periodic motion, and (iv) a sub-algorithm interpreting the motion of moving regions in video. Each of these sub-algorithms characterizes an aspect of fire captured at night by a visible range PTZ camera. Individual decisions of the sub-algorithms are combined together using a least-mean-square (LMS) based decision fusion approach, and fire/nofire decision is reached by an active learning method.

KW - Active learning

KW - Computer vision

KW - Decision fusion

KW - Fire detection

KW - Least-mean-square methods

KW - On-line learning

UR - http://www.scopus.com/inward/record.url?scp=67649662241&partnerID=8YFLogxK

U2 - 10.1016/j.firesaf.2009.04.003

DO - 10.1016/j.firesaf.2009.04.003

M3 - Article

AN - SCOPUS:67649662241

SN - 0379-7112

VL - 44

SP - 860

EP - 868

JO - Fire Safety Journal

JF - Fire Safety Journal

IS - 6

ER -

Video based wildfire detection at night

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this