DOI QR코드

DOI QR Code

Method of Tunnel Incidents Detection Using Background Image

배경영상을 이용한 터널 유고 검지 방법

  • Received : 2012.09.11
  • Accepted : 2012.12.06
  • Published : 2012.12.31

Abstract

This study suggested a method of detecting an incident inside tunnel by using camera that is installed within the tunnel. As for the proposed incident detection method, a static object, travel except vehicles, smoke, and contra-flow were detected by extracting the moving object through using the real-time background image differencing after receiving image from the camera, which is installed inside the tunnel. To detect the moving object within the tunnel, the positive background image was created by using the moving information of the object. The incident detection method was developed, which is strong in a change of lighting that occurs within the tunnel, and in influence of the external lighting that occurs in the entrance and exit of the tunnel. To examine the efficiency of the suggested method, the experimental images were acquired from Marae tunnel and Expo tunnel in Yeosu of Jeonnam and from Unam tunnel in Imsil of Jeonbuk. Number of images, which were used in experiment, included 20 cases for static object, 20 cases for travel except vehicles, 4 cases for smoke, and 10 cases for contra-flow. As for the detection rate, all of the static object, the travel except vehicles, and the contra-flow were detected in the experimental image. In case of smoke, 3 cases were detected. Thus, excellent performance could be confirmed. The proposed method is now under operation in Marae tunnel and Expo tunnel in Yeosu of Jeonnam and in Unam tunnel in Imsil of Jeonbuk. To examine accurate efficiency, the evaluation of performance is considered to be likely to be needed after acquiring the incident videos, which actually occur within tunnel.

본 논문은 터널 내에 설치된 카메라를 이용하여 터널 내 유고를 검지하는 방법을 제안하였다. 제안한 유고 검지 방법은 터널 내 설치된 카메라에서 영상을 입력받아 실시간으로 배경영상 차이법을 이용하여 움직이는 객체를 추출하여 정지물체, 차량 외 통행, 연기, 역주행을 검지하였다. 터널 내 이동하는 객체를 검지하기 위하여 객체의 이동 정보를 이용하여 능동적인 배경영상을 생성하였으며, 터널 내에서 발생하는 조명의 변화, 터널 입 출구에서 발생하는 외부 조명의 영향에 강인한 유고 검지 방법을 개발하였다. 제안한 방법의 성능을 알아보기 위하여 전남 여수의 마래터널 및 엑스포터널, 전북 임실의 운암터널에서 실험영상을 취득하였다. 실험에 사용한 영상의 개수는 정지물체 20건, 차량 외 통행 20건, 연기 4건, 역주행 10건이며 검지율은 정지물체, 차량외통행, 역주행은 실험 영상에서 모두 검지하였으며 연기의 경우 3건을 검지하여 우수한 성능을 확인할 수 있었다. 제안한 방법은 현재 전남 여수의 마래터널 및 엑스포터널, 전북 임실의 운암터널에서 운영중에 있으며 정확한 성능을 알아보기 위해서는 터널 내에서 실제 발생하는 유고 동영상을 획득한 뒤 성능 평가를 해야 할 것으로 사료된다.

Keywords

References

  1. HeeSin Lee, SungHwan Jeong, Joonwhoan Lee, "Vision-Based Fase Detection System for Tunnel Incidens", Korea ITS Journal, Vol. 9, No. 1, pp. 9-18, 2010.
  2. Shunsuke Kamijo, Hiroshi Inoue, "Incident Detection from Low-angle Images of Heavy Traggic in Tunnels", IEEE Intelligent Transportation Systems Conference, pp. 81-86, 2007, Article(CrossRefLink)
  3. BingFei Wu, ChihChung Kao, ChihChun Liu, ChungJui Fan, ChaoJung Chen, "The Vision-based Vehicle Detection and Incident Detection System in Hsueh-Shan Tunnel", IEEE International Symposium Industrial Electronics, pp. 1394-1399, 2008.
  4. DarShyang Lee, "Effective Gaussian Mixture Learning for Video Background Subtraction", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 27, No. 5, pp. 827-832, May 2005, Article(CrossRefLink) https://doi.org/10.1109/TPAMI.2005.102
  5. SungHwan Jeong, Joonwhoan Lee, "Non-Parametric Background Image Generation Based on Moving Objects", IEEK Conference, Vol. 34, No. 1, pp. 765-768, 2011.
  6. SungHwan Jeong, HeeSin Lee, Joonwhoan Lee, "Detection Method of Accident and Parking Violation for Uninterrupted Flow Facility," Korea ITS Conference, pp. 205-208, 2009.
  7. Du-Ming Tsai, Chien-Ta Lin, Jeng-Fung Chen, "The evaluation of normalized cross correlations for defect detection", Pattern Recognition Letters, Vol. 24, pp. 2525-2535, 2003, Article(CrossRefLink) https://doi.org/10.1016/S0167-8655(03)00098-9
  8. Du-Ming Tsai, Chien-Ta Lin, "Fast normalized cross correlation for defect detection", Pattern Recognition Letters, Vol. 24, pp. 2625-2631, 2003, Article(CrossRefLink) https://doi.org/10.1016/S0167-8655(03)00106-5
  9. Timo Ojala, Matti Pietikainen, Maenpaa, "Multisolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 7, 2002, Article(CrossRefLink)
  10. Yu Cui, Hua Dong, Enze Zhou, "An Early Fire Detection Method Based on Smoke Texture Analysis and Discrimination", IEEE Congress on Image and Signal Processing, pp. 95-99, 2008, Article(CrossRefLink)
  11. Rafael C. Gonzalez, Richard E. Woods, "Digital Image Processing - Second Edition," Prentice Hall, pp. 534-550, 2002.
  12. SungHwan Jeong, Joonwhoan Lee, "Measurement of the Traffic Congestion using Difference of Images in Intersection", IEEK Conference, pp. 801-802, 2008.