Extending GKLT Tracking—Feature Tracking for Controlled Environments with Integrated Uncertainty Estimation

  • Michael Trummer
  • Christoph Munkelt
  • Joachim Denzler
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5575)

Abstract

Guided Kanade-Lucas-Tomasi (GKLT) feature tracking offers a way to perform KLT tracking for rigid scenes using known camera parameters as prior knowledge, but requires manual control of uncertainty. The uncertainty of prior knowledge is unknown in general. We present an extended modeling of GKLT that overcomes the need of manual adjustment of the uncertainty parameter. We establish an extended optimization error function for GKLT feature tracking, from which we derive extended parameter update rules and a new optimization algorithm in the context of KLT tracking. By this means we give a new formulation of KLT tracking using known camera parameters originating, for instance, from a controlled environment. We compare the extended GKLT tracking method with the original GKLT and the standard KLT tracking using real data. The experiments show that the extended GKLT tracking performs better than the standard KLT and reaches an accuracy up to several times better than the original GKLT with an improperly chosen value of the uncertainty parameter.

Keywords

Uncertainty Parameter Camera Parameter Feature Tracking Warping Function Epipolar Line 
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.
    Wenhardt, S., Deutsch, B., Angelopoulou, E., Niemann, H.: Active Visual Object Reconstruction using D-, E-, and T-Optimal Next Best Views. In: Computer Vision and Pattern Recognition, CVPR 2007, June 2007, pp. 1–7 (2007)Google Scholar
  2. 2.
    Chen, S.Y., Li, Y.F.: Vision Sensor Planning for 3D Model Acquisition. IEEE Transactions on Systems, Man and Cybernetics – B 35(4), 1–12 (2005)MathSciNetGoogle Scholar
  3. 3.
    Lucas, B., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Proceedings of 7th International Joint Conference on Artificial Intelligence, pp. 674–679 (1981)Google Scholar
  4. 4.
    Baker, S., Matthews, I.: Lucas-Kanade 20 Years On: A Unifying Framework. International Journal of Computer Vision 56, 221–255 (2004)CrossRefGoogle Scholar
  5. 5.
    Fusiello, A., Trucco, E., Tommasini, T., Roberto, V.: Improving feature tracking with robust statistics. Pattern Analysis and Applications 2, 312–320 (1999)CrossRefGoogle Scholar
  6. 6.
    Zinsser, T., Graessl, C., Niemann, H.: High-speed feature point tracking. In: Proceedings of Conference on Vision, Modeling and Visualization (2005)Google Scholar
  7. 7.
    Heigl, B.: Plenoptic Scene Modelling from Uncalibrated Image Sequences. PhD thesis, Friedrich-Alexander-Universität Erlangen-Nürnberg (2003)Google Scholar
  8. 8.
    Trummer, M., Denzler, J., Munkelt, C.: KLT Tracking Using Intrinsic and Extrinsic Camera Parameters in Consideration of Uncertainty. In: Proceedings of 3rd International Conference on Computer Vision Theory and Applications (VISAPP), vol. 2, pp. 346–351 (2008)Google Scholar
  9. 9.
    Trummer, M., Denzler, J., Munkelt, C.: Guided KLT Tracking Using Camera Parameters in Consideration of Uncertainty. Lecture Notes in Communications in Computer and Information Science (CCIS). Springer, Heidelberg (to appear)Google Scholar
  10. 10.
    Dempster, A., Laird, N., Rubin, D.: Maximum likelihood from incomplete data. Journal of the Royal Statistical Society 39, 1–38 (1977)MATHGoogle Scholar
  11. 11.
    Kuehmstedt, P., Munkelt, C., Matthins, H., Braeuer-Burchardt, C., Notni, G.: 3D shape measurement with phase correlation based fringe projection. In: Osten, W., Gorecki, C., Novak, E.L. (eds.) Optical Measurement Systems for Industrial Inspection V, vol. 6616, p. 66160B. SPIE (2007)Google Scholar
  12. 12.
    Walker, M.W., Shao, L., Volz, R.A.: Estimating 3-D location parameters using dual number quaternions. CVGIP: Image Understanding 54(3), 358–367 (1991)CrossRefMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Michael Trummer
    • 1
  • Christoph Munkelt
    • 2
  • Joachim Denzler
    • 1
  1. 1.Chair for Computer VisionFriedrich-Schiller University of JenaJenaGermany
  2. 2.Optical SystemsFraunhofer SocietyJenaGermany

Personalised recommendations