BTaRoT: Bayesian Tracking and Reasoning over Time

Lead Research Organisation: University of Cambridge
Department Name: Engineering


In this project we will provide new advances in computational methods for reasoning about many objects that evolve in a scene over time. Information about such objects arrives, typically in a real-time data feed, from sensors such as radar, sonar, LIDAR and video. The tracking problem for such scenarios is a well-trodden area, studied for many decades by many researchers. The new and exciting part of this project is in automated understanding of the `social interactions' that underlie a multi-object scene. Can we learn the emerging network structure that develops between objects, in terms of things like who is following who, where is a particular group of objects heading (danger zone or friendly air-field?), has an object left one group and joined another, has a new set of network interactions suddenly come into force? We also seek to integrate this kind of deeper understanding of a complex scene with a simultaneous handling of all of the sensor information available and the decision-making tasks that are required (which sensors to swich on/off, whether an object is friendly or a source of danger, whether an object behaves like a land-rover or a civilian car).

These sophisticated and difficult problems can all be posed very elegantly using probability theory, and in particular using Bayesian theory, a generic inferential and decision-making methodology that allows one to infer hidden information about a system given data from sensors and some prior beliefs about general behaviour patterns of objects. While generic and straightforward to pose, there are substantial challenges for our problem area in terms of how to pose the underlying prior models (what is a good way to model the random behaviour of networked objects in a scene?), and how do we carry out the very demanding computational calculations that are required for many-object scenes? These modelling and computational challenges form a major part of the project, and will require substantial new theoretical and applied algorithm development over the course of the project. We will develop novel computational methods based principally around Monte Carlo computing, in which very carefully designed randomised data are used to approximate very accurately the integrations and optimisations required in the Bayesian approach.

The outcomes from this ambitious project could cause a paradigm shift in tracking methodology if successful, moving away from the traditional viewpoint of a scene in which objects move independently of one another, towards an integrated viewpoint where object interactions are automatically learned and used in improved decision-making processes. We anticipate that the impact will be substantial across a wide range of related disciplines, from ecology and animal behaviour studies through to economic and social networking.

Planned Impact

BTaRoT is expected to generate scientific innovations aimed at processing heterogeneous sensor data and knowledge extraction for high-dimensional systems. As such, the program will generate considerable impact for a wide range of academic and non-academic beneficiaries, principal amongst whom are:
a) The sensor signal analysis community including academia and industry;
b) Our collaborating industrial partner, directly;
c) The research community, particularly in the areas of signal processing and engineering;
d) The project personnel: the EPSRC funded postdoctoral researchers and PhD students from both teams in Cambridge and Lancaster;
e) Society in general.
The project impact will involve both novel theoretical developments and knowledge transfer of the new methodologies to industry. A strong team is formed which has already an existing collaboration. The partners have been able to leverage their relationship with the wide range of users both in the academic area and industry. The project will afford new partnerships to be formed based on the EPSRC funding. Since the partners are actively involved in many external organisations and networks we will be able to link strongly with these organisations to strengthen the research base. BTaRoT seeks to develop a suite of objective simulation tests to benchmark the performance of developed methods and to draw on its existing industrial collaboration with QinetiQ. The PI in Lancaster will also exploit all benefits of InfoLab21, which hosts specialised ICT companies and hence this is a unique environment for dissemination and knowledge transfer of the obtained results.
A number of specific activities will be undertaken:
Secondment and visits of RAs or staff from partners or users.
Regular plenary workshops to bring together the consortium and wider users group to exchange information and update users on progress.
A dedicated web site will be developed to enable access to latest results and progress. Latest news and significant advances will be considered for release to the wider media as appropriate.


10 25 50
Description In the grant so far we have developed new methodologies for tracking of multiple objects using sequential Monte Carlo methods, both filtering and smoothing, and have applied them in new areas such as dynamic brain network modelling, finance and multiple object tracking
Exploitation Route Our work can be applied now in many areas including animal behavioural modelling and brain science.
Sectors Aerospace, Defence and Marine,Digital/Communication/Information Technologies (including Software),Security and Diplomacy

Description Brain networks collaboration - Addenbrookes Hospital 
Organisation Cambridge University Hospitals NHS Foundation Trust
Country United Kingdom 
Sector Public 
PI Contribution We have developed new methods for analysing dynamic brain connectivity network data
Collaborator Contribution The partners have provided us with state of the art data sets from FMRI and provided guidance on modelling issues
Impact Tracking changes in functional connectivity of brain networks from resting-state fMRI using particle filters Conference Paper published Apr 2015 in 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Authors: M Faizan Ahmad, James Murphy, Deniz Vatansever, Emmanuel A Stamatakis, Simon Godsill A further two papers are in submission (1 to appear in ICASSP 2016) and more in preparation A collaborative grant proposal also being prepared.
Start Year 2014