School of Computer Science and Informatics

Visual computing

If AI enables computers to ‘think’ visual computing enables them to see, observe and transfer knowledge to real-world applications.

We are surrounded by more images than ever before - surveillance cameras in the street through to those in factories performing quality control to the smart phone shots that are shared on social media. And then there's medical imaging, autonomous guided vehicles, self-targeting missile systems, applications in agriculture, construction, entertainment, sports analytics, and so on.

While it is relatively straightforward to capture the raw data – and images are captured, stored and processed in their billions every year - the subsequent stage of analysing the images and extracting meaning from them is much more challenging because real life data tends to be noisy, fragmentary, and complex. This is one of the focuses of the visual computing research group.

Our work in visual computing explores visual analysis tools to help scientists and researchers better process large, multi-dimensional data. This has an impact on fields of work in engineering, earth sciences, healthcare, biology, medicine, psychology, architecture, computer music and quantum control.

Our work currently focuses on human-centric visual computers and our teams work across computer vision and computer graphics, geometric computing and multimedia data.

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 discrete forms such as meshes and point clouds.

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 deforming objects.