Advertisement

Robust Tracking via Dual Constrained Filters

  • Bo YuanEmail author
  • Tingfa Xu
  • Bo Liu
  • Yu Bai
  • Ruoling Yang
  • Xueyuan Sun
  • Yiwen Chen
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 516)

Abstract

In this paper, we propose a novel correlation filter framework constrained by dual filters. The Minimum Output Sum of Squared Error (MOSSE) filter is the unbiased estimate of the filter which easily to cause overfitting. The trained filter by linear ridge regression is the biased estimate of the filter which can deal with the overfitting. We combine the advantages of the two filters to constrain the trained filter which optimizes our model. To deal with background clutter, clipping background patches around the target position up, down, left, and right, we add the cropped background patches to the learning filter. To overcome the challenge of occlusion, we introduce a novel criterion, Average Peak-to-Correlation Energy (APCE). Extensive experiments on the CVPR 2013 Benchmark well demonstrate that our tracker can effectively solve the background clutter and occlusion. Both quantitative analysis and qualitative analysis show that our tracker outperforms some state-of-the-art trackers.

Keywords

Dual filters Background clutter Occlusion CVPR 2013 Benchmark 

Notes

Acknowledgments

This work was supported by the Major Science Instrument Program of the National Natural Science Foundation of China under grant 61527802, and the General Program of National Nature Science Foundation of China under grants 61371132 and 61471043.

References

  1. 1.
    Bolme DS, Beveridge JR. Visual object tracking using adaptive correlation filters. In: IEEE computer vision and pattern recognition; 2010. p. 2544–50.Google Scholar
  2. 2.
    Henriques JF, Rui C, Martins P. Exploiting the circulant structure of tracking-by-detection with kernels. In: Computer vision—ECCV. Berlin: Springer; 2012. p. 702–15.CrossRefGoogle Scholar
  3. 3.
    Danelljan M, Gustav H. Discriminative scale space tracking. IEEE Trans Pattern Anal Mach Intell. 2017;39(8):1561–75.CrossRefGoogle Scholar
  4. 4.
    Henriques JF, Rui C, Martins P. High-speed tracking with kernelized correlation filters. IEEE Trans Pattern Anal Mach Intell. 2015;37(3):583–96.CrossRefGoogle Scholar
  5. 5.
    Li Y, Zhu J. Adaptive kernel correlation filter tracker with feature integration, vol. 8926. Springer; 2014. p. 254–65.Google Scholar
  6. 6.
    Wang MM, Liu Y, Huang ZY. Large margin object tracking with circulant feature maps. In: IEEE computer vision and pattern recognition; 2017. p. 4800–8.Google Scholar
  7. 7.
    Wu Y, Lmi J, Yang MH. Online object tracking: a benchmark. In: IEEE computer vision and pattern recognition; 2013. p. 2411–8.Google Scholar
  8. 8.
    Mueller M, Smith N, Ghanem B. Context-aware correlation filter tracking. In: IEEE computer vision and pattern recognition; 2017. p. 1387–95.Google Scholar
  9. 9.
    Sunando S. Struck: structured output tracking with kernels. IEEE Trans Pattern Anal Mach Intell. 2015;38(10):2096–109.Google Scholar
  10. 10.
    Kalal Z, Mikolajczyj K, Matas J. Tracking-learning-detection. IEEE Trans Pattern Anal Mach Intell. 2012;34(7):1409–22.CrossRefGoogle Scholar
  11. 11.
    Kwon J, Lee KM. Visual tracking decomposition. In: IEEE computer vision and pattern recognition; 2010. p. 1269–76.Google Scholar
  12. 12.
    Medioni G. Exploring supporters and distracters in unconstrained environments. In: IEEE computer vision and pattern recognition; 2011. p. 1177–84.Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Bo Yuan
    • 1
    Email author
  • Tingfa Xu
    • 1
  • Bo Liu
    • 1
  • Yu Bai
    • 1
  • Ruoling Yang
    • 1
  • Xueyuan Sun
    • 1
  • Yiwen Chen
    • 1
  1. 1.School of Optics and PhotonicsBeijing Institute of TechnologyBeijingChina

Personalised recommendations