Sensor Based Motion Tracking and Recognition in Martial Arts Training

Loading...
Thumbnail Image

Date

Authors

Agojo, Stephan

Mark

E

Journal Title

Journal ISSN

Volume Title

Publisher

Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií

ORCID

Abstract

In various martial arts, competitors are interested in quantifying and categorising techniques which are exercised during training. The implementation of embedded systems into training gear, especially a portable wireless body worn system, based on inertial sensors, facilitates the quantification and categorisation of forces and accelerations involved during the training of martial arts. The scope of this paper is to give a brief overview of contemporary technology and devices, describe key methods that are implemented in such devices and as well to provide a project outline. For this reason a literature research was carried out using search engines and databases. The search yielded that devices are capable of tracking activities of daily life; however only one product was found which can track and recognise techniques applied in martial arts training just for the upper body. The realisation of a sensor based tracking system which can track and classify different exercises is possible with present technology. Even so, different challenges such as implementing a sensor fusion and classifier algorithm need to be overcome. Therefore, the project development has to be viewed as an iterative process.
In various martial arts, competitors are interested in quantifying and categorising techniques which are exercised during training. The implementation of embedded systems into training gear, especially a portable wireless body worn system, based on inertial sensors, facilitates the quantification and categorisation of forces and accelerations involved during the training of martial arts. The scope of this paper is to give a brief overview of contemporary technology and devices, describe key methods that are implemented in such devices and as well to provide a project outline. For this reason a literature research was carried out using search engines and databases. The search yielded that devices are capable of tracking activities of daily life; however only one product was found which can track and recognise techniques applied in martial arts training just for the upper body. The realisation of a sensor based tracking system which can track and classify different exercises is possible with present technology. Even so, different challenges such as implementing a sensor fusion and classifier algorithm need to be overcome. Therefore, the project development has to be viewed as an iterative process.

Description

Citation

AGOJO, S. Sensor Based Motion Tracking and Recognition in Martial Arts Training [online]. Brno: Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií. 2017.

Document type

Document version

Date of access to the full text

Language of document

en

Study field

Biomedical and Ecological Engineering

Comittee

doc. Ing. Daniel Schwarz, Ph.D. (předseda) doc. Ing. Jiří Kozumplík, CSc. (místopředseda) Ing. Vratislav Harabiš, Ph.D. (člen) Ing. Jiří Sekora, MBA (člen) MUDr. Šárka Sekorová (člen) Ing. Martin Mézl, Ph.D. (člen)

Date of acceptance

2017-08-31

Defence

Student has presented his thesis and committee has been acquainted with reviews. Prof. Sauermann: How did you evaluate results? Did you just counted or were you recorded on video? Why do you think there's a difference in the classification? Doc. Schwarz: How did you divided your set to training and testing sets? Was there no cross validation? Ing. Mézl: Could it work as recognition system for anybody else but you? Student has defended final thesis and answered questions of opponent and committee.

Result of defence

práce byla úspěšně obhájena

DOI

Collections

Endorsement

Review

Supplemented By

Referenced By

Citace PRO