Advertisement

Machine Vision and Applications

, Volume 16, Issue 5, pp 321–329 | Cite as

Preemptive RANSAC for live structure and motion estimation

  • David Nistér
Original Paper

Abstract

A system capable of performing robust live ego-motion estimation for perspective cameras is presented. The system is powered by random sample consensus with preemptive scoring of the motion hypotheses. A general statement of the problem of efficient preemptive scoring is given. Then a theoretical investigation of preemptive scoring under a simple inlier–outlier model is performed. A practical preemption scheme is proposed and it is shown that the preemption is powerful enough to enable robust live structure and motion estimation.

Keywords

Structure from motion Real-time Robust estimation 3D-Reconstruction Ego-motion 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Triggs, B., McLauchlan, P., Hartley, R., Fitzgibbon, A.: Bundle adjustment—a modern synthesis. Springer Lecture Notes on Computer Science, vol. 1883, pp. 298–375. Springer Verlag, Berlin Heidelberg New York (2000)Google Scholar
  2. 2.
    Fischler, M., Bolles, R.: Random sample consensus: a paradigm for model fitting with application to image analysis and automated cartography. Commun. Assoc. Comp. Mach. 24, 381–395 (1981)MathSciNetGoogle Scholar
  3. 3.
    Torr, P., Zisserman, A.: MLESAC: a new robust estimator with application to estimating image geometry. Comput. Vision Image Understand. 78, 138–156 (2000)CrossRefGoogle Scholar
  4. 4.
    Torr, P., Murray, D.: The development and comparison of robust methods for estimating the fundamental matrix. Int. J. Comput. Vision 24(3), 271–300 (1997)CrossRefGoogle Scholar
  5. 5.
    Torr, P., Murray, D.: Outlier detection and motion segmentation. In: SPIE Sensor Fusion Conference VI, pp. 432–443, September 1993Google Scholar
  6. 6.
    Zhang, Z.: Determining the epipolar geometry and its uncertainty: a review. Int. J. Comput. Vision 27(2), 161–195 (1998)CrossRefGoogle Scholar
  7. 7.
    Beardsley, P., Zisserman, A., Murray, D.: Sequential updating of projective and affine structure from motion. Int. J. Comput. Vision 23(3), 235–259 (1997)CrossRefGoogle Scholar
  8. 8.
    Nistér, D.: Reconstruction from uncalibrated sequences with a hierarchy of trifocal tensors. In: Proceedings of the European Conference on Computer Vision, vol. 1, pp. 649–663 (2000)Google Scholar
  9. 9.
    Nistér, D.: In: Automatic dense reconstruction from uncalibrated video sequences. PhD Thesis, Royal Institute of Technology KTH, ISBN 91-7283-053-0, March 2001Google Scholar
  10. 10.
    Pollefeys, M., Koch, R., Van Gool, L.: Self-calibration and metric reconstruction in spite of varying and unknown internal camera parameters. Int. J. Comput. Vision 32(1), 7–25 (1999)CrossRefGoogle Scholar
  11. 11.
    Pollefeys, M., Verbiest, F., Van Gool, L.: Surviving dominant planes in uncalibrated structure and motion recovery. In: Proceedings of the European Conference on Computer Vision, vol. 2, pp. 837–851 (2002)Google Scholar
  12. 12.
    Torr, P., Fitzgibbon, A., Zisserman, A.: The problem of degeneracy in structure and motion recovery from uncalibrated image sequences. Int. J. Comput. Vision 32(1), 27–44 (1999)CrossRefGoogle Scholar
  13. 13.
    2d3 Ltd. Boujou, http://www.2d3.com
  14. 14.
    Oliensis, J.: A critique of structure from motion algorithms. Comput. Vision Image Understand. 80, 172–214 (2000)CrossRefzbMATHGoogle Scholar
  15. 15.
    Nistér, D.: An efficient solution to the five-point relative pose problem. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 195–202 (2003)Google Scholar
  16. 16.
    Hartley, R., Silpa-Anan, C.: Reconstruction from two views using approximate calibration. In: Proceedings of the 5th Asian Conference on Computer Vision, Melbourne, Australia, January 2002Google Scholar
  17. 17.
    Björkman, M., Eklundh, J.: Real-time epipolar geometry estimation and disparity. In: Proceedings of the International Conference on Computer Vision, pp. 234–241 (1999)Google Scholar
  18. 18.
    Chiuso, A., Favaro, P., Jin, H., Soatto, S.: 3-D motion and structure causally integrated over time: implementation. In: Proceedings of the European Conference on Computer Vision. Lecture Notes in Computer Science, vol. 1842, pp. 735–750. Springer Verlag, Berlin Heidelberg New York (2000)Google Scholar
  19. 19.
    Jin, H., Favaro, P., Soatto, S.: Real-time 3-D motion and structure from point features: a front-end system for vision-based control and interaction. In: Proceedings of the IEEE Interantional Conference on Computer Vision and Pattern Recognition, pp. 778–779 (2000)Google Scholar
  20. 20.
    Jin, H., Favaro, P., Soatto, S.: Real-time feature tracking and outlier rejection with changes in illumination. In: International Conference on Computer Vision, pp. 684–689 (2001)Google Scholar
  21. 21.
    Chum, O., Matas, J.: Randomized RANSAC with T d,d test. In: Proceedings of the British Machine Vision Conference, pp. 448–457 (2002)Google Scholar
  22. 22.
    Tordoff, B., Murray, D.: Guided sampling and consensus for motion estimation. In: Proceedings of the European Conference on Computer Vision. Springer Lecture Notes on Computer Science, vol. 2350, pp. 82–96 (2002)Google Scholar
  23. 23.
    Haralick, R., Lee, C., Ottenberg, K., Nölle, M.: Review and analysis of solutions of the three point perspective pose estimation problem. Int. J. Comput. Vision 13(3), 331–356 (1994)CrossRefGoogle Scholar
  24. 24.
    Press, W., Teukolsky, S., Vetterling, W., Flannery, B.: Numerical recipes in C. Cambridge University Press, Cambridge (1988)zbMATHGoogle Scholar
  25. 25.
    Lacey, A., Pinitkarn, N., Thacker, N.: An evaluation of the performance of RANSAC algorithms for stereo camera calibration. In: Proceedings of British Machine Vision Conference, pp. 646–655 (2000)Google Scholar

Copyright information

© Springer-Verlag 2005

Authors and Affiliations

  1. 1.Sarnoff CorporationPrincetonUSA
  2. 2.Center for Visualization and Virtual Environments, Computer Science DepartmentUniversity of KentuckyLexingtonUSA

Personalised recommendations