Advertisement

Statistical 3-D object localization without segmentation using wavelet analysis

  • Josef Pösl
  • Heinrich Niemann
Pose Estimation
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1296)

Abstract

This paper presents a new approach for statistical object localization. The localization scheme is directely based on local features, which are extracted for all image positions, in contrast to segmentation in classical schemes. Hierarchical Gabor filters are used to extract local features. With these features statistical object models are built for the different scale levels of the Gabor filters. The localization is then performed by a maximum likelihood estimation on the different scales successively. Results for the localization of real images of 2-D and 3-D objects are shown.

Keywords

Feature Vector Local Feature Scale Level Gabor Filter Gabor Wavelet 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    M. Black and A. Jepson. Eigentracking: Robust matching and tracking of articulated objects using a view-based representation. In B. Buxton and R. Cipolla, editors, Computer Vision-ECCV '96, volume I of Lecture Notes in Computer Science, pages 329–341, Heidelberg, 1996. Springer.Google Scholar
  2. 1.
    M. Black and A. Jepson. Eigentracking: Robust matching and tracking of articulated objects using a view-based representation. In B. Buxton and R. Cipolla, editors, Computer Vision-ECCV '96, volume I of Lecture Notes in Computer Science, pages 329–341, Heidelberg, 1996. Springer.Google Scholar
  3. 2.
    J. G. Daugman. Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. Journal of the Optical Society of America A, 2(7):1160–1169, 1985.Google Scholar
  4. 3.
    J. Hornegger and H. Niemann. Statistical learning, localization, and identification of objects. In ICCV 95 [4], pages 914–919.Google Scholar
  5. 4.
    Proceedings of the 5th international Conference on Computer Vision (ICCV), Boston, June 1995. IEEE Computer Society Press.Google Scholar
  6. 5.
    H. Kollnig and H.-H. Nagel. 3D pose estimation by fitting gradients directly to polyhedral models. In ICCV 95 [4], pages 569–574.Google Scholar
  7. 6.
    V. Kumar and E. S. Manolakos. Unsupervised model-based object recognition by parameter estimation of hierarchical mixtures. In Proceedings of the International Conference on image Processing (ICIP), pages 967–970, Lausanne, Schweiz, September 1996. IEEE Computer Society Press.Google Scholar
  8. 7.
    B. S. Manjunath, C. Shekhar, and R. Chellappa. A new approach to image feature detection with applications. Pattern Recognition, 29(4):627–640, 1996.CrossRefGoogle Scholar
  9. 8.
    H. Murase and S. K. Nayar. Visual learning and recognition of 3-D objects from appearance. International Journal of Computer Vision, 14(1):5–24, January 1995.CrossRefGoogle Scholar
  10. 9.
    A. Shustorovich. Scale specific and robust edge/line encoding with linear combinations of gabor wavelets. Pattern Recognition, 27(5):713–725, 1994.CrossRefGoogle Scholar
  11. 10.
    P. Viola and W. Wells III. Alignment by maximization of mutual information. In ICCV 95 [4], pages 16–23.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Josef Pösl
    • 1
  • Heinrich Niemann
    • 1
  1. 1.Lehrstuhl für Mustererkennung (Informatik 5)Universität Erlangen-NürnbergErlangenGermany

Personalised recommendations