Skip to main content
Log in

Visual SLAM Based on Rigid-Body 3D Landmarks

  • Published:
Journal of Intelligent & Robotic Systems Aims and scope Submit manuscript

Abstract

In current visual SLAM methods, point-like landmarks (As in Filliat and Meyer (Cogn Syst Res 4(4):243–282, 2003), we use this expression to denote a landmark generated by a point or an object considered as punctual.) are used for representation on maps. As the observation of each point-like landmark gives only angular information about a bearing camera, a covariance matrix between point-like landmarks must be estimated in order to converge with a global scale estimation. However, as the computational complexity of covariance matrices scales in a quadratic way with the number of landmarks, the maximum number of landmarks that is possible to use is normally limited to a few hundred. In this paper, a visual SLAM system based on the use of what are called rigid-body 3D landmarks is proposed. A rigid-body 3D landmark represents the 6D pose of a rigid body in space (position and orientation), and its observation gives full-pose information about a bearing camera. Each rigid-body 3D landmark is created from a set of N point-like landmarks by collapsing 3N state components into seven state components plus a set of parameters that describe the shape of the landmark. Rigid-body 3D landmarks are represented and estimated using so-called point-quaternions, which are introduced here. By using rigid-body 3D landmarks, the computational time of an EKF-SLAM system can be reduced up to 5.5%, as the number of landmarks increases. The proposed visual SLAM system is validated in simulated and real video sequences (outdoor). The proposed methodology can be extended to any SLAM system based on the use of point-like landmarks, including those generated by laser measurement.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Filliat, D., Meyer, J.-A.: Map-based navigation in mobile robots: I. A review of localization strategies. Cogn. Syst. Res. 4(4), 243–282 (2003)

    Article  Google Scholar 

  2. Neira, J., Davison, A.J., Leonard, J.J.: Guest editorial special issue on visual SLAM. IEEE Trans. Robotics 24(4), 929–931 (2008)

    Article  Google Scholar 

  3. Hauke Strasdat, J., Montiel, M. Davison, A.J.: Scale Drift-Aware Large Scale Monocular SLAM, RSS (2010)

  4. Civera, J, Grasa, O.G., Davison, A.J., Montiel, J.M.M.: 1-point RANSAC for EKF-based Structure from Motion, IROS 2009 Proceedings, pp. 3498–3504

  5. Handa, A., Chli, M., Strasdat, H., Davison, A.J.: Scalable Active Matching, Proc. 2010 IEEE Conf. on Computer Vision and Pattern Recognition, June 13–18, 2010, San Francisco

  6. Davison, A.J., Reid, I.D., Molton, N., Otasse, O.: MonoSLAM: Real-time single camera SLAM. IEEE Trans. Pattern Anal. Mach. Intell. 29(6), 1052–1067 (2007)

    Article  Google Scholar 

  7. Nistér, D., Naroditsky, O., Bergen, J.: Visual odometry for ground vehicle applications. J. Field Robot. 23(1), 3–20 (2006)

    Article  MATH  Google Scholar 

  8. Nistér, D.: Preemptive RANSAC for live structure and motion estimation. Mach. Vis. Appl. 16(5), 321–329 (2005)

    Article  Google Scholar 

  9. Davison, A.J.: Real-time simultaneous localisation and mapping with a single camera, ICCV 2003 Proceedings, pp. 1403–1410 vol. 2

  10. Newcombe, R, Davison, A.J.: Live Dense Reconstruction with a Single Moving Camera, IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2010)

  11. Angeli, A., Davison, A.J.: Live Feature Clustering in Video Using Appearance and 3D Geometry, BMVC (2010)

  12. Gee, A.P., Chekhlov, D., Calway, A., Mayol-Cuevas, W.: Discovering higher level structure in visual SLAM. IEEE Trans. Robotics 24(5), 980–990 (2008)

    Article  Google Scholar 

  13. Kwon, J., Lee, K.M.: Monocular SLAM with Locally Planar Landmarks via Geometric Rao-Blackwellized Particle Filtering on Lie Groups, 2010 IEEE Conf. on Computer Vision and Pattern Recognition-CVPR 2010, pp. 1522–1529, 13–18 June 2010, San Francisco, USA

  14. Civera, J., Davison, A.J., Martínez-Montiel, M.: Inverse depth parametrization for monocular SLAM. IEEE Trans. Robotics 24(5), 932–945 (2008)

    Article  Google Scholar 

  15. Pathak, K., Birk, A., Vaskevicius, N., Poppinga, J.: Fast registration based on noisy planes with unknown correspondences for 3D mapping. IEEE Trans. Robotics 26(3), 424–441 (2010)

    Article  Google Scholar 

  16. Kohlhepp, P., Pozzo, P., Walther, M., Dillmann, R.: Sequential 3D-SLAM for mobile action planning, Proc. 2004 IEEE/RSJ International Conf. on Intelligent Robots and Systems, Sendai, Japan

  17. Pathak, K., Birk, A., Vaskevicius, N., Pfingsthorn, M., Schwertfeger, S., Poppinga, J.: Online 3D SLAM by registration of large planar surface segments and closed form pose-graph relaxation. J. Field Robot. 27(1), 52–84 (2009)

    Article  Google Scholar 

  18. Magnusson, M., Lilienthal, A., Duckett, T.: Scan registration for autonomous mining vehicles using 3D-NDT. J. Field Robot. 24(10), 803–827 (2007)

    Article  Google Scholar 

  19. Hamilton, W.R.: On quaternions, or on a new system of imaginaries in algebra. Philos. Mag. 25(3), 489–495 (1844)

    MathSciNet  Google Scholar 

  20. Loncomilla, P.: Generación automática de landmarks visuales naturales tridimensionales basada en descriptores locales para auto-localización de robots móviles, Ph.D. Thesis, Universidad de Chile (2010)

  21. Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. Comput. Vis. Image Underst. 110(3), 346–359 (2008)

    Article  Google Scholar 

  22. Haralick, B.M., Lee, Ch.-N., Ottenberg, K., Nölle, M.: Review and analysis of solutions of the three point perspective pose estimation problem. Int. J. Comput. Vis. 13(3), 331–356 (1994)

    Article  Google Scholar 

  23. Harris, C., Stephens, M.: A combined corner and edge detector. Proc. of the 4th Alvey Vision Conference, pp. 147–151

  24. Loncomilla, P., Ruiz del Solar, J.: A fast probabilistic model for hypothesis rejection in SIFT-based object recognition, Lecture Notes in Computer Science 4225 (CIARP 2006). Springer, 696–705

  25. Ruiz-del-Solar, J., Loncomilla, P.: Robot head pose detection and gaze direction determination using local invariant features. Adv. Robot. 23(3), 305–328 (2009)

    Article  Google Scholar 

  26. Welch, G., Bishop, G.: An introduction to the Kalman filter. University of North Carolina, Chapel Hill (1995)

    Google Scholar 

  27. LINPACK library official site: http://www.netlib.org/linpack/

  28. Grosse-Kunstleve, R.W., Terwilliger, T.C., Adams, P.D.: Experience converting a large Fortran-77 program to C++. IUCr Comp. Comm. 10, 75–84 (2009)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Patricio Loncomilla.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Loncomilla, P., del Solar, J.R. Visual SLAM Based on Rigid-Body 3D Landmarks. J Intell Robot Syst 66, 125–149 (2012). https://doi.org/10.1007/s10846-011-9601-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10846-011-9601-5

Keywords

Navigation