Journal of Korean Tunnelling and Underground Space Association (한국터널지하공간학회 논문집)

Korean Tunnelling and Underground Space Association (한국터널지하공간학회)
권호 표지
DOI QR코드

DOI QR Code

Development of a deep-learning based tunnel incident detection system on CCTVs

딥러닝 기반 터널 영상유고감지 시스템 개발 연구

  • Shin, Hyu-Soung (Extreme Construction Research Center, Korea Institute of Civil Engineering and Building Technology) ;
  • Lee, Kyu-Beom (Geotechnical Engineering Research Institute, Korea Institute of Civil Engineering and Building Technology Integrated Master's and Doctoral Degree Course, Geo-space Engineering Department, University of Science & Technology) ;
  • Yim, Min-Jin (Geotechnical Engineering Research Institute, Korea Institute of Civil Engineering and Building Technology) ;
  • Kim, Dong-Gyou (Geotechnical Engineering Research Institute, Korea Institute of Civil Engineering and Building Technology)
  • 신휴성 (한국건설기술연구원 극한건설연구단) ;
  • 이규범 (한국건설기술연구원 지반연구소, 과학기술연합대학원대학교(UST) 지반신공간공학과) ;
  • 임민진 (한국건설기술연구원 지반연구소) ;
  • 김동규 (한국건설기술연구원 지반연구소)
  • Received : 2017.09.20
  • Accepted : 2017.11.09
  • Published : 2017.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, current status of Korean hazard mitigation guideline for tunnel operation is summarized. It shows that requirement for CCTV installation has been gradually stricted and needs for tunnel incident detection system in conjunction with the CCTV in tunnels have been highly increased. Despite of this, it is noticed that mathematical algorithm based incident detection system, which are commonly applied in current tunnel operation, show very low detectable rates by less than 50%. The putative major reasons seem to be (1) very weak intensity of illumination (2) dust in tunnel (3) low installation height of CCTV to about 3.5 m, etc. Therefore, an attempt in this study is made to develop an deep-learning based tunnel incident detection system, which is relatively insensitive to very poor visibility conditions. Its theoretical background is given and validating investigation are undertaken focused on the moving vehicles and person out of vehicle in tunnel, which are the official major objects to be detected. Two scenarios are set up: (1) training and prediction in the same tunnel (2) training in a tunnel and prediction in the other tunnel. From the both cases, targeted object detection in prediction mode are achieved to detectable rate to higher than 80% in case of similar time period between training and prediction but it shows a bit low detectable rate to 40% when the prediction times are far from the training time without further training taking place. However, it is believed that the AI based system would be enhanced in its predictability automatically as further training are followed with accumulated CCTV BigData without any revision or calibration of the incident detection system.

본 논문에서는 2016년을 기준으로 강화된 터널 방재시설 설치 및 관리지침과, 점차 강화되고 있는 터널 CCTV설치 터널등급 기준과 터널 영상유고감지 시스템의 설치 운용에 대한 요구의 증가 상황을 정리해 보고하였다. 그럼에도, 가동중인 알고리즘 기반의 터널 영상유고감시 시스템의 정상 인지율은 50%가 채 되지 않는 것으로 파악되었으며, 그에 대한 주원인은 터널 내 낮은 조도, 심한 먼지로 인한 영상 선명도 저하, 낮은 CCTV 설치위치로 인한 이동객체의 겹침현상 등으로 파악되었다. 따라서, 본 연구에서는 이러한 열악한 조건에서도 영상유고 정상 인지율을 확보할 수 있는 딥러닝 기반 영상유고감지 시스템을 개발하였으며, 이에 대한 이론적 배경 제시와 시스템의 타당성 검토 연구가 진행되었다. 개발 시스템의 타당성 검토 연구는 터널 방재시설 및 관리지침 내 영상유고감지 항목중 정지 및 역주행 차량을 감지하는 주요 정보인 차량 객체 인식과 보행자 감지를 중심으로 진행되었다. 또한, (1) 동일 터널 내에서 학습과 추론이 이루어 지는 경우와 (2) 다양한 터널의 영상 정보를 통합 학습하고, 각 터널의 영상유고감지에 투입되는 경우, 두개의 시나리오를 설정하여 타당성 검토를 진행하였다. 두 시나리오 모두 일정 시간의 학습 자료와 유사한 상황에 대해서는 열악한 터널환경과 무관하게 그 감지성능이 80% 이상으로 우수하나, 추가 학습 없이 학습된 시간 구간과 멀어질수록 그 추론 성능은 상대적으로 낮은 40% 수준으로 떨어짐을 알 수 있었다. 그러나, 시간이 지남에 따라 자동으로 누적되어 확장되는 영상유고 빅데이터를 반복적으로 학습함으로써, 설치된 영상유고감지 시스템의 보완이나 보정절차 없이도 자동으로 그 영상유고감지 성능이 향상될 수 있음을 보였다.

