Tracking the Pose of Objects through Subspace

  • Simon Léonard
  • Martin Jägersand
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2749)

Abstract

Tracking the pose of an object is a fundamental operation in computer vision. Yet, achieving this task for arbitrary objects without requiring a priori knowledge remains a major stumbling block. This paper introduces a method for tracking the pose of a moving object without requiring its 3D model or textured surfaces. In the first step, a sequence of images-poses pairs is obtained and PCA coefficients are derived from the image sequence. Then, a piecewise linear observation mapping is build between the poses and the PCA coefficients. The mapping is then used in the observation model of a Kalman filter that tracks the pose of the object.

Keywords

Computer Vision Kalman Filter Computer Graphic Texture Surface Observation 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.

References

  1. 1.
    Black, M.J., Jepson, A.D.: EigenTracking: robust matching and tracking of articu lated objects using a view-based representation. IJCV 25 (1998) 63–84CrossRefGoogle Scholar
  2. 2.
    Irani, M.: Multi-frame optical flow estimation using subspace constraints. ICCV (1999) 626–633Google Scholar
  3. 3.
    Jagersand, M.: Image based view synthesis of articulated agents. CVPR (1997) 1047–1053Google Scholar
  4. 4.
    Jolliffe, I.T.: Principal Component Analysis Springer, New York, (2002)Google Scholar
  5. 5.
    Linde, Y., Buzo, A., Gray, R.M.: An algorithm for vector quantizer design. IEEE Transactions on Communications (1980) 702–710Google Scholar
  6. 6.
    Lowe, D.G.: Fitting parameterized three-dimensional models to images. PAMI 13 (1991) 441–450Google Scholar
  7. 7.
    Murase, H., Nayar, S.K.: Visual learning and recognition of 3D objects from appearance. IJCV 14 (1995) 5–24CrossRefGoogle Scholar
  8. 8.
    Nayar, S.K., Nene, S.A., Murase, H.: Subspace methods for robot vision. RA 12 (1996) 750–758Google Scholar
  9. 9.
    Shi, J., Tomasi, C: Good features to track. CVPR (1994) 593–600Google Scholar
  10. 10.
    Tomasi, C, Kanade, T.: Shape and motion from image streams under orthography: a factorization method. IJCV 9 (1992) 137–154CrossRefGoogle Scholar
  11. 11.
    Turk, M., Pentland, A.P.: Eigenfaces for recognition. CogNeuro 3 (1991) 71–96Google Scholar
  12. 12.
    Welch, G., Bishop, G.: An introduction to the Kalman filter SIGGRAPH (2001) short courseGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Simon Léonard
    • 1
  • Martin Jägersand
    • 1
  1. 1.University of AlbertaEdmontonCanada

Personalised recommendations