English

Markerless Motion Capture in the Crowd

Social and Information Networks 2012-04-17 v1 Human-Computer Interaction

Abstract

This work uses crowdsourcing to obtain motion capture data from video recordings. The data is obtained by information workers who click repeatedly to indicate body configurations in the frames of a video, resulting in a model of 2D structure over time. We discuss techniques to optimize the tracking task and strategies for maximizing accuracy and efficiency. We show visualizations of a variety of motions captured with our pipeline then apply reconstruction techniques to derive 3D structure.

Keywords

Cite

@article{arxiv.1204.3596,
  title  = {Markerless Motion Capture in the Crowd},
  author = {Ian Spiro and Thomas Huston and Christoph Bregler},
  journal= {arXiv preprint arXiv:1204.3596},
  year   = {2012}
}

Comments

Presented at Collective Intelligence conference, 2012 (arXiv:1204.2991)

R2 v1 2026-06-21T20:50:19.041Z