The KIPS Transactions:PartB (정보처리학회논문지B)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Robust Vision Based Algorithm for Accident Detection of Crossroad

교차로 사고감지를 위한 강건한 비젼기반 알고리즘

  • 정성환 (전북대학교 컴퓨터공학과) ;
  • 이준환 (전북대학교 컴퓨터공학과)
  • Received : 2010.12.22
  • Accepted : 2011.05.19
  • Published : 2011.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

The purpose of this study is to produce a better way to detect crossroad accidents, which involves an efficient method to produce background images in consideration of object movement and preserve/demonstrate the candidate accident region. One of the prior studies proposed an employment of traffic signal interval within crossroad to detect accidents on crossroad, but it may cause a failure to detect unwanted accidents if any object is covered on an accident site. This study adopted inverse perspective mapping to control the scale of object, and proposed different ways such as producing robust background images enough to resist surrounding noise, generating candidate accident regions through information on object movement, and by using edge information to preserve and delete the candidate accident region. In order to measure the performance of proposed algorithm, a variety of traffic images were saved and used for experiment (e.g. recorded images on rush hours via DVR installed on crossroad, different accident images recorded in day and night rainy days, and recorded images including surrounding noise of lighting and shades). As a result, it was found that there were all 20 experiment cases of accident detected and actual effective rate of accident detection amounted to 76.9% on average. In addition, the image processing rate ranged from 10~14 frame/sec depending on the area of detection region. Thus, it is concluded that there will be no problem in real-time image processing.

본 논문에서는 객체이동을 고려한 배경영상 생성과 사고 후보영역의 보존 및 검증하는 방법을 포함하는 개선된 교차로 교통사고 감지 방법을 제안한다. 교차로 내 신호등 주기를 이용한 교차로 사고감지 방법이 제안된 바 있는데 이는 사고 객체의 가려짐이 발생할 경우 사고를 감지하지 못하는 문제가 발생할 수 있다. 본 논문에서는 역원근변환을 수행하여 객체의 크기를 일정하게 하였으며, 환경잡음에 강건한 배경영상 생성, 객체의 이동정보를 이용한 사고 후보영역의 생성, 에지 정보를 이용한 사고 후보영역의 보존 및 삭제 방법 등을 제안한다. 제안한 알고리즘의 성능을 알아보기 위하여 교차로에 설치된 DVR을 통해 출퇴근 시간대의 영상, 야간 및 주간의 우천 시의 다양한 사고 영상, 조명 및 그림자의 환경적 잡음이 포함된 영상을 저장하여 실험하였다. 실험 결과 실험에 포함된 20건의 사고를 모두 감지하였으며 실제 사고 유효 획득률은 76.9%로 나타났다. 또한 검지영역의 면적에 따라 초당 10~14프레임의 처리속도를 나타내어 실시간 처리에 문제가 없을 것으로 판단된다.

