Speeding Up SURF

  • Peter Abeles
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8034)


SURF has emerged as one of the more popular feature descriptors and detectors in recent years. While considerably faster than SIFT, it is still considered too computationally expensive for many applications. In this paper, several algorithmic changes are proposed to create two new SURF like descriptors and a SURF like feature detector. The proposed changes have comparable stability to the reference implementation, yet a byte code implementation is able run several times faster than the native reference implementation and faster than all other open source implementations tested.


Interest Point Reference Library Runtime Performance Interest Point Detection Algorithmic Change 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bay, H., Ess, A., Tuytelaars, T., Gool, L.V.: Surf: Speeded up robust features. Computer Vision and Image Understanding (CVIU) 110, 356–359 (2008)CrossRefGoogle Scholar
  2. 2.
    Lowe, D.: Distinctive image features from scale-invariant keypoints, cascade filtering approach. International Journal of Computer Vision (IJCV) 60, 91–110 (2004)CrossRefGoogle Scholar
  3. 3.
    Tola, E., Lepetit, V., Fua, P.: Daisy: an Efficient Dense Descriptor Applied to Wide Baseline Stereo. Pattern Analysis and Machine Intelligence 32, 815–830 (2010)CrossRefGoogle Scholar
  4. 4.
    Juan, L., Gwon, O.: A Comparison of SIFT, PCA-SIFT and SURF. International Journal of Image Processing (IJIP) 3, 143–152 (2009)Google Scholar
  5. 5.
    Calonder, M., Lepetit, V., Strecha, C., Fua, P.: BRIEF: Binary Robust Independent Elementary Features. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 778–792. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  6. 6.
    Abeles, P.: Boofcv (Version 0.5),
  7. 7.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Computer Vision and Pattern Recognition, CVPR, pp. 511–518 (2001)Google Scholar
  8. 8.
    Simard, P., Bottou, L., Haffner, P., LeCun, Y.: A fast convolution algorithm for signal processing and neural networks. In: NIPS (1998)Google Scholar
  9. 9.
    Lindeberg, T.: Feature detection with automatic scale selection. IJCV 30, 79–116 (1998)CrossRefGoogle Scholar
  10. 10.
    Brown, M., Lowe, D.: Invariant features from interest point groups. In: BMVC (2002)Google Scholar
  11. 11.
    Edelman, S., Intrator, N., Poggio, T.: Complex cells and object recognition (1997),
  12. 12.
    Agrawal, M., Konolige, K., Blas, M.R.: CenSurE: Center surround extremas for realtime feature detection and matching. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 102–115. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  13. 13.
    Orlinski, A.: Pan-o-matic (Version 0.9.4),
  14. 14.
    Evans, C.: The opensurf computer vision library, (Build May 27, 2010)
  15. 15.
    Stromberg, A., Jojopotato, N.: Jopensurf (SVN r24) Note: Port of OpenSURF,
  16. 16.
    Liu, L., Mahon, I.: Opencv (Version 2.3.1 SVN r6879),
  17. 17.
    Bay, H., Gool, L.V.: Surf: Speeded up robust feature (Version 1.0.9),
  18. 18.
    Fantacci, C., Martini, A., Mitreski, M.: Javasurf (SVN r4) Note: Refactored P-SURF,
  19. 19.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 27, 1615–1630 (2005)CrossRefGoogle Scholar
  20. 20.
    Cornelis, N., Van Gool, L.: Fast scale invariant feature detection and matching on programmable graphics hardware. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2008 (2008)Google Scholar
  21. 21.
    Schmid, C., Mohr, R., Bauckhage, C.: Evaluation of interest point detectors. Int. J. Comput. Vision 37, 151–172 (2000)CrossRefzbMATHGoogle Scholar
  22. 22.
    Gauglitz, S., Höllerer, T., Turk, M.: Evaluation of interest point detectors and feature descriptors for visual tracking. International Journal of Computer Vision 94, 335–360 (2011)CrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Peter Abeles
    • 1
  1. 1.Robotic InceptionAustralia

Personalised recommendations