The strategic objective of this platform grant is to underpin Audio-Visual Media Research within the Centre for Vision, Speech and Signal Processing (CVSSP) to pursue fundamental research combining internationally leading expertise in understanding of real-world audio and visual data, and to transfer this capability to impact new application domains. Our goal is to pioneer new technologies which impact directly on industry practice in healthcare, sports, retail, communication, entertainment and training. This builds on CVSSP's unique track-record of world-leading research in both audio and visual machine perception which has enabled ground-breaking technology exploited by UK industry. The strategic contribution and international standing of the centres research in audio and visual media has been recognised by EPSRC through two previous platform grant awards (2003-14) and two programme grant awards in 2013 and 2015. Platform Grant funding is requested to reinforce the critical mass of expertise and knowledge of specialist facilities required to contribute advance in both fundamental understanding and pioneering new technology. In particular this Platform Grant will catalyse advances in multi-sensory machine perception building on the Centre's unique strengths in audio and vision. Key experienced post-doctoral researchers have specialist knowledge and practical know-how, which is an important resource for training new researchers and for maintaining cutting edge research using state-of-the-art facilities. Strategically the Platform Grant will build on recent independent advances in audio and visual scene analysis to lead multi-sensory understanding and modelling of real-world scenes. Research advances will provide the foundation for UK industry to lead the development of technologies ranging from intelligent sensing for healthcare and assisted living to immersive entertainment production. Platform Grant funding will also strengthen CVSSP's international collaboration with leading groups world-wide through extended research secondments US (Washington, USC), Asia (Tsinghua, Tianjin, Kyoto, Tokyo, KAUST) and Europe (INRIA, MPI, Fraunhofer, ETH, EPFL, KTH, CTU, UPF).

The SESAME consortium is a newly-formed multidisciplinary group that proposes to investigate the use of wireless sensor-based systems in enhancing the performance of elite athletes and young athletes who have been identified as having world class potential. The project has goals of enhancing performance, improving coach education, and advancing sports science. Despite a specific focus on athletics, the technical approach and its solutions will be deliberately generic, to enable their subsequent application to a wider range of training and healthcare scenarios. At present, only a limited set of sensing technologies are available for the coaching of elite athletes, including motion capture, fixed force plates and video recording for feedback. However, they often disrupt the sporting activity and the data they return are difficult to interpret to provide appropriate feedback. Wireless sensing technologies, ranging from accelerometry and magnetometry through to accurate positioning systems, have the capacity to revolutionise the field, by providing information about limb positioning and orientation, athlete location, muscular function, and physiological status, all in real time. Through the SESAME project, dynamic data will come from wearable non-intrusive sensors, augmented by passive video capture. Raw sensor data will be processed to extract meaningful information using a combination of sensor fusion and stochastic signal processing to derive information that is meaningful to coaches and athletes. This will take place in the knowledge that human biomechanics constrains movement and will take account of errors introduced by sensor attachment mechanisms and sensor mispositioning. Biomechanical and physiological performance models will be informed by captured sensor data, and from them idealised movements and the performance effects of deviations will be captured.A comprehensive study of human factors is essential if coaches and athletes are to derive real benefit from SESAME. Ethnographic studies will be undertaken with coaches - to build expert domain-specific knowledge, to capture their cognitive models of performance, and to assist in the design of user interfaces. Feedback to coaches and athletes will be in two forms: (i) graphical, both as a data stream that has been processed to respect the coaches' cognitive models and by overlaying sensor data on video; (ii) as real-time feedback if feasible: e.g. using buzzers. Analysis of an athlete's performance is not only a real-time activity: a definitive record of sensor data, decision support recommendations, medical advice and any clinical events will be maintained, allowing users to take account of relevant medical inputs. Such an approach also allows for comparative studies between athletes and the mining of such information both to improve biological performance models and to understand the effect of deviation from the ideal and precursors to injury. The focus of the work will be on running - specifically sprinting. However, given the national importance of the 2012 Olympic Games we will also explore the possibility of using the technology in other athletic disciplines, more general forms of exercise, and rehabilitation following injury. Should time permit, wider applications such as gait analysis for cerebral palsy patients will also be explored. Athletic training is a highly demanding application domain from the viewpoint of wireless sensor networking / it is necessary to develop and integrate novel sensors, QoS-driven real-time networking, and system autoconfiguration, all using an extensible generic software infrastructure. Consequently, solving problems in this challenging domain will provide a necessary building block for the solution of more generic problems in ubiquitous and sentient computing.The SESAME consortium contains a blend of expertise that is essential for progress in deploying technology in this domain.

