Robust Scale-Adaptive Mean-Shift for Tracking

  • Tomas Vojir
  • Jana Noskova
  • Jiri Matas
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7944)


Mean-Shift tracking is a popular algorithm for object tracking since it is easy to implement and it is fast and robust. In this paper, we address the problem of scale adaptation of the Hellinger distance based Mean-Shift tracker.

We start from a theoretical derivation of scale estimation in the Mean-Shift framework. To make the scale estimation robust and suitable for tracking, we introduce regularization terms that counter two major problem: (i) scale expansion caused by background clutter and (ii) scale implosion on self-similar objects. To further robustify the scale estimate, it is validated by a forward-backward consistency check.

The proposed Mean-shift tracker with scale selection is compared with recent state-of-the-art algorithms on a dataset of 48 public color sequences and it achieved excellent results.


object tracking mean-shift scale estimation 


  1. 1.
    Bradski, G.R.: Computer Vision Face Tracking For Use in a Perceptual User Interface. Intel Technology Journal Q2 (1998)Google Scholar
  2. 2.
    Collins, R.T.: Mean-shift blob tracking through scale space. In: Computer Vision and Pattern Recognition, pp. 234–240. IEEE Computer Society (2003)Google Scholar
  3. 3.
    Comaniciu, D., Ramesh, V., Meer, P.: Real-time tracking of non-rigid objects using mean shift, pp. 142–149 (2000)Google Scholar
  4. 4.
    Fukunaga, K., Hostetler, L.: The estimation of the gradient of a density function, with applications in pattern recognition. Information Theory 21(1), 32–40 (1975)MathSciNetzbMATHCrossRefGoogle Scholar
  5. 5.
    Hare, S., Saffari, A., Torr, P.: Struck: Structured output tracking with kernels. In: International Conference Computer Vision, pp. 263–270 (November 2011)Google Scholar
  6. 6.
    Kalal, Z., Matas, J., Mikolajczyk, K.: P-N Learning: Bootstrapping Binary Classifiers by Structural Constraints. In: Conference on Computer Vision and Pattern Recognition (2010)Google Scholar
  7. 7.
    Klein, D.A., Schulz, D., Frintrop, S., Cremers, A.B.: Adaptive real-time video-tracking for arbitrary objects. In: Intelligent Robots and Systems, pp. 772–777 (October 2010)Google Scholar
  8. 8.
    Liang, D., Huang, Q., Jiang, S., Yao, H., Gao, W.: Mean-shift blob tracking with adaptive feature selection and scale adaptation. In: International Conference Image Processing (2007)Google Scholar
  9. 9.
    Ning, J., Zhang, L., Zhang, D., Wu, C.: Robust mean-shift tracking with corrected background-weighted histogram. Computer Vision, IET 6(1), 62–69 (2012)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Ning, J., Zhang, L., Zhang, D., Wu, C.: Scale and orientation adaptive mean shift tracking. Computer Vision, IET 6(1), 52–61 (2012)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Ning, J., Zhang, L., Zhang, D., Wu, C.: Scale and orientation adaptive mean shift tracking. Computer Vision, IET 6(1), 52–61 (2012)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Pu, J.-X., Peng, N.-S.: Adaptive kernel based tracking using mean-shift. In: Campilho, A., Kamel, M.S. (eds.) ICIAR 2006. LNCS, vol. 4141, pp. 394–403. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  13. 13.
    Čehovin, L., Kristan, M., Leonardis, A.: An adaptive coupled-layer visual model for robust visual tracking. In: 13th International Conference on Computer Vision (November 2011)Google Scholar
  14. 14.
    Yang, C., Duraiswami, R., Davis, L.: Efficient mean-shift tracking via a new similarity measure. In: Computer Vision and Pattern Recognition, vol. 1, pp. 176–183 (June 2005)Google Scholar
  15. 15.
    Zhang, K., Zhang, L., Yang, M.-H.: Real-time compressive tracking. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part III. LNCS, vol. 7574, pp. 864–877. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  16. 16.
    Zhao, C., Knight, A., Reid, I.: Target tracking using mean-shift and affine structure. In: ICPR, pp. 1–5 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Tomas Vojir
    • 1
  • Jana Noskova
    • 2
  • Jiri Matas
    • 1
  1. 1.The Center for Machine PerceptionFEE CTU in PraguePrague 2Czech Republic
  2. 2.Faculty of Civil EngineeringCTU in PraguePrague 6Czech Republic

Personalised recommendations