2D Action Recognition Serves 3D Human Pose Estimation

  • Juergen Gall
  • Angela Yao
  • Luc Van Gool
Conference paper

DOI: 10.1007/978-3-642-15558-1_31

Part of the Lecture Notes in Computer Science book series (LNCS, volume 6313)
Cite this paper as:
Gall J., Yao A., Van Gool L. (2010) 2D Action Recognition Serves 3D Human Pose Estimation. In: Daniilidis K., Maragos P., Paragios N. (eds) Computer Vision – ECCV 2010. ECCV 2010. Lecture Notes in Computer Science, vol 6313. Springer, Berlin, Heidelberg

Abstract

3D human pose estimation in multi-view settings benefits from embeddings of human actions in low-dimensional manifolds, but the complexity of the embeddings increases with the number of actions. Creating separate, action-specific manifolds seems to be a more practical solution. Using multiple manifolds for pose estimation, however, requires a joint optimization over the set of manifolds and the human pose embedded in the manifolds. In order to solve this problem, we propose a particle-based optimization algorithm that can efficiently estimate human pose even in challenging in-house scenarios. In addition, the algorithm can directly integrate the results of a 2D action recognition system as prior distribution for optimization. In our experiments, we demonstrate that the optimization handles an 84D search space and provides already competitive results on HumanEva with as few as 25 particles.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Supplementary material

978-3-642-15558-1_31_MOESM1_ESM.avi (13.9 mb)
Electronic Supplementary Material (14,210 KB)

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Juergen Gall
    • 1
  • Angela Yao
    • 1
  • Luc Van Gool
    • 1
    • 2
  1. 1.Computer Vision LaboratoryETH ZurichSwitzerland
  2. 2.KU LeuvenBelgium

Personalised recommendations