Adaptive Probabilistic Visual Tracking with Incremental Subspace Update

  • David Ross
  • Jongwoo Lim
  • Ming-Hsuan Yang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3022)

Abstract

Visual tracking, in essence, deals with non-stationary data streams that change over time. While most existing algorithms are able to track objects well in controlled environments, they usually fail if there is a significant change in object appearance or surrounding illumination. The reason being that these visual tracking algorithms operate on the premise that the models of the objects being tracked are invariant to internal appearance change or external variation such as lighting or viewpoint. Consequently most tracking algorithms do not update the models once they are built or learned at the outset. In this paper, we present an adaptive probabilistic tracking algorithm that updates the models using an incremental update of eigenbasis. To track objects in two views, we use an effective probabilistic method for sampling affine motion parameters with priors and predicting its location with a maximum a posteriori estimate. Borne out by experiments, we demonstrate the proposed method is able to track objects well under large lighting, pose and scale variation with close to real-time performance.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Black, M.J., Jepson, A.D.: Eigentracking: Robust matching and tracking of articulated objects using view-based representation. In: Buxton, B., Cipolla, R. (eds.) ECCV 1996. LNCS, vol. 1064, pp. 329–342. Springer, Heidelberg (1996)CrossRefGoogle Scholar
  2. 2.
    Morency, L.P., Rahimi, A., Darrell, T.: Adaptive view-based appearance models. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 803–810 (2003)Google Scholar
  3. 3.
    Birchfield, S.: Elliptical head tracking using intensity gradient and color histograms. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 232–237 (1998)Google Scholar
  4. 4.
    Wu, Y., Huang, T.: A co-inference approach for robust visual tracking. In: Proceedings of the Eighth IEEE International Conference on Computer Vision, vol. 2, pp. 26–33 (2001)Google Scholar
  5. 5.
    Isard, M., Blake, A.: Contour tracking by stochastic propagation of conditional density. In: Buxton, B., Cipolla, R. (eds.) ECCV 1996. LNCS, vol. 1064, pp. 343–356. Springer, Heidelberg (1996)CrossRefGoogle Scholar
  6. 6.
    La Cascia, M., Sclaroff, S., Athitsos, V.: Fast, reliable head tracking under varying illumination: An approach based on registration of texture-mapped 3D models. IEEE Transactions on Pattern Analysis and Machine Intelligence 22, 322–336 (2000)CrossRefGoogle Scholar
  7. 7.
    Black, M.J., Fleet, D.J., Yacoob, Y.: Robustly estimating changes in image appearance. Computer Vision and Image Understanding 78, 8–31 (2000)CrossRefGoogle Scholar
  8. 8.
    Harville, M.: A framework for high-level feedback to adaptive, per-pixel mixture of Gaussian background models. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 531–542. Springer, Heidelberg (2002)Google Scholar
  9. 9.
    Adelson, E.H., Bergen, J.R.: The plenoptic function and the elements of early vision. In: Landy, M., Movshon, J.A. (eds.) Computational Models of Visual Processing, pp. 1–20. MIT Press, Cambridge (1991)Google Scholar
  10. 10.
    Belhumeur, P.N., Kriegman, D.J.: What is the set of images of an object under all possible illumination conditions. International Journal of Computer Vision 28, 1–16 (1998)CrossRefGoogle Scholar
  11. 11.
    Hallinan, P.: A low-dimensional representation of human faces for arbitrary lighting conditions. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 995–999 (1994)Google Scholar
  12. 12.
    Basri, R., Jacobs, D.: Lambertian reflectance and linear subspaces. In: Proceedings of the Eighth IEEE International Conference on Computer Vision, vol. 2, pp. 383–390 (2001)Google Scholar
  13. 13.
    Lucas, B., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Proceedings of International Joint Conference on Artificial Intelligence, pp. 674–679 (1981)Google Scholar
  14. 14.
    Black, M.J., Fleet, D.J., Yacoob, Y.: A framework for modeling appearance change in image sequence. In: Proceedings of the Sixth IEEE International Conference on Computer Vision, pp. 660–667 (1998)Google Scholar
  15. 15.
    Brand, M.: Morphable 3D models from video. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 315–322 (2001)Google Scholar
  16. 16.
    Brand, M.: Incremental singular value decomposition of uncertain data with missing values. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 707–720. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  17. 17.
    Levy, A., Lindenbaum, M.: Sequential Karhunen-Loeve basis extraction and its application to images. IEEE Transactions on Image Processing 9, 1371–1374 (2000)MATHCrossRefGoogle Scholar
  18. 18.
    Comaniciu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 603–619 (2002)CrossRefGoogle Scholar
  19. 19.
    Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence 25, 564–577 (2003)CrossRefGoogle Scholar
  20. 20.
    Hager, G., Belhumeur, P.: Real-time tracking of image regions with changes in geometry and illumination. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 403–410 (1996)Google Scholar
  21. 21.
    Shashua, A.: Geometry and Photometry in 3D Visual Recognition. PhD thesis, Massachusetts Institute of Technology (1992)Google Scholar
  22. 22.
    De la Torre, F., Gong, S., McKenna, S.J.: View-based adaptive affine tracking. In: Burkhardt, H.-J., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1406, pp. 828–842. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  23. 23.
    Jepson, A.D., Fleet, D.J., El-Maraghi, T.F.: Robust online appearance models for visual tracking. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 415–422 (2001)Google Scholar
  24. 24.
    Hager, G.D., Belhumeur, P.N.: Efficient region tracking with parametric models of geometry and illumination. IEEE Transactions on Pattern Analysis and Machine Intelligence 20, 1025–1039 (1998)CrossRefGoogle Scholar
  25. 25.
    Jordan, M.I. (ed.): Learning in Graphical Models. MIT Press, Cambridge (1999)Google Scholar
  26. 26.
    Tipping, M.E., Bishop, C.M.: Probabilistic principal component analysis. Journal of the Royal Statistical Society, Series B 61, 611–622 (1999)MATHCrossRefMathSciNetGoogle Scholar
  27. 27.
    Roweis, S.: EM algorithms for PCA and SPCA. In: Jordan, M.I., Kearns, M.J., Solla, S.A. (eds.) Advances in Neural Information Processing Systems 10, pp. 626–632. MIT Press, Cambridge (1997)Google Scholar
  28. 28.
    Champagne, B., Liu, Q.G.: Plane rotation-based EVD updating schemes for efficient subspace tracking. IEEE Transactions on Signal Processing 46, 1886–1900 (1998)CrossRefGoogle Scholar
  29. 29.
    Golub, G.H., Van Loan, C.F.: Matrix Computations. The Johns Hopkins University Press, Baltimore (1996)MATHGoogle Scholar
  30. 30.
    Jolliffe, I.T.: Principal Component Analysis. Springer, Heidelberg (2002)MATHGoogle Scholar
  31. 31.
    Vermaak, J., Pérez, P., Gangnet, M., Blake, A.: A framework for high-level feedback to adaptive, per-pixel mixture of Gaussian background models. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 645–660. Springer, Heidelberg (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • David Ross
    • 1
  • Jongwoo Lim
    • 2
  • Ming-Hsuan Yang
    • 3
  1. 1.University of TorontoTorontoCanada
  2. 2.University of Illinois at Urbana-ChampaignUrbanaUSA
  3. 3.Honda Research InstituteMountain ViewUSA

Personalised recommendations