Localization of a Monocular Camera using a Feature-based Probabilistic Map

특징점 기반 확률 맵을 이용한 단일 카메라의 위치 추정방법

  • 김형진 (KAIST 건설 및 환경공학과) ;
  • 이동화 (KAIST 건설 및 환경공학과) ;
  • 오택준 (KAIST 건설 및 환경공학과) ;
  • 명현 (KAIST 건설 및 환경공학과)
  • Received : 2014.11.15
  • Accepted : 2015.02.25
  • Published : 2015.04.01


In this paper, a novel localization method for a monocular camera is proposed by using a feature-based probabilistic map. The localization of a camera is generally estimated from 3D-to-2D correspondences between a 3D map and an image plane through the PnP algorithm. In the computer vision communities, an accurate 3D map is generated by optimization using a large number of image dataset for camera pose estimation. In robotics communities, a camera pose is estimated by probabilistic approaches with lack of feature. Thus, it needs an extra system because the camera system cannot estimate a full state of the robot pose. Therefore, we propose an accurate localization method for a monocular camera using a probabilistic approach in the case of an insufficient image dataset without any extra system. In our system, features from a probabilistic map are projected into an image plane using linear approximation. By minimizing Mahalanobis distance between the projected features from the probabilistic map and extracted features from a query image, the accurate pose of the monocular camera is estimated from an initial pose obtained by the PnP algorithm. The proposed algorithm is demonstrated through simulations in a 3D space.


Grant : 실외환경에 강인한 도로 기반 저가형 자율주행기술 개발

Supported by : 산업통상자원부


  1. T. Jebara, A. Azarbayejani, and A. Pentland, "3D structure from 2D motion," Signal Processing Magazine, vol. 16, no. 3, pp. 66-84, 1999.
  2. B. Triggs, P. F. Hartley, R. I. Hartley, and A. Fitzgibbon, "Bundle adjustment-a modern synthesis," In Vision Algorithms: Theory and Practice, pp. 298-372, 2000.
  3. G. Lu and C. Kambhamettu, "Image-based indoor localization system based on 3D SfM model," IS&T/SPIE Electronic Imaging. International Society for Optics and Photonics, pp. 90250H-90250H-8, Dec. 2013.
  4. H. Kim, D. Lee, T. Oh, and H. Myung, "Camera pose estimation using probabilistic feature map," Proc. of ICROS (Institute of Control, Robotics and Systems) 2014 Daejeon-Chungchung Branch Conference (in Korean), KAIST, Nov. 2014.
  5. T. Sattler, B. Leibe, and L. Kobbelt, "Fast image-based localization using direct 2D-to-3D matching," Proc. of ICCV (Int'l Conf. on Computer Vision) 2011, pp. 667-674, Nov. 2011.
  6. M. G. Dissanayake, P. Newman, S. Clark, and H. F. Durrantwhyte, "A solution to the simultaneous localization and map building (SLAM) problem," Robotics and Automation, IEEE Transactions on, vol. 17, no. 3, pp. 229-241, Jun. 2001.
  7. D. Lee, H. Kim, and H. Myung, "Image feature-based real-time RGB-D 3D SLAM with GPU acceleration," Journal of Institute of Control, Robotics and Systems (in Korean), vol. 19, no. 5, pp. 457-461, May 2013.
  8. Y. -S. Jeon, J. Choi, and J. O. Lee, "Development of a SLAM system for small UAVs in indoor environments using gaussian processes," Journal of Institute of Control, Robotics and Systems (in Korean), vol. 20, no. 11, pp. 1098-1102, Nov. 2014.
  9. S. Thrun, W. Burgard, and D. Fox, Probabilistic Robotics, MIT press, 2005.
  10. T. Lemaire, S. Lacroix, and J. Sola, "A practical 3D bearing-only SLAM algorithm," Proc. of IROS(Intelligent Robots and Systems) 2005, pp. 2449-2454, Aug. 2005.
  11. A. J. Davison, I. D. Reid, and N. D. Molton, "MonoSLAM: Real-time single camera SLAM," Pattern Analysis and Machine Intelligence, vol. 29, no. 6, pp. 1052-1067, 2007.
  12. A. Costa, G. Kantor, and H. Choset, "Bearing-only landmark initialization with unknown data association," Proc. of ICRA (Int'l Conf. on Robotics and Automation) 2004, vol. 2, pp. 1764-1770, 2004.
  13. T. Bailey, "Constrained initialisation for bearing-only SLAM," Proc. of ICRA (Int'l Conf. on Robotics and Automation) 2003, vol. 2, pp. 1966-1971, 2003.
  14. R. C. Smith and P. Cheeseman, "On the representation and estimation of spatial uncertainty," The International Journal of Robotics Research, vol. 5, no. 4, pp. 56-68, 1986.
  15. A. Irschara, C. Zach, J. M. Frahm, and H. Bischof, "From structure-from-motion point clouds to fast location recognition," Computer Vision and Pattern Recognition, 2009, pp. 2599-2606, 2009.
  16. G. Lu, V. Ly, H. Shen, A. Kolagunda, and C. Kambhamettu, "Improving image-based localization through increasing correct feature correspondences," Advances in Visual Computing, pp. 312-321, 2013.
  17. V. Lepetit, F. Moreno-Noguer, and P. Fua, "Epnp: An accurate o (n) solution to the pnp problem," International Journal of Computer Vision, vol. 81, no. 2, pp. 155-166, 2009.