Distance matrices as invariant features for classifying MoCap data

Antônio Wilson Vieira; Thomas Lewiner; William Schwartz; Mario F. M. Campos

Geometric Modeling

Distance matrices as invariant features for classifying MoCap data

Antônio Wilson Vieira, Thomas Lewiner, William Schwartz, Mario F. M. Campos

ICPR 2012 (21st International Conference on Pattern Recognition): pp. 2934-2937 (November 2012)

Distance matrices as invariant features for classifying MoCap data

abstract

Abstract

This work introduces a new representation for Motion Capture data (MoCap) that is invariant under rigid transformation and robust for classification and annotation of MoCap data. This representation relies on distance matrices that fully characterize the class of identical postures up to the body position or orientation. This high dimensional feature descriptor is tailored using PCA and incorporated into an action graph based classification scheme. Classification experiments on publicly available data show the accuracy and robustness of the proposed MoCap representation.

downloads

Downloads

PDF paper431 KB poster (PDF)550 KB

cite

BibTeX

@inproceedings{mocap_desc_icpr,
  author        = {Antônio Wilson Vieira and Thomas Lewiner and William Schwartz and Mario F. M. Campos},
  title         = {Distance matrices as invariant features for classifying MoCap data},
  year          = {2012},
  month         = {november},
  booktitle     = {ICPR 2012 (21st International Conference on Pattern Recognition)},
  pages         = {2934--2937},
  publisher     = {IEEE},
  address       = {Tsukuba Science City, Japan},
  url           = {https://thomas.lewiner.org/pdfs/mocap_desc_icpr.pdf}
}