SURF: Speeded Up Robust Features

  • Herbert Bay
  • Tinne Tuytelaars
  • Luc Van Gool
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3951)

Abstract

In this paper, we present a novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust Features). It approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster.

This is achieved by relying on integral images for image convolutions; by building on the strengths of the leading existing detectors and descriptors (in casu, using a Hessian matrix-based measure for the detector, and a distribution-based descriptor); and by simplifying these methods to the essential. This leads to a combination of novel detection, description, and matching steps. The paper presents experimental results on a standard evaluation set, as well as on imagery obtained in the context of a real-life object recognition application. Both show SURF’s strong performance.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Lindeberg, T.: Feature detection with automatic scale selection. IJCV 30(2), 79–116 (1998)CrossRefGoogle Scholar
  2. 2.
    Lowe, D.: Distinctive image features from scale-invariant keypoints, cascade filtering approach. IJCV 60, 91–110 (2004)CrossRefGoogle Scholar
  3. 3.
    Mikolajczyk, K., Schmid, C.: An affine invariant interest point detector. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 128–142. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  4. 4.
    Ke, Y., Sukthankar, R.: PCA-SIFT: A more distinctive representation for local image descriptors. In: CVPR, vol. (2), pp. 506–513 (2004)Google Scholar
  5. 5.
    Tuytelaars, T., Van Gool, L.: Wide baseline stereo based on local, affinely invariant regions. In: BMVC, pp. 412–422 (2000)Google Scholar
  6. 6.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: BMVC, pp. 384–393 (2002)Google Scholar
  7. 7.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. In: CVPR, vol. 2, pp. 257–263 (2003)Google Scholar
  8. 8.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. PAMI 27, 1615–1630 (2005)CrossRefGoogle Scholar
  9. 9.
    Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Van Gool, L.: A comparison of affine region detectors. IJCV 65, 43–72 (2005)CrossRefGoogle Scholar
  10. 10.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: Proceedings of the Alvey Vision Conference, pp. 147–151 (1988)Google Scholar
  11. 11.
    Mikolajczyk, K., Schmid, C.: Indexing based on scale invariant interest points. In: ICCV, vol. 1, pp. 525–531 (2001)Google Scholar
  12. 12.
    Lowe, D.: Object recognition from local scale-invariant features. In: ICCV (1999)Google Scholar
  13. 13.
    Kadir, T., Brady, M.: Scale, saliency and image description. IJCV 45(2), 83–105 (2001)CrossRefMATHGoogle Scholar
  14. 14.
    Jurie, F., Schmid, C.: Scale-invariant shape features for recognition of object categories. In: CVPR, vol. II, pp. 90–96 (2004)Google Scholar
  15. 15.
    Mikolajczyk, K., Schmid, C.: Scale and affine invariant interest point detectors. IJCV 60, 63–86 (2004)CrossRefGoogle Scholar
  16. 16.
    Florack, L.M.J., ter Haar Romeny, B.M., Koenderink, J.J., Viergever, M.A.: General intensity transformations and differential invariants. JMIV 4, 171–187 (1994)MathSciNetCrossRefGoogle Scholar
  17. 17.
    Mindru, F., Tuytelaars, T., Van Gool, L., Moons, T.: Moment invariants for recognition under changing viewpoint and illumination. CVIU 94, 3–27 (2004)Google Scholar
  18. 18.
    Baumberg, A.: Reliable feature matching across widely separated views. In: CVPR, pp. 774–781 (2000)Google Scholar
  19. 19.
    Schaffalitzky, F., Zisserman, A.: Multi-view matching for unordered image sets, or how do I organize my holiday snaps? In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 414–431. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  20. 20.
    Freeman, W.T., Adelson, E.H.: The design and use of steerable filters. PAMI 13, 891–906 (1991)CrossRefGoogle Scholar
  21. 21.
    Carneiro, G., Jepson, A.: Multi-scale phase-based local features. In: CVPR, vol. (1), pp. 736–743 (2003)Google Scholar
  22. 22.
    Se, S., Ng, H., Jasiobedzki, P., Moyung, T.: Vision based modeling and localization for planetary exploration rovers. In: Proceedings of International Astronautical Congress (2004)Google Scholar
  23. 23.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: CVPR, vol. (1), pp. 511–518 (2001)Google Scholar
  24. 24.
    Koenderink, J.: The structure of images. Biological Cybernetics 50, 363–370 (1984)MathSciNetCrossRefMATHGoogle Scholar
  25. 25.
    Lindeberg, T.: Discrete Scale-Space Theory and the Scale-Space Primal Sketch, PhD, KTH Stockholm, KTH (1991)Google Scholar
  26. 26.
    Lindeberg, T., Bretzner, L.: Real-time scale selection in hybrid multi-scale representations. In: Scale-Space, pp. 148–163 (2003)Google Scholar
  27. 27.
    Brown, M., Lowe, D.: Invariant features from interest point groups. In: BMVC (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Herbert Bay
    • 1
  • Tinne Tuytelaars
    • 2
  • Luc Van Gool
    • 1
    • 2
  1. 1.ETH ZurichSwitzerland
  2. 2.Katholieke Universiteit LeuvenBelgium

Personalised recommendations