Ambient Assisted Living with Multiview Low Data Rate Imaging
Self-funded PhD students only
School of Computing
Applications accepted all year round
The work on this project will:
- develop novel approaches to ADL recognition using multiple cameras with low overall data rates
- investigate techniques for data fusion from multiple views
- look into adapting existing or researching new methods for recognition from low data rate video
Ambient Assisted Living explores how technological solutions and infrastructure can allow people with additional care needs to live independently in their preferred environment.
Elderly people and those with long-term health conditions are two of the largest target groups for AAL systems. Due to the rapid increases in the cost of traditional care models and approaches, and the challenges presented by an ageing population, AAL is hugely important to the future of healthcare services.
One of the main areas for AAL systems is Recognition of Activities of Daily Living (ADL), which can be used to detect common emergency situations, such as falls. Monitoring ADL has also the potential to help with more complex issues, such as medication, personal care, activity levels, and behaviour trends – all of which are essential to creating a safe independent living environment.
Recent work on ADL recognition has focused on using video data from cameras located in a person’s home. In general, using environmental rather than wearable sensors is less cumbersome for users and creates less interference with their daily routines. Video is one of the richest information sources compared with other types of sensors, such as audio, motion, pressure, or usage.
Human activity recognition from video has been an active area of research with some very promising recent results, such as deep learning-based approaches. However, one of the main requirements for AAL systems is the ability to deploy these techniques in typical residential environments.
One of the challenges posed by residential environments for video-based recognition is field of view limitations. Even within a single room, there are likely to be obstructed areas for any given point of view, caused by room configuration, furniture, and other objects, so a single camera is likely to be ineffective. The need for flexible positioning of possibly multiple cameras raises another set of practical problems: connectivity and power supply.
The aim of this project is to develop novel approaches to ADL recognition using multiple cameras with low overall data rates. The use of multiple cameras can help dealing with obstructions in typical residential environments and also to cover multiple rooms in a dwelling.
Low data rates (e.g. due to low resolution, low frame rates, or likely both) can facilitate the use of battery powered cameras with wireless connectivity. This will enable flexible camera positioning and easy retrofitting into existing housing. The project will investigate techniques for data fusion from multiple views and and will look into adapting existing or researching new methods for recognition from low data rate video.
Funding Availability: Self-funded PhD students only
PhD full-time and part-time courses are eligible for the UK Government Doctoral Loan (UK and EU students only).
Home/EU full-time students: £4,327 p/a*
Home/EU part-time students: £2,164 p/a*
International full-time students: £15,900 p/a*
International part-time students: £7,950 p/a*
*Fees are subject to annual increase
By Publication Fees 2020
Members of staff: £1,610 p/a*
External candidates: £4,327 p/a*
*Fees are subject to annual increase
- You'll need a good first degree from an internationally recognised university (minimum upper second class or equivalent, depending on your chosen course) or a Master’s degree in Computer Science or related discipline.
- In exceptional cases, we may consider equivalent professional experience and/or Qualifications.
- English language proficiency at a minimum of IELTS band 6.5 with no component score below 6.0.
We'd welcome applications from candidates with good software development skills, knowledge and/or experience in machine learning or pattern recognition and knowledge and/or experience in computer vision or image processing.
How to apply
We’d encourage you to contact Dr Rinat Khusainov (firstname.lastname@example.org) to discuss your interest before you apply, quoting the project code CCTS4610219. Please note: to be considered for this self-funded PhD opportunity you must quote project code when applying.
When you are ready to apply, you can use our online application form and select ‘Computing’ as the subject area. Make sure you submit a personal statement, proof of your degrees and grades, details of two referees, proof of your English language proficiency and an up-to-date CV.
Our ‘How to Apply’ page offers further guidance on the PhD application process.