Advertisement

Stable Structure from Motion for Unordered Image Collections

  • Carl Olsson
  • Olof Enqvist
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6688)

Abstract

We present a non-incremental approach to structure from motion. Our solution is based on robustly computing global rotations from relative geometries and feeding these into the known-rotation framework to create an initial solution for bundle adjustment. To increase robustness we present a new method for constructing reliable point tracks from pairwise matches. We show that our method can be seen as maximizing the reliability of a point track if the quality of the weakest link in the track is used to evaluate reliability. To estimate the final geometry we alternate between bundle adjustment and a robust version of the known-rotation formulation. The ability to compute both structure and camera translations independent of initialization makes our algorithm insensitive to degenerate epipolar geometries. We demonstrate the performance of our system on a number of image collections.

Keywords

Image Point Point Track Bundle Adjustment Epipolar Geometry Robust Version 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    The MOSEK optimization toolbox for MATLAB manualGoogle Scholar
  2. 2.
    Agarwal, S., Snavely, N., Simon, I., Sietz, S., Szeliski, R.: Building rome in a day. In: Int. Conf. Computer Vision (2010)Google Scholar
  3. 3.
    Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: Surf: Speeded up robust features. Computer Vision and Image Understanding (2008)Google Scholar
  4. 4.
    Beder, C., Steffen, R.: Determining an initial image pair for fixing the scale of a 3D reconstruction from an image sequence. In: Franke, K., Müller, K.-R., Nickolay, B., Schäfer, R. (eds.) DAGM 2006. LNCS, vol. 4174, pp. 657–666. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  5. 5.
    Bondy, J.A., Murty, U.S.R.: Graph Theory. Springer, Heidelberg (2008)CrossRefzbMATHGoogle Scholar
  6. 6.
    Brown, M., Lowe, D.: Unsupervised 3d object recognition and reconstruction in unordered datasets. In: Conf. 3-D Digital Imaging and Modeling (2005)Google Scholar
  7. 7.
    Cornelis, K., Verbiest, F., Van Gool, L.: Drift detection and removal for sequential structure from motion algorithms. Trans. Pattern Analysis and Machine Intelligence (2004)Google Scholar
  8. 8.
    Dai, Y., Trumpf, J., Li, H., Barnes, N., Hartley, R.: Rotation averaging with application to camera-rig calibration. In: Asian Conf. on Computer Vision (2009)Google Scholar
  9. 9.
    Dalalyan, A., Keriven, R.: L1-penalized robust estimation for a class of inverse problems arising in multiview geometry. Neural Information Processing Systems (2009)Google Scholar
  10. 10.
    Enqvist, O., Kahl, F., Olsson, C.: Stable structure from motion using rotational consistency. Technical report, Centre for Mathematical Sciences, Lund University (2010)Google Scholar
  11. 11.
    Fitzgibbon, A., Zisserman, A.: Automatic camera recovery for closed or open image sequences. In: Eur. Conf. Computer Vision (1998)Google Scholar
  12. 12.
    Gherardi, R., Farenzena, M., Fusiello, A.: Improving the efficiency of hierarchical structure-and-motion. In: Conf. Computer Vision and Pattern Recognition (2010)Google Scholar
  13. 13.
    Govindu, V.: Combining two-view constraints for motion estimation. In: Conf. Computer Vision and Pattern Recognition (2001)Google Scholar
  14. 14.
    Govindu, V.: Robustness in motion averaging. In: Eur. Conf. Computer Vision (2006)Google Scholar
  15. 15.
    Kahl, F., Hartley, R.: Multiple view geometry under the L  ∞ -norm. Trans. Pattern Analysis and Machine Intelligence (2008)Google Scholar
  16. 16.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. Journal of Computer Vision (2004)Google Scholar
  17. 17.
    Martinec, D., Pajdla, T.: Robust rotation and translation estimation in multiview reconstruction. In: Conf. Computer Vision and Pattern Recognition (2007)Google Scholar
  18. 18.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. Trans. Pattern Analysis and Machine Intelligence (2005)Google Scholar
  19. 19.
    Nistér, D.: Reconstruction from uncalibrated sequences with a hierarchy of trifocal tensors. In: Eur. Conf. Computer Vision (2000)Google Scholar
  20. 20.
    Nistér, D.: An efficient solution to the five-point relative pose problem. Trans. Pattern Analysis and Machine Intelligence (2004)Google Scholar
  21. 21.
    Nistér, D., Stewénius, H.: Scalable recognition with a vocabulary tree. In: Conf. Computer Vision and Pattern Recognition (2006)Google Scholar
  22. 22.
    Olsson, C., Hartley, I., Eriksson, A.: Outlier removal using duality. In: Conf. Computer Vision and Pattern Recognition (2010)Google Scholar
  23. 23.
    Schaffalitzky, F., Zisserman, A.: Multi-view matching for unordered image sets, or How do I organize my holiday snaps?. In: Eur. Conf. Computer Vision (2002)Google Scholar
  24. 24.
    Snavely, N., Seitz, S.M., Szeliski, R.: Modeling the world from Internet photo collections. Int. Journal on Computer Vision 80(2), 189–210 (2008)CrossRefGoogle Scholar
  25. 25.
    Szeliski, R.: Computer Vision: Algorithms and Applications. Springer, Heidelberg (2010)zbMATHGoogle Scholar
  26. 26.
    Thormaehlen, T., Broszio, H., Weissenfeld, A.: Keyframe selection for camera motion and structure estimation from multiple views. In: Eur. Conf. Computer Vision (2004)Google Scholar
  27. 27.
    Torr, P., Fitzgibbon, A., Zisserman, A.: The problem of degeneracy in structure and motion recovery from uncalibrated image sequences. Int. Journal on Computer Vision (1999)Google Scholar
  28. 28.
    Triggs, B., McLauchlan, P., Hartley, R., Fitzgibbon, A.: Bundle adjustment - a modern synthesis. In: Int. Conf. Computer Vision (1999)Google Scholar
  29. 29.
    Zach, C., Klopschitz, M., Pollefeys, M.: Disambiguating visual relations using loop constraints. In: Conf. Computer Vision and Pattern Recognition (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Carl Olsson
    • 1
  • Olof Enqvist
    • 1
  1. 1.Centre for Mathematical SciencesLund UniversitySweden

Personalised recommendations