Tracking 3D Human Pose with Large Root Node Uncertainty

Ben Daubney*, Xianghua Xie

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Representing articulated objects as a graphical model has gained much popularity in recent years, often the root node of the graph describes the global position and orientation of the object. In this work a method is presented to robustly track 3D human pose by permitting greater uncertainty to be modeled over the root node than existing techniques allow. Significantly, this is achieved without increasing the uncertainty of remaining parts of the model. The benefit is that a greater volume of the posterior can be supported making the approach less vulnerable to tracking failure. Given a hypothesis of the root node state a novel method is presented to estimate the posterior over the remaining parts of the body conditioned on this value. All probability distributions are approximated using a single Gaussian allowing inference to be carried out in closed form. A set of deterministically selected sample points are used that allow the posterior to be updated for each part requiring just seven image likelihood evaluations making it extremely efficient. Multiple root node states are supported and propagated using standard sampling techniques. We believe this to be the first work devoted to efficient tracking of human pose whilst modeling large uncertainty in the root node and demonstrate the presented method to be more robust to tracking failures than existing approaches.

Original languageEnglish
Title of host publication2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherInstitute of Electrical and Electronics Engineers
Number of pages8
ISBN (Electronic)978-1-4577-0395-9
ISBN (Print)978-1-4577-0394-2
Publication statusPublished - 2011
Externally publishedYes
EventIEEE Conference on Computer Vision and Pattern Recognition (CVPR) - Colorado Springs, Colombia
Duration: 20 Jun 201125 Jun 2011

Publication series

NameIEEE Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919


ConferenceIEEE Conference on Computer Vision and Pattern Recognition (CVPR)
CityColorado Springs


  • Unvertainty
  • Quaternions
  • Gaussian distribution
  • Three dimensional displays
  • Humans
  • Approximation methods
  • Probabilistic logic
  • statistical distributions
  • Gaussian processes
  • graph theory
  • impage representation
  • image sampling
  • inference mechanisms
  • object tracking
  • pose estimation
  • solid modelling
  • standard sampling technique
  • 3D human pose tracking
  • large root node uncertainty
  • articulated object representation


Dive into the research topics of 'Tracking 3D Human Pose with Large Root Node Uncertainty'. Together they form a unique fingerprint.

Cite this