Semi-supervised On-Line Boosting for Robust Tracking

  • Helmut Grabner
  • Christian Leistner
  • Horst Bischof
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5302)


Recently, on-line adaptation of binary classifiers for tracking have been investigated. On-line learning allows for simple classifiers since only the current view of the object from its surrounding background needs to be discriminiated. However, on-line adaption faces one key problem: Each update of the tracker may introduce an error which, finally, can lead to tracking failure (drifting). The contribution of this paper is a novel on-line semi-supervised boosting method which significantly alleviates the drifting problem in tracking applications. This allows to limit the drifting problem while still staying adaptive to appearance changes. The main idea is to formulate the update process in a semi-supervised fashion as combined decision of a given prior and an on-line classifier. This comes without any parameter tuning. In the experiments, we demonstrate real-time tracking of our SemiBoost tracker on several challenging test sequences where our tracker outperforms other on-line tracking methods.


Feature Selection Unlabeled Data Tracking Loop Robust Tracking Unlabeled Sample 
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.

Supplementary material

978-3-540-88682-2_19_MOESM1_ESM.avi (28.1 mb)
Supplementary material(28,805 KB)


  1. 1.
    Avidan, S.: Support vector tracking. IEEE Trans. PAMI 26, 1064–1072 (2004)CrossRefGoogle Scholar
  2. 2.
    Lepetit, V., Lagger, P., Fua, P.: Randomized trees for real-time keypoint recognition. In: Proc. CVPR, vol. 2, pp. 775–781 (2005)Google Scholar
  3. 3.
    Özuysal, M., Fua, P., Lepetit, V.: Fast keypoint recognition in ten lines of code. In: CVPR (2007)Google Scholar
  4. 4.
    Grabner, H., Grabner, M., Bischof, H.: Real-time tracking via on-line boosting. In: Proc. BMVC, vol. 1, pp. 47–56 (2006)Google Scholar
  5. 5.
    Collins, R., Liu, Y., Leordeanu, M.: Online selection of discriminative tracking features. IEEE Trans. PAMI 27(10), 1631–1643 (2005)CrossRefGoogle Scholar
  6. 6.
    Lim, J., Ross, D., Lin, R., Yang, M.: Incremental learning for visual tracking. In: Saul, L.K., Weiss, Y., Bottou, L. (eds.) NIPS, vol. 17, pp. 793–800. MIT Press, Cambridge (2005)Google Scholar
  7. 7.
    Avidan, S.: Ensemble tracking. In: Proc. CVPR, vol. 2, pp. 494–501 (2005)Google Scholar
  8. 8.
    Grabner, H., Bischof, H.: On-line boosting and vision. In: Proc. CVPR, vol. 1, pp. 260–267 (2006)Google Scholar
  9. 9.
    Matthews, I., Ishikawa, T., Baker, S.: The template update problem. IEEE Trans. PAMI 26, 810–815 (2004)CrossRefGoogle Scholar
  10. 10.
    Grabner, M., Grabner, H., Bischof, H.: Learning features for tracking. In: Proc. CVPR (2007)Google Scholar
  11. 11.
    Tang, F., Brennan, S., Zhao, Q., Tao, H.: Co-tracking using semi-supervised support vector machines. In: Proc. ICCV, pp. 1–8 (2007)Google Scholar
  12. 12.
    Woodley, T., Stenger, B., Cipolla, R.: Tracking using online feature selection and a local generative model. In: Proc. BMVC (2007)Google Scholar
  13. 13.
    Grossberg, S.: Competitive learning: From interactive activation to adaptive resonance. Neural networks and natural intelligence, 213–250 (1998)Google Scholar
  14. 14.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc. CVPR, vol. I, pp. 511–518 (2001)Google Scholar
  15. 15.
    Li, Y., Ai, H., Yamashita, T., Lao, S., Kawade, M.: Tracking in low frame rate video: A cascade particle filter with discriminative observers of different lifespans. In: Proc. CVPR, pp. 1–8 (2007)Google Scholar
  16. 16.
    Zhu, X.: Semi-supervised learning literature survey. Technical Report 1530, Computer Sciences, University of Wisconsin-Madison (2005)Google Scholar
  17. 17.
    Mallapragada, P.K., Jin, R., Jain, A.K., Liu, Y.: Semiboost: Boosting for semi-supervised learning. Technical report, Department of Computer Science and Engineering, Michigan State University (2007)Google Scholar
  18. 18.
    Leistner, C., Grabner, H., Bischof, H.: Semi-supervised boosting using visual similarity learning. In: Proc. CVPR (to appear, 2008)Google Scholar
  19. 19.
    Schapire, R.: The boosting approach to machine learning: An overview. In: Proceedings MSRI Workshop on Nonlinear Estimation and Classification (2001)Google Scholar
  20. 20.
    Freund, Y., Schapire, R.: A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences 55(1), 119–139 (1997)MathSciNetCrossRefzbMATHGoogle Scholar
  21. 21.
    Friedman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: a statistical view of boosting. Annals of Statistics 28(2), 337–407 (2000)MathSciNetCrossRefzbMATHGoogle Scholar
  22. 22.
    Tieu, K., Viola, P.: Boosting image retrieval. In: Proc. CVPR, pp. 228–235 (2000)Google Scholar
  23. 23.
    Oza, N., Russell, S.: Online bagging and boosting. In: Proceedings Artificial Intelligence and Statistics, pp. 105–112 (2001)Google Scholar
  24. 24.
    Hertz, T., Bar-Hillel, A., Weinshall, D.: Learning distance functions for image retrieval. In: Proc. CVPR, vol. 2, pp. 570–577 (2004)Google Scholar
  25. 25.
    Balcan, M.F., Blum, A., Yang, K.: Co-training and expansion: Towards bridging theory and practice. In: NIPS. MIT Press, Cambridge (2004)Google Scholar
  26. 26.
    Girosi, F., Chan, N.: Prior knowledge and the creation of virtual examples for rbf networks. In: IEEE Workshop on Neural Networks for Signal Processing (1995)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Helmut Grabner
    • 1
    • 2
  • Christian Leistner
    • 1
  • Horst Bischof
    • 1
  1. 1.Institute for Computer Graphics and VisionGraz University of TechnologyAustria
  2. 2.Computer Vision LaboratoryETH ZurichSwitzerland

Personalised recommendations