The Multidisciplinary University Research Initiative (MURI) is a US Department of Defense (DoD) research programme, sponsored by the Office of Naval Research, the Army Research Office and the Air Force Office of Scientific Research.
In 2017, the Ministry of Defence and the Engineering and Physical Sciences Council (EPSRC) agreed to allow UK institutions the opportunity to engage in MURI and obtain funding from the programme by joining a US-led research proposal.
The University of Surrey will contribute its expertise in vision, speech and signal processing to the MURI-funded research project ‘Semantic Information Pursuit for Multimodal Data Analysis’, led by John Hopkins University in the US.
The project comes under the topic 'Characterisation of Information Content in Data for Multimodal Data Analysis' in the MURI call for proposals. It will address the challenges surrounding information extraction from visual and audio sensors, such as cameras and microphones.
Machine perception concerns itself with extracting useful information from data gathered by sensors, in order to assist with tasks. The goal of the research will be to advance machine perception technology, allowing cameras and microphones to extract useful information from an environment and separate it from ‘nuisance’ factors such as illumination, blur, noise and object pose.
The collaborative research team will also work towards developing information theory and finding effective ways to characterise 'information semantics’. This will enable future machine perception systems to extract meaningful and actionable information from sensors mounted on autonomous vehicles, installed in smart cities, or supporting assisted living.
The research team consists of members from the UK universities of Surrey, Oxford, University College London and Imperial College London, and the US universities of Maryland, John Hopkins, Stanford, California (Berkeley), California (Los Angeles) and Southern California.
Professor Josef Kittler, of the Centre for Vision, Speech and Signal Processing (CVSSP) at the University of Surrey (Department of Electrical and Electronic Engineering), will lead Surrey’s contribution to the project.
Professor Kittler commented: "This is an exciting opportunity, which will allow us to address fundamental research questions relating to big data, machine learning and information theory in the context of machine perception, in collaboration with world-leading teams of outstanding complementary expertise."
The University looks forward to working with US and UK partners on this exciting collaborative research project, seeking to answer the key questions of how we measure information and how the extraction of information from data can become a more robust and effective process.