Experimental Equipment Call 2014
Lead Research Organisation:
University of Surrey
Department Name: DVC (Research and Innovation)
Abstract
As per advice from EPSRC, please see the attachments for a full description of the proposed research.
Planned Impact
As per advice from EPSRC, please see the attachments for the Pathways to Impact document which includes an impact summary.
People |
ORCID iD |
| Michael Kearney (Principal Investigator) |
Publications
Coleman P
(2018)
An Audio-Visual System for Object-Based Audio: From Recording to Listening
in IEEE Transactions on Multimedia
Fowler S
(2018)
Human-Centric Scene Understanding from Single View 360 Video
Gilbert A
(2020)
Inpainting of Wide-Baseline Multiple Viewpoint Video.
in IEEE transactions on visualization and computer graphics
Gilbert A
(2018)
Fusing Visual and Inertial Sensors with Semantics for 3D Human Pose Estimation
in International Journal of Computer Vision
Hilton A
(2018)
AVSU
Iwaya LH
(2023)
On the privacy of mental health apps: An empirical investigation and its implications for app development.
in Empirical software engineering
Kim H
(2021)
Acoustic Room Modelling Using 360 Stereo Cameras
in IEEE Transactions on Multimedia
Kim H
(2018)
Multimodal Visual Data Registration for Web-Based Visualization in Media Production
in IEEE Transactions on Circuits and Systems for Video Technology
| Description | Establishment of the first multiple camera 4K Ultra high-definition studio facility in the UK to support research with the creative industries. This provides the platform to underpin existing research and has been leveraged to initiate new research in VR content production and light-field cameras in collaboration with world-leading companies in the creative industries. Portable multiple camera acquisition hardware enabling initiation of research in non-contact monitoring of people for applications in healthcare with the Surrey Sleep Research Centre and Surrey Clinical Research Centre. |
| Exploitation Route | Portable multiple camera acquisition hardware enabling initiation of research in non-contact monitoring of people for applications in healthcare with the Surrey Sleep Research Centre and Surrey Clinical Research Centre. |
| Sectors | Creative Economy,Digital/Communication/Information Technologies (including Software),Healthcare |
| Description | The EPSRC Audio-Visual Platform Grant funding has enabled initiation of collaboration with the Surrey Sleep Research Centre investigating non-contact methods for monitoring of people during sleep. Audio-visual sensing will enable characterisation of sleep patterns and behaviour from sound and motion. The use of non-contact sensing will allow deployment of sleep monitoring in peoples homes. Initial collaboration is developing and evaluating non-contact sensing methods against gold-standard contact sensing which can only be used in controlled environments. The EPSRC Equipment Refresh funding has enabled internal collaborations between the Surrey Sleep Research Centre, CVSSP, and the School of Psychology. The Grant has also enabled collaborations with the University of Oxford and Imperial College London. All this research is focussed on investigating novel methods to record and manipulate sleep in the laboratory and at home. Methods include video analysis of sleep and neuromodulation through phase locked auditory stimulation. Importantly, the University of Surrey is now part of the UK Dementia Research Institute and the research led by UoS will be based to a large extent on our capability, enabled by the equipment grant, to develop and evaluate non-contact sensing methods against gold-standard contact sensing which can only be used in controlled environments. The use of non-contact sensing will allow sleep monitoring in dementia in the home environment. ' The Equipment refresh has also enabled CVSSP to develop a new generation of research into non-contact measurement of human skeletal and surface motion. This has resulted in the first real-time portable technology for accurate non-contact measurement of skeletal motion from video. The technology has enabled for the first time measurement of human motion in unconstrained situations such as outdoor scenes for use in film and games content production. The technology is also being transferred for human movement measurement in healthcare applications in collaboration with the Surrey Sleep Research Centre and for measurement of movement in animals for health and welfare applications. This has provided the infrastructure for a number of new projects including the EPSRC Audio-Visual Research Platform Grant, InnovateUK Polymersive Project in collaboration with the BBC on advanced immersive content production, and the award of two prestigious personal fellowship to Dr Armin Mustafa Royal Academy of Engineering Fellowship in 4D Visual Perception and Dr Charles Malleson Leverhulme Early Career Research Fellowship in Non-contact Measurement of Animal Motion. This will utilise the multiple camera capture to open up new research directions and application for video-based understanding of dynamic scenes and human movement. |
| First Year Of Impact | 2018 |
| Sector | Creative Economy,Healthcare |
| Impact Types | Cultural,Societal,Economic,Policy & public services |
| Description | Ammo - Tracking and understanding animal motion in the wild |
| Amount | £93,000 (GBP) |
| Organisation | The Leverhulme Trust |
| Sector | Charity/Non Profit |
| Country | United Kingdom |
| Start | 10/2019 |
| End | 09/2022 |
| Description | Audio-Visual Media Research Platform |
| Amount | £1,577,223 (GBP) |
| Funding ID | EP/P022529/1 |
| Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
| Sector | Public |
| Country | United Kingdom |
| Start | 08/2017 |
| End | 07/2022 |
| Description | Collaborative R&D |
| Amount | £593,355 (GBP) |
| Funding ID | 102685 |
| Organisation | Innovate UK |
| Sector | Public |
| Country | United Kingdom |
| Start | 07/2016 |
| End | 12/2017 |
| Description | Collaborative R&D |
| Amount | £560,225 (GBP) |
| Funding ID | 102686 |
| Organisation | Innovate UK |
| Sector | Public |
| Country | United Kingdom |
| Start | 07/2016 |
| End | 12/2017 |
| Description | Engineering Integrated Dementia cAre (EIDA) |
| Amount | £20,000,000 (GBP) |
| Organisation | UK Dementia Research Institute |
