Advertisement

Learning to Select Long-Track Features for Structure-From-Motion and Visual SLAM

  • Jonas ScheerEmail author
  • Mario Fritz
  • Oliver Grau
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9796)

Abstract

With the emergence of augmented reality platforms, Structure-From-Motion or visual SLAM approaches have regained in importance in order to deliver the next generation of immersive 3D experiences. As a new quality is achieved by deployment on mobile devices, computational efficiency plays an important role. In this work, we aim to reduce complexity by limiting the number of features without sacrificing quality. We select a subset of image features, using a learning based approach. A random forest is trained to pick 2D image features which are likely to be significant for a 3D reconstruction. Additionally, we aim for an objective that selects long track features, so that they can be “re-used” in multiple frames. We evaluate our feature selection technique on real world sequences and show a significant reduction of image features and the resulting decreased computation time is not effecting the accuracy of the 3D reconstruction.

Keywords

Random Forest Feature Reduction Feature Match Camera View Feature Selection Technique 
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.
    Breiman, L., Friedman, J., Olshen, R., Stone, C.: Classification and Regression Trees. Wadsworth and Brooks, Monterey (1984)zbMATHGoogle Scholar
  2. 2.
    Gionis, A., Indyk, P., Motwani, R.: Similarity search in high dimensions via hashing. In: Proceedings of the 25th International Conference on Very Large Data Bases. VLDB 1999, pp. 518–529. Morgan Kaufmann Publishers Inc., San Francisco (1999). http://dl.acm.org/citation.cfm?id=645925.671516
  3. 3.
    Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, Cambridge (2004). ISBN: 0521540518CrossRefzbMATHGoogle Scholar
  4. 4.
    Hartmann, W., Havlena, M., Schindler, K.: Predicting matchability. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9–16, June 2014Google Scholar
  5. 5.
    Hauagge, D., Snavely, N.: Image matching using local symmetry features. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 206–213, June 2012Google Scholar
  6. 6.
    Kalman, R.: On the general theory of control systems. IRE Trans. Autom. Control 4(3), 110–110 (1959)CrossRefGoogle Scholar
  7. 7.
    Khan, N., McCane, B., Mills, S.: Feature set reduction for image matching in large scale environments. In: Proceedings of the 27th Conference on Image and Vision Computing New Zealand, IVCNZ 2012, pp. 67–72. ACM, New York (2012). http://doi.acm.org/10.1145/2425836.2425852
  8. 8.
    Klein, G., Murray, D.: Parallel tracking and mapping for small AR workspaces. In: Proceedings of the Sixth IEEE and ACM International Symposium on Mixed and Augmented Reality (ISMAR’07), Nara, Japan, November 2007Google Scholar
  9. 9.
    Leutenegger, S., Chli, M., Siegwart, R.: BRISK: binary robust invariant scalable keypoints. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 2548–2555, November 2011Google Scholar
  10. 10.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints, vol. 60, pp. 91–110. Kluwer Academic Publishers, Hingham, November 2004. http://dx.doi.org/10.1023/B:VISI.0000029664.99615.94
  11. 11.
    Rosten, E., Drummond, T.W.: Machine learning for high-speed corner detection. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol. 3951, pp. 430–443. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  12. 12.
    Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: ORB: an efficient alternative to sift or surf. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 2564–2571, November 2011Google Scholar
  13. 13.
    Silpa-Anan, C., Hartley, R.: Optimised KD-trees for fast image descriptor matching. In: IEEE Conference on Computer Vision and Pattern Recognition, 2008. CVPR 2008, pp. 1–8, June 2008Google Scholar
  14. 14.
    Snavely, N., Seitz, S.M., Szeliski, R.: Photo tourism: exploring photo collections in 3D. ACM Trans. Graph. 25(3), 835–846 (2006)CrossRefGoogle Scholar
  15. 15.
    Stefan, W.: Random-forests (2012). https://github.com/stefan-w/random-forests
  16. 16.
    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: IEEE Conference on Computer Vision and Pattern Recognition, 2008. CVPR 2008, pp. 1–8, June 2008Google Scholar
  17. 17.
    Sweeney, C.: Theia Multiview Geometry Library: Tutorial & Reference. University of California Santa BarbaraGoogle Scholar
  18. 18.
    Triggs, B., McLauchlan, P.F., Hartley, R.I., Fitzgibbon, A.W.: Bundle adjustment – a modern synthesis. In: Triggs, B., Zisserman, A., Szeliski, R. (eds.) ICCV-WS 1999. LNCS, vol. 1883, pp. 298–372. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  19. 19.
    Vedaldi, A., Fulkerson, B.: VLFeat: An open and portable library of computer vision algorithms (2008). http://www.vlfeat.org
  20. 20.
    Zhang, G., Vela, P.A.: Good features to track for visual SLAM, June 2015Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  1. 1.Intel Visual Computing InstituteSaarbrückenGermany
  2. 2.Max-Planck Institute for InformaticsSaarbrückenGermany

Personalised recommendations