Coupling Semi-supervised Learning and Example Selection for Online Object Tracking

  • Min YangEmail author
  • Yuwei Wu
  • Mingtao Pei
  • Bo Ma
  • Yunde Jia
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9006)


Training example collection is of great importance for discriminative trackers. Most existing algorithms use a sampling-and-labeling strategy, and treat the training example collection as a task that is independent of classifier learning. However, the examples collected directly by sampling are not intended to be useful for classifier learning. Updating the classifier with these examples might introduce ambiguity to the tracker. In this paper, we introduce an active example selection stage between sampling and labeling, and propose a novel online object tracking algorithm which explicitly couples the objectives of semi-supervised learning and example selection. Our method uses Laplacian Regularized Least Squares (LapRLS) to learn a robust classifier that can sufficiently exploit unlabeled data and preserve the local geometrical structure of feature space. To ensure the high classification confidence of the classifier, we propose an active example selection approach to automatically select the most informative examples for LapRLS. Part of the selected examples that satisfy strict constraints are labeled to enhance the adaptivity of our tracker, which actually provides robust supervisory information to guide semi-supervised learning. With active example selection, we are able to avoid the ambiguity introduced by an independent example collection strategy, and to alleviate the drift problem caused by misaligned examples. Comparison with the state-of-the-art trackers on the comprehensive benchmark demonstrates that our tracking algorithm is more effective and accurate.


Object Tracking Unlabeled Data Classifier Learning Appearance Variation Label Noise 
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.



This work was supported in part by the Natural Science Foundation of China (NSFC) under grant NO. 61203291, the 973 Program of China under grant NO. 2012CB720000, the Specialized Research Fund for the Doctoral Program of Higher Education of China (20121101120029), and the Specialized Fund for Joint Building Program of Beijing Municipal Education Commission.

Supplementary material

336669_1_En_31_MOESM1_ESM.pdf (1.1 mb)
Supplementary material (pdf 1,118 KB)


