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

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

DOI QR Code

Preliminary study on car detection and tracking method using surveillance camera in tunnel environment for accident detection

터널 내 유고상황 자동 판정을 위한 선행 연구: CCTV를 이용한 차량의 탐지와 추적 기법 고찰

  • Oh, Young-Sup (Research & Development Department, SB Network Ltd.) ;
  • Shin, Hyu-Soung (Extreme Construction Research Center, Korea Institute of Civil Engineering and Building Technology)
  • 오영섭 ((주)SB네트워크, 연구개발실) ;
  • 신휴성 (한국건설기술연구원 극한건설연구단)
  • Received : 2017.08.24
  • Accepted : 2017.09.14
  • Published : 2017.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Surveillance cameras installed in tunnels capture the various video frames effected by dynamic and variable factors. In addition, localizing and managing the cameras in tunnel is not affordable, and quality of capturing frame is effected by time. In this paper, we introduce a new method to detect and track the vehicles in tunnel by using surveillance cameras installed in a tunnel. It is difficult to detect the video frames directly from surveillance cameras due to the motion blur effect and blurring effect on lens by dirt. In order to overcome this difficulties, two new methods such as Differential Frame/Non-Maxima Suppression (DFNMS) and Haar Cascade Detector to track cars are proposed and investigated for their feasibilities. In the study, it was shown that high precision and recall values could be achieved by the two methods, which then be capable of providing practical data and key information to an automatic accident detection system in tunnels.

터널 내의 CCTV 영상은 동적으로 변화하는 요소들에 의해 영향을 받는 다양한 영상들을 촬영한다. 또한, 카메라의 상태 또한 관리 및 배치가 쉽지 않아 터널 내부 환경 변화에 따라 영상이 달라지는 경향이 있다. 본 논문에서는 터널 내에 설치된 CCTV 카메라 영상을 이용해 차량을 탐지하고 그 차량을 지속적으로 추적하는 새로운 방법을 소개한다. 터널 내 CCTV 카메라 영상은 모션블러 효과와 먼지로 인한 렌즈 흐려짐 효과로 인해 바로 차량을 탐지할 수 없다는 문제점이 있다. 본 논문에서는 이를 극복하기 위해 차영상/비-최대 억제 기법과 Haar Cascade 기법 등에 대한 효과 검토 실험을 제안하고 수행하였다. 본 논문에서 제안하는 방법을 통해 터널 내에 설치된 CCTV에서 차량의 탐지와 추적을 효과적으로 수행할 수 있으며 다양한 터널 유고상황을 자동으로 파악하기 위한 중요 정보를 확보할 수 있었다.

Keywords

References

  1. Alonso, J.D., Vidal, R.R., Rotter, A., Muhlenberg, M. (2008), "Lane-change decision aid system based on motion-driven vehicle tracking", in IEEE Transactions on Vehicular Technology, Vol. 57, No. 5, pp. 2736-2746. https://doi.org/10.1109/TVT.2008.917220
  2. Cekander, R., Han, F., Kumar, R., Shan,Y., Sawhney, H.S. (2006), A two-stage approach to people and vehicle detection with HOG-Based SVM.
  3. Chen, C.T., Su, C.Y., Kao, W.C. (2010), "An enhanced segmentation on vision-based shadow removal for vehicle detection", The 2010 International Conference on Green Circuits and Systems, Shanghai, 2010, pp. 679-682.
  4. Hartigan, J.A., Wong, M.A. (1979), "Algorithm AS 136: A k-means clustering algorithm." Journal of the Royal Statistical Society, Series C (Applied Statistics) 28.1, pp. 100-108.
  5. Haselhoff, A., Kummert, A. (2009), "A vehicle detection system based on Haar and Triangle features", 2009 IEEE Intelligent Vehicles Symposium, Xi'an, pp. 261-266.
  6. Javed, O., Shah, M. (2002), "Tracking and object classification for automated surveillance", Computer Vision-ECCV 2002, 7th European Conference on Computer Vision, Copenhagen, Denmark, May 28-31, Proceedings Part IV, pp. 343-357.
  7. Neubeck, A., Van Gool, L. (2006), "Efficient non-maximum suppression", 18th International Conference on Pattern Recognition (ICPR'06), Hong Kong, pp. 850-855.
  8. Omar, J., Mubarak, S. (2002), Tracking and object classification for automated surveillance. Lecture Notes in Computer Science, 2353, pp. 343-357.
  9. Shin, H.S., Kim, D.G., 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. 95-107. https://doi.org/10.9711/KTAJ.2017.19.1.095
  10. Tsai, L.W., Hsieh, J.W., Fan, K.C. (2007), "Vehicle detection using normalized color and edge map." IEEE transactions on Image Processing 16.3, pp. 850-864. https://doi.org/10.1109/TIP.2007.891147
  11. Unzueta, L., Nieto, M., Cortes, A., Barandiaran, J., Otaegui, O., Sanchez, P. (2012), "Adaptive multicue background subtraction for robust vehicle counting and classification", in IEEE Transactions on Intelligent Transportation Systems, Vol. 13, No. 2, pp. 527-540. https://doi.org/10.1109/TITS.2011.2174358
  12. Viola, P., Jones, M. (2001), "Rapid object detection using a boosted cascade of simple features", in Proceedings IEEE Conference, Computer Vision and Pattern Recognition, Kauai, HI, USA, pp. 511-518.
  13. Yu, S., Zheng, S., Yang, H., Liang, L. (2013), "Vehicle logo recognition based on Bag-of-Words", 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance, Krakow, pp. 353-358.
  14. Zhang, H., Wu, K. (2012), "A vehicle detection algorithm based on three-frame differencing and background subtraction", Computational Intelligence and Design (ISCID), 2012 Fifth International Symposium on, Vol. 1.