Affordable Long-Term Quality of Motion Assessment in Co-Residencial Environments (Egypt Case Study)

Project Details


Research work at the University of Bristol on online quality of motion assessment [1,2] for monitoring functional mobility and risk of fall amongst the elderly, including Parkinsons patients, at their homes utilises affordable depth sensors. The affordability makes the approach ideal for developing countries, with the technique requiring minimal expertise setup.

Recently, [3] published the first of its kind cross-sectional study on the assessment of the elderly’s functional mobility in Egypt recruiting 304 subjects. The work highlighted the need for longitudinal assessment of functional mobility in the country. Using online quality of motion assessment [1,2], unique results can be obtained in the subject’s natural environment over a lengthened period of time.

Interestingly, developing countries pose a challenge due to the common co-residential arrangements for the elderly (i.e living with adult children). Action recognition and pose estimation demands robust online detection of the motion-to-be-monitored (e.g. sitting to standing). The recent work of the collaborator, Dr Hussein, [4,5] is a step towards robust online action recognition.

The collaboration brings together both works towards affordable quality of motion assessment in co-residential environments. This collaboration is a first step towards high-impact research for longitudinal assessment of functional mobility in developing countries, with Egypt as a case study.

[1] L Tao, A Paiment, D Damen, et al (2016). A Comparative Study of Pose Representation and Dynamics Modelling for Online Motion Quality Assessment. Computer Vision and Image Understanding.
[2] A Paiment, L Tao, S Hannuna, M Camplani, D Damen, M Mirmehdi (2014). Online quality assessment of human movement from skeleton data. British Machine Vision Conference.
[3] M Kamel (2013). Risk factors of falls among elderly living in Urban Suez – Egypt. The Pan African Medical Journal.
[4] A Sharaf, M Torki, M Hussein, M El-Saban (2015). Real-time Multi-scale Action Detection From 3D Skeleton Data. IEEE Conference on Applications of Computer Vision.
[5] M Meshry, M Hussein, M Torki (2016). Linear-time Online Action Detection From 3D Skeletal Data Using Bags of Gesturelets. IEEE Conference on Applications of Computer Vision.
Effective start/end date1/03/1631/07/16

Structured keywords

  • Digital Health


Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.