Accurate Interpolation in Appearance-Based Pose Estimation

  • Erik Jonsson
  • Michael Felsberg
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4522)

Abstract

One problem in appearance-based pose estimation is the need for many training examples, i.e. images of the object in a large number of known poses. Some invariance can be obtained by considering translations, rotations and scale changes in the image plane, but the remaining degrees of freedom are often handled simply by sampling the pose space densely enough. This work presents a method for accurate interpolation between training views using local linear models. As a view representation local soft orientation histograms are used. The derivative of this representation with respect to the image plane transformations is computed, and a Gauss-Newton optimization is used to optimize all pose parameters simultaneously, resulting in an accurate estimate.

Keywords

Augmented Reality Query Image Weighting Kernel Gradient Magnitude Local Linear Model 
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.
Download to read the full conference paper text

References

  1. 1.
    Atkeson, C.G., Moore, A.W., Schaal, S.: Locally weighted learning. Artificial Intelligence Review 11, 11–73 (1997)CrossRefGoogle Scholar
  2. 2.
    Comport, A., Marchand, E., Chaumette, F.: A real-time tracker for markerless augmented reality. In: Proc. The Second IEEE and ACM International Symposium on Mixed and Augmented Reality, pp. 36–45. IEEE Computer Society Press, Los Alamitos (2003)CrossRefGoogle Scholar
  3. 3.
    Felsberg, M., Forssén, P.-E., Scharr, H.: Channel smoothing: Efficient robust smoothing of low-level signal features. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(2), 209–222 (2006)CrossRefGoogle Scholar
  4. 4.
    Granlund, G.H.: An associative perception-action structure using a localized space variant information representation. In: Sommer, G., Zeevi, Y.Y. (eds.) AFPAC 2000. LNCS, vol. 1888, pp. 48–68. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  5. 5.
    Lowe, D.G.: Object recognition from local scale-invariant features. In: IEEE Int. Conf. on Computer Vision, Sept. 1999, IEEE Computer Society Press, Los Alamitos (1999)Google Scholar
  6. 6.
    Moore, A.W., Schneider, J., Deng, K.: Efficient locally weighted polynomial regression predictions. In: Proc. 14th International Conference on Machine Learning, pp. 236–244. Morgan Kaufmann, San Francisco (1997)Google Scholar
  7. 7.
    Murase, H., Nayar, S.K.: Visual learning and recognition of 3-d objects from appearance. International Journal of Computer Vision 14(1), 5–24 (1995)CrossRefGoogle Scholar
  8. 8.
    Nocedal, J., Wright, S.J.: Numerical Optimization. Springer, Heidelberg (1999)MATHGoogle Scholar
  9. 9.
    Obdrzalek, S., Matas, J.: Object recognition using local affine frames on distinguished regions. In: British Machine Vision Conf. (2002)Google Scholar
  10. 10.
    Pentland, A., Moghaddam, B., Starner, T.: View-based and modular eigenspaces for face recognition. In: CVPR (1994)Google Scholar
  11. 11.
    Cipolla, R., Drummond, T.: Real-time visual tracking of complex structures. IEEETransactions on Pattern Analysis and Machine Intelligence 24(7) (2002)Google Scholar
  12. 12.
    Unser, M.: Splines: A perfect fit for signal and image processing. IEEE Signal Processing Magazine 16(6), 22–38 (1999)CrossRefGoogle Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Erik Jonsson
    • 1
  • Michael Felsberg
    • 1
  1. 1.Computer Vision Laboratory, Dept. of Electrical Engineering, Linköping University 

Personalised recommendations