DOI QR코드

DOI QR Code

Automatic fire detection system using Bayesian Networks

베이지안 네트워크를 이용한 자동 화재 감지 시스템

  • Published : 2008.04.30

Abstract

In this paper, we propose a new vision-based fire detection method for a real-life application. Most previous vision-based methods using color information and temporal variation of pixel produce frequent false alarms because they used a lot of heuristic features. Furthermore there is also computation delay for accurate fire detection. To overcome these problems, we first detected candidated fire regions by using background modeling and color model of fire. Then we made probabilistic models of fire by using a fact that fire pixel values of consecutive frames are changed constantly and applied them to a Bayesian Network. In this paper we used two level Bayesian network, which contains the intermediate nodes and uses four skewnesses for evidence at each node. Skewness of R normalized with intensity and skewnesses of three high frequency components obtained through wavelet transform. The proposed system has been successfully applied to many fire detection tasks in real world environment and distinguishes fire from moving objects having fire color.

본 논문에서는 실시간 화재 감지를 위해 비전 기반의 새로운 화재 감지 기법을 제안한다. 기존의 비전기반 화재감지 기법에서는 컬러정보와 픽셀들의 시간적인 변화량 검출을 위해 다수의 휴리스틱한 특징들을 적용함으로써 실험결과가 환경의 변화에 민감한 문제들이 존재했다. 또한 정확한 화재감지를 위해서 많은 연산을 수행함으로써 감지시간 길어지는 단점이 있었다. 이러한 문제점들을 극복하기 위해서 본 논문에서는 시간축 상에서 불규칙하게 변화하는 화재의 특성을 분석하고 이를 토대로 확률 모델을 구성하여 이를 베이지안 네트워크(Bayesian network)에 적용하는 새로운 방법을 제안한다. 우선, 배경 모델링과 컬러 모델을 적용하여 화재 후보 영역을 검출하고, 이 후보 영역에서 명암도에 평준화된 Red 색상의 왜도(skewness)와 웨이블릿 변환을 통하여 얻어진 3가지 고주파 성분의 왜도를 노드로 갖는 베이지안 네트워크를 구성하여 최종 화재를 감별한다. 실생활 환경에서 촬영된 화재 영상에 대한 실험 결과는 빠른 검출 속도와 우수한 화재 검출 성능을 보여주고 있다.

Keywords

References

  1. B. U. Toreyin, Y. Dedeoglu, U Gudukbay, A. E. Cetin, “Computer vision based method for real-time fire and flame detection”, Pattern Recognition Letters, Vol.27, pp.49-58, Jan. 2006 https://doi.org/10.1016/j.patrec.2005.06.015
  2. T. Celik, H. Demirel, H. Ozkaramanli, M. Uyguroglu, “Fire detection using statistical color model in video sequences”, Journal of Visual Communication and Image Representation, Vol.18, pp.176-185, Apr. 2007 https://doi.org/10.1016/j.jvcir.2006.12.003
  3. W. Phillips, III, M. Shah, and N. da Vitoria Lobo, “Flame recognition in video”, Fifth IEEE Workshop on Applications of Computer Vision, Vol.23, pp.224-229, Jan. 2000
  4. T. Chen, P. Wu, Y. Chiou, “An early fire-detection method based on image processing”, ICIP, Vol.3, pp.1707-1710, Oct. 2004
  5. K. Cheong, B. Ko and J. Nam, “Vision sensor-based fire monitoring system for smart home”, The first Int. Conference on Ubiquitous Information & Applications, Vol.1, pp.1453-1462, Feb. 2007
  6. Y. Dedeoglu, “Moving object detection, tracking and classification for smart video surveillance”, Master's Thesis, Dept. of Computer Eng. Bilkent University, Ankara, 2004
  7. I. Kopilovic, B. Vagvolgyi, T. Sziranyi, “Application of Panoramic Annular Lens for Motion Analysis Tasks: Surveillance and Smoke Detection”, In IEEE International Conference on Pattern Recognition, Vol.4, pp.14-717, 2000
  8. R. O. Duda, P. E. Hart and D. G. Stork, “Pattern Classification”, Willey-Interscience, Second Edition, 2001
  9. H. Byun, B. Ko, “Robust Face Detection and Tracking For Real-Life Applications”, International Journal of Pattern Recognition and Artificial Intelligence, Vol.17, No.6, pp.1035-1055, Feb. 2003 https://doi.org/10.1142/S0218001403002721
  10. T. Celik, H. Demirel, H. Ozkaramanli and M. Uyguroglu, “Fire detection using statistical color model in video sequences”, Journal of Visual Communication and Image Representation, Vol.18, pp.176-185, 2007 https://doi.org/10.1016/j.jvcir.2006.12.003
  11. C. Stauffer and W. Grimson, “Adaptive background mixture models for real-time tracking”, IEEE International Conference on Computer Vision and Pattern Recognition, Vol.2, pp.246-252, 1999
  12. K. Kim, T.H. Chalidabhongse, D. Harwood and L. Davis, “Real-time foreground-background segmentation using codebook model”, Real-time imaging, Vol.11, Issue 3, pp.167-256, 2005 https://doi.org/10.1016/j.rti.2005.06.001

Cited by

  1. Early fire detection algorithm based on irregular patterns of flames and hierarchical Bayesian Networks vol.45, pp.4, 2010, https://doi.org/10.1016/j.firesaf.2010.04.001