Skip to main content
SpringerLink
Log in

Efficient Hierarchical Triplet Merging for Camera Pose Estimation

  • Conference paper
  • First Online:
Pattern Recognition (GCPR 2014)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 8753))

Included in the following conference series:

Abstract

This paper deals with efficient means for camera pose estimation for difficult scenes. Particularly, we speed up the combination of image triplets to image sets by hierarchical merging and a reduction of the number of merged points. By image sets we denote a generalization of image sequences where images can be linked in multiple directions, i.e., they can form a graph. To obtain reliable results for triplets, we use large numbers of corresponding points. For a high-quality and yet efficient merging of the triplets we propose strategies for the reduction of the number of points. The strategies are evaluated based on statistical measures employing the full covariance information for the camera poses from bundle adjustment. We show that to obtain a statistically sound result, intuitively appealing deterministic reduction strategies are problematic and that a simple reduction strategy based on random deletion was evaluated best. We also discuss the benefits of the evaluation measures for finding conceptual and implementation weaknesses. The paper is illustrated with a number of experiments giving standard deviations for all values.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Agarwal, S., Snavely, N., Simon, I., Seitz, S., Szeliski, R.: Building rome in a Day. In: Twelfth International Conference on Computer Vision, pp. 72–79 (2009)

    Google Scholar 

  2. Bartelsen, J., Mayer, H., Hirschmüller, H., Kuhn, A., Michelini, M.: Orientation and dense reconstruction from unordered wide baseline image sets. Photogram. Fernerkun. Geoinformation 4(12), 4–432 (2012)

    Google Scholar 

  3. Fischler, M., Bolles, R.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)

    Article  MathSciNet  Google Scholar 

  4. Fitzgibbon, A.W., Zisserman, A.: Automatic camera recovery for closed or open image sequences. In: Burkhardt, H.-J., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1406, pp. 311–326. Springer, Heidelberg (1998)

    Google Scholar 

  5. Förstner, W., Dickscheid, T., Schindler, F.: Detecting interpretable and accurate scale-invariant keypoints. In: Twelfth International Conference on Computer Vision, pp. 2256–2263 (2009)

    Google Scholar 

  6. Frahm, J.-M., Fite-Georgel, P., Gallup, D., Johnson, T., Raguram, R., Wu, C., Jen, Y.-H., Dunn, E., Clipp, B., Lazebnik, S., Pollefeys, M.: Building rome on a cloudless day. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 368–381. Springer, Heidelberg (2010)

    Chapter  Google Scholar 

  7. Jeong, Y., Nistér, D., Steedly, D., Szeliski, R., Kweon, I.S.: Pushing the envelope of modern methods for bundle adjustment. IEEE Trans. Pattern Anal. Mach. Intell. 34(8), 1605–1617 (2012)

    Article  Google Scholar 

  8. Jian, Y.D., Balcan, D., Dellaert, F.: Generalized subgraph preconditioners for large-scale bundle adjustment. In: Thirteenth International Conference on Computer Vision, pp. 295–302 (2011)

    Google Scholar 

  9. Klingner, B., Martin, D., Roseborough, J.: Street view motion-from-structure-from-motion. In: Fourteenth International Conference on Computer Vision, pp. 953–960 (2013)

    Google Scholar 

  10. Klopschitz, M., Irschara, A., Reitmayr, G., Schmalstieg, D.: Robust incremental structure from motion. In: Fifth International Symposium on 3D Data Processing, Visualization and Transmission (3DPVT), pp. 1–7 (2010)

    Google Scholar 

  11. Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)

    Article  Google Scholar 

  12. Mayer, H., Bartelsen, J., Hirschmüller, H., Kuhn, A.: Dense 3D reconstruction from wide baseline image sets. In: Dellaert, F., Frahm, J.-M., Pollefeys, M., Leal-Taixé, L., Rosenhahn, B. (eds.) Real-World Scene Analysis 2011. LNCS, vol. 7474, pp. 285–304. Springer, Heidelberg (2012)

    Chapter  Google Scholar 

  13. McGlone, J. (ed.): Manual of Photogrammetry, 6th edn. American Society of Photogrammetry and Remote Sensing, Bethesda (2013)

    Google Scholar 

  14. Strecha, C., von Hansen, W., Van Gool, L., Fua, P., Thoennessen, U.: On benchmarking camera calibration and multi-view stereo for high resolution imagery. In: Computer Vision and Pattern Recognition, pp. 1–8 (2008)

    Google Scholar 

  15. Torr, P., Zisserman, A.: Robust parametrization and computation of the trifocal tensor. Image Vis. Comput. 15, 591–605 (1997)

    Article  Google Scholar 

Download references

Acknowledgments

We want to thank Wolfgang Förstner for his invaluable recommendations and clarifications and the reviewers for their helpful comments.

Author information

Authors and Affiliations

  1. Institute of Applied Computer Science, Bundeswehr University Munich, Neubiberg, Germany

    Helmut Mayer

Authors
  1. Helmut Mayer
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Helmut Mayer .

Editor information

Editors and Affiliations

  1. Department of Mathematics and Computer Science, University of Münster, Münster, Germany

    Xiaoyi Jiang

  2. Computer Science Department 5, University of Erlangen-Nürnberg, Erlangen, Germany

    Joachim Hornegger

  3. Department of Computer Science, University of Kiel, Kiel, Germany

    Reinhard Koch

Rights and permissions

Reprints and permissions

Copyright information

© 2014 Springer International Publishing Switzerland

About this paper

Cite this paper

Mayer, H. (2014). Efficient Hierarchical Triplet Merging for Camera Pose Estimation. In: Jiang, X., Hornegger, J., Koch, R. (eds) Pattern Recognition. GCPR 2014. Lecture Notes in Computer Science(), vol 8753. Springer, Cham. https://doi.org/10.1007/978-3-319-11752-2_32

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-11752-2_32

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-11751-5

  • Online ISBN: 978-3-319-11752-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation