Journal of the Institute of Electronics and Information Engineers (전자공학회논문지)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지
DOI QR코드

DOI QR Code

Localization of A Moving Vehicle using Backward-looking Camera and 3D Road Map

후방 카메라 영상과 3차원 도로지도를 이용한 이동차량의 위치인식

  • Choi, Sung-In (School of Electrical and Electronic Engineering, Kyungpook National University) ;
  • Park, Soon-Yong (School of Computer Science and Engineering, Kyungpook National University)
  • 최성인 (경북대학교 전자전기컴퓨터학부) ;
  • 박순용 (경북대학교 IT대학 컴퓨터학부)
  • Received : 2012.09.06
  • Published : 2013.03.25
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a new visual odometry technique by combining a forward-looking stereo camera and a backward-looking monocular camera. The main goal of the proposed technique is to identify the location of a moving vehicle which travels long distance and comes back to the initial position in urban road environments. While the vehicle is moving to the destination, a global 3D map is updated continuously by a stereo visual odometry technique using a graph theorem. Once the vehicle reaches the destination and begins to come back to the initial position, a map-based monocular visual odometry technqieu is used. To estimate the position of the returning vehicle accurately, 2D features in the backward-looking camera image and the global map are matched. In addition, we utilize the previous matching nodes to limit the search ranges of the next vehicle position in the global map. Through two navigation paths, we analyze the accuracy of the proposed method.

본 논문에서는 실외 도로환경에서 주행하는 차량의 위치를 추정하기 위한 비쥬얼 오도메트리 기술을 제안한다. 제안하는 방법은 운전자의 이동계획에 따라 차량의 초기위치에서 원거리에 위치한 특정 목적지를 방문한 후 지나온 경로를 따라 다시 초기위치로 정확하게 복귀해야 하는 차량의 위치인식을 위해 사용된다. 위치인식에는 차량 전방의 3차원 정보획득을 위한 스테레오 카메라와 후방의 영상을 획득하는 단일 카메라를 사용한다. 차량이 목적지를 향해 순방향 주행할 때는 전방 스테레오 비쥬얼 오도메트리(stereo visual odometry)를 이용하여 이동차량의 위치를 추정하고 동시에 도로 및 주변 환경에 대한 3차원 전역지도를 그래프 구조로 생성한다. 차량이 목적지에 도달하여 복귀할 때는 후방의 단일 카메라에서 획득한 2차원 영상과 전역지도를 바탕으로 모노 비쥬얼 오도메트리(monocular visual odometry)로 위치를 추정한다. 복귀하는 차량의 위치를 정확하게 추정하기 위해서는 효과적인 전역지도의 노드 탐색방법이 요구된다. 후방 카메라의 영상 특징과 전역지도의 각 노드의 영상 특징을 정합하고 지도에 저장된 3차원 좌표를 이용하여 차량의 위치를 추정하였다. 또한 3차원 위치추정에 성공한 이전노드들의 정보를 바탕으로 매 영상 프레임마다 적응적으로 탐색영역을 확장하거나 줄이도록 하였다. 두 개의 서로 다른 경로에 대한 실험을 통하여 제안하는 방법의 성능을 검증하였다.

