Frame-Frame Matching for Realtime Consistent Visual Mapping

Kurt Konolige, Motilal Agrawal

Abstract

Many successful indoor mapping techniques employ frame-to-frame matching of laser scans to produce detailed local maps, as well as closing large loops. In this paper, we propose a framework for applying the same techniques to visual imagery, matching visual frames with large numbers of point features. The relationship between frames is kept as a nonlinear measurement, and can be used to solve large loop closures quickly. Both monocular (bearing-only) and binocular vision can be used to generate matches. Other advantages of our system are that no special landmark initialization is required, and large loops can be solved very quickly.

References

  1. Agrawal, M. and Konolige, K. Real-time Localization in Outdoor Environments using Stereo Vision and Inexpensive GPS. Proceedings of the International Conference on Pattern Recognition (2006)
  2. Davison, A. Realtime SLAM with a single camera. Proc. ICCV, 2003.
  3. Craig, J.J. Introduction to robotics: mechanics and control, AddisonWesley, MA, 1989.
  4. Eade, E. and T. Drummond, "Scalable Monocular SLAM," CVPR (2006).
  5. Engels, C., H. Stewénius, D. Nistér. Bundle Adjustment Rules. Photogrammetric Computer Vision (PCV), September 2006.
  6. Fischler, M. and R. Bolles. Random sample consensus: a paradigm for model fitting with application to image analysis and automated cartography. Commun. ACM., 24:381-395, 1981.
  7. Govindu, V. M. Lie-algebraic averaging for globally consistent motion estimation. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, June 2004.
  8. Gutmann, J. S. and K. Konolige. Incremental Mapping of Large Cyclic Environments. In CIRA 99, Monterey, California, 1999.
  9. Haralick, R., C. Lee, K. Ottenberg, M. Nolle. Review and analysis of solutions of the three point perspective pose estimation problem. IJCV (1994).
  10. Hartley, R. and A. Zisserman. Multiple View Geometry in Computer Vision, Second Edition. Cambridge University Press, 2003.
  11. Hahnel, D., W. Burgard, D. Fox, and S. Thrun. An efficient FastSLAM algorithm for generating maps of large-scale cyclic environments from raw laser range measurements. In Proc. of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), 2003.
  12. Konolige, K. Large-Scale Map Making. In Proc. AAAI, San Jose, California (2004).
  13. Konolige, K. SLAM via variable reduction from constraint maps. In Proc. ICRA, March 2005.
  14. Konolige, K., Agrawal, M., Bolles, R., Cowan, C., Fischler, M. and Gerkey, B. Outdoor Mapping and Navigation using Stereo Vision. Proceedings of the International Symposium on Experimental Robotics, Brazil (2006)
  15. Lu, F. and E. E. Milios. Globally consistent range scan alignment for environment mapping. Autonomous Robots, 4(4), 1997.
  16. Montemerlo, M. and S. Thrun. Large-scale robotic 3-d mapping of urban structures. In ISER, Singapore, 2004.
  17. Montemerlo, M., Thrun, S., Koller, D. and Wegbreit, B. FastSLAM: A factored solution to the simultaneous localization and mapping problem. AAAI (2002).
  18. Nister, D., O. Naroditsky, and J. Bergen. Visual odometry. In Proc CVPR, June 2004.
  19. Olson, C. F., L. H. Matthies, M. Schoppers, and M. W. Maimone. Robust stereo egomotion for long distance navigation. In Proc CVPR, 2000.
  20. Ryan, E., Singh, H., and J. Leonard, “Exactly sparse delayed state filters,” in Proc ICRA, April 2005.
  21. Se, S., Lowe, D. G., and J. J. Little. Vision-Based Global Localization and Mapping for Mobile Robots. IEEE Transactions on Robotics, 21(3), June 2005.
  22. Se, S., Lowe, D. G., and J. J. Little. Mobile robot localization and mapping with uncertainty using scale-invariant visual landmarks, Int. J. Robot. Res.21(8), Aug. 2002.
  23. Sim, R., P. Elinas, M. Griffin, and J. J. Little. Vision-based slam using the raoblackwellised particle filter. In IJCAI Workshop on Reasoningwith Uncertainty in Robotics, 2005.
  24. Singh, H., C. Roman, O. Pizarro, and R. Eustice, Advances in high-resolution imaging from underwater vehicles, Intl. Symp. on Robotics Research, October 2005
  25. Triggs, B., P. McLauchlan, R. Hartley, and A. Fitzgibbon. Bundle adjustment - a modern synthesis. In Vision Algorithms: Theory & Practice. Springer-Verlag, 2000.
  26. Walter, M, Ryan, E, and J. J. Leonard. A provably consistent method for imposing exact sparsity in feature-based SLAM information filters. In Proc. ISRR, October 2005.
Download


Paper Citation


in Harvard Style

Konolige K. and Agrawal M. (2007). Frame-Frame Matching for Realtime Consistent Visual Mapping . In Robot Vision - Volume 1: Robot Vision, (VISAPP 2007) ISBN 978-972-8865-76-4, pages 13-26. DOI: 10.5220/0002068800130026


in Bibtex Style

@conference{robot vision07,
author={Kurt Konolige and Motilal Agrawal},
title={Frame-Frame Matching for Realtime Consistent Visual Mapping},
booktitle={Robot Vision - Volume 1: Robot Vision, (VISAPP 2007)},
year={2007},
pages={13-26},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002068800130026},
isbn={978-972-8865-76-4},
}


in EndNote Style

TY - CONF
JO - Robot Vision - Volume 1: Robot Vision, (VISAPP 2007)
TI - Frame-Frame Matching for Realtime Consistent Visual Mapping
SN - 978-972-8865-76-4
AU - Konolige K.
AU - Agrawal M.
PY - 2007
SP - 13
EP - 26
DO - 10.5220/0002068800130026