Robust Tracking with Weighted Online Structured Learning

  • Rui Yao
  • Qinfeng Shi
  • Chunhua Shen
  • Yanning Zhang
  • Anton van den Hengel
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7574)


Robust visual tracking requires constant update of the target appearance model, but without losing track of previous appearance information. One of the difficulties with the online learning approach to this problem has been a lack of flexibility in the modelling of the inevitable variations in target and scene appearance over time. The traditional online learning approach to the problem treats each example equally, which leads to previous appearances being forgotten too quickly and a lack of emphasis on the most current observations. Through analysis of the visual tracking problem, we develop instead a novel weighted form of online risk which allows more subtlety in its representation. However, the traditional online learning framework does not accommodate this weighted form. We thus also propose a principled approach to weighted online learning using weighted reservoir sampling and provide a weighted regret bound as a theoretical guarantee of performance. The proposed novel online learning framework can handle examples with different importance weights for binary, multiclass, and even structured output labels in both linear and non-linear kernels. Applying the method to tracking results in an algorithm which is both efficient and accurate even in the presence of severe appearance changes. Experimental results show that the proposed tracker outperforms the current state-of-the-art.


Online Learning Online Algorithm Appearance Model Visual Tracking Robust Tracking 
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.


  1. 1.
    Wang, S., Lu, H., Yang, F., Yang, M.H.: Superpixel tracking. In: Proc. ICCV, pp. 1323–1330 (2011)Google Scholar
  2. 2.
    Adam, A., Rivlin, E., Shimshoni, I.: Robust fragments-based tracking using the integral histogram. In: Proc. CVPR, vol. 1, pp. 798–805 (2006)Google Scholar
  3. 3.
    Ross, D.A., Lim, J., Lin, R.S., Yang, M.H.: Incremental learning for robust visual tracking. Int. J. Comput. Vision 77, 125–141 (2008)CrossRefGoogle Scholar
  4. 4.
    Kwon, J., Lee, K.M.: Visual tracking decomposition. In: Proc. CVPR (2010)Google Scholar
  5. 5.
    García Cifuentes, C., Sturzel, M., Jurie, F., Brostow, G.J.: Motion models that only work sometimes. In: Proc. BMVC (2012)Google Scholar
  6. 6.
    Mei, X., Ling, H.: Robust visual tracking and vehicle classification via sparse representation. IEEE Trans. on PAMI 33, 2259–2272 (2011)CrossRefGoogle Scholar
  7. 7.
    Li, H., Shen, C., Shi, Q.: Real-time visual tracking using compressive sensing. In: Proc. CVPR, pp. 1305–1312 (2011)Google Scholar
  8. 8.
    Grabner, H., Leistner, C., Bischof, H.: Semi-supervised On-Line Boosting for Robust Tracking. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 234–247. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  9. 9.
    Grabner, H., Grabner, M., Bischof, H.: Real-time tracking via on-line boosting. In: Proc. BMVC, vol. 1, pp. 47–56 (2006)Google Scholar
  10. 10.
    Avidan, S.: Ensemble tracking. IEEE Trans. on PAMI 29, 261–271 (2007)CrossRefGoogle Scholar
  11. 11.
    Babenko, B., Yang, M.H., Belongie, S.: Visual Tracking with Online Multiple Instance Learning. In: Proc. CVPR, pp. 983–999 (2009)Google Scholar
  12. 12.
    Li, X., Shen, C., Shi, Q., Dick, A.R., van den Hengel, A.: Non-sparse linear representations for visual tracking with online reservoir metric learning. In: Proc. CVPR (2012)Google Scholar
  13. 13.
    Li, X., Dick, A.R., Wang, H., Shen, C., van den Hengel, A.: Graph mode-based contextual kernels for robust svm tracking. In: Proc. ICCV, pp. 1156–1163 (2011)Google Scholar
  14. 14.
    Hare, S., Saffari, A., Torr, P.: Struck: Structured output tracking with kernels. In: Proc. ICCV, pp. 263–270 (2011)Google Scholar
  15. 15.
    Avidan, S.: Support vector tracking. IEEE Trans. on PAMI 26(8), 1064–1072 (2004)CrossRefGoogle Scholar
  16. 16.
    Blaschko, M.B., Lampert, C.H.: Learning to Localize Objects with Structured Output Regression. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 2–15. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  17. 17.
    Tsochantaridis, I., Joachims, T., Hofmann, T., Altun, Y.: Large margin methods for structured and interdependent output variables. JMLR 6, 1453–1484 (2005)MathSciNetzbMATHGoogle Scholar
  18. 18.
    Bordes, A., Bottou, L., Gallinari, P., Weston, J.: Solving multiclass support vector machines with larank. In: Proc. ICML, pp. 89–96 (2007)Google Scholar
  19. 19.
    Bordes, A., Usunier, N., Bottou, L.: Sequence Labelling SVMs Trained in One Pass. In: Daelemans, W., Goethals, B., Morik, K. (eds.) ECML PKDD 2008, Part I. LNCS (LNAI), vol. 5211, pp. 146–161. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  20. 20.
    Shalev-Shwartz, S., Singer, Y.: A primal-dual perspective of online learning algorithms. Machine Learning 69, 115–142 (2007)CrossRefGoogle Scholar
  21. 21.
    Efraimidis, P.S., Spirakis, P.G.: Weighted random sampling with a reservoir. Inf. Process. Lett. 97, 181–185 (2006)MathSciNetzbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Rui Yao
    • 1
    • 2
  • Qinfeng Shi
    • 2
  • Chunhua Shen
    • 2
  • Yanning Zhang
    • 1
  • Anton van den Hengel
    • 2
  1. 1.School of Computer ScienceNorthwestern Polytechnical UniversityChina
  2. 2.School of Computer ScienceThe University of AdelaideAustralia

Personalised recommendations