  1. 1.
    Ross, D., Lim, J., Lin, R., Yang, M.H.: Incremental learning for robust visual tracking. Int. J. Comput. Vis. 77, 125–141 (2008)CrossRefGoogle Scholar
  2. 2.
    Kwon, J., Lee, K.: Visual tracking decomposition. In: CVPR, pp. 1269–1276 (2010)Google Scholar
  3. 3.
    Mei, X., Ling, H.: Robust visual tracking using \(\ell 1\) minimization. In: ICCV, pp. 1–8 (2009)Google Scholar
  4. 4.
    Zhong, W., Lu, H., Yang, M.H.: Robust object tracking via sparsity-based collaborative model. In: CVPR, pp. 1838–1845 (2012)Google Scholar
  5. 5.
    Jia, X., Lu, H., Yang, M.H.: Visual tracking via adaptive structural local sparse appearance model. In: CVPR, pp. 1822–1829 (2012)Google Scholar
  6. 6.
    Wang, N., Wang, J., Yeung, D.Y.: Online robust non-negative dictionary learning for visual tracking. In: ICCV, pp. 657–664 (2013)Google Scholar
  7. 7.
    Wu, Y., Ma, B., Yang, M., Zhang, J., Jia, Y.: Metric learning based structural appearance model for robust visual tracking. IEEE Trans. Circuits Syst. Video Technol. 24, 865–877 (2014)CrossRefGoogle Scholar
  8. 8.
    Wang, D., Lu, H., Yang, M.H.: Least soft-thresold squares tracking. In: CVPR, pp. 2371–2378 (2013)Google Scholar
  9. 9.
    Hare, S., Saffari, A., Torr, P.H.: Struck: structured output tracking with kernels. In: ICCV, pp. 263–270 (2011)Google Scholar
  10. 10.
    Zhang, K., Zhang, L., Yang, M.-H.: Real-time compressive tracking. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part III. LNCS, vol. 7574, pp. 864–877. Springer, Heidelberg (2012) CrossRefGoogle Scholar
  11. 11.
    Li, X., Shen, C., Dick, A.R., van den Hengel, A.: Learning compact binary codes for visual tracking. In: CVPR, pp. 2419–2426 (2013)Google Scholar
  12. 12.
    Yao, R., Shi, Q., Shen, C., Zhang, Y., van den Hengel, A.: Part-based visual tracking with online latent structural learning. In: CVPR, pp. 2363–2370 (2013)Google Scholar
  13. 13.
    Bai, Q., Wu, Z., Sclaroff, S., Betke, M., Monnier, C.: Randomized ensemble tracking. In: ICCV, pp. 2040–2047 (2013)Google Scholar
  14. 14.
    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
  15. 15.
    Babenko, B., Yang, M.H., Belongie, S.: Robust object tracking with online multiple instance learning. IEEE Trans. Pattern Anal. Mach. Intell. 33, 1619–1632 (2011)CrossRefGoogle Scholar
  16. 16.
    Saffari, A., Leistner, C., Godec, M., Bischof, H.: Robust multi-view boosting with priors. In: Saffari, A., Leistner, C., Godec, M., Bischof, H. (eds.) ECCV 2010, Part III. LNCS, vol. 6313, pp. 776–789. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  17. 17.
    Bai, Y., Tang, M.: Robust tracking via weakly supervised ranking SVM. In: CVPR, pp. 1854–1861 (2012)Google Scholar
  18. 18.
    Gao, J., Xing, J., Hu, W., Maybank, S.: Discriminant tracking using tensor representation with semi-supervised improvement. In: ICCV (2013)Google Scholar
  19. 19.
    Kalal, Z., Matas, J., Mikolajczyk, K.: P-N learning: bootstrapping binary classifiers by structural constraints. In: CVPR, pp. 49–56 (2010)Google Scholar
  20. 20.
    Supancic III, J.S., Ramanan, D.: Self-paced learning for long-term tracking. In: CVPR, pp. 2379–2386 (2013)Google Scholar
  21. 21.
    Belkin, M., Niyogi, P., Sindhwani, V.: Manifold regularization: a geometric framework for learning from labeled and unlabeled examples. J. Mach. Learn. Res. 7, 2399–2434 (2006)zbMATHMathSciNetGoogle Scholar
  22. 22.
    Cohn, D.A., Ghahramani, Z., Jordan, M.I.: Active learning with statistical models. J. Artif. Intell. Res. 4, 129–145 (1996)zbMATHGoogle Scholar
  23. 23.
    Atkinson, A.C., Donev, A.N.: Optimum Experimental Designs. Oxford University Press, New York (2002) Google Scholar
  24. 24.
    Santner, J., Leistner, C., Saffari, A., Pock, T., Bischof, H.: PROST: parallel robust online simple tracking. In: CVPR, pp. 723–730 (2010)Google Scholar
  25. 25.
    Yu, K., Bi, J., Tresp, V.: Active learning via transductive experimental design. In: ICML, pp. 1081–1088 (2006)Google Scholar
  26. 26.
    He, X., Min, W., Cai, D., Zhou, K.: Laplacian optimal design for image retrieval. In: ACM SIGIR, pp. 119–126 (2007)Google Scholar
  27. 27.
    He, X.: Laplacian regularized d-optimal design for active learning and its application to image retrieval. IEEE Trans. Image Process. 19, 254–263 (2010)CrossRefMathSciNetGoogle Scholar
  28. 28.
    Zelnik-Manor, L., Perona, P.: Self-tuning spectral clustering. In: NIPS, pp. 1601–1608 (2004)Google Scholar
  29. 29.
    Isard, M., Blake, A.: Condensation - conditional density propagation for visual tracking. Int. J. Comput. Vis. 29, 5–28 (1998)CrossRefGoogle Scholar
  30. 30.
    Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark. In: CVPR, pp. 2411–2418 (2013)Google Scholar
  31. 31.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. 886–893 (2005)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Min Yang
    • 1
    Email author
  • Yuwei Wu
    • 1
  • Mingtao Pei
    • 1
  • Bo Ma
    • 1
  • Yunde Jia
    • 1
  1. 1.Beijing Laboratory of Intelligent Information TechnologySchool of Computer Science, Beijing Institute of TechnologyBeijingChina

Personalised recommendations