Robust Tracking of Stochastic Deformable Models in Long Image Sequences

Charles Kervrann, Fabrice Heitz

Abstract

We describe a method for the temporal tracking of stochastic deformable models in long image sequences. The object representation relies on a hierarchical statistical description of the deformations applied to a template. A Bayesian estimate of the deformations is obtained by maximizing a highly non-linear joint probability distribution. Time consuming global (stochastic) optimization techniques are necessary to obtain optimal solutions unless a good initial guess is available. A good initialization is provided by a recursive temporal filtering of the parameters of the deformable template, combined with a detection of abrupt changes. This procedure yields robust segmentations and enables to track reliably complex deformable structures as is demonstrated here on real-world image sequences showing hand and mouth movements.<
BibTeX
@inproceedings{kervrann1994robust,
  author = {Charles Kervrann and Fabrice Heitz},
  title = {{Robust Tracking of Stochastic Deformable Models in Long Image Sequences}},
  booktitle = {ICIP},
  year = {1994},
  doi = {10.1109/icip.1994.413882},
}

Loading related content...

Figure