Journal of the Institute of Convergence Signal Processing (융합신호처리학회논문지)

The Korea Institute of Convergence Signal Processing (한국융합신호처리학회)
권호 표지

Measurement of Spatial Traffic Information by Image Processing

영상처리를 이용한 공간 교통정보 측정

  • 권영탁 (명지대학교 정보통신공학과) ;
  • 소영성 (명지대학교 정보통신공학과)
  • Published : 2001.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

Traffic information can be broadly categorized into point information and spatial information. Point information can be obtained by chocking only the presence of vehicles at prespecified points(small area), whereas spatial information can be obtained by monitoring large area of traffic scene. To obtain spatial information by image processing, we need to track vehicles in the whole area of traffic scene. Image detector system based on global tracking consists of video input, vehicle detection, vehicle tracking, and traffic information measurement. For video input, conventional approaches used auto iris which is very poor in adaptation for sudden brightness change. Conventional methods for background generation do not yield good results in intersections with heave traffic and most of the early studies measure only point information. In this paper, we propose user-controlled iris method to remedy the deficiency of auto iris and design flame difference-based background generation method which performs far better in complicated intersections. We also propose measurement method for spatial traffic information such as interval volume/lime/velocity, queue length, and turning/forward traffic flow. We obtain measurement accuracy of 95%∼100% when applying above mentioned new methods.

교통정보는 크게 지점정보와 공간정보로 나눌 수 있다. 지점정보는 한 지점에서의 차량의 유무 판정을 통해 얻을 수 있는 정보이며, 공간정보는 일정 공간을 관찰해야만 얻을 수 있는 고급 교통정보이다. 영상처리를 이용해 공간정보를 측정하기 위해서는 차량의 전역 추적을 필요로 하는데 전역 추적에 기반한 영상검지기는 비디오 입력, 차량 탐지, 차량 추적, 교통정보 측정의 네 부분으로 나눌 수 있다. 기존의 연구들은 비디오 입력시 자동 아이리스를 사용하여 급격한 밝기변화에 대응치 못하는 단점이 있고 차량 탐지시 기존의 배경생성 방법들은 정체가 심한 교차로에서 매우 좋지 않은 결과를 보인다. 또한 대부분의 연구에서 교통정보 측정을 지점 정보로만 국한하였다. 본 연구에서는 자동 아이리스의 단점 개선을 위해 사용자 제어 아이리스 방법을 제안하였고, 복잡한 교차로에서도 배경생성을 견고히 할 수 있는 장면차이 기반 배경생성 방법을 제안하였다. 또한 통행량/시간/속도는 물론 대기행렬 길이, 회전/직진 교통류의 공간 교통정보를 측정하는 방법을 제안하였고 실제 실험을 해 본 결과 95%∼100%의 정확도를 보였다.

