DOI QR코드

DOI QR Code

차량의 움직임 벡터와 체류시간 기반의 교차로 추돌 검출

Traffic Collision Detection at Intersections based on Motion Vector and Staying Period of Vehicles

  • 신윤철 (한국항공대학교 항공전자 및 정보통신공학부) ;
  • 박주헌 (한국항공대학교 항공전자 및 정보통신공학부) ;
  • 이명진 (한국항공대학교 항공전자 및 정보통신공학부)
  • Shin, Youn-Chul (School of Avionics and Telecommunication Engineering, Korea Aerospace University) ;
  • Park, Joo-Heon (School of Avionics and Telecommunication Engineering, Korea Aerospace University) ;
  • Lee, Myeong-Jin (School of Avionics and Telecommunication Engineering, Korea Aerospace University)
  • 투고 : 2013.01.25
  • 심사 : 2013.02.28
  • 발행 : 2013.02.28

초록

최근 영상처리 기법에 기반한 지능형 교통시스템의 개발이 활성화되고 있다. 본 논문에서는 도심 사거리에서 획득한 비디오를 분석하여 차량의 움직임 변화와 체류시간에 기반한 추돌 검출 알고리즘을 제안한다. 가우시안 혼합 모델 기반으로 생성된 배경과 입력영상의 차 영상으로부터 관심영역(ROI)안의 객체를 추출한다. 추출된 객체에 대해 계산된 움직임벡터와 화면 내 차량 체류시간을 이용하여 교차로 내 차량추돌과 교통체증을 검출하였다. 제안된 알고리즘은 추돌을 포함한 실제 교차로 영상에 대해 테스트되었고, 탐지율은 85.7%이고, 오탐율은 7.7%였다.

Recently, intelligent transportation system based on image processing has been developed. In this paper, we propose a collision detection algorithm based on the analysis of motion vectors and the staying periods of vehicles in intersections. Objects in the region of interest are extracted from the subtraction image between background images based on Gaussian mixture model and input images. Collisions and traffic jams are detected by analysing measured motion vectors of vehicles and their staying periods in intersections. Experiments are performed on video sequences actually recoded at intersections. Correct detection rate and false alarm rate are 85.7% and 7.7%, respectively.

키워드

참고문헌

  1. Won-Sik Sin, Se-do Oh, Young-Jin Kim, "Developme nt of Traffic Congestion Prediction Module Using Vehicle Detection System for Intelligent Transportati on System", Korean Institute of Industrial Engineers, IE interfaces, vol. 23, no. 4, pp. 349-356, Dec 2010
  2. Chang Choi, Mi-Young Cho, Jun-Ho Choi, Dong-Jin Choi, Pan-Koo Kim, "Auto-Analysis of Traffic Flow through Semantic Modeling of Moving Objects", The Journal of Korean Institute of Intelligent Transport Systems, vol. 8, no. 6, pp. 36-45, Nov 2009
  3. "A Study for Improvement Measures of Urban Intersection Safety", Korea Transportation Safety Authority, 2006
  4. Yong-Kul Ki, Dong-Yung Lee, "A Traffic Accident Recording and Reporting Model at Inters- ections", IEEE Trans. Intelligent Transportation Systems, vol. 8, pp. 188-194, Issue 2, Jun 2007 https://doi.org/10.1109/TITS.2006.890070
  5. Joon-young Min, Ju-taek Oh, Myung-seob Kim, Tea-won Kim, "A Development of a Automatic Detection Program for Traffic Conflicts", The Journal of Korean Institute of Intelligent Transport Systems, vol. 7, no. 5, pp. 64-76, Oct 2008
  6. Chris Stauffer, W.E.L Grimson, "Adaptive back- grou nd mixture models for real-time tracking", IEEE Computer Society Conference on.Computer Vision and Pattern Recognition, vol.2, pp. 246-252, 1999.
  7. Robert Walczyk, Alistair Armitage and David Binnie, "Comparative study on connected com- ponent labeling algorithms for embedded video processing systems", IPCV 2010, LasVegas, USA, pp. 853-859.