On the Optimization of Advanced DCF-Trackers

  • Joakim JohnanderEmail author
  • Goutam Bhat
  • Martin Danelljan
  • Fahad Shahbaz Khan
  • Michael Felsberg
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11129)


Trackers based on discriminative correlation filters (DCF) have recently seen widespread success and in this work we dive into their numerical core. DCF-based trackers interleave learning of the target detector and target state inference based on this detector. Whereas the original formulation includes a closed-form solution for the filter learning, recently introduced improvements to the framework no longer have known closed-form solutions. Instead a large-scale linear least squares problem must be solved each time the detector is updated. We analyze the procedure used to optimize the detector and let the popular scheme introduced with ECO serve as a baseline. The ECO implementation is revisited in detail and several mechanisms are provided with alternatives. With comprehensive experiments we show which configurations are superior in terms of tracking capabilities and optimization performance.



This work was supported by Swedish Foundation for Strategic Research (SymbiCloud); Swedish Research Council (EMC 2, starting grant 2016-05543); CENIIT grant (18.14); Swedish National Infrastructure for Computing; and Wallenberg AI, Autonomous Systems and Software Program (WASP) funded by the Knut and Alice Wallenberg Foundation.


  1. 1.
    Barzilai, J., Borwein, J.M.: Two-point step size gradient methods. IMA J. Numer. Anal. 8(1), 141–148 (1988)MathSciNetzbMATHCrossRefGoogle Scholar
  2. 2.
    Bolme, D.S., Beveridge, J.R., Draper, B.A., Lui, Y.M.: Visual object tracking using adaptive correlation filters. In: CVPR (2010)Google Scholar
  3. 3.
    Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J., et al.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends® Mach. Learn. 3(1), 1–122 (2011)zbMATHGoogle Scholar
  4. 4.
    Cehovin, L., Kristan, M., Leonardis, A.: Is my new tracker really better than yours? In: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 540–547. IEEE (2014)Google Scholar
  5. 5.
    Danelljan, M., Bhat, G., Shahbaz Khan, F., Felsberg, M.: ECO: Efficient convolution operators for tracking. In: CVPR (2017)Google Scholar
  6. 6.
    Danelljan, M., Hager, G., Khan, F.S., Felsberg, M.: Discriminative scale space tracking. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1561–1575 (2016)CrossRefGoogle Scholar
  7. 7.
    Danelljan, M., Häger, G., Shahbaz Khan, F., Felsberg, M.: Learning spatially regularized correlation filters for visual tracking. In: ICCV (2015)Google Scholar
  8. 8.
    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). Scholar
  9. 9.
    Danelljan, M., Shahbaz Khan, F., Felsberg, M., van de Weijer, J.: Adaptive color attributes for real-time visual tracking. In: CVPR (2014)Google Scholar
  10. 10.
    Felsberg, M.: Enhanced distribution field tracking using channel representations. In: ICCV Workshop (2013)Google Scholar
  11. 11.
    Galoogahi, H.K., Fagg, A., Huang, C., Ramanan, D., Lucey, S.: Need for speed: a benchmark for higher frame rate object tracking. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1134–1143. IEEE (2017)Google Scholar
  12. 12.
    Galoogahi, H.K., Sim, T., Lucey, S.: Correlation filters with limited boundaries. In: CVPR (2015)Google Scholar
  13. 13.
    Gundogdu, E., Alatan, A.A.: Good features to correlate for visual tracking. IEEE Trans. Image Process. 27(5), 2526–2540 (2018)MathSciNetCrossRefGoogle Scholar
  14. 14.
    He, Z., Fan, Y., Zhuang, J., Dong, Y., Bai, H.: Correlation filters with weighted convolution responses. In: ICCV Workshops, pp. 1992–2000 (2017)Google Scholar
  15. 15.
    Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. TPAMI 37(3), 583–596 (2015)CrossRefGoogle Scholar
  16. 16.
    Kristan, M., et al.: The visual object tracking VOT2016 challenge results. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 777–823. Springer, Cham (2016). Scholar
  17. 17.
    Kristan, M., et al.: The visual object tracking VOT2017 challenge results. In: ICCV Workshop (2017)Google Scholar
  18. 18.
    Liang, P., Blasch, E., Ling, H.: Encoding color information for visual tracking: algorithms and benchmark. TIP 24(12), 5630–5644 (2015)MathSciNetGoogle Scholar
  19. 19.
    Lukezic, A., Vojír, T., Zajc, L.C., Matas, J., Kristan, M.: Discriminative correlation filter tracker with channel and spatial reliability. Int. J. Comput. Vis. 126(7), 671–688 (2018). Scholar
  20. 20.
    Ma, C., Huang, J.B., Yang, X., Yang, M.H.: Hierarchical convolutional features for visual tracking. In: ICCV (2015)Google Scholar
  21. 21.
    Nocedal, J., Wright, S.J.: Numerical Optimization, 2nd edn. Springer, New York (2006). Scholar
  22. 22.
    Shewchuk, J.R.: An introduction to the conjugate gradient method without the agonizing pain. Technical report, Pittsburgh, PA, USA (1994)Google Scholar
  23. 23.
    Wu, Y., Lim, J., Yang, M.H.: Object tracking benchmark. TPAMI 37(9), 1834–1848 (2015)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Joakim Johnander
    • 1
    • 2
    Email author
  • Goutam Bhat
    • 1
  • Martin Danelljan
    • 1
  • Fahad Shahbaz Khan
    • 1
    • 3
  • Michael Felsberg
    • 1
  1. 1.CVL, Department of Electrical EngineeringLinköping UniversityLinköpingSweden
  2. 2.ZenuityGothenburgSweden
  3. 3.Inception Institute of Artificial IntelligenceAbu DhabiUAE

Personalised recommendations