Advertisement

Online Learning of Linear Predictors for Real-Time Tracking

  • Stefan Holzer
  • Marc Pollefeys
  • Slobodan Ilic
  • David Joseph Tan
  • Nassir Navab
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7572)

Abstract

Although fast and reliable, real-time template tracking using linear predictors requires a long training time. The lack of the ability to learn new templates online prevents their use in applications that require fast learning. This especially holds for applications where the scene is not known a priori and multiple templates have to be added online. So far, linear predictors had to be either learned offline [1] or in an iterative manner by starting with a small sized template and growing it over time [2]. In this paper, we propose a fast and simple reformulation of the learning procedure that allows learning new linear predictors online.

Keywords

template tracking template learning linear predictors 

References

  1. 1.
    Jurie, F., Dhome, M.: Hyperplane approximation for template matching. PAMI (2002)Google Scholar
  2. 2.
    Holzer, S., Ilic, S., Navab, N.: Adaptive linear predictors for real-time tracking. In: CVPR, San Francisco, CA, USA (2010)Google Scholar
  3. 3.
    Lucas, B., Kanade, T.: An Iterative Image Registration Technique with an Application to Stereo Vision. In: International Joint Conference on Artificial Intelligence (1981)Google Scholar
  4. 4.
    Shum, H.Y., Szeliski, R.: Construction of panoramic image mosaics with global and local alignment. IJCV (2000)Google Scholar
  5. 5.
    Hager, G., Belhumeur, P.: Efficient region tracking with parametric models of geometry and illumination. PAMI (1998)Google Scholar
  6. 6.
    Cascia, M., Sclaroff, S., Athitsos, V.: Fast, reliable head tracking under varying illumination: An approach based on registration of texture-mapped 3d models. PAMI (2000)Google Scholar
  7. 7.
    Dellaert, F., Collins, R.: Fast image-based tracking by selective pixel integration. In: ICCV Workshop of Frame-Rate Vision (1999)Google Scholar
  8. 8.
    Baker, S., Matthews, I.: Equivalence and efficiency of image alignment algorithms. In: Conference on Computer Vision and Pattern Recognition, Los Alamitos, CA, USA (2001)Google Scholar
  9. 9.
    Baker, S., Matthews, I.: Lucas-kanade 20 years on: A unifying framework. IJCV (2004)Google Scholar
  10. 10.
    Malis, E.: Improving vision-based control using efficient second-order minimization techniques. In: ICRA (2004)Google Scholar
  11. 11.
    Benhimane, S., Malis, E.: Homography-based 2d visual tracking and servoing. International Journal of Robotics Research (2007)Google Scholar
  12. 12.
    Jurie, F., Dhome, M.: Real time robust template matching. In: BMVC (2002)Google Scholar
  13. 13.
    Gräßl, C., Zinßer, T., Niemann, H.: Efficient hyperplane tracking by intelligent region selection. In: Image Analysis and Interpretation (2004)Google Scholar
  14. 14.
    Parisot, P., Thiesse, B., Charvillat, V.: Selection of reliable features subsets for appearance-based tracking. Signal-Image Technologies and Internet-Based System (2007)Google Scholar
  15. 15.
    Matas, J., Zimmermann, K., Svoboda, T., Hilton, A.: Learning efficient linear predictors for motion estimation. In: Computer Vision, Graphics and Image Processing (2006)Google Scholar
  16. 16.
    Mayol, W.W., Murray, D.W.: Tracking with general regression. Journal of Machine Vision and Applications (2008)Google Scholar
  17. 17.
    Zimmermann, K., Matas, J., Svoboda, T.: Tracking by an optimal sequence of linear predictors. PAMI (2009)Google Scholar
  18. 18.
    Özuysal, M., Fua, P., Lepetit, V.: Fast Keypoint Recognition in Ten Lines of Code. In: CVPR, Minneapolis, MI, USA (2007)Google Scholar
  19. 19.
    Holzer, S., Hinterstoisser, S., Ilic, S., Navab, N.: Distance transform templates for object detection and pose estimation. In: CVPR (2009)Google Scholar
  20. 20.
    Hinterstoisser, S., Benhimane, S., Navab, N., Fua, P., Lepetit, V.: Online learning of patch perspective rectification for efficient object detection. In: CVPR (2008)Google Scholar
  21. 21.
    Hinterstoisser, S., Kutter, O., Navab, N., Fua, P., Lepetit, V.: Real-time learning of accurate patch rectification. In: CVPR (2009)Google Scholar
  22. 22.
    Hinterstoisser, S., Lepetit, V., Ilic, S., Fua, P., Navab, N.: Dominant orientation templates for real-time detection of texture-less objects. In: CVPR (2010)Google Scholar
  23. 23.
    Gräßl, C., Zinßer, T., Niemann, H.: Illumination Insensitive Template Matching with Hyperplanes. In: Michaelis, B., Krell, G. (eds.) DAGM 2003. LNCS, vol. 2781, pp. 273–280. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  24. 24.
    Penrose, R.: A generalized inverse for matrices. In: Proceedings of the Cambridge Philosophical Society (1955)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Stefan Holzer
    • 1
  • Marc Pollefeys
    • 2
  • Slobodan Ilic
    • 1
  • David Joseph Tan
    • 1
  • Nassir Navab
    • 1
  1. 1.Department of Computer ScienceTechnische Universität München (TUM)GarchingGermany
  2. 2.Department of Computer ScienceETH ZurichZurichSwitzerland

Personalised recommendations