The construction sector is strategically important to the UK economy, employing 3.1 million people (>9% of the workforce), producing £370 billion in turnover, and exporting more than £8 billion in products and services. However, its current philosophy is resource and cost inefficient and environmentally unsustainable, through its low productivity, slow technology adoption and tendency to demolish and rebuild. Metal 3D printing offers opportunities to solve these challenges and lead to a more productive, innovative and sustainable construction sector. Metal 3D printing technology has transformed other engineering disciplines, including the biomedical and aeronautical sectors, while its application within the construction sector is still in its infancy. The technology has been fundamentally proven through the MX3D Bridge, the first metal 3D printed structure that was opened in July 2021, however there are still a number of barriers preventing more widespread adoption. Current equipment and processes produce elements that have significant material and geometric variability, within the same build and between repeated builds, which is not optimal for real-world use. Furthermore, the limited availability of suitable printing equipment has prevented research into the development of this novel manufacturing technique and its applications to the construction sector. ICWAAM will be a globally unique metal 3D printing facility, dedicated to large-scale, cost-effective applications for the construction sector. It will offer new research capabilities into the printing process, automated manufacture and the repair and upgrade of our critical infrastructure, along with the printing of complex, materially efficient geometries, which are uneconomical or impossible with standard techniques. ICWAAM will fundamentally challenge the current philosophy of the construction industry and lead to its transformation into a more productive, innovative and sustainable sector, with increased worker safety. Without direct access to large-scale metal 3D printing equipment, such as ICWAAM, researchers are unable to undertake this critical research and development, to solve the longstanding challenges in the construction sector.

The SESAME consortium is a newly-formed multidisciplinary group that proposes to investigate the use of wireless sensor-based systems in enhancing the performance of elite athletes and young athletes who have been identified as having world class potential. The project has goals of enhancing performance, improving coach education, and advancing sports science. Despite a specific focus on athletics, the technical approach and its solutions will be deliberately generic, to enable their subsequent application to a wider range of training and healthcare scenarios. At present, only a limited set of sensing technologies are available for the coaching of elite athletes, including motion capture, fixed force plates and video recording for feedback. However, they often disrupt the sporting activity and the data they return are difficult to interpret to provide appropriate feedback. Wireless sensing technologies, ranging from accelerometry and magnetometry through to accurate positioning systems, have the capacity to revolutionise the field, by providing information about limb positioning and orientation, athlete location, muscular function, and physiological status, all in real time. Through the SESAME project, dynamic data will come from wearable non-intrusive sensors, augmented by passive video capture. Raw sensor data will be processed to extract meaningful information using a combination of sensor fusion and stochastic signal processing to derive information that is meaningful to coaches and athletes. This will take place in the knowledge that human biomechanics constrains movement and will take account of errors introduced by sensor attachment mechanisms and sensor mispositioning. Biomechanical and physiological performance models will be informed by captured sensor data, and from them idealised movements and the performance effects of deviations will be captured. A comprehensive study of human factors is essential if coaches and athletes are to derive real benefit from SESAME. Ethnographic studies will be undertaken with coaches - to build expert domain-specific knowledge, to capture their cognitive models of performance, and to assist in the design of user interfaces. Feedback to coaches and athletes will be in two forms: (i) graphical, both as a data stream that has been processed to respect the coaches' cognitive models and by overlaying sensor data on video; (ii) as real-time feedback if feasible: e.g. using buzzers. Analysis of an athlete's performance is not only a real-time activity: a definitive record of sensor data, decision support recommendations, medical advice and any clinical events will be maintained, allowing users to take account of relevant medical inputs. Such an approach also allows for comparative studies between athletes and the mining of such information both to improve biological performance models and to understand the effect of deviation from the ideal and precursors to injury. The focus of the work will be on running - specifically sprinting. However, given the national importance of the 2012 Olympic Games we will also explore the possibility of using the technology in other athletic disciplines, more general forms of exercise, and rehabilitation following injury. Should time permit, wider applications such as gait analysis for cerebral palsy patients will also be explored. Athletic training is a highly demanding application domain from the viewpoint of wireless sensor networking / it is necessary to develop and integrate novel sensors, QoS-driven real-time networking, and system autoconfiguration, all using an extensible generic software infrastructure. Consequently, solving problems in this challenging domain will provide a necessary building block for the solution of more generic problems in ubiquitous and sentient computing.The SESAME consortium contains a blend of expertise that is essential for progress in deploying technology in this domain.

