Unsupervised Temporal Segmentation of Skeletal Motion Data using Joint Distance Representation

Christian Lins, Sebastian M. Müller, Max Pfingsthorn, Marco Eichelberg, Alexander Gerka, Andreas Hein

Abstract

In this paper, we present an online method for the unsupervised segmentation of skeletal motion capture data for the assessment of unfavorable or harmful postures in the context of musculoskeletal disorders. The long-time motion capture data is segmented into short motion sequences using joint distances of the captured skeleton. We use the difference between joint distance matrices to detect variances in motion dynamics in which the motion is separated into either a dynamic motion or a static posture. Then, the static posture can be evaluated using well-known posture assessment methods such as the Ovako Working postures Analysing System (OWAS) to derive risk factors for musculoskeletal disorders. The algorithm works in real-time so that it can be incorporated in live warning systems for unfavorable or harmful postures. We evaluated the segmentation algorithm by comparing it with results from state-of-the-art offline motion segmentation algorithms as gold standard. Results show that the algorithm approaches the performance of state-of-the-art offline segmentation algorithms.

References

Download


Paper Citation


in Harvard Style

Lins C., Müller S., Pfingsthorn M., Eichelberg M., Gerka A. and Hein A. (2018). Unsupervised Temporal Segmentation of Skeletal Motion Data using Joint Distance Representation.In Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5: HEALTHINF, ISBN 978-989-758-281-3, pages 478-485. DOI: 10.5220/0006598904780485


in Bibtex Style

@conference{healthinf18,
author={Christian Lins and Sebastian M. Müller and Max Pfingsthorn and Marco Eichelberg and Alexander Gerka and Andreas Hein},
title={Unsupervised Temporal Segmentation of Skeletal Motion Data using Joint Distance Representation},
booktitle={Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5: HEALTHINF,},
year={2018},
pages={478-485},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006598904780485},
isbn={978-989-758-281-3},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5: HEALTHINF,
TI - Unsupervised Temporal Segmentation of Skeletal Motion Data using Joint Distance Representation
SN - 978-989-758-281-3
AU - Lins C.
AU - Müller S.
AU - Pfingsthorn M.
AU - Eichelberg M.
AU - Gerka A.
AU - Hein A.
PY - 2018
SP - 478
EP - 485
DO - 10.5220/0006598904780485