THIS PAGE INCORPORATES CASCADING STYLE SHEET! TO VIEW PAGE CORRECTLY PLEASE UPDATE TO A CSS COMPLIANT BROWSER
Flexible Flow for 3D Non-Rigid Tracking and Shape Recovery
UR > CS > Research > Vision > Publications > Flexible Flow for 3D Non-Rigid Tracking and Shape Recovery
pdf 951 KB
ps.gz 1.26 MB
ps 3.52 MB
@InProceedings{sanders:OD-Theory:AAAI02,
  author =       {Mathew Brand and Rahul Bhotika},
  title =        {Flexible Flow for 3D Non-Rigid Tracking and Shape Recovery},

  booktitle =    {Proc. {AAAI02} Conf. on Computer Vision and Pattern Recognition {CVPR2001"},},
  year =         {2001},
  address =      {Kauai, Hawaii},
  month =        {Dec},

  publisher =    {{IEEE} Computer Society Press},

  abstract =    {We introduce linear methods for model-based tracking of nonrigid 3D objects and for acquiring such models from video.  3D motions and flexions are calculated directly from image intensities without information-lossy intermediate results.  Measurement uncertainty is quantified and fully propagated through the inverse model to yeild posterior mean(PM) and/or mode (MAP) pose estimates.  A Bayesian framework manages uncertainty, accommodates priors, and gives confidence meansures.  We obtain highly accurate and robust closed-form estimators by minimizing information loss from non-reversible (inner-product and least-squares) operations, and, when unavoidable, performing such operations with the appropriate error norm.  For model acquisition, we show how to refine a crude or gneric model to fit the video subjuct.  We demonstrate with tracking, model refinement, and super-resolution texture lifting from low-quality low-resolution video. },

 
}