Efficiency of HSV over RGB Gaussian Mixture Model for Fire Detection

Pavel  Chmelar; Abdsamad Benkrid

doi:10.1109/Radioelek.2014.6828426

Efficiency of HSV over RGB Gaussian Mixture Model for Fire Detection

Pavel Chmelar, Abdsamad Benkrid

University of Pardubice

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Computer Vision based systems have already been proposed to detect fire automatically. To increase the reliability of such systems, Gaussian Mixture Models of fire need to be developed in order to decide if an object in a scene is a fire or no. The models are trained using color images in RGB color model. We, however, believe HSV model is more suitable to present the statistics of a set of colored images precisely. To vindicate this claim, the paper includes a rigorous comparative evaluation of the two aforementioned color models in a fire detection system to demonstrate the superiority of the HSV color model. It makes hence the recommendation of using the latter model in vision based fire detection systems.

Original language	English
Title of host publication	Radioelektronika 2014
Subtitle of host publication	Proceedings of the 24th International Conference
Editors	Oldrich Ondracek, Jozef Pucik, Miroslav Hagara
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-4
Number of pages	4
ISBN (Print)	978-1-4799-3715-8, 9781479937134
DOIs	https://doi.org/10.1109/Radioelek.2014.6828426
Publication status	Published - Apr 2014
Event	Radioelektronika 2014: 24th International Conference - Bratislava, Slovakia Duration: 15 Apr 2014 → 16 Apr 2014 http://www.ieee.org/conferences_events/conferences/conferencedetails/index.html?Conf_ID=33045

Conference

Conference	Radioelektronika 2014
Country/Territory	Slovakia
City	Bratislava
Period	15/04/14 → 16/04/14
Internet address	http://www.ieee.org/conferences_events/conferences/conferencedetails/index.html?Conf_ID=33045

Keywords

fire detection system
RGB model
HSV model
Gaussian mixture model

Access to Document

10.1109/Radioelek.2014.6828426

Cite this

@inproceedings{f802edbe3b574e7db96975956bc6bde9,

title = "Efficiency of HSV over RGB Gaussian Mixture Model for Fire Detection",

abstract = "Computer Vision based systems have already been proposed to detect fire automatically. To increase the reliability of such systems, Gaussian Mixture Models of fire need to be developed in order to decide if an object in a scene is a fire or no. The models are trained using color images in RGB color model. We, however, believe HSV model is more suitable to present the statistics of a set of colored images precisely. To vindicate this claim, the paper includes a rigorous comparative evaluation of the two aforementioned color models in a fire detection system to demonstrate the superiority of the HSV color model. It makes hence the recommendation of using the latter model in vision based fire detection systems.",

keywords = "fire detection system, RGB model, HSV model, Gaussian mixture model",

author = "Pavel Chmelar and Abdsamad Benkrid",

year = "2014",

month = apr,

doi = "10.1109/Radioelek.2014.6828426",

language = "English",

isbn = "978-1-4799-3715-8",

pages = "1--4",

editor = "Oldrich Ondracek and Jozef Pucik and Miroslav Hagara",

booktitle = "Radioelektronika 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "Radioelektronika 2014 : 24th International Conference ; Conference date: 15-04-2014 Through 16-04-2014",

url = "http://www.ieee.org/conferences_events/conferences/conferencedetails/index.html?Conf_ID=33045",

}

Chmelar, P & Benkrid, A 2014, Efficiency of HSV over RGB Gaussian Mixture Model for Fire Detection. in O Ondracek, J Pucik & M Hagara (eds), Radioelektronika 2014: Proceedings of the 24th International Conference. Institute of Electrical and Electronics Engineers Inc., pp. 1-4, Radioelektronika 2014, Bratislava, Slovakia, 15/04/14. https://doi.org/10.1109/Radioelek.2014.6828426

Efficiency of HSV over RGB Gaussian Mixture Model for Fire Detection. / Chmelar, Pavel ; Benkrid, Abdsamad.
Radioelektronika 2014: Proceedings of the 24th International Conference. ed. / Oldrich Ondracek; Jozef Pucik; Miroslav Hagara. Institute of Electrical and Electronics Engineers Inc., 2014. p. 1-4.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Efficiency of HSV over RGB Gaussian Mixture Model for Fire Detection

AU - Chmelar, Pavel

AU - Benkrid, Abdsamad

PY - 2014/4

Y1 - 2014/4

N2 - Computer Vision based systems have already been proposed to detect fire automatically. To increase the reliability of such systems, Gaussian Mixture Models of fire need to be developed in order to decide if an object in a scene is a fire or no. The models are trained using color images in RGB color model. We, however, believe HSV model is more suitable to present the statistics of a set of colored images precisely. To vindicate this claim, the paper includes a rigorous comparative evaluation of the two aforementioned color models in a fire detection system to demonstrate the superiority of the HSV color model. It makes hence the recommendation of using the latter model in vision based fire detection systems.

AB - Computer Vision based systems have already been proposed to detect fire automatically. To increase the reliability of such systems, Gaussian Mixture Models of fire need to be developed in order to decide if an object in a scene is a fire or no. The models are trained using color images in RGB color model. We, however, believe HSV model is more suitable to present the statistics of a set of colored images precisely. To vindicate this claim, the paper includes a rigorous comparative evaluation of the two aforementioned color models in a fire detection system to demonstrate the superiority of the HSV color model. It makes hence the recommendation of using the latter model in vision based fire detection systems.

KW - fire detection system

KW - RGB model

KW - HSV model

KW - Gaussian mixture model

UR - http://www.proceedings.com/22464.html

U2 - 10.1109/Radioelek.2014.6828426

DO - 10.1109/Radioelek.2014.6828426

M3 - Conference contribution

SN - 978-1-4799-3715-8

SN - 9781479937134

SP - 1

EP - 4

BT - Radioelektronika 2014

A2 - Ondracek, Oldrich

A2 - Pucik, Jozef

A2 - Hagara, Miroslav

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - Radioelektronika 2014

Y2 - 15 April 2014 through 16 April 2014

ER -

Efficiency of HSV over RGB Gaussian Mixture Model for Fire Detection

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this