[Jobinfo] Fwd: [Edinburghvisionec] JOB: Edinburgh postdoc in visual behaviour understanding

-------- Forwarded Message --------
Subject: 	[Edinburghvisionec] JOB: Edinburgh postdoc in visual behaviour 
understanding
Date: 	Tue, 15 Sep 2020 14:51:29 +0100
From: 	Bob Fisher <rbf@inf.ed.ac.uk>
To: 	EdinburghVisionEC@inf.ed.ac.uk



JOB: Edinburgh postdoc in visual behaviour understanding
Applications are invited for a Research Associate in Visual Behaviour 
Understanding
in the School of Informatics, University of Edinburgh.
The School of Informatics, located in the heart of Edinburgh, is the largest
institution of this kind in the UK and one of the largest in Europe.
See: https://www.ed.ac.uk/informatics/

The application area of the computer vision research to be undertaken by
this researcher is non-intrusive monitoring of ageing people in their own
home or in a care home situation.

The research will be undertaken in the recently formed Advanced Care 
Research
Centre (ACRC) at the University of Edinburgh, a cross-university centre 
focussing
on the technological, medical, and sociological issues needed to support the
day-to-day living of ageing people. This project will part of the ACRC's New
Technologies of Care research programme and the post-holder will be 
primarily
based at the Edinburgh BioQuarter.

This full-time position is fixed term for 30 months.

Informal enquiries to be directed to Professor Bob Fisher: 
R.B.Fisher@ed.ac.uk
or Professor Ram Ramamoorthy: s.ramamoorthy@ed.ac.uk

Salary grade scale: UE07 : 33,797 - 40,322 GBP / year

Feedback is only provided to interviewed candidates.

Closing date is 5pm (GMT) on 14th October 2020.
Vacancy Reference: 053187
See: 
https://www.vacancies.ed.ac.uk/pls/corehrrecruit/erq_jobspec_version_4.display_form

Further Information

The data will come from RGBD cameras and other sensors (some wearable,
some embedded). One responsibility of the researcher will be to develop
several reliable video analysis components oriented around colour and 
possibly
depth imagery taken from fixed cameras in an indoor environment. The 
lighting
would not be controllable, so the analysis would have to cope with a variety
of lighting conditions, including direct sunlight from outside, as well 
as changing
locations and source types of indoor lighting. The purpose of the 
analysis is to
detect events such as falls, lack of activity such as arising from a medical
situation, and quantifying the level of activity at different time scales.
Frame rates will be low, e.g. 5 frames per second; however all 
processing will
need to be done at video rates on low power GPUs and CPUs, such as on an 
NVidia
Jetson Nano. The components would need to be integrated into a larger
hardware/software system, and evaluated as part of that larger system.

The second responsibility is in the area of activity modelling methods and
sequential decision making. The activity modelling task is targeted at 
understanding
what an elderly person is doing, quantifying the amount of activity at 
different
time scales and using these models for advice giving and coaching. While 
similar
to the analysis described above, in this case the analysis will also 
take into
account additional signals, such as from accelerometers and gyroscopes 
embedded
in wearables. The sequential decision making research will investigate 
advanced
methods for determining when a notifiable event has occurred, how to 
build causal
models of such events and how this can be turned into actionable advice 
to the
various involved stakeholders.

_______________________________________________
Edinburghvisionec mailing list
Edinburghvisionec@inf.ed.ac.uk
http://lists.inf.ed.ac.uk/mailman/listinfo/edinburghvisionec

-- 
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.cg.tuwien.ac.at/pipermail/jobinfo/attachments/20200915/23835722/attachment.htm>