This research area focuses on the theory and fundamental underpinning of Image and vision computing in both two dimensions (2D) and three dimensions (3D), across the electromagnetic spectrum.
This research area focuses on the theory and fundamental underpinning of Image and Vision Computing in both two dimensions (2D) and three dimensions (3D), across the electromagnetic spectrum, with applications including:
- feature and pattern analysis
- pattern recognition
- computer-based image interpretation, excluding medical image processing – see the Medical imaging research area
- document image processing
- video image processing and analysis
- image databases
- machine vision
- robotics.
Our strategy recognises image and vision computing’s importance to data science and its underpinning of research across sectors such as robotics, security, defence, healthcare, communications, creative industries, media and manufacturing.
Aims
Exploiting multi-modal data
We aim to have a research area which continues to address growing relevance to data science, for analysing, understanding and exploiting the ever-increasing visual data and information (including multi-modal data) generated by broadcast media, social media and other sources. We aim for a portfolio which further explores and exploits the links between language and vision, addressing challenges in multi-modal interface research.
Increasing scene understanding for robot vision
We are aiming for an increase in collaboration by researchers working in this area with robotics and autonomous systems, in terms of making a strong contribution to scene understanding for robot vision (together with the research areas Vision, hearing and other senses and Artificial intelligence technologies).
More realistic rendering
We are aiming for a research area which continues to reflect a high degree of relevance to the creative industries, working with the Graphics and visualisation research area, in terms of image capture and analysis for more realistic rendering of scenes and faces. The Graphics and visualisation research area will also be maintained to reflect the contribution that the Image and vision computing research area will continue to have in developing biometric technologies and its importance in security and defence.
Underpinning cross-sector research
We want our portfolio to continue to meet the demand for core capability and to underpin image and vision computing research across many sectors, including:
- robotics
- security
- defence
- healthcare – for example, activity monitoring in the home environment
communications - environment
- manufacturing
- media
- the creative industries.
Medical imaging
We need researchers who consider what contribution they can make to the Medical imaging research area, in the context of understanding and extracting clinically relevant information from medical images.
Investing in early-career researchers
We’re aiming for a portfolio with a greater proportion of early-career researchers, to ensure the longer-term health of this research area.
Contributing to cross-ICT priorities
Researchers working in this area should play an important role in delivering the objectives of EPSRC’s Future intelligent technologies and Data enabled decision making cross-ICT priorities which are part of the Information and communication technologies theme. They should also be well-placed to contribute to the other EPSRC cross-ICT priorities.
To maximise the impact of these contributions, Image and vision computing area researchers should ensure effective communication with researchers in other contributing areas, including:
- Artificial intelligence technologies
- Graphics and visualisation
- Vision, hearing and other senses
- Human-computer interaction.
Addressing public trust and privacy
Researchers should acknowledge and demonstrate the importance of responsible innovation in their proposals, in relation to addressing the issues of trust, identity and privacy when using visual data from large-scale social networks and surveillance sources, and where there are issues in using technology which will need to be accepted and trusted by the general public (for example computer vision systems in driverless cars).