Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Measurement of the Visibility of the Smoke Images using PCA

PCA를 이용한 연기 영상의 가시도 측정

  • Yu, Young-Jung (Department of Computer Engineering, Busan University of Foreign Studies) ;
  • Moon, Sang-ho (Department of Computer Engineering, Busan University of Foreign Studies) ;
  • Park, Seong-Ho (Information Technology Center, Pusan National University)
  • Received : 2018.09.17
  • Accepted : 2018.11.05
  • Published : 2018.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

When fires occur in high-rise buildings, it is difficult to determine whether each escape route is safe because of complex structure. Therefore, it is necessary to provide residents with escape routes quickly after determining their safety. We propose a method to measure the visibility of the escape route due to the smoke generated in the fire by analyzing the images. The visibility can be easily measured if the density of smoke detected in the input image is known. However, this approach is difficult to use because there are no suitable methods for measuring smoke density. In this paper, we use principal component analysis by extracting a background image from input images and making it training data. Background images and smoke images are extracted from images given as inputs, and then the learned principal component analysis is applied to map of as a new feature space, and the change is calculated and the visibility due to the smoke is measured.

고층 빌딩에서 화재가 발생하는 경우 복잡한 구조로 인해 다양한 대피 통로가 존재하며 각 대피 통로의 안전성 여부를 파악하는 것이 어렵다. 고층 빌딩 화재 시 거주자들에게 신속히 탈출 경로를 제공하는 것이 필요하며 이를 위해서 대피 통로의 안정성 여부를 파악할 필요가 있다. 본 논문에서는 대피 통로의 안정성 여부 파악을 위해 영상을 분석하여 화재 시 발생하는 연기로 인한 대피 통로의 가시도를 측정하는 방법을 제안한다. 입력 영상에서 연기를 검출한 후 검출된 연기의 밀도를 알 수 있다면 가시도를 쉽게 측정할 수 있지만, 연기 검출이나 연기 밀도 측정에 관한 적절한 방법이 없어 이러한 접근법을 사용하기는 어렵다. 본 논문에서는 입력 영상에서 배경 영상을 추출하고 이를 학습 데이터로 하여 주성분 분석 학습을 한다. 이후 입력으로 주어지는 영상에서 배경 영상과 연기 영상을 추출하고 학습된 주성분 분석을 적용하여 새로운 특징 공간으로 사상한 후 변화량을 계산하여 연기로 인한 가시도를 측정한다.

Keywords

HOJBC0_2018_v22n11_1474_f0001.png 이미지

Fig. 1 Training data for principal component analysis separated from a background image

HOJBC0_2018_v22n11_1474_f0002.png 이미지

Fig. 2 Restored image after applying the transform matrix U according to the dimension d of the separated background image at 800 frames

HOJBC0_2018_v22n11_1474_f0003.png 이미지

Fig. 3 Noise image and Image restored after conversion using transformation matrix U

HOJBC0_2018_v22n11_1474_f0004.png 이미지

Fig. 4 Visibility measurement results of image when applying different feature vector dimension

HOJBC0_2018_v22n11_1474_f0005.png 이미지

Fig. 5 Visibility measurement results of image when the number of training data is different

References

  1. B. Nadella, "Eye Detection and Tracking and Eye Gaze Estimation," Asia-pacific Journal of Convergent Research Interchange, vol. 1, no. 2, pp. 25-41, Aug. 2015. https://doi.org/10.21742/apjcri.2015.06.04
  2. N. Fujiwara, and K. Terada, "Extraction of a Smoke Region using Fractal Coding," in Proceedings of IEEE International Symposium on Communication and Information, pp.659-662, 2004.
  3. I. Kopilovic, B. Vagvolgyi, and T. Sziranyi, "Application of Panoramic Annular Lens for Motion Analysis Tasks: Surveillance and Smoke Detection," in Proceedings of 15th International Conference on Pattern Recognition, pp. 714-717, 2004.
  4. C. Yu, Z. Mei, and X. Zhang, "A Real-time Video Fire Flame and Smoke Detection Algorithm," in Proceedings of 9th Asia-Oceania Symposium on Fire Science and Technology, pp. 891-898, 2013.
  5. B. D. Lucas, and T. Kanade, "An Iterative Image Registration Technique with an Application to Stereo Vision," in Proceedings of the 7th International Joint Conference on Artificial Intelligence, pp. 674-679, 1981.
  6. B. U. Toreyin, Y. Dedeoglu, and A. E. Cetin, "Wavelet Based Real-time Smoke Detection in Video," in Proceedings of 13th European Signal Processing Conference, pp. 1-4, 2005.
  7. A. Rafiee, and R. Tavakoli, "Fire and Smoke Detection using Wavelet Analysis and Disorder Characteristics," in Proceedings of 3rd International Conference on Computer Research and Development, pp.262-265, 2011.
  8. J. S. Perez, E. Meinhardt-Llopis, and G. Facciolo, "Tv-l1 Optical Flow Estimation," Image Processing On Line, vol. 3, pp.137-150, Jul. 2013. https://doi.org/10.5201/ipol.2013.26
  9. A. Stadler, and T. Ike, "Real Time Video Based Smoke Detection using Double Optical Flow Estimation," International Journal of Energy and Power Engineering, vol. 10, no. 9, pp. 1632-1637, Sep. 2016.
  10. Y. Jia, J. Yuan, J. Wang, J. Fang, Q. Zhang and Y. Zhang, "A Saliency-Based Method for Early Smoke Detection in Video Sequences," Fire Technology, vol. 52, pp.1271-1292, Sep. 2016. https://doi.org/10.1007/s10694-014-0453-y
  11. G. Lin, Y. Zhang, Q. Zhang, Y. Jia, G. Xu, and J. Wang, "Smoke Detection in Video Sequences Based on Dynamic Texture using Volume Local Binary Patterns," Transactions on Internet and Information Systems, vol. 11, no. 11, pp. 5522-5536, Nov. 2017.
  12. Y.J. Yu, S.H. Moon, S.H. Park, and C.G. Lee, "A Study on the Visibility Measurement of CCTV Video for Fire Evacuation Guidance," Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology, vol. 7, no. 12, pp. 947-954, Dec. 2017.
  13. B. J. Kim, "Feature Extraction on High Dimensional Data using Incremental PCA," Journal of the Korea Institute of Information and Communication Engineering, vol. 8, no. 7, pp. 1475-1479, Aug. 2004.
  14. P. KaewTraKullPong, and R. Bowden, "An Improved Adaptive Background Mixture Model for Real-time Tracking with Shadow Detection," in Video-based Surveillance Systems: Computer Vision and Distributed Processing, Kluwer Academic Pub., ch. 11, pp. 135-144, 2002.

Cited by

  1. 온실 내 환경데이터 분석을 통한 파프리카 온실의 식별 vol.30, pp.1, 2018, https://doi.org/10.12791/ksbec.2021.30.1.019