IS = { zkontrolovano 29 Dec 2006 },
  UPDATE  = { 2006-07-17 },
  author =       {Zimmermann, Karel and 
                  Svoboda, Tom{\' a}{\v s} and 
                  Matas, Ji{\v r}{\' i}},
  title =        {Multiview 3{D} Tracking with an Incrementally 
                  Constructed 3{D} Model},
  booktitle =    {Third International Symposium on 3D Data
                  Processing, Visualization and Transmission (3DPVT)},
  isbn =         {978-0-7695-2825-0},
  bookpages =    {1116},
  year =         {2006},
  pages =        {488--495},
  publisher =    {IEEE Computer Society},
  address =      {Piscataway, USA},
  month =        {June},
  day =          {13-16},
  organization = {University of North Carolina},
  venue =        {University of North Carolina, Chapel Hill, USA},
  project =      {1M0567,1ET101210407,FP6-IST-027787,
                  CTU0608813, specific research},
  psurl =        {[zimmerk-3dpvt06.pdf]},
  authorship =   {50-40-10},
  annote = { A novel object representation for tracking is proposed.
    The tracked object is represented as a constellation of spatially
    localised linear predictors which are learned on a single training
    image.  In the learning stage, sets of pixels whose intensities
    allow for optimal least square predictions of the transformations
    are selected as a support of the linear predictor.  The approach
    comprises three contributions: learning object specific linear
    predictors, explicitly dealing with the predictor precision --
    computational complexity trade-off and selecting a view-specific
    set of predictors suitable for global object motion estimate.
    Robustness to occlusion is achieved by RANSAC procedure.  The
    learned tracker is very efficient, achieving frame rate generally
    higher than 30 frames per second despite the Matlab
  note = {CD-ROM},