Keywords

References

  1. 이형석, 김영욱, 권대길, 박기현, 이경복, 한민홍, "영상과 음향기반의 교차로 내 교통사고 검지시스템의 구현," 제어자동화시스템공학회, Vol.10, No.6, 2004.
  2. 김만배, 유성준, 김완기, "교통사고 자동기록장치의 설치효과 분석," 대한전자공학회, 텔레콤, Vol. 22, No. 2, pp. 18-26, 2006.
  3. 정성환, 이준환, "신호등 주기를 이용한 교차로 교통사고감지 알고리즘," 한국정보처리학회, Vol.16-B, No.1, pp.17-24, 2009. https://doi.org/10.3745/KIPSTB.2009.16-B.1.17
  4. Young-Kul Ki, Dong-Young Lee, "A Traffic Accident Recording and Reporting Model at Intersections," IEEE Transaction on Intelligent Transportation System, Vol.8, No.2, 2007. https://doi.org/10.1109/TITS.2006.890070
  5. Shunsuke Kamijo, Yasuyuki Matsushita, Katsushi Ikeuchi, Masao Sakauchi, "Traffic Monitoring and Accident Detection at Intersections," IEEE Transaction on Intelligent Transportation System, Vol.1, No.2, 2000. https://doi.org/10.1109/6979.880968
  6. Veeraraghavan H., Masoud O., Papanikolopoulos N.P., "Computer Vision Algorithms for Intersection Monitoring," IEEE Transactions on Intelligent Transportation Systems, Vol.4, No.2, pp.78-89, 2003. https://doi.org/10.1109/TITS.2003.821212
  7. ZuWhan Kim, "Real Time Object Tracking based on Dynamic Feature Grouping with Background Subtraction," IEEE Conference on Computer Vision and Pattern Recognition, 2008. https://doi.org/10.1109/CVPR.2008.4587551
  8. 이희신, 이준환, "특징점 추적을 이용한 끼어들기 위반차량 검지시스템," 한국ITS학회, Vol.8, No.2, pp.36-44, 2009.
  9. ZuWhan Kim, Jitendra Malik, "Fast Vehicle Detection With Probabilistic Feature Grouping and Its Application to Vehicle Tracking," IEEE International Conference On Computer Vision, Vol.1, pp.524-531, 2003. https://doi.org/10.1109/ICCV.2003.1238392
  10. Gianluca Antonini, Jean Philippe Thiran, "Counting Pedestrians in Video Sequence Using Trajectory Clustering," IEEE Transactions on Circuits and Sustem for Video Technology, Vol.16, No.8, 2006. https://doi.org/10.1109/TCSVT.2006.879118
  11. Jae-Young Choi, Jin-Woo Choi, and Young-Kyu Yang, "Improved Tracking of Multiple Vehicles Using Invariant Feature-Based Matching," Pattern Recognition and Machine Intelligence LNCS, Vol.4815, pp.649-656, 2007. https://doi.org/10.1007/978-3-540-77046-6_80
  12. ZuWhan Kim, Gabriel Gomes, Robert Hranac, Alexander Sakbardonis, "A Machine Vision System for Generating Vehicle Trajectories over Extended Freeway Segments," 12th World Congress on Intelligent Transportation Systems, 2005.
  13. Michael Haag, Hans-Hellmut Nagel, "Combination of Edge Element and Optical Flow Estimates for 3D-Model-Based Vehicle Tracking in Traffic Image Sequence," International Journal of Computer Vision, Vol.35, No.3, pp.295-319, 1999. https://doi.org/10.1023/A:1008112528134
  14. Dongjin Han, Matthew J. Leotta, David B. Cooper, Joseph L. Mundy, "Vehicle Class Recognition from Video based on 3D Curve Probes," 2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, pp.285-292, 2005. https://doi.org/10.1109/VSPETS.2005.1570927
  15. W. Forstner and E. Gulch, "A Fast Operator for Detection and Precise Location of Distinct Points, Corners, and Centers of Circular Features," In Ptoc. Intercommision Conf. on Fast Processing of Phtogrammetric Data, pp.281-305, 1987.
  16. D. M. Ha, J. -M. Lee, Y. -D. Kim, "Neural-edge-based vehicle detection and traffic parameter extraction," Image and Vision Computing, Vol.22, pp.899-907, 2004. https://doi.org/10.1016/j.imavis.2004.05.006
  17. Yiyan WANG, Yuexian ZOU, Hang SHI, He ZHAO, "Video Image Detection System for Signaled Traffic Intersection," International Conference on Hybrid Intelligent System, 2009
  18. 정성환, 이준환, "신경망을 이용한 차량 객체의 그림자 제거," 한국ITS학회, Vol.7, No.1. pp.32-41. 2008.
  19. Andrea Prati, Inana Mikic, Mohan M. Trivedi, Rita Cucchiara, "Detecting Moving Shadow: Formulation, Algorithm and Evaluation," IEEE Transaction Pattern Analysis and Machine Intelligence, Vol.25, No.7, pp.918-923, 2003. https://doi.org/10.1109/TPAMI.2003.1206520
  20. Rita Cucchiara, Costantino Grana, Massimo Piccardi, Andrea Prati, Stefano Sirotti, "Improving Shadow Suppression in Moving Object Detection with HSV Color Information," Proc. IEEE Intelligent Transportation System Conference, pp.334-339. 2001. https://doi.org/10.1109/ITSC.2001.948679
  21. Rafael C. Gonzalez, Richard E. Woods, "Digital Image Processing-Second Edition," Prentice Hall,, 2002.
  22. 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. https://doi.org/10.1109/TPAMI.2005.102
  23. Chee Sun Won, Dong Kwon Park, Soo Jun Park, "Efficient Use of MPEG-7 Edge Histogram Descriptor," ETRI Journal, Vol.24, No.1, pp.23-30, 2002. https://doi.org/10.4218/etrij.02.0102.0103