Advertisement

Beyond feature integration: a coarse-to-fine framework for cascade correlation tracking

  • Dongdong LiEmail author
  • Gongjian Wen
  • Yangliu Kuai
  • Fatih Porikli
Original Paper

Abstract

Discriminative correlation filters (DCF) have achieved enormous popularity in the tracking community. Recently, the performance advancement in DCF-based trackers is predominantly driven by the use of convolutional features. In pursuit of extreme tracking performance, state-of-the-art trackers (e.g., cascade correlation tracking [1] and HCF [2]) equip DCF with hierarchical convolutional features to capture both semantics and spatial details of the target appearance. While such methods have been shown to work well, multiple feature integration results in high model complexity which significantly increases the over-fitting risk and computational burden. In this paper, we present a coarse-to-fine framework for cascade correlation tracking (CCT). Instead of integrating hierarchical features, this framework decomposes a complicated tracker into two low-complexity modules, a coarse tracker \({\mathcal {C}}\) and a refined tracker \({\mathcal {R}}\), working in a coarse-to-fine manner. The coarse tracker \({\mathcal {C}}\) employs low-resolution semantic convolutional features extracted from a large search area to cope with large target displacement and appearance change between adjacent frames. By contrast, the refined tracker \({\mathcal {R}}\) employs high-resolution handcraft features extracted from a small search area to further refine the coarse location of \({\mathcal {C}}\). Our CCT tracker enjoys the strong discriminative power of \({\mathcal {C}}\) and the high efficiency of \({\mathcal {R}}\). Experiments on the OTB2013 and TC128 benchmarks show that CCT performs favorably against state-of-the-art trackers.

Keywords

Correlation filter Coarse to fine Visual tracking 

Notes

Acknowledgements

This work is supported by the Natural Science Foundation of China (NSFC) (Nos. 61701506, 61671456).

