Multi-sensor classification of tennis strokes

Damien Connaghan; Phillip Kelly; Noel E. O'Connor; Mark Gaffney; Michael Walsh; Cian O'Mathuna

doi:10.1109/ICSENS.2011.6127084

Multi-sensor classification of tennis strokes

Damien Connaghan
, Phillip Kelly
, Noel E. O'Connor
, Mark Gaffney
, Michael Walsh
, Cian O'Mathuna

Research output: Chapter in Book/Report/Conference proceedings › Conference proceeding › peer-review

Abstract

In this work, we investigate tennis stroke recognition using a single inertial measuring unit attached to a player's forearm during a competitive match. This paper evaluates the best approach for stroke detection using either accelerometers, gyroscopes or magnetometers, which are embedded into the inertial measuring unit. This work concludes what is the optimal training data set for stroke classification and proves that classifiers can perform well when tested on players who were not used to train the classifier. This work provides a significant step forward for our overall goal, which is to develop next generation sports coaching tools using both inertial and visual sensors in an instrumented indoor sporting environment.

Original language	English
Title of host publication	IEEE Sensors 2011 Conference, SENSORS 2011
Pages	1437-1440
Number of pages	4
DOIs	https://doi.org/10.1109/ICSENS.2011.6127084
Publication status	Published - 2011
Externally published	Yes
Event	10th IEEE SENSORS Conference 2011, SENSORS 2011 - Limerick, Ireland Duration: 28 Oct 2011 → 31 Oct 2011

Publication series

Name	Proceedings of IEEE Sensors

Conference

Conference	10th IEEE SENSORS Conference 2011, SENSORS 2011
Country/Territory	Ireland
City	Limerick
Period	28/10/11 → 31/10/11

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Access to Document

10.1109/ICSENS.2011.6127084

Cite this

@inproceedings{796e83a5d7cf472f81399d8a464cb45c,

title = "Multi-sensor classification of tennis strokes",

abstract = "In this work, we investigate tennis stroke recognition using a single inertial measuring unit attached to a player's forearm during a competitive match. This paper evaluates the best approach for stroke detection using either accelerometers, gyroscopes or magnetometers, which are embedded into the inertial measuring unit. This work concludes what is the optimal training data set for stroke classification and proves that classifiers can perform well when tested on players who were not used to train the classifier. This work provides a significant step forward for our overall goal, which is to develop next generation sports coaching tools using both inertial and visual sensors in an instrumented indoor sporting environment.",

author = "Damien Connaghan and Phillip Kelly and O'Connor, \{Noel E.\} and Mark Gaffney and Michael Walsh and Cian O'Mathuna",

year = "2011",

doi = "10.1109/ICSENS.2011.6127084",

language = "English",

isbn = "9781424492886",

series = "Proceedings of IEEE Sensors",

pages = "1437--1440",

booktitle = "IEEE Sensors 2011 Conference, SENSORS 2011",

note = "10th IEEE SENSORS Conference 2011, SENSORS 2011 ; Conference date: 28-10-2011 Through 31-10-2011",

}

TY - GEN

T1 - Multi-sensor classification of tennis strokes

AU - Connaghan, Damien

AU - Kelly, Phillip

AU - O'Connor, Noel E.

AU - Gaffney, Mark

AU - Walsh, Michael

AU - O'Mathuna, Cian

PY - 2011

Y1 - 2011

N2 - In this work, we investigate tennis stroke recognition using a single inertial measuring unit attached to a player's forearm during a competitive match. This paper evaluates the best approach for stroke detection using either accelerometers, gyroscopes or magnetometers, which are embedded into the inertial measuring unit. This work concludes what is the optimal training data set for stroke classification and proves that classifiers can perform well when tested on players who were not used to train the classifier. This work provides a significant step forward for our overall goal, which is to develop next generation sports coaching tools using both inertial and visual sensors in an instrumented indoor sporting environment.

AB - In this work, we investigate tennis stroke recognition using a single inertial measuring unit attached to a player's forearm during a competitive match. This paper evaluates the best approach for stroke detection using either accelerometers, gyroscopes or magnetometers, which are embedded into the inertial measuring unit. This work concludes what is the optimal training data set for stroke classification and proves that classifiers can perform well when tested on players who were not used to train the classifier. This work provides a significant step forward for our overall goal, which is to develop next generation sports coaching tools using both inertial and visual sensors in an instrumented indoor sporting environment.

UR - https://www.scopus.com/pages/publications/84856897888

U2 - 10.1109/ICSENS.2011.6127084

DO - 10.1109/ICSENS.2011.6127084

M3 - Conference proceeding

AN - SCOPUS:84856897888

SN - 9781424492886

T3 - Proceedings of IEEE Sensors

SP - 1437

EP - 1440

BT - IEEE Sensors 2011 Conference, SENSORS 2011

T2 - 10th IEEE SENSORS Conference 2011, SENSORS 2011

Y2 - 28 October 2011 through 31 October 2011

ER -

Multi-sensor classification of tennis strokes

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this