THIS PAGE INCORPORATES CASCADING STYLE SHEET! TO VIEW PAGE CORRECTLY PLEASE UPDATE TO A CSS COMPLIANT BROWSER
A Probablistic Theory of Occupancy and Emptiness:
UR > CS > Research > Vision > Publications > A Probablistic Theory of Occupancy and Emptiness:
@InProceedings{Bhotika:Prob Theory of Occupancy & Emptiness:TR01,
  author =       {Rahul Bhotika, David J. Fleet, and Kiriakos N. Kutulakos},
  title =        {A Probablistic Theory of Occupancy and Emptiness:},

  booktitle =    {Technical Report {TR01}},
  year =         {2001},
  address =      {},
  month =        {jul # "~28--" aug # "~01"},

  publisher =    {{AAAI} Press},

  pages =        {777--784},

  abstract =    { We present the theory behind TOD (the Temporal Object
                  Discoverer), a novel unsupervised system that uses
                  only temporal information to discover objects across
                  image sequences acquired by any number of
                  uncalibrated cameras. The process is divided into
                  three phases: (1) Extraction of each pixel's
                  temporal signature, a partition of the pixel's
                  observations into sets that stem from different
                  objects; (2) Construction of a global schedule that
                  explains the signatures in terms of the lifetimes of
                  a set of quasi-static objects; (3) Mapping of each
                  pixel's observations to objects in the schedule
                  according to the pixel's temporal signature. Our
                  Global Scheduling (GSched) algorithm provably
                  constructs a valid and complete global schedule when
                  certain observability criteria are met. Our
                  Quasi-Static Labeling (QSL) algorithm uses the
                  schedule created by GSched to produce the
                  maximally-informative mapping of each pixel's
                  observations onto the objects they stem from. Using
                  GSched and QSL, TOD ignores distracting motion,
                  correctly deals with complicated occlusions, and
                  naturally groups observations across cameras. The
                  sets of 2D masks recovered are suitable for
                  unsupervised training and initialization of object
                  recognition and tracking systems.},

}