From Image to Stability: Learning Dynamics from Human Pose

Jesse Scott, Bharadwaj Ravichandran, Christopher Funk, Robert T. Collins, Yanxi Liu

ECCV 2020

doi:10.1007/978-3-030-58592-1_32 /eccv/2020/scott2020eccv-image/

Abstract

We propose and validate two end-to-end deep learning architectures to learn foot pressure distribution maps (dynamics) from 2D or 3D human pose (kinematics). The networks are trained using 1.36 million synchronized pose+pressure data pairs from 10 subjects performing multiple takes of a 5-minute long choreographed Taiji sequence. Using leave-one-subject-out cross validation, we demonstrate reliable and repeatable foot pressure prediction, setting the first baseline for solving a non-obvious pose to pressure cross-modality mapping problem in computer vision. Furthermore, we compute and quantitatively validate Center of Pressure (CoP) and Base of Support (BoS), two key components for stability analysis, from the predicted foot pressure distributions.

PDF ECCV Semantic Scholar

Cite

Text

Scott et al. "From Image to Stability: Learning Dynamics from Human Pose." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58592-1_32

Markdown

[Scott et al. "From Image to Stability: Learning Dynamics from Human Pose." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/scott2020eccv-image/) doi:10.1007/978-3-030-58592-1_32

BibTeX

@inproceedings{scott2020eccv-image,
  title     = {{From Image to Stability: Learning Dynamics from Human Pose}},
  author    = {Scott, Jesse and Ravichandran, Bharadwaj and Funk, Christopher and Collins, Robert T. and Liu, Yanxi},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2020},
  doi       = {10.1007/978-3-030-58592-1_32},
  url       = {https://mlanthology.org/eccv/2020/scott2020eccv-image/}
}