Research on Human Gesture Recognition Algorithm Based on Multi-Scale Sparse Neural Network
Lexuan Huang, Shenggang Yan, Jianguo Liu
2022
Abstract
Human posture classification, as a part of human activity recognition, has a wide range of applications in medical treatment, nursing, sports injury protection, safety monitoring, and other fields. Along with the increasing hardware computing power and storage performance, an extensive amount of large data can be stored and computed as time series in real-time. But in the face of vast amount of data generated by inertial sensors, there is still a lot of room for development in real-time data processing. Multiscale Sparse Neural Networks are in this paper, realize the judgment and classification of the posture of the human body. The data is the human body pose by the nine-axis inertial sensor and the huge amount of data and real-time calculation have been taken into account. Compared to other methods, ours performs state-of-the-art on the WISDM and UCI-HAR datasets, and achieves good results on our own datasets.
DownloadPaper Citation
in Harvard Style
Huang L., Yan S. and Liu J. (2022). Research on Human Gesture Recognition Algorithm Based on Multi-Scale Sparse Neural Network. In Proceedings of the 3rd International Symposium on Automation, Information and Computing - Volume 1: ISAIC; ISBN 978-989-758-622-4, SciTePress, pages 457-464. DOI: 10.5220/0011951500003612
in Bibtex Style
@conference{isaic22,
author={Lexuan Huang and Shenggang Yan and Jianguo Liu},
title={Research on Human Gesture Recognition Algorithm Based on Multi-Scale Sparse Neural Network},
booktitle={Proceedings of the 3rd International Symposium on Automation, Information and Computing - Volume 1: ISAIC},
year={2022},
pages={457-464},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011951500003612},
isbn={978-989-758-622-4},
}
in EndNote Style
TY - CONF
JO - Proceedings of the 3rd International Symposium on Automation, Information and Computing - Volume 1: ISAIC
TI - Research on Human Gesture Recognition Algorithm Based on Multi-Scale Sparse Neural Network
SN - 978-989-758-622-4
AU - Huang L.
AU - Yan S.
AU - Liu J.
PY - 2022
SP - 457
EP - 464
DO - 10.5220/0011951500003612
PB - SciTePress