Advertisement

Inverse Composition for Multi-kernel Tracking

  • Rémi Megret
  • Mounia Mikram
  • Yannick Berthoumieu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4338)

Abstract

Existing multi-kernel tracking methods are based on a forwards additive motion model formulation. However this approach suffers from the need to estimate an update matrix for each iteration. This paper presents a general framework that extends the existing approach and that allows to introduce a new inverse compositional formulation which shifts the computation of the update matrix to a one time initialisation step. The proposed approach thus reduces the computational complexity of each iteration, compared to the existing forwards approach. The approaches are compared both in terms of algorithmic complexity and quality of the estimation.

Keywords

Spatial Error Color Distribution Gradient Base Optimisation Inverse Approach Epanechnikov Kernel 
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.
    Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence 25, 564–575 (2003)CrossRefGoogle Scholar
  2. 2.
    Fan, Z., Wu, Y., Yang, M.: Multiple collaborative kernel tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA, pp. 502–509 (2005)Google Scholar
  3. 3.
    Hager, G.D., Dewan, M., Stewart, C.V.: Multiple kernel tracking with SSD. In: IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC, USA, pp. 790–797 (2004)Google Scholar
  4. 4.
    Georgescu, B., Meer, P.: Point matching under large image deformations and illumination changes. IEEE Transactions on Pattern Analysis and Machine Intelligence 26, 674–688 (2004)CrossRefGoogle Scholar
  5. 5.
    Baker, S., Matthews, I.: Lucas-kanade 20 years on: A unifying framework. International Journal of Computer Vision 56, 221–255 (2004)CrossRefGoogle Scholar
  6. 6.
    Pérez, P., Hue, C., Vermaak, J., Gangnet, M.: Color-based probabilistic tracking. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 661–675. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  7. 7.
    Elgammal, A.M., Duraiswami, R., Davis, L.S.: Probabilistic tracking in joint feature-spatial spaces. In: IEEE Conference on Computer Vision and Pattern Recognition, Madison, WI, USA, pp. 781–788 (2003)Google Scholar
  8. 8.
    Zhang, H., Huang, W., Huang, Z., Li, L.: Affine object tracking with kernel-based spatial-color representation. In: IEEE Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA, pp. 293–300 (2005)Google Scholar
  9. 9.
    Guskov, I.: Kernel-based template alignment. In: IEEE Conference on Computer Vision and Pattern Recognition, New-York, USA, pp. 610–617 (2006)Google Scholar
  10. 10.
    Liu, T.L., Chen, H.T.: Real-time tracking using trust-region methods. IEEE Transactions on Pattern Analysis and Machine Intelligence 26, 397–402 (2003)Google Scholar
  11. 11.
    Baker, S., Matthews, I.: Equivalence and efficiency of image alignment algorithms. In: IEEE Conference on Computer Vision and Pattern Recognition, Kauai, HI, USA, pp. 1090–1097 (2001)Google Scholar
  12. 12.
    Jurie, F., Dhome, M.: Hyperplane approximation for template matching. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 996–1000 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Rémi Megret
    • 1
  • Mounia Mikram
    • 1
  • Yannick Berthoumieu
    • 1
  1. 1.UMR 5131, Laboratoire d’Automatique, Productique et SignalUniversité Bordeaux 1/ENSEIRBTalenceFrance

Personalised recommendations