Automated Analysis and Quantification of Human Mobility Using a Depth Sensor
- Submitting institution
-
Manchester Metropolitan University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2332
- Type
- D - Journal article
- DOI
-
10.1109/JBHI.2016.2558540
- Title of journal
- IEEE Journal of Biomedical and Health Informatics
- Article number
- -
- First page
- 939
- Volume
- 21
- Issue
- 4
- ISSN
- 2168-2194
- Open access status
- Compliant
- Month of publication
- June
- Year of publication
- 2016
- URL
-
https://e-space.mmu.ac.uk/617068/
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
2
- Research group(s)
-
B - Human Centred-Computing
- Citation count
- 19
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper proposes a new framework for the automatic recognition of clinically relevant mobility impairments using markerless motion capture based on our published dataset (k3da.leightley.com). Instead of relying on the velocity of each joint, a set of novel joint-group features is used which prove to be more reliable and accurate. It formed the basis for a collaboration with Massey University (New Zealand) funded by The Royal Society (IE150436). It also produced 2 collaborative PhD projects and follow-up papers. We later demonstrated that the technique can be used for a Sensory Organisation Test (Maudsley-Barton 2020), when validated with a Balance Master.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -