Using LSTM for Automatic Classification of Human Motion Capture Data

Rogério E. da Silva, Jan Ondřej, Aljosa Smolic

2019

Abstract

Creative studios tend to produce an overwhelming amount of content everyday and being able to manage these data and reuse it in new productions represent a way for reducing costs and increasing productivity and profit. This work is part of a project aiming to develop reusable assets in creative productions. This paper describes our first attempt using deep learning to classify human motion from motion capture files. It relies on a long short-term memory network (LSTM) trained to recognize action on a simplified ontology of basic actions like walking, running or jumping. Our solution was able of recognizing several actions with an accuracy over 95% in the best cases.

Paper Citation

in Harvard Style

E. da Silva R., Ondřej J. and Smolic A. (2019). Using LSTM for Automatic Classification of Human Motion Capture Data. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 1: GRAPP; ISBN 978-989-758-354-4, SciTePress, pages 236-243. DOI: 10.5220/0007349902360243

in Bibtex Style

@conference{grapp19,
author={Rogério E. da Silva and Jan Ondřej and Aljosa Smolic},
title={Using LSTM for Automatic Classification of Human Motion Capture Data},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 1: GRAPP},
year={2019},
pages={236-243},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007349902360243},
isbn={978-989-758-354-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 1: GRAPP
TI - Using LSTM for Automatic Classification of Human Motion Capture Data
SN - 978-989-758-354-4
AU - E. da Silva R.
AU - Ondřej J.
AU - Smolic A.
PY - 2019
SP - 236
EP - 243
DO - 10.5220/0007349902360243
PB - SciTePress