The Journal of the Korea institute of electronic communication sciences (한국전자통신학회논문지)

Korea Institute of Electronic Communication Science (한국전자통신학회)
권호 표지
DOI QR코드

DOI QR Code

Real-time Smoke Detection Based on Colour Information, Morphological and Dynamic Features of the Smoke

연기의 색 정보, 형태학적 및 동적 특징 기반의 실시간 연기 검출

  • 김현태 (동의대학교 멀티미디어공학과) ;
  • 박장식 (경성대학교 전자공학과)
  • Received : 2014.11.18
  • Accepted : 2015.01.12
  • Published : 2015.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a system which can detect the smoke in real time from the high-quality IP camera. For real-time processing, open directly the RTSP streams transmitted from the IP camera using the library FFmpeg as opening a video file. To recognize smoke, color information and morphological characteristics of smoke, as well as the dynamic characteristics of the smoke also considered for candidate regions. To combine the characteristics of the various smoke effectively, the Adaboost algorithm, was used as the boosting algorithm finally. Through the experiments with input videos from IP camera, the proposed algorithms were useful to detect smokes.

본 논문에서는 고화질 IP 카메라로부터 입력되는 영상으로부터 실시간으로 연기를 검출할 수 있는 시스템을 제안한다. 실시간 처리를 위해 FFmpeg 라이브러리를 이용하여 비디오 파일을 오픈하는 것처럼 IP 카메라로부터 전송되는 RTSP 스트림을 직접 오픈한다. 연기 검출을 위해 연기 후보 영역에 대해 연기의 색정보 및 형태학적 특성은 물론, 연기의 동적 특성까지 고려한다. 최종적으로 다양한 연기의 특성들을 효율적으로 결합하기 위해 부스팅 알고리즘으로 Adaboost 알고리즘을 사용한다. 실험 결과를 통하여 제안하는 방법이 연기를 검출하는 데 효과적인 것을 보인다.

Keywords

References

  1. K. Park and H. Kim, "A Study for Video-based Vehicle Surveillance on Outdoor Road," J. of the Korea Institute of Electronic Communication Science, vol. 8, no. 11, 2013, pp. 1647-1653. https://doi.org/10.13067/JKIECS.2013.8.11.1647
  2. H. Kim and J. Park, "Smoke Detection in Outdoor Using Its Statistical Characteristics," J. of the Korea Institute of Electronic Communication Science, vol. 9, no. 2, 2014, pp. 149-154. https://doi.org/10.13067/JKIECS.2014.9.2.149
  3. G. Healey, D. Slater, T. Lin, B. Drda, and A. D. Goedeke, "A System for Real-time Fire Detection," Proc. on IEEE Computer Vision and Pattern Recognition Conf. (CVPR93), New York, NY, June 1993, pp. 605-606.
  4. B. U. Toreyin, Y. Dedeoglu, U. Gudukbay, and A. E. Cetin, "Computer vision based method for real-time and flame detection," Pattern Recognition Letters, Elsevier, vol. 27, issue 1, 2006, pp. 49-58. https://doi.org/10.1016/j.patrec.2005.06.015
  5. J. Jung, J. Kim, D. Kim, S. Kwon, J. Lee, S. Ju, H. Im, N. Jung, C. Park, and K. Ryu, "Design and implementation of smart multimedia editor system based on education cloud services system," Proc. on Human and Computer Interface Conf. (HCI2014), Jeongseon, Korea, Feb. 2014, pp. 913-916.
  6. H. Kim, "Real-time Flame Detection Using Colour and Dynamic Features of Flame Based on FFmpeg," J. of the Korea Institute of Electronic Communication Science, vol. 9, no. 9, 2014, pp. 977-982. https://doi.org/10.13067/JKIECS.2014.9.9.977
  7. G. Kim, G. Lee, J. Kim, and J. Park, "Vehicle Detection Using Optimal Features for Adaboost," J. of the Korea Institute of Electronic Communication Science, vol. 8, no. 8, 2013, pp. 1129-1135. https://doi.org/10.13067/JKIECS.2013.8.8.1129