Fire detection in infrared video using wavelet analysis

Behcet Uǧur Töreyin; Ramazan Gökberk Cinbiş; Yiǧithan Dedeoǧlu; Ahmet Enis Çetin

doi:10.1117/1.2748752

Fire detection in infrared video using wavelet analysis

Behcet Uǧur Töreyin^*, Ramazan Gökberk Cinbiş, Yiǧithan Dedeoǧlu, Ahmet Enis Çetin

^*Corresponding author for this work

Bilkent University

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

62 Citations (Scopus)

Abstract

A novel method to detect flames in infrared (IR) video is proposed. Image regions containing flames appear as bright regions in IR video. In addition to ordinary motion and brightness clues, the flame flicker process is also detected by using a hidden Markov model (HMM) describing the temporal behavior. IR image frames are also analyzed spatially. Boundaries of flames are represented in wavelet domain and the high frequency nature of the boundaries of fire regions is also used as a clue to model the flame flicker. All of the temporal and spatial clues extracted from the IR video are combined to reach a final decision. False alarms due to ordinary bright moving objects are greatly reduced because of the HMM-based flicker modeling and wavelet domain boundary modeling.

Original language	English
Article number	067204
Journal	Optical Engineering
Volume	46
Issue number	6
DOIs	https://doi.org/10.1117/1.2748752
Publication status	Published - Jun 2007
Externally published	Yes

Keywords

Hidden Markov models
Infrared video fire detection
Segmentation
Video event detection
Video object contour analysis
Wavelet transform

Access to Document

10.1117/1.2748752

Cite this

@article{bf9d6a53875d4177986d97c9eb4759ca,

title = "Fire detection in infrared video using wavelet analysis",

abstract = "A novel method to detect flames in infrared (IR) video is proposed. Image regions containing flames appear as bright regions in IR video. In addition to ordinary motion and brightness clues, the flame flicker process is also detected by using a hidden Markov model (HMM) describing the temporal behavior. IR image frames are also analyzed spatially. Boundaries of flames are represented in wavelet domain and the high frequency nature of the boundaries of fire regions is also used as a clue to model the flame flicker. All of the temporal and spatial clues extracted from the IR video are combined to reach a final decision. False alarms due to ordinary bright moving objects are greatly reduced because of the HMM-based flicker modeling and wavelet domain boundary modeling.",

keywords = "Hidden Markov models, Infrared video fire detection, Segmentation, Video event detection, Video object contour analysis, Wavelet transform",

author = "T{\"o}reyin, {Behcet Uǧur} and Cinbi{\c s}, {Ramazan G{\"o}kberk} and Yiǧithan Dedeoǧlu and {\c C}etin, {Ahmet Enis}",

year = "2007",

month = jun,

doi = "10.1117/1.2748752",

language = "English",

volume = "46",

journal = "Optical Engineering",

issn = "0091-3286",

publisher = "SPIE",

number = "6",

}

TY - JOUR

T1 - Fire detection in infrared video using wavelet analysis

AU - Töreyin, Behcet Uǧur

AU - Cinbiş, Ramazan Gökberk

AU - Dedeoǧlu, Yiǧithan

AU - Çetin, Ahmet Enis

PY - 2007/6

Y1 - 2007/6

N2 - A novel method to detect flames in infrared (IR) video is proposed. Image regions containing flames appear as bright regions in IR video. In addition to ordinary motion and brightness clues, the flame flicker process is also detected by using a hidden Markov model (HMM) describing the temporal behavior. IR image frames are also analyzed spatially. Boundaries of flames are represented in wavelet domain and the high frequency nature of the boundaries of fire regions is also used as a clue to model the flame flicker. All of the temporal and spatial clues extracted from the IR video are combined to reach a final decision. False alarms due to ordinary bright moving objects are greatly reduced because of the HMM-based flicker modeling and wavelet domain boundary modeling.

AB - A novel method to detect flames in infrared (IR) video is proposed. Image regions containing flames appear as bright regions in IR video. In addition to ordinary motion and brightness clues, the flame flicker process is also detected by using a hidden Markov model (HMM) describing the temporal behavior. IR image frames are also analyzed spatially. Boundaries of flames are represented in wavelet domain and the high frequency nature of the boundaries of fire regions is also used as a clue to model the flame flicker. All of the temporal and spatial clues extracted from the IR video are combined to reach a final decision. False alarms due to ordinary bright moving objects are greatly reduced because of the HMM-based flicker modeling and wavelet domain boundary modeling.

KW - Hidden Markov models

KW - Infrared video fire detection

KW - Segmentation

KW - Video event detection

KW - Video object contour analysis

KW - Wavelet transform

UR - http://www.scopus.com/inward/record.url?scp=34548017199&partnerID=8YFLogxK

U2 - 10.1117/1.2748752

DO - 10.1117/1.2748752

M3 - Article

AN - SCOPUS:34548017199

SN - 0091-3286

VL - 46

JO - Optical Engineering

JF - Optical Engineering

IS - 6

M1 - 067204

ER -

Fire detection in infrared video using wavelet analysis

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this