Keywords

References

  1. Choi, J.M., Kwon, J.O. (2010), "Converged security market trend report", Samsung SDS, Samsung SDS Journal of IT Services, Vol.7, No. 2, pp. 13-29.
  2. Everingham, M., Gool, L.V., Williams, C.K.I., Winn, J., Zisserman, A. (2010), "The pascal visual object classes (VOC) challenge", International Journal of Computer Vision, Vol. 88, No. 2, pp. 303-338. https://doi.org/10.1007/s11263-009-0275-4
  3. Geiger, A., Lenz, P., Stiller, C., Urtasun, R. (2013), "Vision meets robotics: The KITTI dataset", The International Journal of Robotics Research, Vol. 32, No. 11, pp. 1231-1237. https://doi.org/10.1177/0278364913491297
  4. Girshick, R., Donahue, J., Darrell, T., Malik, J. (2014), "Rich feature hierarchies for accurate object detection and semantic segmentation", The IEEE conference on Computer Vision and Pattern Recognition, pp. 580-587.
  5. Girshick, R. (2015), "Fast R-CNN", The IEEE international conference on computer vision, pp. 1440-1448.
  6. Hinton, G.E., Osindero, S., Teh, Y.W. (2006), "A fast learning algorithm for deep belief nets", Neural Computation, Vol. 18, No. 7, pp. 1527-1554. https://doi.org/10.1162/neco.2006.18.7.1527
  7. Simonyan, K., Zisserman, A. (2014), "Very deep convolutional networks for large-scale image recognition", arXiv preprint, arXiv: 1409.1556.
  8. Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L. (2014), "Large-scale video classification with convolutional neural networks", The IEEE conference on Computer Vision and Pattern Recognition. pp. 1725-1732.
  9. Kim, T.B. (2016), "The national highway, expressway tunnel video incident detection system performance analysis and reflect attributes for double deck tunnel in great depth underground space", Journal of the Korea Institute of Information and Communication Engineering, Vol. 20, No. 7, pp. 1325-1334. https://doi.org/10.6109/jkiice.2016.20.7.1325
  10. Korea Tunneling and Underground Space Association (KTA) (2015), Study on revision of installation and operation guideline for hazard mitigation facilities of road tunnels, Ministry of Land Infrastructure and Transport (MOLIT), pp. 326.
  11. Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollar, P., Zitnick, C.L. (2014), "Microsoft coco: Common objects in context", European Conference on Computer Vision. Springer, Cham, pp. 740-755.
  12. Ministry of Land, Infrastructure and Transport (MOLIT) (2016a), "Attempt for faultless safety system of road tunnels", Press Release.
  13. Ministry of Land, Infrastructure and Transport (MOLIT) (2016b), Guideline of installation and management of disaster prevention facilities on road tunnels.
  14. Mu, Z. (2004), "Recall, precision and average precision", Working Paper, Department of Statistics and Actuarial Science, University of Waterloo, Vol. 2, pp. 30.
  15. National Committee for Land and Transport (2016), "Tunnel accidents increase, but tunnel incident automatic detection system often fails in operation", Press Release from parliamentary inspection of MOLIT. Congressman Yoon Hoo-Dyuk.
  16. Park, J.K., Park, Y.K., On, H.I., Kang, D.J. (2015), "Object perception methods in image using deep learning", Institute of Control, Robotics and Systems, Journal of Institute of Control, Robotics and Systems, Vol. 21, No. 4, pp. 21-26. https://doi.org/10.5302/J.ICROS.2015.14.9055
  17. Ren, S., He, K., Girshick, R., Sun, J. (2015), "Faster R-CNN: Towards real-time object detection with region proposal networks", Advances in Neural Information Processing Systems 28, pp. 91-99.
  18. Roh, C.G., Park, B.J., Kim, J.S. (2016), "A study on the contents for operation of tunnel management systems using a view synthesis technology", The Journal of the Korea Contents Association, Vol. 16, No. 6, pp. 507-515. https://doi.org/10.5392/JKCA.2016.16.06.507
  19. Samuel, A.L. (1959), "Some studies in machine learning using the game of checkers", IBM Journal of Research and Development, Vol. 3, No. 3, pp. 210-229. https://doi.org/10.1147/rd.33.0210
  20. Shin, H.S., Kim, D.K., Yim, M.J., Lee, K.B., Oh, Y.S. (2017), "A preliminary study for development of an automatic incident detection system on CCTV in tunnels based on a machine learning algorithm", Journal of Korean Tunnelling and Underground Space Association, Vol. 19, No. 1, pp. 96-107.
  21. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R. (2014), "Dropout: a simple way to prevent neural networks from overfitting", Journal of Machine Learning Research, Vol. 15, No. 1, pp. 1929-1958.
  22. LeCun, Y., Boser, B.E., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W.E., Jackel, L.D. (1990), "Handwritten digit recognition with a back-propagation network", Advances in Neural Information Processing Systems, pp. 396-404.
  23. LeCun, Y., Yoshua, B., Geoffrey, H. (2015), "Deep learning", Nature, Vol. 521, pp. 436-444. https://doi.org/10.1038/nature14539
  24. Yoshua, B., Courville, A., Vincent, P. (2013), "Representation learning: a review and new perspectives", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 35, No. 8, pp. 1798-1828. https://doi.org/10.1109/TPAMI.2013.50