German Conference on Pattern Recognition

GCPR 2014: Pattern Recognition pp 253-264

Test-Time Adaptation for 3D Human Pose Estimation

  • Sikandar Amin
  • Philipp Müller
  • Andreas Bulling
  • Mykhaylo Andriluka
Conference paper

DOI: 10.1007/978-3-319-11752-2_20

Volume 8753 of the book series Lecture Notes in Computer Science (LNCS)
Cite this paper as:
Amin S., Müller P., Bulling A., Andriluka M. (2014) Test-Time Adaptation for 3D Human Pose Estimation. In: Jiang X., Hornegger J., Koch R. (eds) Pattern Recognition. GCPR 2014. Lecture Notes in Computer Science, vol 8753. Springer, Cham

Abstract

In this paper we consider the task of articulated 3D human pose estimation in challenging scenes with dynamic background and multiple people. Initial progress on this task has been achieved building on discriminatively trained part-based models that deliver a set of 2D body pose candidates that are then subsequently refined by reasoning in 3D [1, 4, 5]. The performance of such methods is limited by the performance of the underlying 2D pose estimation approaches. In this paper we explore a way to boost the performance of 2D pose estimation based on the output of the 3D pose reconstruction process, thus closing the loop in the pose estimation pipeline. We build our approach around a component that is able to identify true positive pose estimation hypotheses with high confidence. We then either retrain 2D pose estimation models using such highly confident hypotheses as additional training examples, or we use similarity to these hypotheses as a cue for 2D pose estimation. We consider a number of features that can be used for assessing the confidence of the pose estimation results. The strongest feature in our comparison corresponds to the ensemble agreement on the 3D pose output. We evaluate our approach on two publicly available datasets improving over state of the art in each case.

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Sikandar Amin
    • 1
    • 2
  • Philipp Müller
    • 2
  • Andreas Bulling
    • 2
  • Mykhaylo Andriluka
    • 2
    • 3
  1. 1.Technische Universität MünchenMunichGermany
  2. 2.Max Planck Institute for InformaticsSaarbrückenGermany
  3. 3.Stanford UniversityStanfordUSA