Tactical Performance Insights for Australian Rules Football Using Deep Learning

Zac Born

doi:10.26182/3sv1-h009

Tactical Performance Insights for Australian Rules Football Using Deep Learning

Zac Born

School of Human Sciences

Research output: Thesis › Doctoral Thesis

621 Downloads (Pure)

Abstract

The analysis of tactical behaviour in invasion-based sports is imperative to gaining a competitive advantage over opposition teams. This thesis aimed to derive novel insights into the tactical behaviour of professional Australian Rules Football teams through the use of deep learning tools adapted from the sub-fields of natural language processing and multiple object tracking. Specifically, methods to automatically categorise ball movement strategies, forecast future ball possessions, and track the movement of athletes were developed. In doing so, this thesis lays the foundations for the development for interactive play sketching tools in Australian Rules Football.

Original language	English
Qualification	Doctor of Philosophy
Awarding Institution	The University of Western Australia
Supervisors/Advisors	Mian, Ajmal, Supervisor Alderson, Jacqueline, Supervisor Weber, Jason, Supervisor, External person
Thesis sponsors	Australian Government Research Training Program
Award date	28 Mar 2023
DOIs	https://doi.org/10.26182/3sv1-h009
Publication status	Unpublished - 2022

Access to Document

10.26182/3sv1-h009

THESIS - DOCTOR OF PHILOSOPHY - BORN Zac - 2023 - Part 1 & 2
This work is protected by Copyright. You may print or download ONE copy of this document for the purpose of your own non-commercial research or study. Any other use requires permission from the copyright owner. The Copyright Act requires you to attribute any copyright works you quote or paraphrase.
THESIS - DOCTOR OF PHILOSOPHY - BORN Zac - 2023 - Part 3 & 4
This work is protected by Copyright. You may print or download ONE copy of this document for the purpose of your own non-commercial research or study. Any other use requires permission from the copyright owner. The Copyright Act requires you to attribute any copyright works you quote or paraphrase.

1 Conference paper

Kick It to Me, or Maybe Not – How Player Roles Affect AFL Possessions
Born, Z., Weber, J., Mian, A. & Alderson, J., 2022, Proceedings of the 9th International Performance Analysis Workshop and Conference & 5th IACSS Conference. Switzerland: Springer International Publishing AG, 8 p. (Advances in Intelligent Systems and Computing).
Research output: Chapter in Book/Conference paper › Conference paper › peer-review

Cite this

@phdthesis{2f8af4462e884553ac82fe930f70d32a,

title = "Tactical Performance Insights for Australian Rules Football Using Deep Learning",

abstract = "The analysis of tactical behaviour in invasion-based sports is imperative to gaining a competitive advantage over opposition teams. This thesis aimed to derive novel insights into the tactical behaviour of professional Australian Rules Football teams through the use of deep learning tools adapted from the sub-fields of natural language processing and multiple object tracking. Specifically, methods to automatically categorise ball movement strategies, forecast future ball possessions, and track the movement of athletes were developed. In doing so, this thesis lays the foundations for the development for interactive play sketching tools in Australian Rules Football.",

keywords = "Australian Rules Football, Deep Learning, Tactical Behaviour, Data Analytics, Athlete Tracking, Team Sport",

author = "Zac Born",

year = "2022",

doi = "10.26182/3sv1-h009",

language = "English",

school = "The University of Western Australia",

}

TY - BOOK

T1 - Tactical Performance Insights for Australian Rules Football Using Deep Learning

AU - Born, Zac

PY - 2022

Y1 - 2022

N2 - The analysis of tactical behaviour in invasion-based sports is imperative to gaining a competitive advantage over opposition teams. This thesis aimed to derive novel insights into the tactical behaviour of professional Australian Rules Football teams through the use of deep learning tools adapted from the sub-fields of natural language processing and multiple object tracking. Specifically, methods to automatically categorise ball movement strategies, forecast future ball possessions, and track the movement of athletes were developed. In doing so, this thesis lays the foundations for the development for interactive play sketching tools in Australian Rules Football.

AB - The analysis of tactical behaviour in invasion-based sports is imperative to gaining a competitive advantage over opposition teams. This thesis aimed to derive novel insights into the tactical behaviour of professional Australian Rules Football teams through the use of deep learning tools adapted from the sub-fields of natural language processing and multiple object tracking. Specifically, methods to automatically categorise ball movement strategies, forecast future ball possessions, and track the movement of athletes were developed. In doing so, this thesis lays the foundations for the development for interactive play sketching tools in Australian Rules Football.

KW - Australian Rules Football

KW - Deep Learning

KW - Tactical Behaviour

KW - Data Analytics

KW - Athlete Tracking

KW - Team Sport

U2 - 10.26182/3sv1-h009

DO - 10.26182/3sv1-h009

M3 - Doctoral Thesis

ER -

Tactical Performance Insights for Australian Rules Football Using Deep Learning

Abstract

Access to Document

Fingerprint

Research output

Kick It to Me, or Maybe Not – How Player Roles Affect AFL Possessions

Cite this