Perceiving Systems Conference Paper 2012

From pictorial structures to deformable structures

Frompstods2

Pictorial Structures (PS) define a probabilistic model of 2D articulated objects in images. Typical PS models assume an object can be represented by a set of rigid parts connected with pairwise constraints that define the prior probability of part configurations. These models are widely used to represent non-rigid articulated objects such as humans and animals despite the fact that such objects have parts that deform non-rigidly. Here we define a new Deformable Structures (DS) model that is a natural extension of previous PS models and that captures the non-rigid shape deformation of the parts. Each part in a DS model is represented by a low-dimensional shape deformation space and pairwise potentials between parts capture how the shape varies with pose and the shape of neighboring parts. A key advantage of such a model is that it more accurately models object boundaries. This enables image likelihood models that are more discriminative than previous PS likelihoods. This likelihood is learned using training imagery annotated using a DS “puppet.” We focus on a human DS model learned from 2D projections of a realistic 3D human body model and use it to infer human poses in images using a form of non-parametric belief propagation.

Author(s): Zuffi, S. and Freifeld, O. and Black, M. J.
Book Title: IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)
Pages: 3546--3553
Year: 2012
Month: June
Publisher: IEEE
Project(s):
Bibtex Type: Conference Paper (inproceedings)
Electronic Archiving: grant_archive
Links:
Attachments:

BibTex

@inproceedings{Zuffi:CVPR:2012,
  title = {From pictorial structures to deformable structures},
  booktitle = {IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
  abstract = {Pictorial Structures (PS) define a probabilistic model of 2D articulated objects in images. Typical PS models assume an object can be represented by a set of rigid parts connected with pairwise constraints that define the prior probability of part configurations. These models are widely used to represent non-rigid articulated objects such as humans and animals despite the fact that such objects have parts that deform non-rigidly. Here we define a new Deformable Structures (DS) model that is a natural extension of previous PS models and that captures the non-rigid shape deformation of the parts. Each part in a DS model is represented by a low-dimensional shape deformation space and pairwise potentials between parts capture how the shape varies with pose and the shape of neighboring parts. A key advantage of such a model is that it more accurately models object boundaries. This enables image likelihood models that are more discriminative than previous PS likelihoods. This likelihood is learned using training imagery annotated using a DS “puppet.” We focus on a human DS model learned from 2D projections of a realistic 3D human body model and use it to infer human poses in images using a form of non-parametric belief propagation.},
  pages = {3546--3553},
  publisher = {IEEE},
  month = jun,
  year = {2012},
  slug = {zuffi-cvpr-2012},
  author = {Zuffi, S. and Freifeld, O. and Black, M. J.},
  month_numeric = {6}
}