DOI QR코드

DOI QR Code

Smoke Detection using Region Growing Method

영역 확장법을 이용한 연기검출

  • Published : 2009.08.31

Abstract

In this paper, we propose a smoke detection method using region growing method in outdoor video sequences. Our proposed method is composed of three steps; the initial change area detection step, the boundary finding and expanding step, and the smoke classification step. In the first step, we use a background subtraction to detect changed areas in the current input frame against the background image. In difference images of the background subtraction, we calculate a binary image using a threshold value and apply morphology operations to the binary image to remove noises. In the second step, we find boundaries of the changed areas using labeling algorithm and expand the boundaries to their neighbors using the region growing algorithm. In the final step, ellipses of the boundaries are estimated using moments. We classify whether the boundary is smoke by using the temporal information.

본 논문에서는 옥외 비디오 영상에서 영역 확장법을 이용한 연기 영역검출 방법을 제시한다. 제안된 방법은 차영상에 의한 초기 변화영역 검출 단계, 경계선 검출 및 확장 단계, 특징 검출 및 연기분류의 3단계로 구성된다. 초기 변화영역 검출 단계에서는 배경영상으로 차영상을 계산하고, 초기 임계치를 이용하여 이진영상을 구하고, 잡음 제거를 위하여 모폴로지 연산을 수행한다. 경계선 검출 및 확장 단계는 레이블링 알고리즘에 의해 이진영상에서 변화영역을 검출하고, 각 변화영역의 경계선을 검출한 다음, 차영상과 경계선을 이용하여 확장된 경계선을 계산한다. 특징 검출 및 연기분류 단계에서는 확장된 경계선에 모멘트를 이용하여 타원을 추정하고 타원의 시간에 따른 특징정보를 이용하여 연기 영역을 분류한다.

Keywords

References

  1. B.Ugur Toreyin et al, 'Wavelet based real-time smoke detection in video,' Signal Processing:Image Communication, EURASIP, Elsevier, Vol.20, pp.255-26, 2005 https://doi.org/10.1016/j.image.2004.12.002
  2. Nobuyuki Fujiwara, Kenji Terada, 'Extraction of a Smoke Region Using Fractal Coding,' International Symposium on Communications and Information Technologies, pp.659-662, Sapporo, Japan, Oct. 26-29, 2004 https://doi.org/10.1109/ISCIT.2004.1413797
  3. F.Gomez-Rodriguez et al, 'Smoke Monitoring and measurement Using Image Processing. Application to Forest Fires,' Automatic Target Recognition XIII, Proceedings of SPIE Vol.5094, pp.404-411, 2003 https://doi.org/10.1117/12.487050
  4. Ziyou Xiong et al, 'Video-based Smoke Detection: Possibilities, Techniques, and Challenges,' IFPA, Fire Suppression and Detection Research and Applications - A Technical Working Conference (SUPDET), Orlando, FL, 2007
  5. Roberto Vezzani et al, 'Smoke Detection in Video Surveillance: the Use of ViSOR (Video Surveillance On-line Repository),' Proceeding of ACM International Conference on Image and Video Retrieval, Niagara Falls, Canada, July, 7-9, 2008 https://doi.org/10.1145/1386352.1386392
  6. 김동근, 김원호, '블록기반 차영상과 투영 그래프를 이용한 연기검출,' 한국정보처리학회논문지B, Vol.14B, No.5, 2007년, pp.361-368 https://doi.org/10.3745/KIPSTB.2007.14-B.5.361
  7. A Murat Tekalp, Digital Video Processing, Prentice Hall PTR, 1995
  8. Rocha, L. et al, 'Motion reconstruction using moments analysis,' Computer Graphics and Image Processing, 2004. Proceedings. 17th Brazilian Symposium, pp.354- 361, 17-20 Oct. 2004 https://doi.org/10.1109/SIBGRA.2004.1352981
  9. Chaur-Chin Chen, 'Improved moment invariants for shape discrimination, Pattern recognition,' Vol.26, No.5, pp.683- 686, 1993 https://doi.org/10.1016/0031-3203(93)90121-C
  10. Johannes Kilian, 'Simple Image Analysis By Moments,' http://vaderio.googlepages.com/SimpleImageAnalysisbyMoments.pdf, 2001