Keywords

References

  1. IEEE Trans. Pattern Analysis and Machine Intelligence v.19 no.7 Pfiner: Real-Time Tracking of the Human Body C. Wren;A. Azarbayejani;T. Darrell;A. Pentland
  2. Proc. IEEE Workshop Application of Computer Vision Moving Target Detection and Classification from Real-Time Video A. Lipton;H. Fujiyoshi;R. Patil
  3. Proc. DARPA Image Understanding Workshop Frame-Rate Multibody Tracking for Surveillance T. Boult
  4. Proc. DARPA Image Understanding Workshop Moving Object Detection and Event Recognition Algorithms for Smart Cameras T. Olson;F. Brill
  5. 한국항행학회 논문지 v.3 no.1 차량탐지 정보를 이용한 영상검지기의 배경영상 생성 방법 권영탁;소영성;외3인
  6. IEEE Trans. on Pattern Analysis and Machine Intelligence v.22 no.8 W4: Real-Time Surveillance fo People and Their Activities Ismail Haritaoglu;David Harwood;Larry S. Davis
  7. Proc. Computer Vision and Pattern Recognition Conf. Adaptive Background Mixture Models for Real Time Tracking E. Grimson;C. Stauffer
  8. Real-Time Imaging v.1 A Window-based edge detection technique for measuring road traffic parameters in real-time M. Fathy;M. Y. Siyal
  9. IEEE Trans. v.IE-32 no.3 Traffic Monitoring and Control Using Machine Vision: A Survey Rafael M. Inigo
  10. Robot Vision B. K. P. Horn
  11. Comput. Vision, Graphics, and Image Processing v.17 Determining the instantaneous direction of motion from optic flow generated by a curvilinearly moving observer K. Prazdny
  12. IEEE Comput. v.COMP-14 no.8 Analysis of visual motion by biological and computer system S. Ullman
  13. Proc. 2nd Int. Conf. Comput. Vision Temporal edges : The detection of motion and the computation of optical flow J. H. Duncan;T. Chor
  14. Artificial Intell v.17 Determining optic flow B. K. P. Horn;B. G. Schunk
  15. Comput. Vision, Graphics, and Image Processing v.35 The image flow constraint equation B. G. Schunk
  16. Proc. IEEE Comput. Society Conf. Computer Vision and Pattern Recognition Qualitative detection of motion by a moving observer R. C. Nelson
  17. IEEE Trans. Acoustics, Speech, Signal Processing v.ASSP-37 no.9 Detection algorithms for image sequence analysis T. J. Patterson;D. M Chabries;R. W. Christiansen
  18. Machine Perception R. Nevatia
  19. IEEE Trans. Pattern Anal. Machine Intell. v.PAMI-10 Fuzzy tree automata and syntactic pattern recognition E. T. Lee
  20. IEEE Trans. Pattern Anal. Machine Intell. v.PAMI-10 Structural stereopsis for 3-D Vision K. L. Boyer;A. C. Kak
  21. IEEE Trans. Pattern Anal. Machine Intell. v.PAMI-7 A metric for comparing relational descriptions L. G. Shapiro;R. M. Haralick
  22. PH. D. thesis Dynamic color scene analysis Y. Soh
  23. IEEE Trans. Vehicular Technology v.40 no.1 Vehicle detection video through image processing: The Autoscope system P. G. Michalopoulos
  24. IEEE Trans. Vehicular Technology v.38 no.3 Application of machine vision to traffic monitoring and control R. M. Inigo
  25. Traffic Eng. and Control IMPACTS: An image analysis tool for motorway surveillance N. Hoose
  26. Proc. IEEE workshop on Applications of Comp. Vision A shadow handler in a video-based real-time traffic monitoring system M. Kilger
  27. Pattern Recognition letters v.6 Automatically extracting Traffic data from video tape using the CLIP4 parallel image processor N. Hoose;L. G. Willumsen
  28. Proc. IAPR Workshop on Computer Vision Image Processing Traffic Flow Measuring System of the Hokuriku Expressway K. Kato;et al.
  29. 국가 ITS 기술개발 기반조성을 위한 학술연구 v.3 효율적인 영상검지기를 위한 배경영상 추출 및 갱신방법에 관한 연구 김양주;소영성
  30. 한국항행학회 논문지 v.2 no.2 모션에너지와 예측을 이용한 실시간 이동물체 추적 박철홍;권영탁;소영성
  31. 공학석사 학위논문 영상 처리를 이용한 차량 추출 및 기본 공간 교통정보 측정 방법 연구 김윤진;소영성
  32. Image and Vision Computing v.8 no.3 Predicting multiple feature locations for a class of dynamic image sequences M. J. Flether;R. J. Mitchell
  33. IEEE Trans. Pattern Anal. Machine Intell. v.PAMI-9 no.1 Finding trajectories of feature points in a monocular image sequence I. K. Sethi;R. Jain
  34. Pattern Recognition v.23 no.12 Stationary background generation: An alternative to the difference of two images W. Long;Y. H. Yang
  35. Tech. Report Video Vehicle detection takes a new track W. H. Sowell;J. S. Labatt
  36. Proc. Int'l Conf. Pattern Recognition Illumination assessment for vision-based real-time traffic monitoring L. Wixson
  37. Traffic Technology International Non-intrusive guidance: Independent assessment of alternative defection devices A. E. Polk