[robotics-worldwide] Postdoctoral Research Assistant in Gait and Activity Recognition - Oxford Brookes University (Fabio Cuzzolin)

Fabio Cuzzolin fabio.cuzzolin at brookes.ac.uk
Mon Aug 6 03:46:43 PDT 2012

Faculty of Technology, Design and Environment
Postdoctoral Research Assistant in Gait and Activity Recognition
Starting Salary: £24,520 rising annually to £26,779

This is a fixed term appointment for 11 months.

Starting in October 2012, this position will involve conducting the
bulk of the research activity within the framework of an EPSRC (the
UK’s Engineering and Physical Sciences Research Council) grant on
tensorial modeling of dynamical systems for gait and activity

Identity recognition by gait has been proposed as a novel behavioural
biometric, based on people’s distinctive gait pattern. Nevertheless,
despite its attractive features, gait identification is still far from
being ready to be deployed in practice.  This is because in real-world
scenarios recognition is made extremely difficult by the presence of
nuisance factors such as viewpoint, illumination, clothing, and
others. However, a mathematical formalism general enough to
potentially address the fundamental issue of covariate factors in a
principled way exists under the name of multilinear/tensorial
analysis. Its fundamental assumption is that the various factors
linearly mix to generate the measurements which we observe, in our
case the different walking gaits.

You will be responsible for:
-       formulating an appropriate theoretical framework based on tensorial
analysis and metric learning of generative dynamical models
-       selecting an adequate feature selection and extraction stage
-       implementing the approach by coding the different algorithms
involved in C++/Matlab
-       running tests on all the available benchmark datasets in gait
ID/action recognition
-       disseminating the results via publication at major, relevant
conferences and journals
-       developing a dedicated website on the project.

You should have:
-       a postdoctoral qualification in Computer Science or related fields,
or currently studying for a PhD
-       Substantial research experience as a doctoral student in computer
vision or machine learning
-       an adequate publication record in computer vision or machine learning
-       the potential to conduct research independently
-       coding proficiency in C++ and Matlab

You will have the chance to collaborate with Ph.D. students working on
cutting edge action recognition frameworks and be part of wider effort
on the subject, in the context of the Oxford Brookes vision group.

Applicants should file a formal application by filling the application
form found here:


following the guidelines provided.
Interviews will be conducted in early September.

Further information about the research can be found at the following link:

Please direct all informal enquiries to Dr Fabio Cuzzolin:
fabio.cuzzolin at brookes.ac.uk

Ref: 485/18353/AW
Closing date: August 31 2012

More information about the robotics-worldwide mailing list