IS = { zkontrolovano 24 Jan 2014 },
  UPDATE  = { 2013-09-19 },
  author =      {Voj{\'\i}{\v r}, Tom{\' a}{\v s} and Noskov{\' a}, Jana and Matas, Ji{\v r}{\'\i}},
  title =       {Robust Scale-Adaptive Mean-Shift for Tracking},
  year =        {2013},
  month =       {June},
  pages =       {652-663},
  editor =      {K\"am\"ar\"ainen, Joni-Kristian and Koskela, Markus},
  booktitle =   {SCIA 2013: Proceedings of the 18th Scandinavian Conference on Image Analysis},
  publisher =   {Springer},
  address =     {Berlin, Germany},
  isbn =        {978-3-642-38885-9},
  volume =      {7944},
  series =      {Lecture Notes in Computer Science},
  book_pages =  {733},
  annote =      {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 in- troduce 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 consis- tency check. The proposed Mean-shift
    tracker with scale selection is compared with re- cent
    state-of-the-art algorithms on a dataset of 48 public color
    sequences and it achieved excellent results.},
  keywords =    {object tracking; mean-shift; scale estimation},
  project =     {TACR TE01020415 V3C, GACR P103/12/G084},
  doi =         {10.1007/978-3-642-38886-6=61},