Mixtures of Gaussian process models for human pose estimation

Research output: Contribution to journalArticlepeer-review

Abstract

Discriminative human pose estimation is the problem of inferring the 3D articulated pose of a human directly from an image feature. This is a challenging problem due to the highly non-linear and multi-modal mapping from the image feature space to the pose space. To address this problem, we propose a model employing a mixture of Gaussian processes where each Gaussian process models a local region of the pose space. By employing the models in this way we are able to overcome the limitations of Gaussian processes applied to human pose estimation — their O(N3) time complexity and their uni-modal predictive distribution. Our model is able to give a multi-modal predictive distribution where each mode is represented by a different Gaussian process prediction. A logistic regression model is used to give a prior over each expert prediction in a similar fashion to previous mixture of expert models. We show that this technique outperforms existing state of the art regression techniques on human pose estimation data sets for ballet dancing, sign language and the HumanEva data set.
Original languageEnglish
Pages (from-to)949-957
Number of pages8
JournalImage and Vision Computing
Volume31
Issue number12
Publication statusPublished - 31 Dec 2013

Keywords

  • Computer vision
  • Gaussian processes
  • Human pose estimation
  • Mixture of experts

Fingerprint

Dive into the research topics of 'Mixtures of Gaussian process models for human pose estimation'. Together they form a unique fingerprint.

Cite this