References

  1. 1.
    Danelljan, M., Robinson, A., Khan, F.S., Felsberg, M.: Beyond correlation filters: Learning continuous convolution operators for visual tracking. In: Proceedings , Part V, Computer Vision - ECCV 2016 - 14th European Conference, Amsterdam, The Netherlands, October 11-14, pp. 472–488, (2016)Google Scholar
  2. 2.
    Ma, C., Huang, JB., Yang, X., Yang, MH.: Hierarchical convolutional features for visual tracking. In: IEEE International Conference on Computer Vision (ICCV), (Dec 2015), pp. 3074–3082Google Scholar
  3. 3.
    Lee, K.-H., Hwang, J.-N.: On-road pedestrian tracking across multiple driving recorders. IEEE Trans. Multimed. 17(9), 1429–1438 (2015)CrossRefGoogle Scholar
  4. 4.
    Guan, T., Wang, C.: Registration based on scene recognition and natural features tracking techniques for wide-area augmented reality systems. IEEE Trans. Multimed. 11(8), 1393–1406 (2009)CrossRefGoogle Scholar
  5. 5.
    Guile, W., Kang, W.: Vision-based fingertip tracking utilizing curvature points clustering and hash model representation. IEEE Trans. Multimed. 19(8), 1730–1741 (2017)CrossRefGoogle Scholar
  6. 6.
    Danelljan, M., Khan, FS., Felsberg, M., Weijer, J.v.d. : Adaptive color attributes for real-time visual tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, (June 2014), pp. 1090–1097Google Scholar
  7. 7.
    Danelljan, M., Hager, G., Khan, FS., Felsberg M.: Discriminative scale space tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, (99), pp.1–1 (2016)Google Scholar
  8. 8.
    Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 583–596 (2015)CrossRefGoogle Scholar
  9. 9.
    Ma, C., Yang, X., Zhang, Chongyang., Yang MH.: Long-term correlation tracking. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (June 2015), pp. 5388–5396Google Scholar
  10. 10.
    Bibi, Adel., Mueller, Matthias., Ghanem, Bernard.: Target response adaptation for correlation filter tracking. In Computer Vision - ECCV 2016 - 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VI, pp. 419–433, (2016)Google Scholar
  11. 11.
    Bertinetto, L., Valmadre, J., Golodetz, S., Miksik, O., Torr, P.H.S.: Staple: Complementary learners for real-time tracking. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (June 2016), pp. 1401–1409Google Scholar
  12. 12.
    Mueller, Matthias., Smith, Neil., Ghanem, Bernard.: Context-aware correlation filter tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2017)Google Scholar
  13. 13.
    Danelljan, M., Hger, G., Khan, F.S., Felsberg, M.: Convolutional features for correlation filter based visual tracking. In: IEEE International Conference on Computer Vision Workshop (ICCVW), (Dec 2015), pp. 621–629Google Scholar
  14. 14.
    Kristan, Matej., Leonardis, Aleš., Matas, Jiri., Felsberg, Michael., Pflugfelder, Roman., Čehovin, Luka., Vojir, Tomas., Häger, Gustav., Lukežič, Alan., Fernandez, Gustavo: The visual object tracking vot2016 challenge results. Springer, (Oct 2016)Google Scholar
  15. 15.
    Song, Yibing., Ma, Chao., Gong, Lijun., Zhang, Jiawei., Lau,Rynson W.H., Yang, Ming-Hsuan .: CREST: convolutional residual learning for visual tracking. In: IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22-29 (2017), pp. 2574–2583Google Scholar
  16. 16.
    Danelljan, Martin., Häger, Gustav., Khan, Fahad Shahbaz., Felsberg, Michael.: Accurate scale estimation for robust visual tracking. In: British Machine Vision Conference, BMVC 2014, Nottingham, UK, September 1-5, (2014)Google Scholar
  17. 17.
    Wu, Y., Lim, J., Yang. MH.: Online object tracking: A benchmark. In: IEEE Conference on Computer Vision and Pattern Recognition, (June 2013), pp. 2411–2418Google Scholar
  18. 18.
    Liang, P., Blasch, E., Ling, H.: Encoding color information for visual tracking: algorithms and benchmark. IEEE Trans. Image Process. 24(12), 5630–5644 (2015)MathSciNetCrossRefGoogle Scholar
  19. 19.
    Wu, Y., Lim, J., Yang, M.H.: Object tracking benchmark. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1834–1848 (2015)CrossRefGoogle Scholar
  20. 20.
    Bolme, DS., Beveridge, JR., Draper, BA., Lui, YM.: Visual object tracking using adaptive correlation filters. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, (June 2010), pp. 2544–2550Google Scholar
  21. 21.
    Henriques, João F., Caseiro, Rui., Martins, Pedro., Batista. Jorge P.: Exploiting the circulant structure of tracking-by-detection with kernels. In Computer Vision - ECCV 2012 - 12th European Conference on Computer Vision, Florence, Italy, October 7–13, 2012, Proceedings, Part IV, pp. 702–715, (2012)Google Scholar
  22. 22.
    Valmadre, Jack., Bertinetto, Luca., Henriques, João F., Vedaldi, Andrea., Torr, Philip HS.: End-to-end representation learning for correlation filter based tracking. CoRR, abs/1704.06036, (2017)Google Scholar
  23. 23.
    Danelljan, M., Hger, G., Khan, FS., Felsberg, M.: Learning spatially regularized correlation filters for visual tracking. In: IEEE International Conference on Computer Vision (ICCV), (Dec 2015), pp. 4310–4318Google Scholar
  24. 24.
    Galoogahi, Hamed Kiani., Fagg, Ashton., Lucey, Simon.: Learning background-aware correlation filters for visual tracking. CoRR, abs/1703.04590, (2017)Google Scholar
  25. 25.
    Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking-learning-detection. IEEE Trans. Pattern Anal. Mach. Intell. 34(7), 1409–1422 (2012)CrossRefGoogle Scholar
  26. 26.
    Simonyan, Karen., Zisserman, Andrew.: Very deep convolutional networks for large-scale image recognition. ICLR, (2014)Google Scholar
  27. 27.
    Vedaldi, Andrea., Lenc, Karel.: Matconvnet: Convolutional neural networks for matlab. In: Proceedings of the 23rd ACM international conference on Multimedia, pp. 689–692 (2015)Google Scholar
  28. 28.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), vol. 1 (June 2005), pp. 886–893Google Scholar
  29. 29.
    Bertinetto, Luca., Valmadre, Jack., Henriques, João F., Vedaldi, Andrea ., Torr, Philip H.S. : Fully-convolutional siamese networks for object tracking. In Computer Vision - ECCV 2016 Workshops - Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part II, pp. 850–865, (2016)Google Scholar
  30. 30.
    Fan, Heng., Ling, Haibin.: Parallel tracking and verifying: a framework for real-time and high accuracy visual tracking. In IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22-29 (2017), pp. 5487–5495Google Scholar

Copyright information

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

Authors and Affiliations

  • Dongdong Li
    • 1
    Email author
  • Gongjian Wen
    • 1
  • Yangliu Kuai
    • 1
  • Fatih Porikli
    • 2
  1. 1.College of Electronic ScienceNational University of Defense TechnologyChangshaChina
  2. 2.Research School of EngineeringAustralian National UniversityCanberraAustralia

Personalised recommendations