Optimising the Use of Machine Learning and Computer Vision in Sport: An Ecological Dynamics Perspective - Journal of Expertise 7(2) 20-31

Aug 2, 2026

Upload by Eliana

Although machine learning and computer vision research in sport is expanding, embedding these technologies in athlete development programs does not automatically produce better performance outcomes. Benefits can be constrained by siloed practices within sports organizations and by inconsistent development approaches that hinder skill growth. This position paper argues that effective collaboration among sport scientists, technologists, and practitioners requires a theoretical framework, such as ecological dynamics, to rationalize design and integration. It also explains how this approach can support representative learning design, individualize training and assessment, and enhance coaching quality.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Abstract

Keywords

Introduction

Machine learning in sport performance analysis

Computer vision for images and videos

Risks of siloed working in multidisciplinary teams

Need for organizational structure and theoretical rationalization

Optimising the Use of Machine Learning and Computer Vision in Sport: An Ecological Dynamics Perspective . AULTON, Cavan, STRAFFORD, Ben < [http://orcid.org/0000-0003-4506-9370](http://orcid.org/0000-0003-4506-9370)>, DAVIDS, Keith < [http://orcid.org/0000-0003-1398-6123](http://orcid.org/0000-0003-1398-6123)> and CHIU, ChuangYuan Available from Sheffield Hallam University Research Archive (SHURA) at: [http://shura.shu.ac.uk/33451/](http://shura.shu.ac.uk/33451/) This document is the author deposited version. You are advised to consult the publisher's version if you wish to cite from it. Published version AULTON, Cavan, STRAFFORD, Ben, DAVIDS, Keith and CHIU, Chuang-Yuan (2024) . Optimising the Use of Machine Learning and Computer Vision in Sport: An Ecological Dynamics Perspective. Journal of Expertise, 7 (2), 20-31. Copyright and re-use policy See [http://shura.shu.ac.uk/information.html](http://shura.shu.ac.uk/information.html) Sheffield Hallam University Research Archive [http://shura.shu.ac.uk](http://shura.shu.ac.uk) Optimizing the Use of Machine Learning and Computer Vision in Sport: An Ecological Dynamics Perspective Cavan Aulton, Ben William Strafford, Keith Davids, and Chuang-Yuan Chiu Sport and Physical Activity Research Centre, Department of Sport and Physical Activity, Sheffield Hallam University, UK Correspondence: Cavan Aulton, [ca2644@exchange.shu.ac.uk](ca2644@exchange.shu.ac.uk) Journal of Expertise 2024. Vol. 7(2) © 2024. The authors license this article under the terms of the Creative Commons Attribution 3.0 License. ISSN 2573-2773 Abstract Although machine learning and computer vision is a growing area of research in sports analysis, its implementation in athlete development programs does not guarantee performance improvements. Developers typically design and implement machine learning and computer vision technologies into athlete development programs because of the high level of technical information on performance that can emerge. The value gained from this approach can be limited by siloed working practices in sports organizations and by sporadic approaches to athlete development which can negatively affect skill development. Here, we discuss why the design and integration of machine learning and computer vision in athlete development programs needs to be rationalized by a theoretical framework to guide effective collaborations between sport scientists, technologists, and practitioners. This position paper illustrateshow the use (i.e., design and implementation) of machine learning and computer vision technologies in athlete development programs could be underpinned by the structural organization of a Department of Methodology (DoM), and that underpinned by a theoretical framework, such as ecological dynamics. We outline how the integration of machine learning and computer vision technology, underpinned by an ecological theoretical approach, can accomplish the following: (1) support representative learning design,(2) individualize training and assessment of athletes, and (3), enhance, but not replace, the quality of coaching within athlete development programs. Keywords ecological dynamics, Department of Methodology, machine learning, computer vision, sport science Introduction In recent years, the integration of technology into sports performance and analysis has significantly advanced, particularly with the emergence of methodologies such as machine learning and computer vision technologies, aimed at enriching athlete development programs and enhancing the work of professional support practitioners. Machine learning (ML) involves designing software capable of learning and making predictions or decisions, from large sets of performance data, while continually improving their accuracy by introducing more training data, simulating how humans learn from additional sources of information (Kufel et al., 2023) . Computer Vision (CV) extracts and categorizes inform

FAQs

Why does using machine learning and computer vision in athlete development programs not guarantee performance improvement?

Because technical implementation alone does not ensure better outcomes. Siloed working practices and sporadic development approaches can limit value and negatively affect skill development.

What role does ecological dynamics play in this paper’s argument?

The paper proposes that machine learning and computer vision integration should be rationalized using a theoretical framework, such as ecological dynamics, to guide effective collaborations.

How can the proposed framework improve athlete training and coaching?

It can support representative learning design, individualize training and assessment, and enhance—rather than replace—the quality of coaching in athlete development programs.

Aug 2, 2026

Upload by Eliana