Online Graph-Based Tracking

  • Hyeonseob Nam
  • Seunghoon Hong
  • Bohyung Han
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8693)


Tracking by sequential Bayesian filtering relies on a graphical model with temporally ordered linear structure based on temporal smoothness assumption. This framework is convenient to propagate the posterior through the first-order Markov chain. However, density propagation from a single immediately preceding frame may be unreliable especially in challenging situations such as abrupt appearance changes, fast motion, occlusion, and so on. We propose a visual tracking algorithm based on more general graphical models, where multiple previous frames contribute to computing the posterior in the current frame and edges between frames are created upon inter-frame trackability. Such data-driven graphical model reflects sequence structures as well as target characteristics, and is more desirable to implement a robust tracking algorithm. The proposed tracking algorithm runs online and achieves outstanding performance with respect to the state-of-the-art trackers. We illustrate quantitative and qualitative performance of our algorithm in all the sequences in tracking benchmark and other challenging videos.


Online tracking Bayesian model averaging patch matching 


  1. 1.
    Hong, S., Kwak, S., Han, B.: Orderless tracking through model-averaged posterior estimation. In: ICCV (2013)Google Scholar
  2. 2.
    Korman, S., Avidan, S.: Coherency sensitive hashing. In: ICCV (2011)Google Scholar
  3. 3.
    Bao, C., Wu, Y., Ling, H., Ji, H.: Real time robust l1 tracker using accelerated proximal gradient approach. In: CVPR (2012)Google Scholar
  4. 4.
    Mei, X., Ling, H.: Robust visual tracking using l1 minimization. In: ICCV (2009)Google Scholar
  5. 5.
    Zhong, W., Lu, H., Yang, M.-H.: Robust object tracking via sparsity-based collaborative model. In: CVPR (2012)Google Scholar
  6. 6.
    Han, B., Comaniciu, D., Zhu, Y., Davis, L.: Sequential kernel density approximation and its application to real-time visual tracking. TPAMI 30 (2008)Google Scholar
  7. 7.
    Liu, B., Huang, J., Yang, L., Kulikowski, C.A.: Robust tracking using local sparse appearance model and k-selection. In: CVPR, pp. 1313–1320 (2011)Google Scholar
  8. 8.
    Sevilla-Lara, L., Learned-Miller, E.G.: Distribution fields for tracking. In: CVPR, pp. 1910–1917 (2012)Google Scholar
  9. 9.
    Ross, D.A., Lim, J., Lin, R.-S., Yang, M.-H.: Incremental learning for robust visual tracking. IJCV 77 (2008)Google Scholar
  10. 10.
    Zhang, T., Ghanem, B., Liu, S., Ahuja, N.: Robust visual tracking via multi-task sparse learning. In: CVPR (2012)Google Scholar
  11. 11.
    Kwon, J., Lee, K.M.: Tracking of abrupt motion using wang-landau monte carlo estimation. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 387–400. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  12. 12.
    Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking-Learning-Detection. TPAMI (2012)Google Scholar
  13. 13.
    Babenko, B., Yang, M.-H., Belongie, S.: Robust object tracking with online multiple instance learning. TPAMI 33 (2011)Google Scholar
  14. 14.
    Hare, S., Saffari, A., Torr, P.H.S.: Struck: Structured output tracking with kernels. In: ICCV (2011)Google Scholar
  15. 15.
    Pan, P., Schonfeld, D.: Visual tracking using high-order particle filtering. Signal Processing Letters 18, 51–54 (2011)CrossRefGoogle Scholar
  16. 16.
    Kwak, S., Nam, W., Han, B., Han, J.H.: Learning occlusion with likelihoods for visual tracking. In: ICCV (2011)Google Scholar
  17. 17.
    Buchanan, A.M., Fitzgibbon, A.W.: Interactive feature tracking using K-D trees and dynamic programming. In: CVPR (2006)Google Scholar
  18. 18.
    Gu, S., Zheng, Y., Tomasi, C.: Linear time offline tracking and lower envelope algorithms. In: ICCV (2011)Google Scholar
  19. 19.
    Uchida, S., Fujimura, I., Kawano, H., Feng, Y.: Analytical dynamic programming tracker. In: ACCV (2011)Google Scholar
  20. 20.
    Wei, Y., Sun, J., Tang, X., Shum, H.-Y.: Interactive offline tracking for color objects. In: ICCV (2007)Google Scholar
  21. 21.
    Sun, J., Zhang, W., Tang, X., Shum, H.-Y.: Bi-directional tracking using trajectory segment analysis. In: ICCV (2005)Google Scholar
  22. 22.
    Matthews, I., Ishikawa, T., Baker, S.: The template update problem. IEEE Trans. Pattern Anal. Mach. Intell. 26, 810–815 (2004)CrossRefGoogle Scholar
  23. 23.
    Jepson, A.D., Fleet, D.J., El-Maraghi, T.F.: Robust online appearance models for visual tracking. IEEE Trans. Pattern Anal. Mach. Intell. 25, 1296–1311 (2003)CrossRefGoogle Scholar
  24. 24.
    Hoeting, J.A., Madigan, D., Raftery, A.E., Volinsky, C.T.: Bayesian model averaging: A tutorial. Statistical Science 14 (1999)Google Scholar
  25. 25.
    Wu, Y., Lim, J., Yang, M.-H.: Online object tracking: A benchmark. In: CVPR (2013)Google Scholar
  26. 26.
    Jia, X., Lu, H., Yang, M.-H.: Visual tracking via adaptive structural local sparse appearance model. In: CVPR (2012)Google Scholar
  27. 27.
    Dinh, G.T.B., Vo, N., Medioni: Context tracker: Exploring supporters and distracters in unconstrained environments. In: CVPR (2011)Google Scholar
  28. 28.
    Kwon, J., Lee, K.-M.: Visual tracking decomposition. In: CVPR (2010)Google Scholar
  29. 29.
    Kwon, J., Lee, K.M.: Tracking by sampling trackers. In: ICCV (2011)Google Scholar
  30. 30.
    Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: Exploiting the circulant structure of tracking-by-detection with kernels. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part IV. LNCS, vol. 7575, pp. 702–715. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  31. 31.
    Sevilla-Lara, L., Learned-Miller, E.: Distribution fields for tracking. In: CVPR (2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Hyeonseob Nam
    • 1
  • Seunghoon Hong
    • 1
  • Bohyung Han
    • 1
  1. 1.Department of Computer Science and EngineeringPOSTECHKorea

Personalised recommendations