Classification of Taekwondo Techniques using Deep Learning Methods: First Insights

Paulo Barbosa, Pedro Cunha, Pedro Cunha, Vítor Carvalho, Vítor Carvalho, Filomena Soares

Abstract

Research in motion analysis area has enabled the development of affordable and easy to access technological solutions. The study presented aims to identify and quantify the movements performed by a taekwondo athlete during training sessions using deep learning techniques applied to the data collected in real time. For this purpose, several approaches and methodologies were tested along with a dataset previously developed in order to define which one presents the best results. Considering the specificities of the movements, usually fast and mostly with a high incidence on the legs, it was concluded that the best results were obtained with convolution layers models, such as, Convolutional Neural Networks (CNN) plus Long Short-Term Memory (LSTM) and Convolutional Long Short-Term Memory (ConvLSTM) deep learning models, with more than 90% in terms of accuracy validation.

Download


Paper Citation


in Harvard Style

Barbosa P., Cunha P., Carvalho V. and Soares F. (2021). Classification of Taekwondo Techniques using Deep Learning Methods: First Insights.In Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIODEVICES, ISBN 978-989-758-490-9, pages 201-208. DOI: 10.5220/0010412402010208


in Bibtex Style

@conference{biodevices21,
author={Paulo Barbosa and Pedro Cunha and Vítor Carvalho and Filomena Soares},
title={Classification of Taekwondo Techniques using Deep Learning Methods: First Insights},
booktitle={Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIODEVICES,},
year={2021},
pages={201-208},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010412402010208},
isbn={978-989-758-490-9},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIODEVICES,
TI - Classification of Taekwondo Techniques using Deep Learning Methods: First Insights
SN - 978-989-758-490-9
AU - Barbosa P.
AU - Cunha P.
AU - Carvalho V.
AU - Soares F.
PY - 2021
SP - 201
EP - 208
DO - 10.5220/0010412402010208