Bivariate Feature Localization for SIFT Assuming a Gaussian Feature Shape

  • Kai Cordes
  • Oliver Müller
  • Bodo Rosenhahn
  • Jörn Ostermann
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6453)

Abstract

In this paper, the well-known SIFT detector is extended with a bivariate feature localization. This is done by using function models that assume a Gaussian feature shape for the detected features. As function models we propose (a) a bivariate Gaussian and (b) a Difference of Gaussians. The proposed detector has all properties of SIFT, but provides invariance to affine transformations and blurring. It shows superior performance for strong viewpoint changes compared to the original SIFT. Compared to the most accurate affine invariant detectors, it provides competitive results for the standard test scenarios while performing superior in case of motion blur in video sequences.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Pollefeys, M., Gool, L.V.V., Vergauwen, M., Verbiest, F., Cornelis, K., Tops, J., Koch, R.: Visual modeling with a hand-held camera. International Journal of Computer Vision (IJCV) 59, 207–232 (2004)CrossRefGoogle Scholar
  2. 2.
    Brown, M., Lowe, D.G.: Invariant features from interest point groups. In: British Machine Vision Conference (BMVC), pp. 656–665 (2002)Google Scholar
  3. 3.
    Canny, J.: A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) 8, 679–698 (1986)CrossRefGoogle Scholar
  4. 4.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: Alvey Vision Conference, pp. 147–151 (1988)Google Scholar
  5. 5.
    Lindeberg, T.: Feature detection with automatic scale selection. International Journal of Computer Vision (IJCV) 30, 79–116 (1998)CrossRefGoogle Scholar
  6. 6.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision (IJCV) 60, 91–110 (2004)CrossRefGoogle Scholar
  7. 7.
    Lindeberg, T., Garding, J.: Shape-adapted smoothing in estimation of 3-d shape cues from affine deformations of local 2-d brightness structure. Image and Vision Computing 15, 415–434 (1997)CrossRefGoogle Scholar
  8. 8.
    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
  9. 9.
    Mikolajczyk, K., Schmid, C.: Scale & affine invariant interest point detectors. International Journal of Computer Vision (IJCV) 60, 63–86 (2004)CrossRefGoogle Scholar
  10. 10.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) 27, 1615–1630 (2005)CrossRefGoogle Scholar
  11. 11.
    Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Gool, L.V.: A comparison of affine region detectors. International Journal of Computer Vision (IJCV) 65, 43–72 (2005)CrossRefGoogle Scholar
  12. 12.
    Yu, G., Morel, J.M.: A fully affine invariant image comparison method. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Washington, DC, USA, pp. 1597–1600. IEEE Computer Society, Los Alamitos (2009)Google Scholar
  13. 13.
    Köser, K., Koch, R.: Perspectively invariant normal features. In: IEEE International Conference on Computer Vision (ICCV), pp. 1–8 (2007)Google Scholar
  14. 14.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: British Machine Vision Conference (BMVC), vol. 1, pp. 384–393 (2002)Google Scholar
  15. 15.
    Tuytelaars, T., Mikolajczyk, K.: Local invariant feature detectors: a survey. In: Foundations and Trends in Computer Graphics and Vision, vol. 3 (2008)Google Scholar
  16. 16.
    Ke, Y., Sukthankar, R.: Pca-sift: A more distinctive representation for local image descriptors. In: International Conference on Computer Vision and Pattern Recognition (ICCV), pp. 506–513 (2004)Google Scholar
  17. 17.
    Schmid, C., Mohr, R., Bauckhage, C.: Comparing and evaluating interest points. In: IEEE International Conference on Computer Vision and Pattern Recognition (ICCV), pp. 230–235 (1998)Google Scholar
  18. 18.
    Schmid, C., Mohr, R., Bauckhage, C.: Evaluation of interest point detectors. International Journal of Computer Vision (IJCV) 37, 151–172 (2000)CrossRefMATHGoogle Scholar
  19. 19.
    Mikolajczyk, K., Leibe, B., Schiele, B.: Multiple object class detection with a generative model. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, pp. 26–36 (2006)Google Scholar
  20. 20.
    Sivic, J., Russell, B.C., Efros, A.A., Zisserman, A., Freeman, W.T.: Discovering objects and their location in images. In: IEEE International Conference on Computer Vision, vol. 1, pp. 370–377 (2005)Google Scholar
  21. 21.
    Vatis, Y., Ostermann, J.: Adaptive interpolation filter for h.264/avc. IEEE Transactions on Circuits and Systems for Video Technology 19, 179–192 (2009)CrossRefGoogle Scholar
  22. 22.
    Cordes, K., Müller, O., Rosenhahn, B., Ostermann, J.: Half-sift: High-accurate localized features for sift. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop, Miami Beach, USA, pp. 31–38 (2009)Google Scholar
  23. 23.
    Fischler, R.M.A., Bolles, C.: Random sample consensus: A paradigm for model fitting with application to image analysis and automated cartography. Communications of the ACM 24, 381–395 (1981)MathSciNetCrossRefGoogle Scholar
  24. 24.
    Thormählen, T., Hasler, H., Wand, M., Seidel, H.P.: Merging of feature tracks for camera motion estimation from video. In: 5th European Conference on Visual Media Production (CVMP), pp. 1–8 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Kai Cordes
    • 1
  • Oliver Müller
    • 1
  • Bodo Rosenhahn
    • 1
  • Jörn Ostermann
    • 1
  1. 1.Institut für Informationsverarbeitung (TNT)Leibniz Universität HannoverGermany

Personalised recommendations