Pose extraction and event recognition in combat sports using machine learning technologies at Sheffield Hallam University on FindAPhD.com

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities

Dr Simon Goodwill, Dr Sergio Davies, Dr Chuang-Yuan Chiu No more applications being accepted Competition Funded PhD Project (Students Worldwide)

Sheffield United Kingdom Applied Mathematics Data Analysis Computer Science Software Engineering

About the Project

About the Programme

Applications are invited for Graduate Teaching Assistant PhD scholarships in The Academy of Sport and Physical Activity (ASPA), hosted by the Sport and Physical Activity Research Centre (SPARC), commencing 4th October 2021.

SPARC conducts research activity in a number of key areas and hosts four Research Groups:

· Physical Activity, Wellness and Public Health

· Sports Industry Research Group

· Sports Engineering Research Group

· Sport and Human Performance

https://www.shu.ac.uk/research/specialisms/sport-and-physical-activity-research-centre

In the 2014 Research Excellence Framework (REF), 67% of our research was rated as world-leading and internationally excellent (4* and 3*), with 100% of our research environment judged to be 3* or 4*. Our innovative and applied research is funded through research councils and charities grants, in addition to investment from companies and organisations in the sport and physical activity industry. Staff have well established national and international collaborations with academics and industry/clinical partners. We have a community of approximately 45 postgraduate students in sport and physical activity who are at the heart of contributing to our research output. All doctoral students are supported by a comprehensive programme of doctoral training and encouraged to present their research findings at national and international conferences.

About the PhD GTA programme

GTA scholarships combine PhD study with professional development to gain practical experience in learning, teaching and assessment in Higher Education and provide an excellent opportunity for those wishing to pursue an academic or clinical/academic health career. You will be based in The Academy of Sport and Physical Activity and specifically SPARC. As part of your training, you will be expected to support teaching related activities in that department, up to a maximum of 180 hours per academic year and not more than 6 hours in any one week, in line with University policy. You will be supported to work towards Associate Fellowship of the Higher Education Academy. For more information please visit Sheffield Hallam University PhD scholarships

About the PhD

Machine learning (ML) technologies such as pose estimation and object tracking are starting to be used in commercial performance analysis systems. However, the impact of these analysis systems is limited as the ML models are not sufficiently developed to provide the accuracy and reliability that is required. In training, it is well established that feedback should be provided in real time to maximise the effectiveness of the coaching. Machine learning technologies address this requirement as they can deliver real-time feedback without manual input. In tournament performance analysis, the practitioners have the potential of studying all competitors. However, the significant barrier in this scenario is the time and resource requirement for the analyst to extract the data.

The aim of this PhD is to develop and validate computer-vision based machine learning (ML) technologies to estimate the location and pose of athletes competing in combat sports. The project will benefit from, and build on, the 10+ year research partnerships we have with Team GB sports that include GB Boxing and GB Taekwondo. The output from this research project will directly enrich and inform the training of our Team GB athletes, with the aim of increasing the probability of Olympic medal success.

Who should apply?

Applicants should hold a BSc (1^st or 2:1) degree qualification in computer science, physical sciences, mathematics or sport/physical activity is essential. An MSc degree qualification in a relevant area is desirable. We are offering this as a full-time PhD scholarship. We welcome applications from all members of our community and are particularly encouraging those from diverse groups, such as members of the LGBTQIA+, BAME and disabled communities.

More details of our entry requirements can be found here PHD Sport and Physical Activity Full-time 2021 | Sheffield Hallam University (shu.ac.uk)

How to apply

For more information about how to apply and an application form please visit https://www.shu.ac.uk/research/degrees/apply

For general enquires please contact the Health Research Institute Postgraduate Research Team via email at [Email Address Removed]

For project specific enquiries please contact Dr Simon Goodwill [Email Address Removed]

Submit your application to [Email Address Removed]. Please do not submit your application and references to [Email Address Removed]

What is the submission deadline?

The closing date for applications is Friday 9^th July at 12pm 2021.

Interviews will be held w/c 26^th July 2021.

Start date Monday 4^th October 2021.

Funding Notes

Scholarships are available to Home/EU and International students for 42 months of full-time or 70 months of part-time funding to include: • Annual maintenance stipend at standard UKRI national minimum doctoral stipend rates: £15,609 per annum for 2021/22 full-time study; £7,805 per annum for part-time. The stipend is paid on a monthly basis as a tax-free bursary and intends to cover basic living costs. • University tuition fees at Home/EU levels. If you're required to pay tuition fees at the International rate you will be expected to fund the difference between Home and International fees.

References

Elliott, N., Choppin, S., Goodwill, S., Senior, T., Hart, J., & Allen, T. (2018). Single view silhouette fitting techniques for estimating tennis racket position. Sports Engineering, 21(2), 137-147. doi:10.1007/s12283-017-0243-0
Foster, L., Gielen, M., Beattie, M., & Goodwill, S. R. (2014). Real-time monitoring of user physical activity and position in an outdoor public space. Ubiquitous Computing and Ambient Intelligence, 8867(8867), 100-107. doi:10.1007/978-3-319-13102-3_19
Chiu, C. -Y., Thelwell, M., Goodwill, S., & Dunn, M. (2020). Accuracy of Anthropometric Measurements by a Video-based 3D Modelling Technique. In CMBBE 2019 Conference Proceedings. New York, NY, USA: Springer. doi:10.1007/978-3-030-43195-2
Mcinerney, C., Goodwill, S., Foster, L., & Choppin, S. (2016). Spatio-temporal metrics that distinguish plays in field hockey : a pilot study. In ISPAS 2016 International Workshop (pp. 4 pages). Institute of Technology, Carlow.
Elliott, N., Choppin, S., Goodwill, S., & Allen, T. (2014). Markerless tracking of tennis racket motion using a camera. In Procedia Engineering Vol. 72 (pp. 344-349). Elsevier. doi:10.1016/j.proeng.2014.06.060
Davies, S., Lucas, A., Ricolfe-Viala, C., & Di Nuovo, A. (2021). A Database for Learning Numbers by Visual Finger Recognition in Developmental Neuro-Robotics. Frontiers in Neurorobotics, 15, 12.
Rast, A. D., Adams, S. V., Davidson, S., Davies, S., Hopkins, M., Rowley, A., ... & Cangelosi, A. (2018). Behavioral learning in a cognitive neuromorphic robot: an integrative approach. IEEE transactions on neural networks and learning systems, 29(12), 6132-6144.
Davies, S., Stewart, T., Eliasmith, C., & Furber, S. (2013, August). Spike-based learning of transfer functions with the SpiNNaker neuromimetic simulator. In The 2013 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE.