The Journal of Korean Institute of Communications and Information Sciences (한국통신학회논문지)

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지
DOI QR코드

DOI QR Code

Detection of Illegal U-turn Vehicles by Optical Flow Analysis

옵티컬 플로우 분석을 통한 불법 유턴 차량 검지

  • Song, Chang-Ho (Korea National University of Transportation Department of Electronic Engineering) ;
  • Lee, Jaesung (Korea National University of Transportation Department of Electronic Engineering)
  • Received : 2014.07.14
  • Accepted : 2014.09.15
  • Published : 2014.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Today, Intelligent Vehicle Detection System seeks to reduce the negative factors, such as accidents over to get the traffic information of existing system. This paper proposes detection algorithm for the illegal U-turn vehicles which can cause critical accident among violations of road traffic laws. We predicted that if calculated optical flow vectors were shown on the illegal U-turn path, they would be cause of the illegal U-turn vehicles. To reduce the high computational complexity, we use the algorithm of pyramid Lucas-Kanade. This algorithm only track the key-points likely corners. Because of the high computational complexity, we detect center lane first through the color information and progressive probabilistic hough transform and apply to the around of center lane. And then we select vectors on illegal U-turn path and calculate reliability to check whether vectors is cause of the illegal U-turn vehicles or not. Finally, In order to evaluate the algorithm, we calculate process time of the type of algorithm and prove that proposed algorithm is efficiently.

오늘날 지능형 영상 검지기 시스템(Intelligent Vehicle Detection System)이 추구하는 방향은 기존 시스템의 교통 소통 정보 습득을 넘어서 교통정체, 사고 등과 같은 부정적인 요인을 줄이는 것이다. 본 논문에서는 도로 교통법규 위반 상황 중에서 가장 치명적인 사고를 유발 할 수 있는 불법 유턴 차량을 검지하는 알고리즘을 제안한다. 영상의 옵티컬 플로우 벡터(Optical Flow Vector)를 구하고 이 벡터가 불법 유턴 경로 상에 나타난다면 불법 유턴차량에 의해 생긴 벡터일 확률이 높을 것이라는 점에 착안하여 연구를 진행했다. 옵티컬 플로우 벡터를 구하기 전에 연산량 절감을 위하여 코너(corner)와 같은 특징점을 선지정한 후 그 점들에 대해서만 추적하는 피라미드 루카스-카나데(pyramid Lucas-Kanade) 알고리즘을 사용했다. 이 알고리즘은 연산량이 매우 높기 때문에 먼저 컬러 정보와 진보된 확률적 허프 변환(progressive probabilistic hough transform)으로 중앙선을 검출하고 그 주위 영역에만 적용시켰다. 그리고 검출된 벡터들 중 불법 유턴 경로위의 벡터들을 선별하고 이 벡터들이 불법 유턴 차량에 의해 생긴 벡터들인지 확인하기 위해 신뢰도를 검증하여 불법 유턴 차량을 검지하였다. 최종적으로 알고리즘의 성능을 평가하기 위해 알고리즘별 처리시간을 측정하였으며 본 논문에서 제안한 알고리즘이 효율적임을 증명하였다.

Keywords

References

  1. J. Lee, B. K. Kim, and S. H. Kim, "A study on the application of the interrupted traffic flow incident detection algorithm using fixed detector," J. Korean Soc. Civil Eng., vol. 4, pp. 33-36, Oct. 2000.
  2. Act on Special Cases concerning the Settlement of Traffic Accidents, Korea Law Service Center.
  3. B.-C. Ko, J.-Y. Nam, and J. Y. Kwak, "Object tracking using particle filters in moving camera," J. KICS, vol. 37, no. 5, pp. 375-387, May 2012. https://doi.org/10.7840/KICS.2012.37A.5.375
  4. Y.-E. An and J.-A. Park, "Color correlogram using combined RGB and HSV color spaces for image retrieval," J. KICS, vol. 32, no. 5, pp. 513-519, May 2007.
  5. L. N. P. Boggavarapu, et al. "A robust multi color lane marking detection approach for Indian scenario," Int. J. Advanced Comput. Sci. & Appl., vol. 2, no. 5, pp. 71-75, May 2011. https://doi.org/10.5121/acij.2011.2207
  6. J.-R. Lee, K. Bae, and B. Moon, "A hardware architecture of hough transform using an improved voting scheme," J. KICS, vol. 9, no. 38, pp. 773-781, Sept. 2013. https://doi.org/10.7840/kics.2013.38A.9.773
  7. J. Matas, C. Galambos, and J. Kittler, "Robust detection of lines using the progressive probabilistic hough transform," Computer Vision Image Understanding, vol. 78, no. 1, pp. 119-137, Apr. 2000. https://doi.org/10.1006/cviu.1999.0831
  8. C. Schmid, R. Mohr, and C. Bauckhage, "Evaluation of interest point detectors," Int. J. Computer Vision, vol. 37, no. 2, pp. 151-172, Jun. 2000. https://doi.org/10.1023/A:1008199403446
  9. C. Harris and M. J. Stephens, "A combined corner and edge detector," Alvey Vision Conf., pp. 147-152, Manchester, United Kingdom, Sept. 1988.
  10. H. Moravec, Obstacle avoidance and navigation in the real world by a seeing robot rover, Stanford Univ. CA Dept. Comput. Sci., No. STAN-CS-80-813, 1980.
  11. Baker, Simon, et al., "A database and evaluation methodology for optical flow," Int. J. Computer Vision, vol. 92, no. 1, pp. 1-31, Mar. 2011. https://doi.org/10.1007/s11263-010-0390-2
  12. J.-Y. Bouguet, Pyramidal implementation of the Lucas Kanade feature tracker description of the algorithm, Retrieved June, 15, 2014, from http://robots.stanford.edu/cs223b04/algo_tracking.pdf.
  13. C. Ha, C. Choi, and J. Jeong, "Contrast enhancement algorithm using singular value decomposition and image pyramid," J. KICS, vol. 38, no. 11, pp. 928-937, Nov. 2013. https://doi.org/10.7840/kics.2013.38A.11.928
  14. G. Farneback, "Two-frame motion estimation based on polynomial expansion," Lecture Notes in Comput. Sci., vol. 2749, pp. 363-370, Jun. 2003.