Our research in visual computing spans a wide range of topics in the fields of computer vision, computer graphics, geometric computing and both image and video processing.
A significant theme in our work considers the input, description and editing of solids, surfaces and curves. These are represented analytically, as CAD models and as meshes. Other aspects of our work include the analysis, use and generation of static data such as images, surface meshes and 3D depth scans, as well as time-varying data such as video and 4D scans of moving objects.
Our expertise in this area has been applied to problems from a range of disciplines including engineering, earth sciences, psychology, biology, medicine and even computer music and quantum control.
Computer vision, image and video processing
We have extensive experience in many areas of computer vision, image and video processing. We are working closely with the Schools of Psychology, Engineering, Dentistry and Medicine, and we also collaborate with industrial partners, including Renishaw, Airbus, British Aerospace, Welsh Rugby Union, local Police forces, councils and health services.
The research areas we cover include:
- image (2D and 3D) registration
- analysis of high dimensional image feature spaces
- articulated human motion analysis, including facial dynamics and biometrics
- virtual unrolling of scrolled parchments (and film)
- visual media quality assessment and forgery detection
- visual attention modelling and applications
- video surveillance applications and sports video analysis
- modelling crowd behaviour
- non-photorealistic rendering
- machine and deep learning of imagery and video, including video events.
3D data, mesh processing and CAD applications
We have many years’ experience in 3D data processing and modelling.
As well as devising a range of general purpose algorithms for this task in areas such as registration, segmentation and curve and surface fitting, we have developed higher level algorithms for analysing symmetry and design intent of such models, as well as special purpose algorithms for processing bas-reliefs.
Our work includes:
- reverse engineering of CAD models
- sketch input of solid models
- 3D facial analysis
- 3D reconstruction from 2D images
- 3D shape retrieval and indexing
- geometry processing, including algorithms for constructing shapes, fusing geometric data from different sensor types, low-discrepancy sampling, and data-driven surface modelling.
Computational modelling and control
We are working on theory and algorithms for controlling and modelling physical systems. We are focused on learning to control quantum processes for:
- magnetic resonance imaging and spectroscopy
- quantum spin networks
- quantum spintronic and semiconductor devices
We recently began applying our expertise in machine and deep learning, image and audio analysis to the field of computer music. We are interested in the symbolic analysis of music, including smallest grammers and intelligent music editing, as well as audio transcription and synthesis.
|Data-driven realistic human motion reconstruction||Dr Y Lai||Royal Society||11.97|
|Intrinsic voronol/delaunay structure on 2-manifold mesh and its applications in visual computing||Dr Y Lai||Royal Society||110.71|
|Detecting deceit in humans through multimodal analysis of human behaviour||Professor AD Marshall, Dr S Moore and Professor M Innes||EADS Foundation Wales||125.0|
|Data-driven simulation of quantum spin network devices||Dr F Langbein||Ser Cymru NRN Swansea||59.4|