The Programme is organised into two themes. Research theme one will develop new computer vision algorithms to enable efficient search and description of vast image and video datasets - for example of the entire video archive of the BBC. Our vision is that anything visual should be searchable for, in the manner of a Google search of the web: by specifying a query, and having results returned immediately, irrespective of the size of the data. Such enabling capabilities will have widespread application both for general image/video search - consider how Google's web search has opened up new areas - and also for designing customized solutions for searching. A second aspect of theme 1 is to automatically extract detailed descriptions of the visual content. The aim here is to achieve human like performance and beyond, for example in recognizing configurations of parts and spatial layout, counting and delineating objects, or recognizing human actions and inter-actions in videos, significantly superseding the current limitations of computer vision systems, and enabling new and far reaching applications. The new algorithms will learn automatically, building on recent breakthroughs in large scale discriminative and deep machine learning. They will be capable of weakly-supervised learning, for example from images and videos downloaded from the internet, and require very little human supervision. The second theme addresses transfer and translation. This also has two aspects. The first is to apply the new computer vision methodologies to `non-natural' sensors and devices, such as ultrasound imaging and X-ray, which have different characteristics (noise, dimension, invariances) to the standard RGB channels of data captured by `natural' cameras (iphones, TV cameras). The second aspect of this theme is to seek impact in a variety of other disciplines and industry which today greatly under-utilise the power of the latest computer vision ideas. We will target these disciplines to enable them to leapfrog the divide between what they use (or do not use) today which is dominated by manual review and highly interactive analysis frame-by-frame, to a new era where automated efficient sorting, detection and mensuration of very large datasets becomes the norm. In short, our goal is to ensure that the newly developed methods are used by academic researchers in other areas, and turned into products for societal and economic benefit. To this end open source software, datasets, and demonstrators will be disseminated on the project website. The ubiquity of digital imaging means that every UK citizen may potentially benefit from the Programme research in different ways. One example is an enhanced iplayer that can search for where particular characters appear in a programme, or intelligently fast forward to the next `hugging' sequence. A second is wider deployment of lower cost imaging solutions in healthcare delivery. A third, also motivated by healthcare, is through the employment of new machine learning methods for validating targets for drug discovery based on microscopy images

Living standards in the UK are at significant risk from the rising costs of energy and the increasing gap between demand and the UK's generating capacity. Plugging this gap requires technological innovations which are affordable and can be implemented over reasonably short time-scales. An important area where efficiency gains can be achieved quickly is improving the management of heat released from industrial processes. All industrial and power generation processes produce heat which is often released into the environment in the form of high temperature exhaust products. New technologies are being developed to recover this otherwise wasted energy for use elsewhere, such as electricity, heating or cooling. If applied across the UK manufacturing sector, these technologies could save the energy output of around 20 power stations. Heat-recovery technologies are also used for renewable power from biomass, geothermal, solar-thermal sources and in de-centralized power generation. The development of heat recovery technology is therefore important in terms of cutting our carbon footprint as well as increasing UK energy security. Heat recovery systems work by transferring heat into a high-pressure working-fluid, using a heat exchanger. In order to produce electricity, the working fluid drives a turbine which is connected to an electrical generator. Heat recovery systems often use working fluids which are refrigerants or long-chain hydrocarbons. The properties of these working fluids differ greatly from those which have traditionally been used within turbines (such as air within aero-engines/gas-turbines or water vapour within steam turbines) and can be made up of several components including mixtures of gases and liquids. There is very little known about the behaviour of these unconventional working fluids within turbines largely due to a lack of experimental data with which to test current theories. This is important because turbine designers require accurate models in order to develop high performance machines, and uncertainties in the modelling can have a detrimental impact on both the development costs and the overall performance of a heat recovery system. There is also a potential to exploit the unusual behaviour of these working fluids, such as their ability to change from liquid to gas across the turbine, which can be exploited to increase system power to size ratios (power density) in ways not possible using normal working fluids like water. The project will explore how the behaviour of multi-component fluids can be used to increase turbine performance. In order to achieve this, the work will involve developing methods to simulate multi-component fluids within turbines. The project will use experiments and computational techniques to model these flows and use the results from this work to improve current computational methods. The project involves a collaboration with GE who are global leader in the design, manufacture and supply of heat recovery systems. GE will incorporate the results of this work into their design systems. In doing so, the results from this project will accelerate the development of heat-recovery technologies which will be used world-wide.

Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.

Reliability is essential to the success of renewable energy systems. The estimated life of wind turbines is about 20 years, this is in comparison to 40 years for a conventional steam turbine generator unit. However the failure rate of wind turbines is about 3 times higher than that of conventional generators. The key feature that differentiates a renewable energy source, from conventional generation, is the inherent fluctuation of the source, giving rise to poor reliability due to fatigue cycling and consequently high life-cycle cost. This proposal aims to build a consortium of UK and Chinese researchers to investigate the scientific causes of poor reliability of components and develop solutions to improve it. Stress analysis and impact evaluation will be performed for stresses in thermal, mechanical, or coupled thermo-mechanical domains, taking into account the practical operating conditions. Accelerated aging test will be carried out to identify critical areas where improvement can be made cost-effectively. The research aims to develop new design concepts and new techniques that can be integrated in future renewable energy conversion systems and networks for reliability. Potential new techniques include active thermal management, integrated power smoothing, and mechanical stress releasing methods. These will be compared with alternative technologies that have been pursued by the consortium members and other researchers, such as gearless direct-drive systems, modular and fault tolerant designs and condition monitoring. The research will initially focus on wind turbines but will be extended to other forms of renewable electrical power generation including wave and tidal stream systems.Five UK and four Chinese universities as well as Chinese Academy of Sciences are initially included in the consortium which is strengthened by seven industrial partners from the two countries, in order to establish the expertise and facilities needed to address the multidisciplinary problem. The programme promotes essential and close interaction between the themes and the individual tasks. The interactions take a range of forms, from providing testing materials and facilities to the development of stress and reliability models for techniques for performance improvement. Chinese organisations will commit 9 PhD studentships to compliment the 7 themed PhD studentships in UK universities. The dissemination will involve academic publications, a dedicated website, consortium meetings, international seminars and events.

Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.