Long-Term Tracking Algorithm with the Combination of Multi-feature Fusion and YOLO

  • Sicong Jiang
  • Jianing Zhang
  • Yunzhou ZhangEmail author
  • Feng Qiu
  • Dongdong Wang
  • Xiaobo Liu
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 875)


In recent year correlation filtering based algorithms have achieved significant performance in tracking. In traditional, the previous frame has been trained in order to get the prediction position of the next frame. However, in experiments we find that once the present frame drifts, the latter frame will be affected and accumulate error, which can cause the loss of the target eventually. In that case, the tracker cannot track a target for a long time. To solve these problems and design an efficient long-term tracking algorithm, we propose a long-term tracking algorithm by combining the short-term tracker and the YOLO v2 detector. We use the SURF algorithm to get the similarity of the tracking result and the current contrast template, once the similarity is lower than a threshold, the YOLO v2 will be activated and find the right target through a three-stage cascade selecting mechanism we designed before, then the short-term tracker will be restarted and the contrast template will be updated. In this way, the short-term tracker can be transformed to a long-term tracker which is able to track a target for a long time in complex circumstance. Besides, we also adopt the compound feature to improve our short-term tracker, so our algorithm has better accuracy and robustness. The experimental results demonstrate the proposed approach outperforms state-of-the-art approaches on large-scale benchmark datasets.


Computer vision Long-term tracking Compound feature Correlation filters 



Supported by National Natural Science Foundation of China (No. 61471110, 61733003), National Key R&D Program of China (No. 2017YFC0805000/5005), Fundamental Research Funds for the Central Universities (N172608005, N160413002).


  1. 1.
    Bolme, D.S., Beveridge, J.R., Draper, B.A., et al.: Visual object tracking using adaptive correlation filters. In: Computer Vision and Pattern Recognition, pp. 2544–2550. IEEE (2010)Google Scholar
  2. 2.
    Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: Exploiting the circulant structure of tracking-by-detection with kernels. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 702–715. Springer, Heidelberg (2012). Scholar
  3. 3.
    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
  4. 4.
    Song, T.E., Jang, K.H.: Visual tracking using weighted discriminative correlation filter. J. Korea Soc. Comput. Inf. 21(11), 49–57 (2016)CrossRefGoogle Scholar
  5. 5.
    Danelljan, M., Khan, F.S., Felsberg, M., et al.: Adaptive color attributes for real-time visual tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1090–1097. IEEE Computer Society (2014)Google Scholar
  6. 6.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, pp. 886–893. IEEE (2005)Google Scholar
  7. 7.
    Ma, C., Yang, X., Zhang, C., et al.: Long-term correlation tracking. In: Computer Vision and Pattern Recognition, pp. 5388–5396. IEEE (2015)Google Scholar
  8. 8.
    Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. arXiv preprint, 1612 (2016)Google Scholar
  9. 9.
    Wang, W., Zhou, Y., Zhu, X., et al.: A real-time tracking method based on SURF. In: International Congress on Image and Signal Processing. IEEE (2016)Google Scholar
  10. 10.
    Sakai, Y., Oda, T., Ikeda, M., et al.: An object tracking system based on SIFT and SURF feature extraction methods. In: International Conference on Network-Based Information Systems, pp. 561–565. IEEE (2015)Google Scholar
  11. 11.
    Wu, Y., Lim, J., Yang, M.-H.: Online object tracking: a benchmark. In: CVPR (2013)Google Scholar
  12. 12.
    Wu, Y., Lim, J., Yang, M.-H.: Object tracking benchmark. TPAMI 37(9), 1834–1848 (2015)CrossRefGoogle Scholar
  13. 13.
    Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking-learning-detection. IEEE Trans. Pattern Anal. Mach. Intell. 34(7), 1409–1422 (2012)CrossRefGoogle Scholar
  14. 14.
    Bertinetto, L., Valmadre, J., Golodetz, S., et al.: Staple: complementary learners for real-time tracking, 38(2), 1401–1409 (2015)Google Scholar
  15. 15.
    Hare, S., Saffari, A., Torr, P.H.S.: Struck: structured output tracking with kernels. In: International Conference on Computer Vision, pp. 263–270. IEEE Computer Society (2011)Google Scholar
  16. 16.
    Kwon, J., Lee, K.M.: Visual tracking decomposition. In: Computer Vision and Pattern Recognition, pp. 1269–1276. IEEE (2010)Google Scholar
  17. 17.
    Dinh, T.B., Vo, N., Medioni, G.: Context tracker: exploring supporters and distracters in unconstrained environments. In: Computer Vision and Pattern Recognition, pp. 1177–1184. IEEE (2011)Google Scholar
  18. 18.
    Kwon, J., Lee, K.M.: Tracking by sampling trackers. In: IEEE International Conference on Computer Vision, pp. 1195–1202. IEEE (2011)Google Scholar
  19. 19.
    Liu, B., Huang, J., Yang, L., et al.: Robust tracking using local sparse appearance model and K-selection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1313–1320. IEEE Computer Society (2011)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • Sicong Jiang
    • 1
  • Jianing Zhang
    • 1
  • Yunzhou Zhang
    • 1
    • 2
    Email author
  • Feng Qiu
    • 2
  • Dongdong Wang
    • 2
  • Xiaobo Liu
    • 2
  1. 1.College of Information Science and EngineeringNortheastern UniversityShenyangChina
  2. 2.Faculty of Robot Science and EngineeringNortheastern UniversityShenyangChina

Personalised recommendations