Robust visual tracking via self-similarity learning

Robust visual tracking via self-similarity learning

For access to this article, please select a purchase option:

Buy article PDF
(plus tax if applicable)
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Your details
Why are you recommending this title?
Select reason:
Electronics Letters — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

Self-similarity is an attractive image property that has been successfully applied to object recognition due to its robustness to severe target appearance variations. However, less attention has been paid to explore self-similarity for visual tracking, mainly because it is difficult to learn self-similarity information between different features suitable for visual tracking. To address this issue, a simple, yet effective approach is presented to learn self-similarity information among the local features extracted from the different regions of the target. The target is first divided into some non-overlapping regions, in which each region is described by the histogram of gradient (HOG) features. Then, an explicit polynomial kernel feature map is constructed, which is capable of characterising the self-similarity information among all the local regions in the targets. Finally, based on the feature maps, a linear support vector machine (SVM) is learnt via an online dual coordinate descent method that offers fast convergence guarantee. Experiments on a large tracking benchmark dataset with 50 sequences demonstrate the superiority of the proposed method over state-of-the-art methods.


    1. 1)
      • 1. Li, X., Hu, W., Shen, C., et al: ‘A survey of appearance models in visual object tracking’, TIST, 2013, 4, p. 58.
    2. 2)
    3. 3)
      • 3. Zhang, K., Liu, Q., Wu, Y., et al: ‘Robust visual tracking via convolutional networks without training’, TIP, 2016, 25, pp. 17791792.
    4. 4)
      • 4. Jia, X., Lu, H., Yang, M.H.: ‘Visual tracking via adaptive structural local sparse appearance model’. CVPR, Providence, RI, USA, June 2012, pp. 18221829.
    5. 5)
      • 5. Zhong, W., Lu, H., Yang, M.H.: ‘Robust object tracking via sparsity-based collaborative model’. CVPR, Providence, RI, USA, June 2012, pp. 18381845.
    6. 6)
      • 6. Zhang, J., Ma, S., Sclaroff, S.: ‘MEEM: robust tracking via multiple experts using entropy minimization’. ECCV, Zürich, Switzerland, September 2014, pp. 188203.
    7. 7)
      • 7. Hare, S., Saffari, A., Torr, P.H.S.: ‘STRUCK: structured output tracking with kernels’. ICCV, Barcelona, Spain, November 2011, pp. 263270.
    8. 8)
      • 8. Gao, J., Ling, H., Hu, W., et al: ‘Transfer learning based visual tracking with Gaussian processes regression’. ECCV, Zürich, Switzerland, September 2014, pp. 188203.
    9. 9)
    10. 10)
      • 10. Wang, N., Shi, J., Yeung, D.Y., et al: ‘Understanding and diagnosing visual tracking systems’. ICCV, Santiago, Chile, December 2015, pp. 31013109.
    11. 11)
      • 11. Wang, N., Yeung, D.Y.: ‘Learning a deep compact image representation for visual tracking’. NIPS, Lake Tahoe, NV, USA, December 2013, pp. 809817.
    12. 12)
      • 12. Danelljan, M., Hager, G., Khan, F., et al: ‘Accurate scale estimation for robust visual tracking’. BMVC, Nottingham, UK, September 2014.
    13. 13)
      • 13. Shechtman, E., Irani, M.: ‘Matching local self-similarities across images and videos’. CVPR, Minneapolis, MN, USA, June 2007, pp. 18.
    14. 14)
      • 14. Deselaers, T., Ferrari, V.: ‘Global and efficient self-similarity for object classification and detection’. CVPR, San Francisco, CA, USA, June 2010, pp. 16331640.
    15. 15)
      • 15. Wu, Y., Lim, J., Yang, M.H.: ‘Online object tracking: a benchmark’. CVPR, Portland, OR, USA, June 2013, pp. 24112418.
    16. 16)

Related content

This is a required field
Please enter a valid email address