IS = { zkontrolovano 03 Jan 2015 },
  UPDATE  = { 2014-12-19 },
  author =      {Tom{\'a}{\v s} Voj{\'\i}{\v r} and Jana Noskov{\' a}
                  and Ji{\v r}{\'\i} Matas},
  affiliation = {13133-13133-13133},
  title =       {Robust scale-adaptive mean-shift for tracking},
  year =        {2014},
  month =       {November},
  pages =       {250 - 258},
  journal =     {Pattern Recognition Letters},
  publisher =   {Elsevier},
  address =     {Amsterdam, Netherlands},
  issn =        {0167-8655},
  volume =      {49},
  number =      {0},
  annote =      {The mean-shift procedure is a popular object tracking
                  algorithm since it is f ast, easy to implement and
                  performs well in a range of conditions. We address
                  the problem of s cale adaptation and present a novel
                  theoretically justified scale estimation mechanism
                  which relies solely on the mean-shift procedure for
                  the Hellinger distance. We also propose two impro
                  vements of the mean-shift tracker that make the
                  scale estimation more robust in the presence of
                  background clutter. The first one is a novel
                  histogram color weighting that exploits the object
                  neighborhood to help discriminate the target called
                  background ratio weighting (BRW). We s how that the
                  BRW improves performance of MS-like tracking methods
                  in general. The second improvement boost the
                  performance of the tracker with the proposed scale
                  estimation by the introduc tion of a
                  forward-backward consistency check and by adopting
                  regularization terms that counter two major
                  problems: scale expansion caused by background
                  clutter and scale implosion on self-similar
                  objects. The proposed mean-shift tracker with scale
                  selection and BRW is compared with recent
                  state-of-the-art algorithms on a dataset of 77
                  public sequences. It outperforms the re ference
                  algorithms in average recall, processing speed and
                  it achieves the best score for 30% of the sequences
                  - the highest percentage among the reference
  keywords =    {tracking, mean-shift},
  project =     {GACR P103/12/G084},
  url =         {http://www.sciencedirect.com/science/article/pii/S0167865514001056},
  doi =         {http://dx.doi.org/10.1016/j.patrec.2014.03.025},