Bristol/UK: Human Action and Expression Recognition
An interdisciplinary research collaboration (IRC) led by the University
of Bristol together with the Universities of Southampton and Reading,
has been awarded a grant by the Engineering and Physical Sciences
Research Council (EPSRC) of around Â£12 million. They will work in
partnership with Bristol City Council, IBM, Toshiba and Knowle West
Media Centre (KWMC).
The collaboration, known as SPHERE (Sensor Platform for HEalthcare in a
Residential Environment), will develop home sensor systems to monitor
the health and wellbeing of the people living at home. Three RA posts
are available beginning in October 2013 and are 3-year appointments
with some possibility of an extension.
The successful candidates will work together with a number of academic
staff in a team to investigate algorithms and models for analyzing and
understanding human activity and behaviour, gait and facial and emotion
expression in cluttered and uncontrolled home environments. The
research and software development will involve feature detection and
tracking, deformable models, statistical modelling and analysis, the
use of one or more cameras, including methods for tracking across
multiple rooms, and many other relevant topics. The posts involve close
collaboration with other SPHERE project personnel â€“ from other
workpackages within the project, including integration of other
sensors, data fusion and data mining â€“ as well as other project
partners at other institutions.
- hold (or be currently in the completion stages of) a PhD degree in
Computer Science or Electronic Engineering or a related discipline, in a
field related (but not limited) to computer vision, machine learning,
statistics or applied mathematics. Candidates should ideally also have
experience in any one or more of the following: human, head, and facial
component tracking; multi-camera analysis; object detection and
recognition; action and event recognition
- have excellent C/C++/Matlab programming and systems integration skills
- have a good publication record in computer vision and/or machine learning
- be able to conduct research independently
- possess good communication and writing skills in English.
There is no formal closing date. Applications will be reviewed when
submitted and appointments will continue until the three positions are
filled. The appointment should start on, or as soon as possible, after
October 1st 2013.