Marine track-before-detect: Machine learning to track multiple objects using raw radar data in the maritime environment

Description

This PhD project aligns with the CDT in Distributed Algorithms: The What, How and where of Next-Generation Data Science.

The University of Liverpool’s Signal Processing group hosts the Centre for Doctoral Training in Distributed Algorithms (CDT) and together the team works in partnership with 30+ external partners from the manufacturing, defence and security sectors to provide a 4-year innovative PhD training programme that will equip its students with: the essential skills needed to become future leaders in distributed algorithms; the technical and professional networks needed to launch a career in next generation data science and future computing; and the confidence to make a positive difference in society, the economy and beyond.  This studentship is co-funded by Leonardo UK – specifically, the Edinburgh site that is a global supplier of sensing and communications for the defence and security sectors and currently funds 3 other CDT PhDs.

This is a data science project that will develop algorithms to detect, track and classify objects on the surface of the sea using non-thresholded radar data, also known as track-before-detect (TkBD). These objects can for example be ships, kayaks or floating objects. The project will first model the received radar signal from the objects, tackling the important challenge of modelling the physical channel and possible sources of clutter, such as sea waves and rain. Model-based and machine learning solutions will be investigated.

The TkBD algorithms will be developed for coherent and non-coherent processing of the radar returns. The theoretical foundations of the TkBD algorithms will be based on the random finite set formulation and message passing among the filters for each object for scalability with a possibly high number of objects. The developed filters will obtain information on the trajectory of each object to provide useful analytics for the characterisation of object dynamics, object type, and behaviour. The optimisation of different parameters of the filter will be carried out for maximum performance. Gaussian and particle implementations of the filters will be explored to capitalise on emerging computation resources, for instance, graphics processing units.

The algorithms will be tested using experimental data obtained by Leonardo.

The successful student will be based at the University of Liverpool and be aligned to the CDT and Signal Processing Group  - a large, successful, social and creative research group that works together solving tough research problems.  Students have two academic supervisors and an industrial partner who provide co-supervision, placements and the opportunity to work on real world challenges. In addition, students attend technical and professional training to gain unparalleled expertise to make a difference now and in the future.

The research group is committed to providing an inclusive environment in which diverse students can thrive. The CDT particularly encourages applications from women, disabled and Black, Asian and Minority Ethnic candidates, who are currently under-represented in the sector.  We can also consider part time PhD students.  We also encourage talented individuals from various backgrounds, with either an UG or MSc in a numerate subject and people with ambition and an interest in making a difference. 

The studentship is open to: UK nationals who are willing and able to undergo security clearance.

Apply now: https://www.liverpool.ac.uk/distributed-algorithms-cdt/apply/

Applicants please note: You must not submit a research proposal. The PhD project is defined. You must provide a supporting statement (no more than 700 words) that explains why you are interested in undertaking a PhD, this specific topic and joining the research group. More application guidance can be found on the apply link above.