Journal of Satellite, Information and Communications (한국위성정보통신학회논문지)

Korea Society of Satellite Technology (한국위성정보통신학회)
권호 표지

The Flame Color Analysis of Color Models for Fire Detection

화재검출을 위한 컬러모델의 화염색상 분석

  • 이현술 (공주대학교 전기전자제어공학부) ;
  • 김원호 (공주대학교 전기전자제어공학부)
  • Received : 2013.09.02
  • Accepted : 2013.09.17
  • Published : 2013.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

This paper describes the color comparison analysis of flame in each standard color model in order to propose the optimal color model for image processing based flame detection algorithm. Histogram intersection values were used to analyze the separation characteristics between color of flame and color of non-flame in each standard color model which are RGB, YCbCr, CIE Lab, HSV. Histogram intersection value in each color model and components is evaluated for objective comparison. The analyzed result shows that YCbCr color model is the most suitable for flame detection by average HI value of 0.0575. Among the 12 components of standard color models, each Cb, R, Cr component has respectively HI value of 0.0433, 0.0526, 0.0567 and they have shown the best flame separation characteristics.

본 논문은 컬러 영상의 색상분석 기반의 화염 검출 알고리즘에 최적인 컬러모델을 도출하여 화재감시 시스템에 적용하기 위한 컬러모델의 화염 색상 비교 분석에 대하여 기술한다. 기존 화재검출 알고리즘에서 많이 사용되는 RGB, YCbCr, CIE Lab, HSV 국제 표준 컬러모델에서 화염과 비화염 영역간의 색상 분리도 특성을 영상의 히스토그램 교차 분석(Histogram Intersection) 기법을 사용하여 정량화하고 분석한다. 4가지 국제 표준 컬러모델에 대한 히스토그램 교차 분석 결과, YCbCr 컬러모델의 평균 히스토그램 교차값이 0.0575로서 화염과 비화염간의 색상 분리도가 가장 우수한 컬러모델임을 확인하였으며, 각 컬러모델을 구성하는 12개 성분들 중에서는 청색차(Cb) 성분, 적색(R) 성분, 적색차(Cr) 성분이 각각 0.0433, 0.0526, 0.0567 로서 화염과 비화염 영역의 색상 분리도 특성이 매우 우수하여, 색상 분석 기반의 화염 검출에 가장 최적이며 실용적인 컬러모델과 성분임을 확인하였다.

Keywords

References

  1. Dong-Yol Yun, Sung-Ho Kim, "A Design of Fire Monitoring System Based On Unmaned Helicopter and Sensor Network", Korea Institute of Intelligent Systems, Vol. 17, pp. 173-178, 2007 https://doi.org/10.5391/JKIIS.2007.17.2.173
  2. Yong-Woo Kim, Do-Hyeon Kim, Ho-Young Kwak, Hee-Dong Park, "A Study of Fire Shunt Guidance Based on Wireless Sensor Network", Korea Multimedia Society, Vol. 11, pp 1547-1554, 2008
  3. Won-Ho Kim, Seung-Kyeom Kim, Jong-Ho Lee, Chang-Ho Hyun, A fire alarm vision system based on IR image processing. IEEE NISS, Vol. 2, 291-293, 2011
  4. Begona C. Arrue, Anibal Ollero and J. Ramiro Martinez de Dios, "An Intelligent System for False Alarm Reduction in Infrared Forest-Fire Detection", IEEE Intelligent Systems and their Applications, May, 2000, Spain
  5. B. Ugur Toreyin, Yigithan Dedeoglu, Ugur Gudukby, A. Enis Cetin. "Computer vision based method for real-time fire and flame detection", Pattern Recognition Letters, vol. 27, pp 49-58, 2011
  6. Juan Chen, Yaping He, Jian Wang "Multi-feature fusion based fast video flame detection", Building and Environment, vol. 45, pp 1113-1122, 2010 https://doi.org/10.1016/j.buildenv.2009.10.017
  7. Turgay Celik "Fast and Efficient Method for Fire Detection Using Image Processing", ETRI Journal, vol. 32, pp 881-890, 2010 https://doi.org/10.4218/etrij.10.0109.0695
  8. S.M. Lee, J.H. Xin, S. Westland. "Evaluating of Image Similarity by Histogram Intersection", Color Research & Application, Vol. 30, No.4, 265-274, 2005
  9. Michael J. Swain, Dana H. Ballard, "Color Indexing", International Journal of Computer Vision, Netherlands, Volume 7, Issue 1, pp 11-32, November, 1991 https://doi.org/10.1007/BF00130487
  10. Ishita Chakraborty, Tanoy Kr. Paul. "A Hybrid Clustering Algorithm for Fire Detection in Video and Analysis with Color based Thresholding Method", International Conference on Advances in Computer Engineering, pp 277-280, 2010