Perceiving Systems Conference Paper 2013

A Non-parametric Bayesian Network Prior of Human Pose

Thumb

Having a sensible prior of human pose is a vital ingredient for many computer vision applications, including tracking and pose estimation. While the application of global non-parametric approaches and parametric models has led to some success, finding the right balance in terms of flexibility and tractability, as well as estimating model parameters from data has turned out to be challenging. In this work, we introduce a sparse Bayesian network model of human pose that is non-parametric with respect to the estimation of both its graph structure and its local distributions. We describe an efficient sampling scheme for our model and show its tractability for the computation of exact log-likelihoods. We empirically validate our approach on the Human 3.6M dataset and demonstrate superior performance to global models and parametric networks. We further illustrate our model's ability to represent and compose poses not present in the training set (compositionality) and describe a speed-accuracy trade-off that allows realtime scoring of poses.

Author(s): Andreas M. Lehrmann and Peter Gehler and Sebastian Nowozin
Book Title: Proceedings IEEE Conf. on Computer Vision (ICCV)
Pages: 1281-1288
Year: 2013
Month: December
Project(s):
Bibtex Type: Conference Paper (inproceedings)
DOI: 10.1109/ICCV.2013.162
Event Name: IEEE International Conference on Computer Vision
Event Place: Sydney, AUS
Electronic Archiving: grant_archive
Attachments:

BibTex

@inproceedings{lehrmann13humanposeprior,
  title = {A Non-parametric {Bayesian} Network Prior of Human Pose},
  booktitle = {Proceedings IEEE Conf. on Computer Vision (ICCV)},
  abstract = {Having a sensible prior of human pose is a vital ingredient for many computer vision applications, including tracking and pose estimation. While the application of global non-parametric approaches and parametric models has led to some success, finding the right balance in terms of flexibility and tractability, as well as estimating model parameters from data has turned out to be challenging. In this work, we introduce a sparse Bayesian network model of human pose that is non-parametric with respect to the estimation of both its graph structure and its local distributions. We describe an efficient sampling scheme for our model and show its tractability for the computation of exact log-likelihoods. We empirically validate our approach on the Human 3.6M dataset and demonstrate superior performance to global models and parametric networks. We further illustrate our model's ability to represent and compose poses not present in the training set (compositionality) and describe a speed-accuracy trade-off that allows realtime scoring of poses.},
  pages = {1281-1288},
  month = dec,
  year = {2013},
  slug = {lehrmann13humanposeprior},
  author = {Lehrmann, Andreas M. and Gehler, Peter and Nowozin, Sebastian},
  month_numeric = {12}
}