Advertisement

Scale estimation-based visual tracking with optimized convolutional activation features

  • Qiang GuoEmail author
  • Xuefei Cao
  • Qinglong Zou
Original Paper
  • 19 Downloads

Abstract

Convolutional neural networks (CNNs) have proven very effective for learning features in visual tracking. While working effectively, it is still very challenging due to the scale variations and deformation, which may cause inconsecutive tracking trajectory and distraction. In this paper, pre-train deep learning network architecture is adopted for visual tracking, by introducing a spectral pooling in the network. Then, we propose an algorithm which, by interpreting scale correlation filters as the corresponding function of convolution filters in deep neural networks, exploits multilevel CNNs activation features into a new tracking framework. Finally, two-stage fine-tuning is then introduced for updating the model to keep long-time tracking. We test the proposed tracking method on large-scale benchmark sequences. Experimental results illustrate the effectiveness of the proposed algorithm compared with other state-of-the-art methods.

Keywords

Convolutional neural networks Correlation filters Spectrum pooling Visual tracking 

Notes

Acknowledgements

This work is supported by the National Natural Sciences Foundation of China under Grant Nos. 61603415, 61602322, 61503274 and the Fundamental Research Funds for the Central Universities under Grant No. D2019021.

References

  1. 1.
    Kristan, M., Matas, J., Leonardis, A., et al.: The visual object tracking vot2015 challenge results. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 1–23 (2015) Google Scholar
  2. 2.
    Danelljan, M., Khan, F.S., Felsberg, M., van de Weijer, J.: Adaptive color attributes for real-time visual tracking. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp. 1090–1097 (2014)Google Scholar
  3. 3.
    Possegger, H., Mauthner, T., Bischof, H.: In defense of color-based model-free tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2113–2120 (2015)Google Scholar
  4. 4.
    Lebeda, K., Hadfield, S., Matas, J., et al.: Texture-independent long-term tracking using virtual corners. IEEE Trans. Image Process. 25(1), 359–371 (2016)MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    Russakovsky, O., Deng, J., Su, H., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Ma, C., Huang, J.B., Yang, X., et al.: Hierarchical convolutional features for visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3074–3082 (2015)Google Scholar
  7. 7.
    Li, H., Li, Y., Porikli, F.: Deeptrack: Learning discriminative feature representations by convolutional neural networks for visual tracking. In: Proceedings of the British Machine Vision Conference. BMVA Press (2014)Google Scholar
  8. 8.
    Ma, C., Xu, Y., Ni, B., et al.: When correlation filters meet convolutional neural networks for visual tracking. IEEE Signal Process. Lett. 23(10), 1454–1458 (2016)CrossRefGoogle Scholar
  9. 9.
    Danelljan, M., Häger, G., Khan, F., et al.: Accurate scale estimation for robust visual tracking. In: British Machine Vision Conference, Nottingham, September 1–5, 2014. BMVA Press (2014)Google Scholar
  10. 10.
    Li, Y., Zhu, J.: A scale adaptive kernel correlation filter tracker with feature integration. In: European Conference on Computer Vision. Springer, pp. 254–265 (2014)Google Scholar
  11. 11.
    Danelljan, M., Hager, G., Khan, F.S., et al.: Convolutional features for correlation filter based visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 58–66 (2015)Google Scholar
  12. 12.
    Wu, Y., Lim, J., Yang, M.H.: Object tracking benchmark. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1834–1848 (2015)CrossRefGoogle Scholar
  13. 13.
    Bolme, D.S., Beveridge, J.R., Draper, B.A., Lui, Y.M.: Visual object tracking using adaptive correlation filters. In: CVPR, 2010 (2010)Google Scholar
  14. 14.
    Danelljan, M., Khan, F.S., Felsberg, M., van de Weijer, J.: Adaptive color attributes for real-time visual tracking. In: CVPR, 2014 (2014)Google Scholar
  15. 15.
    Henriques, J.F., Caseiro, R., Martins, P., et al.: High-speed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 583–596 (2015)CrossRefGoogle Scholar
  16. 16.
    Li, Y., Zhang, Y., Xu, Y., et al.: Robust scale adaptive kernel correlation filter tracker with hierarchical convolutional features. IEEE Signal Process. Lett. 23(8), 1136–1140 (2016)CrossRefGoogle Scholar
  17. 17.
    Zhang, T., Xu, C., Yang, M.-H.: Multi-task correlation particle filter for robust object tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4335–4343 (2017)Google Scholar
  18. 18.
    Wang, N., Li, S., Gupta, A., Yeung, D.-Y.: Transferring rich feature hierarchies for robust visual tracking. arXiv preprint arXiv:1501.04587 (2015)
  19. 19.
    Wang, N., Yeung, D.-Y.: Learning a deep compact image representation for visual tracking. In: Burges, C., Bottou, L., Welling, M., Ghahramani, Z., Weinberger, K. (eds.) Advances in Neural Information Processing Systems 26, pp. 809–817. Red Hook, Curran Associates (2013)Google Scholar
  20. 20.
    Han, B., Sim, J., Adam, H.: Branchout: regularization for online ensemble tracking with convolutional neural networks. In: CVPR, 2017 (2017)Google Scholar
  21. 21.
    Wang, L., Ouyang, W., Wang, X., et al.: Visual tracking with fully convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3119–3127 (2015)Google Scholar
  22. 22.
    Danelljan, M., Robinson, A., Khan, F.S., Felsberg, M.: Beyond correlation filters: learning continuous convolution operators for visual tracking. In: Proceedings of the European Conference on Computer Vision, pp. 472–488 (2016)Google Scholar
  23. 23.
    Nam, H., Han, B.: Learning multi-domain convolutional neural networks for visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4293–4302 (2016)Google Scholar
  24. 24.
    Song, Y., Ma, C., Gong, L., Zhang, J., Lau, R.W.H., Yang, M.-H.:. Crest: convolutional residual learning for visual tracking. In: IEEE International Conference on Computer Vision (2017)Google Scholar
  25. 25.
    Li, B., Yan, J., Wu, W., Zhu, Z., Hu, X.: High performance visual tracking with siamese region proposal network. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)Google Scholar
  26. 26.
    Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.S.: Fully-convolutional siamese networks for object tracking. In: Proceedings of the European Conference on Computer Vision Workshops, pp. 850–865 (2016)Google Scholar
  27. 27.
    Song, Y., Ma, C., Wu, X., Gong, L., Bao, L., Zuo, W., Shen, C., Rynson, L., Yang, M.-H.: Vital: visual tracking via adversarial learning. In: CVPR, 2018 (2018)Google Scholar
  28. 28.
    Rippel, O., Snoek, J., Adams, R.P.: Spectral Representations for Convolutional Neural Networks. Comput, Sci (2015)Google Scholar
  29. 29.
    Vedaldi, A., Lenc, K.: Matconvnet: convolutional neural networks for matlab. In: Proceedings of the 23rd ACM International Conference on Multimedia. ACM, pp. 689–692 (2015)Google Scholar
  30. 30.
    Danelljan, M., Hager, G., Khan, F.S., et al.: Learning spatially regularized correlation filters for visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4310–4318 (2015)Google Scholar
  31. 31.
    Qi, Y., Zhang, S., Qin, L., et al.: Hedged deep tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4303–4311 (2016)Google Scholar
  32. 32.
    Ma, C., Yang, X., Zhang, C., et al.: Long-term correlation tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5388–5396 (2015)Google Scholar
  33. 33.
    Kristan, M., Leonardis, A., Matas, J., Felsberg, M., Pfugfelder, R., Zajc, L.C., Vojir, T., Bhat, G., Lukezic, A., Eldesokey, A., Fernandez, G., et al.: The sixth visual object tracking vot2018 challenge results. In: ECCV Workshops, 2018 (2018)Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Criminal Investigation DepartmentCriminal Investigation Police University of ChinaShenyangChina
  2. 2.Police Terrorism Research CenterCriminal Investigation Police University of ChinaShenyangChina

Personalised recommendations