Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

Fast Spatially-Regularized Correlation Filters for Visual Object Tracking

  • Conference paper
  • First Online:
PRICAI 2018: Trends in Artificial Intelligence (PRICAI 2018)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 11012))

Included in the following conference series:

Abstract

Spatially-regularized correlation filters have achieved great successes in visual object tracking, with excellent tracking accuracy and robustness to various interferences. The performance improvement mainly attributes to spatial regularization (SR), which is a powerful tool to alleviate the boundary effects of correlation filters (CF) based tracking, but on the other hand, also severely harms the efficiency. In this paper, we propose an effective fast spatial regularization model that can be learned within the joint frequency and spatial domain. Extensive experiments on OTB-100 validate the effectiveness and generality of our model in helping state-of-the-art CF trackers to achieve much faster (near 5 times) frame rate and even better tracking accuracy.

P. Zhang and Q. Guo—Both authors contributed equally to this work.

W. Feng—This work is supported by NSFC 61671325, 61572354, 61672376.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    The term single-layer convolution network has been used in feature learning [4, 20]. With the single-layer CNN, we can jointly learn the deep feature representation and filters to get better tracking accuracy by back propagating the loss to feature network in the future.

References

  1. Bertinetto, L., Valmadre, J., Golodetz, S., Miksik, O., Torr, P.H.S.: Staple: complementary learners for real-time tracking. In: CVPR (2016)

    Google Scholar 

  2. Chen, Z., Guo, Q., Wan, L., Feng, W.: Background-suppressed correlation filters for visual tracking. In: ICME (2018)

    Google Scholar 

  3. Choi, J., Chang, H., Jeong, J., Demiris, Y., Jin, Y.: Visual tracking using attention-modulated disintegration and integration. In: CVPR (2016)

    Google Scholar 

  4. Coates, A., Lee, H., Ng, A.: An analysis of single-layer networks in unsupervised feature learning. In: AISTATS (2011)

    Google Scholar 

  5. Danelljan, M., Bhat, G., Khan, F., Felsberg, M.: ECO: efficient convolution operators for tracking. In: CVPR (2017)

    Google Scholar 

  6. Danelljan, M., Häger, G., Khan, F.S., Felsberg, M.: Accurate scale estimation for robust visual tracking. In: BMVC (2014)

    Google Scholar 

  7. Danelljan, M., Häger, G., Khan, F.S., Felsberg, M.: Learning spatially regularized correlation filters for visual tracking. In: ICCV (2015)

    Google Scholar 

  8. Danelljan, M., Robinson, A., Khan, F., Felsberg, M.: Beyond correlation filters: learning continuous convolution operators for visual tracking. In: ECCV (2016)

    Chapter  Google Scholar 

  9. Dollar, P.: Piotr’s computer vision matlab toolbox: histogram of oriented gradients

    Google Scholar 

  10. Feng, W., Jia, J., Liu, Z.Q.: Self-validated labeling of Markov random fields for image segmentation. IEEE TPAMI 32(10), 1871–1887 (2010)

    Article  Google Scholar 

  11. Galoogahi, H.K., Sim, T., Lucey, S.: Correlation filters with limited boundaries. In: CVPR (2015)

    Google Scholar 

  12. Guo, Q., Feng, W., Zhou, C.: Structure-regularized compressive tracking with online data-driven sampling. IEEE TIP 26(12), 5692–5705 (2017)

    MathSciNet  Google Scholar 

  13. Guo, Q., Feng, W., Zhou, C., Huang, R., Wan, L., Wang, S.: Learning dynamic Siamese network for visual object tracking. In: ICCV (2017)

    Google Scholar 

  14. Guo, Q., Sun, S., Ren, X., Dong, F., Gao, B., Feng, W.: Frequency-tuned active contour model. Neurocomputing 275, 2307–2316 (2018)

    Article  Google Scholar 

  15. Han, R.Z., Guo, Q., Feng, W.: Content-related spatial regularization for visual object tracking. In: ICME (2018)

    Google Scholar 

  16. Hare, S., Saffari, A., Torr, P.H.S.: Struck: structured output tracking with kernels. In: ICCV (2011)

    Google Scholar 

  17. Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. IEEE TPAMI (2015)