The SESAME consortium is a newly-formed multidisciplinary group that proposes to investigate the use of wireless sensor-based systems in enhancing the performance of elite athletes and young athletes who have been identified as having world class potential. The project has goals of enhancing performance, improving coach education, and advancing sports science. Despite a specific focus on athletics, the technical approach and its solutions will be deliberately generic, to enable their subsequent application to a wider range of training and healthcare scenarios. At present, only a limited set of sensing technologies are available for the coaching of elite athletes, including motion capture, fixed force plates and video recording for feedback. However, they often disrupt the sporting activity and the data they return are difficult to interpret to provide appropriate feedback. Wireless sensing technologies, ranging from accelerometry and magnetometry through to accurate positioning systems, have the capacity to revolutionise the field, by providing information about limb positioning and orientation, athlete location, muscular function, and physiological status, all in real time. Through the SESAME project, dynamic data will come from wearable non-intrusive sensors, augmented by passive video capture. Raw sensor data will be processed to extract meaningful information using a combination of sensor fusion and stochastic signal processing to derive information that is meaningful to coaches and athletes. This will take place in the knowledge that human biomechanics constrains movement and will take account of errors introduced by sensor attachment mechanisms and sensor mispositioning. Biomechanical and physiological performance models will be informed by captured sensor data, and from them idealised movements and the performance effects of deviations will be captured. A comprehensive study of human factors is essential if coaches and athletes are to derive real benefit from SESAME. Ethnographic studies will be undertaken with coaches - to build expert domain-specific knowledge, to capture their cognitive models of performance, and to assist in the design of user interfaces. Feedback to coaches and athletes will be in two forms: (i) graphical, both as a data stream that has been processed to respect the coaches' cognitive models and by overlaying sensor data on video; (ii) as real-time feedback if feasible: e.g. using buzzers. Analysis of an athlete's performance is not only a real-time activity: a definitive record of sensor data, decision support recommendations, medical advice and any clinical events will be maintained, allowing users to take account of relevant medical inputs. Such an approach also allows for comparative studies between athletes and the mining of such information both to improve biological performance models and to understand the effect of deviation from the ideal and precursors to injury. The focus of the work will be on running - specifically sprinting. However, given the national importance of the 2012 Olympic Games we will also explore the possibility of using the technology in other athletic disciplines, more general forms of exercise, and rehabilitation following injury. Should time permit, wider applications such as gait analysis for cerebral palsy patients will also be explored. Athletic training is a highly demanding application domain from the viewpoint of wireless sensor networking / it is necessary to develop and integrate novel sensors, QoS-driven real-time networking, and system autoconfiguration, all using an extensible generic software infrastructure. Consequently, solving problems in this challenging domain will provide a necessary building block for the solution of more generic problems in ubiquitous and sentient computing.The SESAME consortium contains a blend of expertise that is essential for progress in deploying technology in this domain.