Gaussian Process Latent Variable Models for Human Pose Estimation

  • Carl Henrik Ek
  • Philip H. S. Torr
  • Neil D. Lawrence
Conference paper

DOI: 10.1007/978-3-540-78155-4_12

Part of the Lecture Notes in Computer Science book series (LNCS, volume 4892)
Cite this paper as:
Ek C.H., Torr P.H.S., Lawrence N.D. (2008) Gaussian Process Latent Variable Models for Human Pose Estimation. In: Popescu-Belis A., Renals S., Bourlard H. (eds) Machine Learning for Multimodal Interaction. MLMI 2007. Lecture Notes in Computer Science, vol 4892. Springer, Berlin, Heidelberg

Abstract

We describe a method for recovering 3D human body pose from silhouettes. Our model is based on learning a latent space using the Gaussian Process Latent Variable Model (GP-LVM) [1] encapsulating both pose and silhouette features Our method is generative, this allows us to model the ambiguities of a silhouette representation in a principled way. We learn a dynamical model over the latent space which allows us to disambiguate between ambiguous silhouettes by temporal consistency. The model has only two free parameters and has several advantages over both regression approaches and other generative methods. In addition to the application shown in this paper the suggested model is easily extended to multiple observation spaces without constraints on type.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Carl Henrik Ek
    • 1
  • Philip H. S. Torr
    • 1
  • Neil D. Lawrence
    • 2
  1. 1.Department of ComputingOxford Brookes UniversityUnited Kingdom
  2. 2.School of Computer ScienceUniversity of ManchesterUnited Kingdom

Personalised recommendations