Advertisement

Efficient Learning of Linear Predictors Using Dimensionality Reduction

  • Stefan Holzer
  • Slobodan Ilic
  • David Joseph Tan
  • Nassir Navab
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7726)

Abstract

Using Linear Predictors for template tracking enables fast and reliable real-time processing. However, not being able to learn new templates online limits their use in applications where the scene is not known a priori and multiple templates have to be added online, such as SLAM or SfM. This especially holds for applications running on low-end hardware such as mobile devices. Previous approaches either had to learn Linear Predictors offline [1], or start with a small template and iteratively grow it over time [2]. We propose a fast and simple learning procedure which reduces the necessary training time by up to two orders of magnitude while also slightly improving the tracking robustness with respect to large motions and image noise. This is illustrated in an exhaustive evaluation where we compare our approach with state-of-the-art approaches. Additionally, we show the learning and tracking in mobile phone applications which demonstrates the efficiency of the proposed approach.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Jurie, F., Dhome, M.: Hyperplane approximation for template matching. IEEE Transactions on Pattern Analysis and Machine Intelligence (2002)Google Scholar
  2. 2.
    Holzer, S., Ilic, S., Navab, N.: Adaptive linear predictors for real-time tracking. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 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. International Journal of Computer Vision (2000)Google Scholar
  5. 5.
    Hager, G., Belhumeur, P.: Efficient region tracking with parametric models of geometry and illumination. IEEE Transactions on Pattern Analysis and Machine Intelligence (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. IEEE Transactions on Pattern Analysis and Machine Intelligence (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. International Journal of Computer Vision (2004)Google Scholar
  10. 10.
    Malis, E.: Improving vision-based control using efficient second-order minimization techniques. In: IEEE International Conference on Robotics and Automation (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: British Machine Vision Conference (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.J.: Learning Efficient Linear Predictors for Motion Estimation. In: Kalra, P., Peleg, S. (eds.) ICVGIP 2006. LNCS, vol. 4338, pp. 445–456. Springer, Heidelberg (2006)CrossRefGoogle 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. IEEE Transactions on Pattern Analysis and Machine Intelligence (2009)Google Scholar
  18. 18.
    Hinterstoisser, S., Benhimane, S., Navab, N., Fua, P., Lepetit, V.: Online learning of patch perspective rectification for efficient object detection. In: Conference on Computer Vision and Pattern Recognition, Anchorage, Alaska (2008)Google Scholar
  19. 19.
    Hinterstoisser, S., Kutter, O., Navab, N., Fua, P., Lepetit, V.: Real-time learning of accurate patch rectification (2009)Google Scholar
  20. 20.
    Hinterstoisser, S., Lepetit, V., Ilic, S., Fua, P., Navab, N.: Dominant orientation templates for real-time detection of texture-less objects (2010)Google Scholar
  21. 21.
    Holzer, S., Hinterstoisser, S., Ilic, S., Navab, N.: Distance transform templates for object detection and pose estimation (2009)Google Scholar
  22. 22.
    Özuysal, M., Fua, P., Lepetit, V.: Fast Keypoint Recognition in Ten Lines of Code. In: Conference on Computer Vision and Pattern Recognition, Minneapolis, MI, USA (2007)Google Scholar
  23. 23.
    Dame, A., Marchand, E.: Accurate real-time tracking using mutual information. In: 2010 9th IEEE International Symposium on Mixed and Augmented Reality (ISMAR), pp. 47–56 (2010)Google Scholar
  24. 24.
    Richa, R., Sznitman, R., Taylor, R., Hager, G.: Visual tracking using the sum of conditional variance. In: 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2953–2958 (2011)Google Scholar
  25. 25.
    Gräßl, C., Zinßer, T., Niemann, H.: Illumination insensitive template matching with hyperplanes. In: Proceedings of Pattern Recognition: 25th DAGM Symposium, Magdeburg, Germany (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

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

Personalised recommendations