We analyse images and related data in order to understand their content, manipulate them, and make decisions.
Images have become ubiquitous in recent years, and their use is now incorporated in many applications covering everyday life, including scientific research and industrial manufacturing. Members of the Computer Vision group are interested and active in a variety of research and applied projects in this area.
We have extensive experience in many areas of computer vision, image and video processing. We have worked closely with the Schools of Psychology, Engineering, Dentistry, Medicine and Optometry, and have also collaborated with industrial partners such as Renishaw, Airbus, British Aerospace, Welsh Rugby Union, local Police forces, councils and health services.
In the future we aim to attract more high quality PhD students and more funding from UKRI and industry.
Examples of prior projects include:
- machine and deep learning of imagery and video
- high resolution surface reconstruction
- computational archaeology
- analysis of high dimensional image feature spaces
- articulated human motion analysis
- sports video analysis
- video surveillance applications
- modelling crowd behaviour
- visual media quality assessment
- forgery detection
- visual attention modelling and applications
- non-photorealistic rendering
- generative image models
- reflection aware visual SLAM
- speech driven facial modelling and video synthesis
- image registration.
Examples of applications of our research include:
- visual avatar for virtual delivery of healthcare
- segmentation of 3D OCT scans of retinas
- the perception of trustworthiness from smiles
- determining the effectiveness of surgery from facial morphology and temporal dynamics
- analysing the effects of alcohol on crowd dynamics
- violence digitally unrolling of fragile parchments from 3D X-ray scans analysis of birch bark manuscripts.
Project name: A BioEngineering approach for the SAFE design and fitting of Respiratory Protective Equipment (BE-SAFE RPE)
Funded by: EPSRC
Co-principal investigators: Professor David Marshall and Professor Paul Rosin
Seminars from members and visitors are presented at the visual computing research seminar series.