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

Vision-Based High Accuracy Vehicle Positioning Technology

비전 기반 고정밀 차량 측위 기술

  • Jo, Sang-Il (Korea National University of Transportation Department of Electronic Engineering) ;
  • Lee, Jaesung (Korea National University of Transportation Department of Electronic Engineering)
  • Received : 2016.09.08
  • Accepted : 2016.11.15
  • Published : 2016.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Today, technique for precisely positioning vehicles is very important in C-ITS(Cooperative Intelligent Transport System), Self-Driving Car and other information technology relating to transportation. Though the most popular technology for vehicle positioning is the GPS, its accuracy is not reliable because of large delay caused by multipath effect, which is very bad for realtime traffic application. Therefore, in this paper, we proposed the Vision-Based High Accuracy Vehicle Positioning Technology. At the first step of proposed algorithm, the ROI is set up for road area and the vehicles detection. Then, center and four corners points of found vehicles on the road are determined. Lastly, these points are converted into aerial view map using homography matrix. By analyzing performance of algorithm, we find out that this technique has high accuracy with average error of result is less than about 20cm and the maximum value is not exceed 44.72cm. In addition, it is confirmed that the process of this algorithm is fast enough for real-time positioning at the $22-25_{FPS}$.

최근 활발히 연구되고 있는 차세대 지능형교통시스템(C-ITS), 자율주행 자동차 등 교통관련 IT기술 분야에 있어 차량의 위치를 정밀하게 측정하는 기술은 매우 중요하다. 도로위의 차량 측위를 위한 기술은 GPS 가 대표적이나 도심지로 가면 주위에 고층건물이 많아 GPS 신호가 반사되어 심한 경우는 2~300 m의 오차가 발생할 정도로 정확도가 매우 떨어진다. 따라서 본 논문에서는 비전기반의 고정밀 차량측위 기술을 제안한다. 개략적인 처리과정은 고정된 카메라로부터 입력받은 영상 속에 관심 영역을 설정한 후 영역 내 차량 객체 검출(Vehicle Detection)을 수행하여 객체가 점유하는 도로영역을 계산, 미리 정의된 Homography변환행렬을 이용하여 지도영상으로 사용할 항공시점(Aerial View) 상의 점들로 변환하여 측위를 수행한다. 측위성능분석결과 평균적으로 약 20cm이내의 높은 정확도를 가지고 있으며 최대 오차역시 44.72cm를 넘지 않았다. 또한 $22-25_{FPS}$ 의 빠른 처리로 실시간 측위가 가능함을 확인하였다.

Keywords

References

  1. Lane-Level Vehicle Positioning using DSRC as an Aiding Signal, Transportation Systems Research Group, College of Engineering - Center for Environmental Research and Technology (CE-CERT), University of California, Riverside (UCR).
  2. H.-I. Kim, J. Kim, K.-T. Kim, K.-D. Park, and D. Kim, "Accuracy evaluation of DGPS service via terrestrial digital multimedia broadcasting," J. Navig. Port Res., vol. 36, no. 6, pp. 437-442, 2012. https://doi.org/10.5394/KINPR.2012.36.6.437
  3. C. S. Sin, J. H. Kim, and J. Y. Ahn, "Technical development trends of satellite based augmentation system," Electron. and Telecommun. Trends, vol. 29, no. 3, Jun. 2014.
  4. David M. Bevly, J. Britt, S. Martin, and C. Rose, Auburn's next generation vehicle positioning, http://www.eng.auburn.edu/-dmbevly/FHWA_AU_EAR2/FHWA_final_demo_presentation.pdf
  5. R. Hartley and A. Zisserman, Multiple View Geomerty in Computer Vision, Cambridge University Press, 2nd Ed., 2003.
  6. M. Piccardi, "Background subtraction techniques: a review," IEEE Int. Conf. Systems, Man and Cybernetics, vol. 4. Oct. 2004.
  7. M. Yokoyama and T. Poggio, "A contour-based moving object detection and tracking," in Proc. 2nd Joint IEEE Int. Workshop on VS-PETS, pp. 271-276, Beijing, Oct. 2005.
  8. D. Douglas and T. Peucker, "Algorithms for the reduction of the number of points required for represent a digitized line or its caricature," Canadian Cartographer, vol. 10, pp. 112-122, 1973. https://doi.org/10.3138/FM57-6770-U75U-7727
  9. H. K. Lee, J. G. Lee, and G.-I. Jee. "Channelwise multipath detection for general GPS receivers," J. Inst. Control, Robotics and Syst., vol. 8, no. 9, pp. 818-826, Sept. 2002. https://doi.org/10.5302/J.ICROS.2002.8.9.818