Postgrad LIVE! Study Fairs

Birmingham | Edinburgh | Liverpool | Sheffield | Southampton | Bristol

London School of Hygiene & Tropical Medicine Featured PhD Programmes
University of Kent Featured PhD Programmes
Imperial College London Featured PhD Programmes
University of Oxford Featured PhD Programmes
University College London Featured PhD Programmes

Human Motion Analysis using Computer Vision and Deep Learning

  • Full or part time
  • Application Deadline
    Applications accepted all year round
  • Self-Funded PhD Students Only
    Self-Funded PhD Students Only

Project Description

Analysis of human motion is implicitly or explicitly required in many areas such as healthcare, sports, video surveillance, body-based user interfaces and computer games and animation. Currently, such analysis is usually performed by experts such as medical doctors, physiotherapists and sports scientists, and automatic interpretation of human movements is feasible in only a few cases.

This project will focus on how to process video streams to automate human motion analysis. Appropriate Computer Vision and Machine Learning methods for pose estimation and tracking, gait analysis, motion assessment and activity recognition will be investigated.

Candidates should have appropriate academic qualifications (first or upper second class honours or MSc degree) in Computer Science, Engineering, Mathematics, Physics or other relevant area, strong background in programming and desire to become experts in Computer Vision and Machine Deep Learning.

Qualified applicants are encouraged to contact Dr Dimitrios Makris () to informally discuss the project.

Supervisor’s profile:
http://sec.kingston.ac.uk/about-SEC/people/academic/view_profile.php?id=1201

Google Scholar profile:
https://scholar.google.co.uk/citations?user=vHv7JRcAAAAJ


Funding Notes

There is no funding for this project: applications can only be considered from self-funded candidates

References

[1] Georgios Mastorakis, Tim Ellis, and Dimitrios Makris. "Fall Detection without People: A Simulation Approach Tackling Video Data Scarcity." Expert Systems with Applications (2018).
[2] Bloom, Victoria, Argyriou, Vasileios and Makris, Dimitrios, Linear latent low dimensional space for online early action recognition and prediction. Pattern Recognition, ISSN (print) 0031-3203 (Epub Ahead of Print), 2017
[3] Rodriguez, Mario, Orrite, Carlos, Medrano, Carlos and Makris, Dimitrios (2016) One-shot learning of human activity with an MAP adapted GMM and simplex-HMM. IEEE Transactions on Cybernetics, 47(7), pp. 1769-1780. ISSN (print) 2168-2267
[4] Rodriguez, Mario, Orrite, Carlos, Medrano, Carlos and Makris, Dimitrios, A time flexible kernel framework for video-based activity recognition. Image and Vision Computing, 48-49, pp. 26-36. ISSN (print) 0262-8856, 2016
[5] Bloom, Victoria, Argyriou, Vasileios and Makris, Dimitrios (2016) Hierarchical transfer learning for online recognition of compound actions. Computer Vision and Image Understanding, 144, pp. 62-72. ISSN (print) 1077-3142
[6] Martínez del Rincón, J, Lewandowski, M., Nebel, J.C. and Makris, D. (2014) Generalised Laplacian Eigenmaps for Modelling and Tracking Human Motions. IEEE Transactions on Cybernetics, 44(9), pp. 1646-1660. ISSN (print) 2168-2267, 2014
[7] Lewandowski, Michal, Makris, Dimitrios, Velastin, Sergio A and Nebel, Jean-Christophe, Structural Laplacian eigenmaps for modeling sets of multivariate sequences. IEEE Transactions on Cybernetics, 44(6), pp. 936-949. ISSN (print) 2168-2267, 2014

How good is research at Kingston University in Computer Science and Informatics?

FTE Category A staff submitted: 10.20

Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully





FindAPhD. Copyright 2005-2018
All rights reserved.