A machine learning approach for automatic detection and classification of changes of direction from player tracking data in professional tennis

Brandon Giles, Stephanie Kovalchik, Machar Reid

Research output: Contribution to journalArticle

Abstract

The purpose of this study was to develop an automated method for identifying and classifying change of direction (COD) movements in professional tennis using tracking data. Three sport science and strength and conditioning experts coded match-play footage of nineteen professional tennis players (9 male and 10 female) from the Australian Open Grand Slam for COD of medium and high intensity. A total of 1,494 changes were identified and aligned with 2D player position sampled at 25 Hz based on camera tracking data. Several machine learning classifiers were trained and tested on a set of 1,128 time-motion features. A random forest algorithm was found to have the best out-of-sample performance, classifying medium and high intensity changes with an F1-score of 0.729. This research offers a novel and applicable way for utilising player tracking data and machine learning techniques to automatically identify and classify COD movements in professional tennis.

Original languageEnglish
JournalJournal of Sports Sciences
DOIs
Publication statusPublished - 1 Jan 2019

Fingerprint

Tennis
Sports
Research
Direction compound
Machine Learning

Cite this

@article{dd271c6a1b7646409e42f58ad80efbf3,
title = "A machine learning approach for automatic detection and classification of changes of direction from player tracking data in professional tennis",
abstract = "The purpose of this study was to develop an automated method for identifying and classifying change of direction (COD) movements in professional tennis using tracking data. Three sport science and strength and conditioning experts coded match-play footage of nineteen professional tennis players (9 male and 10 female) from the Australian Open Grand Slam for COD of medium and high intensity. A total of 1,494 changes were identified and aligned with 2D player position sampled at 25 Hz based on camera tracking data. Several machine learning classifiers were trained and tested on a set of 1,128 time-motion features. A random forest algorithm was found to have the best out-of-sample performance, classifying medium and high intensity changes with an F1-score of 0.729. This research offers a novel and applicable way for utilising player tracking data and machine learning techniques to automatically identify and classify COD movements in professional tennis.",
keywords = "analytics, expert performance, Hawk-Eye, tennis movement",
author = "Brandon Giles and Stephanie Kovalchik and Machar Reid",
year = "2019",
month = "1",
day = "1",
doi = "10.1080/02640414.2019.1684132",
language = "English",
journal = "Journal of Sports Science",
issn = "0264-0414",
publisher = "Taylor & Francis",

}

TY - JOUR

T1 - A machine learning approach for automatic detection and classification of changes of direction from player tracking data in professional tennis

AU - Giles, Brandon

AU - Kovalchik, Stephanie

AU - Reid, Machar

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The purpose of this study was to develop an automated method for identifying and classifying change of direction (COD) movements in professional tennis using tracking data. Three sport science and strength and conditioning experts coded match-play footage of nineteen professional tennis players (9 male and 10 female) from the Australian Open Grand Slam for COD of medium and high intensity. A total of 1,494 changes were identified and aligned with 2D player position sampled at 25 Hz based on camera tracking data. Several machine learning classifiers were trained and tested on a set of 1,128 time-motion features. A random forest algorithm was found to have the best out-of-sample performance, classifying medium and high intensity changes with an F1-score of 0.729. This research offers a novel and applicable way for utilising player tracking data and machine learning techniques to automatically identify and classify COD movements in professional tennis.

AB - The purpose of this study was to develop an automated method for identifying and classifying change of direction (COD) movements in professional tennis using tracking data. Three sport science and strength and conditioning experts coded match-play footage of nineteen professional tennis players (9 male and 10 female) from the Australian Open Grand Slam for COD of medium and high intensity. A total of 1,494 changes were identified and aligned with 2D player position sampled at 25 Hz based on camera tracking data. Several machine learning classifiers were trained and tested on a set of 1,128 time-motion features. A random forest algorithm was found to have the best out-of-sample performance, classifying medium and high intensity changes with an F1-score of 0.729. This research offers a novel and applicable way for utilising player tracking data and machine learning techniques to automatically identify and classify COD movements in professional tennis.

KW - analytics

KW - expert performance

KW - Hawk-Eye

KW - tennis movement

UR - http://www.scopus.com/inward/record.url?scp=85074702683&partnerID=8YFLogxK

U2 - 10.1080/02640414.2019.1684132

DO - 10.1080/02640414.2019.1684132

M3 - Article

JO - Journal of Sports Science

JF - Journal of Sports Science

SN - 0264-0414

ER -