Action Graph - A Versatile Data Structure for Action Recognition

Jan Baumann, Raoul Wessel, Björn Krüger, Andreas Weber

2014

Abstract

This work presents a novel and generic data-driven method for recognizing human full body actions from live motion data originating from various sources. The method queries an annotated motion capture database for similar motion segments, capable to handle temporal deviations from the original motion. The approach is online-capable, works in realtime, requires virtually no preprocessing and is shown to work with a variety of feature sets extracted from input data including positional data, sparse accelerometer signals, skeletons extracted from depth sensors and even video data. Evaluation is done by comparing against a frame-based Support Vector Machine approach on a freely available motion capture database as well as a database containing Judo referee signal motions and concludes by demonstrating the applicability of the method in a vision-based scenario using video data.

Paper Citation

in Harvard Style

Baumann J., Wessel R., Krüger B. and Weber A. (2014). Action Graph - A Versatile Data Structure for Action Recognition . In Proceedings of the 9th International Conference on Computer Graphics Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2014) ISBN 978-989-758-002-4, pages 325-334. DOI: 10.5220/0004652703250334

in Bibtex Style

@conference{grapp14,
author={Jan Baumann and Raoul Wessel and Björn Krüger and Andreas Weber},
title={Action Graph - A Versatile Data Structure for Action Recognition},
booktitle={Proceedings of the 9th International Conference on Computer Graphics Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2014)},
year={2014},
pages={325-334},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004652703250334},
isbn={978-989-758-002-4},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Graphics Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2014)
TI - Action Graph - A Versatile Data Structure for Action Recognition
SN - 978-989-758-002-4
AU - Baumann J.
AU - Wessel R.
AU - Krüger B.
AU - Weber A.
PY - 2014
SP - 325
EP - 334
DO - 10.5220/0004652703250334