Visual Tracking via Patch-Based Absorbing Markov Chain

  • Ziwei Xiong
  • Nan Zhao
  • Chenglong LiEmail author
  • Jin Tang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11004)


Bounding box description of target object usually includes background clutter, which easily degrades tracking performance. To handle this problem, we propose a general approach to learn robust object representation for visual tracking. It relies a novel patch-based absorbing Markov chain (AMC) algorithm. First, we represent object bounding box with a graph whose nodes are image patches, and introduce a weight for each patch that describes its reliability belonging to foreground object to mitigate background clutter. Second, we propose a simple yet effective AMC-based method to optimize reliable foreground patch seeds as their qualities are very important for patch weight computation. Third, based on the optimized seeds, we also utilize AMC to compute patch weights. Finally, the patch weights are incorporated into object feature description and tracking is carried out by adopting structured support vector machine algorithm. Experiments on the benchmark dataset demonstrate the effectiveness of our proposed approach.


Visual tracking Absorbing Markov chain Weighted patch representation Seed optimization 



This work was jointly supported by National Natural Science Foundation of China (61702002, 61472002), Natural Science Foundation of Anhui Province (1808085QF187), Natural Science Foundation of Anhui Higher Education Institution of China (KJ2017A017) and Co-Innovation Center for Information Supply & Assurance Technology of Anhui University.


  1. 1.
    Bolme, D.S., Beveridge, J.R., Draper, B.A., Lui, Y.M.: Visual object tracking using adaptive correlation filters. In: IEEE Conference CVPR, pp. 2544–2550 (2010)Google Scholar
  2. 2.
    Chen, D., Yuan, Z., Hua, G., Wu, Y., Zheng, N.: Description-discrimination collaborative tracking. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 345–360. Springer, Cham (2014). Scholar
  3. 3.
    Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. TPAMI 25, 564–577 (2003)CrossRefGoogle Scholar
  4. 4.
    Danelljan, M., Hager, G., Khan, F., Felsberg, M.: Accurate scale estimation for robust visual tracking. In: Proceedings BMVC (2014)Google Scholar
  5. 5.
    Duffner, S., Garcia, C.: Pixeltrack: a fast adaptive algorithm for tracking non-rigid objects. In: Proceedings IEEE Conference ICCV (2013)Google Scholar
  6. 6.
    Hare, S., Saffari, A., Torr, P.H.S.: Struck: structured output tracking with kernels. In: Proceedings IEEE Conference ICCV (2011)Google Scholar
  7. 7.
    He, S., Yang, Q., Lau, R., Wang, J., Yang, M.H.: Visual tracking via locality sensitive histograms. In: Proceedings IEEE Conference CVPR (2013)Google Scholar
  8. 8.
    Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. TPAMI 37, 583–596 (2015)CrossRefGoogle Scholar
  9. 9.
    Jiang, B., Zhang, L., Lu, H., Yang, C., Yang, M.H.: Saliency detection via absorbing markov chain. In: Proceedings IEEE Conference ICCV (2013)Google Scholar
  10. 10.
    Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking-learning-detection. TPAMI 34(7), 1409–1422 (2012)CrossRefGoogle Scholar
  11. 11.
    Kim, H.U., Lee, D.Y., Sim, J.Y., Kim, C.S.: SOWP: spatially ordered and weighted patch descriptor for visual tracking. In: Proceedings IEEE Conference ICCV (2015)Google Scholar
  12. 12.
    Li, C., Liang, X., Lu, Y., Zhao, N., Tang, J.: RGB-T object tracking: benchmark and baseline. arXiv:1805.08982 (2018)
  13. 13.
    Li, C., Lin, L., Zuo, W., Tang, J.: Learning patch-based dynamic graph for visual tracking. In: Proceedings AAAI (2017)Google Scholar
  14. 14.
    Li, C., Lin, L., Zuo, W., Tang, J., Yang, M.H.: Visual tracking via dynamic graph learning. arXiv:1710.01444 (2018)
  15. 15.
    Li, C., Wu, X., Bao, Z., Tang, J.: ReGLe: spatially regularized graph learning for visual tracking. In: MM Proceedings ACM (2017)Google Scholar
  16. 16.
    Li, X., Han, Z., Wang, L., Lu, H.: Visual tracking via random walks on graph model. IEEE Trans. Cybern. 46(9), 2144–2155 (2016)CrossRefGoogle Scholar
  17. 17.
    Liu, T., Wang, G., Yang, Q.: Real-time part-based visual tracking via adaptive correlation filters. In: IEEE Conference CVPR (2015)Google Scholar
  18. 18.
    Ma, C., Yang, X., Zhang, C., Yang, M.H.: Long-term correlation tracking. In: Proceedings IEEE Conference CVPR (2015)Google Scholar
  19. 19.
    Tong, H., Faloutsos, C., Pan, J.Y.: Random walk with restart: fast solutions and applications. KAIS 14(3), 327–346 (2008)zbMATHGoogle Scholar
  20. 20.
    Wang, N., Yeung, D.Y.: Learning a deep compact image representation for visual tracking. In: NIPS, pp. 809–817 (2013)Google Scholar
  21. 21.
    Wu, Y., Lim, J., Yang, M.H.: Object tracking benchmark. TPAMI 37, 1834–1848 (2015)CrossRefGoogle Scholar
  22. 22.
    Yang, F., Lu, H., Yang, M.H.: Robust superpixel tracking. IEEE Trans. Image Process. 23(4), 1639–1651 (2014)MathSciNetCrossRefGoogle Scholar
  23. 23.
    Yeo, D., Son, J., Han, B., Han, J.H.: Superpixel-based tracking-by-segmentation using markov chains. In: CVPR, pp. 511–520 (2017)Google Scholar
  24. 24.
    Zhang, J., Ma, S., Sclaroff, S.: MEEM: robust tracking via multiple experts using entropy minimization. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 188–203. Springer, Cham (2014). Scholar
  25. 25.
    Zhang, K., Zhang, L., hsuan Yang, M.: Real-time compressive tracking. In: Proceedings ECCV (2012)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.School of Computer Science and TechnologyAnhui UniversityHefeiChina

Personalised recommendations