Summary

Computer Vision is a subfield of Artificial Intelligence (AI) and Machine Learning (ML) that develops techniques to train computers to interpret and understand image content. AI and computer vision was virtually unused in sports less than five years ago, but today deep learning and computer vision are used by broadcasters to enhance spectator experience by clubs themselves to become more competitive.

Most major sports involve fast and accurate motion that can sometimes become challenging for coaches and analysts to track and analyse in detail. The data and insights obtained from video footage requires an analyst to spend numerous hours manually annotating events. Sports video footage is usually acquired through one or more cameras. The angle, positioning, hardware and other configurations can vary greatly for each sport. This can pose a challenge for certain computer vision applications.

Recently developed fixed-angle camera systems have offered a low-cost entry point to sports analytics for many non-professional sports. Computer vision techniques are used in these systems to distinguish between the ground, players and other foreground objects. Models can detect the zones of a pitch, track moving players and identify the ball. However, current commercial sports AI platforms fall short when compared to professional sports teams with human based systems.

Restricted field of view means that cameras can miss parts of the field, and some fields are substantially bigger (for example, a GAA pitch is as much as 50% bigger than soccer, rugby, etc) and hence a greater field of view is required without the need for manually controlled cameras. This problem is not unique to GAA, however, as several other sports also use large fields including Polo and Australian rules football. Video resolution is also a problem as many current systems are limited to HD output but 4K is required because the cameras are unmanned and high-quality zoom is needed to identify players and events.

Many clubs have indicated that 4K resolution is essential for accurate match analysis and tactical decision making. Current software is restricted to manual annotation and tagging of events on an offline basis and AI detection is limited and error prone. MetroCCTV has designed bespoke hardware to overcome many of these difficulties. However, the underlying AI models and software are required.

This project focusses on development of the required AI-driven video analytics. Research contributions will focus on

(1) the development of convolutional neural networks to detect in-game events (goals, points, throw-ins, penalties, etc);

(2) detection of individual player behaviours (goal scorers, player infringements, player fitness, etc), building on video-based behavioural analysis research conducted in the ISRC;

(3) generation of realistic defensive and attacking plays based on the ball and team movements using a generative adversarial network to learn spatio-temporal interactions between players' movements and subsequently simulate how the opposing team will react to a newly developed strategy.

The successful candidate will have the opportunity to work at the cutting edge of video sports analytics alongside a well-established CCTV company resulting in high quality publications.


Essential criteria

Applicants should hold, or expect to obtain, a First or Upper Second Class Honours Degree in a subject relevant to the proposed area of study.

We may also consider applications from those who hold equivalent qualifications, for example, a Lower Second Class Honours Degree plus a Master’s Degree with Distinction.

In exceptional circumstances, the University may consider a portfolio of evidence from applicants who have appropriate professional experience which is equivalent to the learning outcomes of an Honours degree in lieu of academic qualifications.

  • Experience using research methods or other approaches relevant to the subject domain
  • A demonstrable interest in the research area associated with the studentship

Desirable Criteria

If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.

  • First Class Honours (1st) Degree
  • Masters at 70%
  • For VCRS Awards, Masters at 75%
  • Experience using research methods or other approaches relevant to the subject domain
  • Work experience relevant to the proposed project
  • Experience of presentation of research findings

Funding and eligibility

This project is funded by: DfE CAST

The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £ 16,840 (tbc) per annum for three years (subject to satisfactory academic performance). This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher. • Candidates with pre-settled or settled status under the EU Settlement Scheme, who also satisfy a three year residency requirement in the UK prior to the start of the course for which a Studentship is held MAY receive a Studentship covering fees and maintenance. • Republic of Ireland (ROI) nationals who satisfy three years’ residency in the UK prior to the start of the course MAY receive a Studentship covering fees and maintenance (ROI nationals don’t need to have pre-settled or settled status under the EU Settlement Scheme to qualify). • Other non-ROI EU applicants are ‘International’ are not eligible for this source of funding. • Applicants who already hold a doctoral degree or who have been registered on a programme of research leading to the award of a doctoral degree on a full-time basis for more than one year (or part-time equivalent) are NOT eligible to apply for an award.


The Doctoral College at Ulster University