Keywords

References

  1. R. Madhavan and E. Messina, "Iterative registration of 3d lader data for autonomous navigation," in Proceedings of the The IEEE Symposium on Intelligent Vehicles, pp. 186-191, 2003.
  2. R. Madhavan, T. Hong and E. Messina, "Temporal range registration for unmanned ground and aerial vehicles," Journal of Intelligent and Robotics Systems, vol. 44, no. 1, pp. 47-69, 2005. https://doi.org/10.1007/s10846-005-9025-1
  3. N. Vandapel and M. Hebert, "3D Rover localization in airborne lader data," The International Symposium on Experimental Robotics, July 2002.
  4. N. Vandapel, R. Raghavendra, R. Donamukkala, and M. Hebert, "Unmanned ground vehicle navigation using aerial lader data," The International Journal of Robotics Research, vol. 25, no. 1, pp. 31-51, 2006. https://doi.org/10.1177/0278364906061161
  5. J. J. Biesiadecki and M. Maimone, "The Mars Exploration Rover Surface Mobility Flight Software: Driving Ambition," in Proceedings of the IEEE conference on Aerospace, 2006.
  6. E. Jones, B. Fulkerson, E. Frazzoli, D. Kumar, R. Walters, J. Radford, R. Mason, "Autonomous Off-Road Driving in the DARPA Grand Challenge," The IEEE Symposium on Position Location, And Navigation 2006.
  7. "Google driverless car", Google, http://en.wikipedia.org/wiki/Google_driverless_car
  8. A. Howard, "Real-time stereo visual odometry for autonomous ground vehicles," in Proceedings of the IEEE conference on Intelligent Robots and Systems, pp. 22-26, 2008.
  9. P. Nunez, R. Vazquez-Mart, A. Bandera, and F. Sandoval, "Combined Constraint Matching Algorithm for Stereo Visual Odometry based on Local Interest Points," in Proceedings of the IEEE conference on Intelligent Robots and Systems, pp. 3095-3100, 2008.
  10. M. Agrawal and K. Konolige, "Real-time Localization in Outdoor Environments using Stereo Vision and Inexpensive GPS," in Proceedings of the IEEE International Conference on Pattern Recognition, pp. 1063-1068, 2006.
  11. I. Parra, M. A. Sotelo, D. F. Llorca, C. Fernandez, A. Llamazares, N. Hernandez and I. Garcia, "Visual odometry and map fusion for GPS navigation assistance," The IEEE Symposium on Industrial Electronics, pp. 832-837, 2011.
  12. L. Wei, C. Cappelle, Y. Ruichek and F. Zann, "GPS and Stereovision-Based Visual Odometry: Application to Urban Scene Mapping and Intelligent Vehicle Localization," The International Journal of Vehicular Technology, vol. 2011, special page 1-13, 2011.
  13. B. Musleh, D. Martin, A. Escalera and J. M. Armingol, "Visual ego motion estimation in urban environments based on U-V disparity," The IEEE Symposium on Intelligent Vehicles, pp. 444-449, 2012.
  14. G. L. Mariottini and S. I. Roumeliotis, "Active Vision-Based Robot Localization and Navigation in a Visual Memory," The IEEE International Conference on Robotics and Automation, 2011.
  15. Z. Zhu, T. Oskiper, S. Samarasekera, H. Sawhney and R. Kumar, "Ten-fold improvement in visual odometry using landmark matching," in Proceedings of the IEEE International Conference on Computer Vision, 2007.
  16. Z. Zhu, T. Oskiper, S. Samarasekera, R. Kumar and H. Sawhney, "Real-time Global Localization with a Pre-Built Visual Landmark Database," in Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, 2008.
  17. A. Geiger, M. Roser and R. Urtasun, "Effcient large-scale stereo matching," in Proceedings of the Asian Conference on Computer Vision, 2010.
  18. R. Hartley and A. Zisserman, "Multiple View Geometry in Computer Vision,' 2nd Ed, Cambridge University Press, 2004.
  19. H. Bay, A. Ess, T. Tuytelaars, L. V. Gool, "SURF: Speeded Up Robust Features", Computer Vision and Image Understanding (CVIU), Vol. 110, No. 3, pp. 346-359, 2008. https://doi.org/10.1016/j.cviu.2007.09.014
  20. S. Umeyama, "Least-Square Estimation of Transformation Parameters Between Two Patterns," In IEEE Transaction on Pattern Analysis and Machine Intelligence, 4(13): 376-380, April, 1991.
  21. K. Levenberg, "A method for the solution of certain non-linear problems in least square," The Quarterly of Applied Mathmatics, pp. 164-168, 1944.
  22. M. Muja and D. G. Lowe, "Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration", in International Conference on Computer Vision Theory and Applications, 2009.
  23. E. Trucco and A. Verri, "Introductory Techniques for 3-D Computer Vision," pp. 132-134, 1998.
  24. "Camera Calibration Toolbox for Matlab," http://www.vision.caltech.edu/bouguetj/calib_doc/
  25. S. I. Choi, L. Zhang, and S. Y. Park, "Stereo Vision based Motion Adjustment of 2D Laser Scan Matching," in Proceedings of the International Conference on Image and Vision Computing New Zealand, 2011.
  26. D. Nister, 0. Naroditsky, J. Bergen, "Visual Odometry," in Proceedings of the International Conference on Computer Vision and Pattern Recognition, pp. 652-659, 2004.
  27. A. J. Davison, I. Reid, N. Molton and O. Stasse, "MonoSLAM: Real-time single camera SLAM," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 29, No. 6, pp 1052-1067, 2007. https://doi.org/10.1109/TPAMI.2007.1049