    Google Scholar 

  18. Huang, R., Feng, W., Sun, J.: Color feature reinforcement for co-saliency detection without single saliency residuals. IEEE SPL 24(5), 569–573 (2017)

    Google Scholar 

  19. Van De Weijer, J., Schmid, C., Verbeek, J., Larlus, D.: Learning color names for real-world applications. IEEE TIP 18(7), 1512–1523 (2009)

    MathSciNet  MATH  Google Scholar 

  20. Knerr, S., Personnaz, L., Dreyfus, G.: Handwritten digit recognition by neural networks with single-layer training. IEEE TNN 3(6), 962–968 (1992)

    Google Scholar 

  21. Kristan, M., Matas, J., Leonardis, A., Vojir, T., Pflugfelder, R., Fernandez, G., Nebehay, G., Porikli, F., Cehovin, L.: A novel performance evaluation methodology for single-target trackers. IEEE TPAMI 38(11), 2137–2155 (2016)

    Article  Google Scholar 

  22. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)

    Google Scholar 

  23. Li, Y., Zhu, J.: A scale adaptive kernel correlation filter tracker with feature integration. In: ECCVW (2014)

    Google Scholar 

  24. Lukezic, A., Vojir, T., Cehovin, L., Matas, J., Kristan, M.: Discriminative correlation filter with channel and spatial reliability. In: CVPR (2017)

    Google Scholar 

  25. Ma, C., Huang, J.B., Yang, X., Yang, M.H.: Hierarchical convolutional features for visual tracking. In: ICCV (2015)

    Google Scholar 

  26. Ma, C., Yang, X., Zhang, C., Yang, M.H.: Long-term correlation tracking. In: CVPR (2015)

    Google Scholar 

  27. Mathieu, M., Henaff, M., Lecun, Y.: Fast training of convolutional networks through FFTs. In: ICLR (2014)

    Google Scholar 

  28. Mueller, M., Smith, N., Ghanem, B.: Context-aware correlation filter tracking. In: CVPR (2017)

    Google Scholar 

  29. Nam, H., Han, B.: Learning multi-domain convolutional neural networks for visual tracking. In: CVPR (2016)

    Google Scholar 

  30. Ning, J., Yang, J., Jiang, S., Zhang, L., Yang, M.: Object tracking via dual linear structured SVM and explicit feature map. In: CVPR (2016)

    Google Scholar 

  31. Valmadre, J., Bertinetto, L., Henriques, J.F., Vedaldi, A., Torr, P.H.S.: End-to-end representation learning for correlation filter based tracking. In: CVPR (2017)

    Google Scholar 

  32. Wang, M., Liu, Y., Huang, Z.: Large margin object tracking with circulant feature maps. In: CVPR (2017)

    Google Scholar 

  33. Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark. In: CVPR (2013)

    Google Scholar 

  34. Zhou, C., Guo, Q., Wan, L., Feng, W.: Selective object and context tracking. In: ICASSP (2017)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, Tianjin University, Tianjin, China

    Pengyu Zhang, Qing Guo & Wei Feng

  2. Key Research Center for Surface Monitoring and Analysis of Cultural Relics, SACH, Beijing, China

    Pengyu Zhang, Qing Guo & Wei Feng

Authors
  1. Pengyu Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Qing Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Wei Feng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Wei Feng .

Editor information

Editors and Affiliations

  1. Southeast University, Nanjing, China

    Xin Geng

  2. University of Tasmania, Hobart, Tasmania, Australia

    Byeong-Ho Kang

Rights and permissions

Reprints and permissions

Copyright information

© 2018 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Zhang, P., Guo, Q., Feng, W. (2018). Fast Spatially-Regularized Correlation Filters for Visual Object Tracking. In: Geng, X., Kang, BH. (eds) PRICAI 2018: Trends in Artificial Intelligence. PRICAI 2018. Lecture Notes in Computer Science(), vol 11012. Springer, Cham. https://doi.org/10.1007/978-3-319-97304-3_5

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-97304-3_5

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-97303-6

  • Online ISBN: 978-3-319-97304-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation