Advertisement

Deep Convolutional Features for Correlation Filter Based Tracking with Parallel Network

  • Jinglin Zhou
  • Rong Wang
  • Jianwei Ding
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 875)

Abstract

Visual tracking has made great progress in either efficiency or accuracy, but still remain imperfections in accurately tracking on the premise of real time. In this paper, we propose a parallel network to integrate two trackers for real-time and high accuracy tracking. In our tracking framework, both trackers are based on correlation filters running in parallel, with one using hand-crafted features (tracker A) for efficiency and another using deep convolutional features (tracker B) for accuracy. And the tracking results are under supervision by a novel criterion. Furthermore, the sample models trained for correlation filter are optimized by controlling sampling frequency. For evaluation, our tracker is experimented on the datasets OTB2013 and OTB2015, demonstrating a higher accuracy than the state-of-the-art trackers on the premise of real time, especially in the situation of object deformation and occlusion.

Keywords

Tracking Convolutional feature Correlation filter Parallel network 

Notes

Acknowledgments

This work is supported by National Key Research and Development Plan under Grant No. 2016YFC0801005. This work is supported by the National Natural Science Foundation of China under Grant No. 61503388.

References

  1. 1.
    Pohlen, T., Hermans, A., Mathias, M., Leibe, B.: Full-resolution residual networks for semantic segmentation in street scenes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3309–3318. IEEE Press, Hawaii (2017)Google Scholar
  2. 2.
    Bagautdinov, T., et al.: Social scene understanding: end-to-end multi-person action localization and collective activity recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3425–3434. IEEE Press, Hawaii (2017)Google Scholar
  3. 3.
    Galoogahi, H.K., et al.: Learning background-aware correlation filters for visual tracking. In: IEEE International Conference on Computer Vision, Venice, pp. 1135–1143 (2017)Google Scholar
  4. 4.
    Danelljan, M., Robinson, A., Shahbaz Khan, F., Felsberg, M.: Beyond correlation filters: learning continuous convolution operators for visual tracking. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 472–488. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46454-1_29CrossRefGoogle Scholar
  5. 5.
    Fan, H., Ling, H.: Parallel tracking and verifying: a framework for real-time and high accuracy visual tracking. In: IEEE International Conference on Computer Vision, Venice, pp. 5486–5494 (2017)Google Scholar
  6. 6.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar
  7. 7.
    Nam, H., Han, B.: Learning multi-domain convolutional neural networks for visual tracking. In: IEEE Conference on Computer Vision and Pattern Recognition. IEEE Press, Las Vegas (2016)Google Scholar
  8. 8.
    Valmadre, J., Bertinetto, L., Henriques, J., Vedaldi, A., Torr, P.H.S.: End-to-end representation learning for correlation filter based tracking. In: IEEE International Conference on Computer Vision, Venice, pp. 5000–5008 (2017)Google Scholar
  9. 9.
    Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.S.: Fully-convolutional siamese networks for object tracking. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 850–865. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-48881-3_56CrossRefGoogle Scholar
  10. 10.
    Kang, K., et al.: Object detection from video tubelets with convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 817–825. IEEE Press, Las Vegas (2016)Google Scholar
  11. 11.
    Bolme, D.S., Beveridge, J.R., Draper, B.A., Lui, Y.M.: Visual object tracking using adaptive correlation filters. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2544–2550. IEEE Press, San Francisco (2010)Google Scholar
  12. 12.
    Henriques, J.F., et al.: High-speed tracking with kernelized correlation filter. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 37, pp. 583–596 (2015)Google Scholar
  13. 13.
    Danelljan, M., Hager, G., Khan, F.S., Felsberg, M.: Learning spatially regularized correlation filters for visual tracking. In: IEEE International Conference on Computer Vision, pp. 4310–4318 (2016)Google Scholar
  14. 14.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Comput. Sci. (2014)Google Scholar
  15. 15.
    Danelljan, M., et al.: ECO: efficient convolution operators for tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6931–6939. IEEE Press, Hawaii (2017)Google Scholar
  16. 16.
    Wu, Y., Lim, J., Yang, M.-H.: Object tracking benchmark. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1834–1848 (2015)CrossRefGoogle Scholar
  17. 17.
    Bertinetto, L., et al.: Staple: complementary learners for real-time tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1401–1409. IEEE Press, Las Vegas (2016)Google Scholar
  18. 18.
    Ma, C., Yang, X., et al.: Long-term correlation tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5388–5396. IEEE Press (2016)Google Scholar
  19. 19.
    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).  https://doi.org/10.1007/978-3-319-10599-4_13 CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.People’s Public Security, University of ChinaBeijingChina

Personalised recommendations