Automatic Weed Imaging and Analysis
Current agricultural techniques for management of weeds in crop fields often involve the wide-scale spraying of herbicides, which is expensive both economically and environmentally. In addition, an increasing global population requires an increasing crop output, which in turn requires more efficient use of existing agricultural land.
Read more about the Automatic Weed Imaging and Analysis project
Face recognition using photometric stereo (Photoface)
UWE, Imperial College London and its partners have received £672,000 in funding for the three-year project from the Engineering and Physical Sciences Research Council's (EPSRC) Fighting Crime programme. The main aims of this project are:
- Develop a photometric stereo-based technique for accurately recovering the three-dimensional structure of moving faces.
- Utilise the three-dimensional data to advance existing face recognition technology.
4D data capture - real-time 3D
While static 3D face representation and recognition have gained significant attention, not much has been done on the characterisation of 3D facial expressions and their evolution.
Existing taxonomies of facial expression are still based on poor facial data representations and thus fail to provide for the next generation of precise and realistic representation required in dynamic 3D facial expression, where the role of micro-level features and movements is essential.
The 4D Vision project is aimed at capturing both facial macro and micro-movements that are fundamental in a number of tasks such as detection of deceptive behaviour, realistic modelling of facial expression for gaming characters and so on.
The expected outcomes for the 4D Vision project are new imaging capabilities for high-speed, high resolution capture of facial movements combined with robust, multi-resolution analysis, realistic visualisation and fast interaction.
Read more about the 4D capture system.
Application of photometric stereo in dermatology
A computational approach is adopted to redesign a device to inspect the skin primarily for dermatological uses. It is capable of capturing images of the skin, generating 3D views to display on a host or client screen and analysing the images to detect the presence of skin cancer - specifically malignant melanoma. The device should be able to help experts differentiate between malignant melanoma and benign skin lesions.
Read more about the Photometric Stereo in Dermatology project.
Novel Non-invasive Assessment of Respiratory Function (NORM)
The NORM project aims to develop a new type of medical respiratory monitoring system, using non-contact, non-invasive optical and dynamic photometric stereo techniques, to monitor movements of the thorax and abdomen in real-time. The data gathered will enable the construction of a 4D (space and time) model of the patient, which will enable the diagnosis of respiratory diseases and conditions that compromise normal respiratory function.
This type of system will lend itself well to very young children, or patients with significant respiratory compromise, where current invasive methods would be undesirable and inaccurate. The system will be calibrated to provide existing normal-breathing metrics, such as Tidal Volume, Respiration Rate, and Tidal Flow-Volume Loops; and determine new metrics to detect anomalous breathing behaviour.
Read more about the Novel Non-invasive Assessment of Respiratory Function (NORM) project.
Stealthy object detection and recognition
UWE's idea for a portable device to automatically detect and recognise potential threats to troops in war zones has succeeded under the MOD's Competition of Ideas scheme. The idea has won funding to be develop a prototype in conjunction with partners SEA (Group) Ltd. The project, led by Prof Melvyn Smith, could help detect camouflaged objects or people, and could contribute to the detection of weapons, such as guns or explosives, hidden under clothing.
Read more about the Stealthy object detection and recognition.
Quality control of specular ceramic materials
This Great Western Research (GWR) - funded project is undertaken in collaboration with Surface Inspection Ltd. Two separated sets of information are to be generated from specular surfaces while they are on-line; a detailed description of the surface morphology and a selective description of the surface reflectivity.
Read more about the Quality control of specular ceramic materials.
Use of 3D facial asymmetry in better diagnosis and treatment of skull abnormalities in children (Plagiocephaly)
The project has received Medical Research Council (MRC) funding to research skull abnormalities in children and is in collaboration with North Bristol NHS Trust and the London Orthotic Consultancy. The work will use innovative 3D imaging techniques to accurately measure the faces and heads of groups of children to look for links between abnormality in head shape and subtle signatures present in facial features.