| Sector | Charity/Non Profit |
| Country | United Kingdom |
| Start | 06/2019 |
| End | 06/2025 |
| Description | Platform Grant |
| Amount | £1,539,409 (GBP) |
| Funding ID | EP/P022529/1 |
| Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
| Sector | Public |
| Country | United Kingdom |
| Start | 05/2017 |
| End | 04/2022 |
| Description | Polymersive Immersive Video Production for Live Events - Innovate-UK - Audience of the Future call |
| Amount | £276,042 (GBP) |
| Organisation | Innovate UK |
| Sector | Public |
| Country | United Kingdom |
| Start | 04/2019 |
| End | 09/2020 |
| Description | Polymersive: Immersive Video Production Tools for Studio and Live Events |
| Amount | £726,251 (GBP) |
| Funding ID | 105168 |
| Organisation | Innovate UK |
| Sector | Public |
| Country | United Kingdom |
| Start | 03/2019 |
| End | 09/2020 |
| Description | Alive Collaboration |
| Organisation | Figment Productions Limited |
| Country | United Kingdom |
| Sector | Private |
| PI Contribution | The portable capture equipment is being used for non-contact monitoring and measurement of people and is supporting both new collaboration and initiation of new collaboration in the healthcare sector. This has resulted in several new collaborative grant awards of which ALIVE is one. |
| Collaborator Contribution | The collaborative partnership aims to make it possible to create immersive Virtual Reality experiences that use live action video , by using light field capture technology. |
| Impact | InnovateUK ALIVE Collaboration with the UK Creative Industries (The Foundry, Figment Productions) which has introduced light-field camera technology (portable cameras arrays) to produce high-quality dynamic 3D content of actor performance. This has enable the production of video-quality immersive VR content with actor performance. Novel methods have been introduced to enable robust reconstruction and segmentation of actors from multiple moving cameras. Our research is developing methods to efficiently reconstruct and represent dynamic actor content which allow rendering within a VR platform. This represents a break through in content production for VR which allows the user to move within the virtual space whilst maintaining the visual quality. |
| Start Year | 2016 |
| Description | Alive Collaboration |
| Organisation | The Foundry Visionmongers Ltd |
| Country | United Kingdom |
| Sector | Private |
| PI Contribution | The portable capture equipment is being used for non-contact monitoring and measurement of people and is supporting both new collaboration and initiation of new collaboration in the healthcare sector. This has resulted in several new collaborative grant awards of which ALIVE is one. |
| Collaborator Contribution | The collaborative partnership aims to make it possible to create immersive Virtual Reality experiences that use live action video , by using light field capture technology. |
| Impact | InnovateUK ALIVE Collaboration with the UK Creative Industries (The Foundry, Figment Productions) which has introduced light-field camera technology (portable cameras arrays) to produce high-quality dynamic 3D content of actor performance. This has enable the production of video-quality immersive VR content with actor performance. Novel methods have been introduced to enable robust reconstruction and segmentation of actors from multiple moving cameras. Our research is developing methods to efficiently reconstruct and represent dynamic actor content which allow rendering within a VR platform. This represents a break through in content production for VR which allows the user to move within the virtual space whilst maintaining the visual quality. |
| Start Year | 2016 |
| Description | Total Capture Collaboration |
| Organisation | Numerion Software Limited |
| Country | United Kingdom |
| Sector | Private |
| PI Contribution | The portable capture equipment has been used for non-contact monitoring and measurement of people, and is supporting both new collaboration and the initiation of new collaboration in the healthcare sector. This has resulted in several new collaborative grant awards of which Total Capture is one. |
| Collaborator Contribution | The Innovate UK Total Capture Collaboration with the UK Creative Industries (The Imaginarium, Numerion) is developing actor performance capture combining video and accelerometer measurements to overcome the restrictions and limitations of existing optical marker based motion capture technologies. |
| Impact | This research has introduced methods to combine video and sensor data which achieve a comparable accuracy and computational performance to state-of-the-art motion capture systems. The approach has a significant advantage over existing technologies overcoming the problems of visual occlusion and close object contact which result in errors in state-of-the-art technologies. The system under development will be deployed in content production for film and games. |
| Start Year | 2016 |
| Description | Total Capture Collaboration |
| Organisation | The Imaginarium Studios Limited |
| Country | United Kingdom |
| Sector | Private |
| PI Contribution | The portable capture equipment has been used for non-contact monitoring and measurement of people, and is supporting both new collaboration and the initiation of new collaboration in the healthcare sector. This has resulted in several new collaborative grant awards of which Total Capture is one. |
| Collaborator Contribution | The Innovate UK Total Capture Collaboration with the UK Creative Industries (The Imaginarium, Numerion) is developing actor performance capture combining video and accelerometer measurements to overcome the restrictions and limitations of existing optical marker based motion capture technologies. |
| Impact | This research has introduced methods to combine video and sensor data which achieve a comparable accuracy and computational performance to state-of-the-art motion capture systems. The approach has a significant advantage over existing technologies overcoming the problems of visual occlusion and close object contact which result in errors in state-of-the-art technologies. The system under development will be deployed in content production for film and games. |
| Start Year | 2016 |