Visual Media Research Platform Grant

Lead Research Organisation: University of Surrey
Department Name: Vision Speech and Signal Proc CVSSP

Abstract

The Visual Media Platform Grant awarded in 2003 has successfully underpinned the expansion of Visual Media Research within CVSSP by supporting key experienced post-doctoral research personnel on a stable long-term basis. Strategically the platform grant has allowed the flexibility to pursue adventurous research providing the foundation to initiate a number of new research projects and collaborations with both industry and international research groups. Stable support of a critical-mass of experience has led to the groups research grant portfolio doubling over the period 2003-07. In addition the platform grant has directly contributed to pioneering two new technologies leading to commercial exploitation: 3D video capture of facial dynamics; and whole-body surface motion capture. The platform grant has allowed the initiation of a number of international collaborations with leading research teams in the US, Europe and Japan. EPSRC platform grant support for Visual Media Research has been pivotal to meeting the strategic objective of increasing the international profile and impact of the research group and individual researchers by enabling adventurous research contributing step changes to the state-of-the-art.The strategic objective of the platform grant renewal is for the Visual Media Research within CVSSP to lead fundamental research internationally to pioneer new technologies which impact directly on industry practice. This will build on the proven success of the platform grant awarded in 2003 as a mechanism for supporting long-term research continuity of key post-doctoral researchers, pursuing adventurous research to initiate new research directions and contributing advances to the leading edge internationally . Renewal of the platform grant is requested to continue to reinforce the critical mass of expertise and knowledge of specialist facilities required to contribute advances in both fundamental understanding and pioneering new technology. Strategically the platform grant renewal aims to build on recent advances in dynamic scene analysis towards understanding and modelling real-world scenes. Increasing relevance and collaboration with the UK entertainment and communications industries, and focusing on international collaborations initiated under the existing platform grant with leading groups in the US (Washington), Japan (Kyoto) and Europe(INRIA,MPI,EPFL,KTH,CTU).

Publications

10 25 50
 
Description Advances in computer vision from controlled static laboratory conditions to highly dynamic scene enabling visual reconstruction and scene understanding for applications ranging from healthcare to entertainment content production.
Exploitation Route research has been widely disseminated to the public and policy makers as well as the academic community and industry
Sectors Creative Economy,Digital/Communication/Information Technologies (including Software),Electronics,Healthcare,Culture, Heritage, Museums and Collections,Security and Diplomacy

URL http://www.surrey.ac.uk/cvssp
 
Description Advanced computer vision and machine learning methods with application for entertainment content production, biometrics, security, healthcare, human-computer interaction and visual communication.
First Year Of Impact 2008
Sector Creative Economy,Digital/Communication/Information Technologies (including Software),Education,Healthcare,Culture, Heritage, Museums and Collections
Impact Types Cultural,Societal,Economic

 
Description ARCHANGEL - Trusted Archives of Digital Public Records
Amount £487,428 (GBP)
Funding ID EP/P03151X/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Public
Country United Kingdom
Start 06/2017 
End 06/2019
 
Description Audio and Video Based Speech Separation for Multiple Moving Sources Within a Room Environment
Amount £359,529 (GBP)
Funding ID EP/H050000/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Public
Country United Kingdom
Start 10/2010 
End 09/2013
 
Description Body Shape Recognition for Online Fashion
Amount £148,661 (GBP)
Funding ID EP/I031936/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Public
Country United Kingdom
Start 10/2011 
End 09/2013
 
Description Face Matching for Automatic Identity Retrieval, Recognition, Verification and Management
Amount £6,104,265 (GBP)
Funding ID EP/N007743/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Public
Country United Kingdom
Start 01/2016 
End 09/2021
 
Description Free-viewpoint Video for Interactive Entertainment Production
Amount £134,237 (GBP)
Funding ID EP/D033926/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Public
Country United Kingdom
Start 05/2006 
End 04/2009
 
Description Learning to Recognise Dynamic Visual Content from Broadcast Footage
Amount £489,782 (GBP)
Funding ID EP/I011811/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Public
Country United Kingdom
Start 09/2011 
End 02/2016
 
Description Multimodal Video Search by Examples (MVSE)
Amount £863,564 (GBP)
Funding ID EP/V002856/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Public
Country United Kingdom
Start 09/2020 
End 09/2023
 
Description Next Stage Digital Economy Centre in the Decentralised Digital Economy (DECaDE)
Amount £3,816,713 (GBP)
Funding ID EP/T022485/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Public
Country United Kingdom
Start 09/2020 
End 09/2025
 
Description Prevention is Better than Cure: Crime Prevention & Detection using in-depth Face Recognition - 2D+3D=ID
Amount £292,661 (GBP)
Funding ID GR/S98528/01 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Public
Country United Kingdom
Start 06/2004 
End 12/2007
 
Description RetinaScan: AI-enabled automated image assessment system for diabetic retinopathy screening
Amount £791,559 (GBP)
Funding ID 104184 
Organisation Innovate UK 
Sector Public
Country United Kingdom
Start 03/2018 
End 08/2020
 
Description Reverse Storyboarding for Video Content Based Retrieval
Amount £124,590 (GBP)
Funding ID EP/D055032/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Public
Country United Kingdom
Start 12/2006 
End 05/2009
 
Description Reverse Storyboarding for Video Content Based Retrieval
Amount £22,450 (GBP)
Funding ID EP/D055032/2 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Public
Country United Kingdom
Start 06/2009 
End 10/2009
 
Description Shape and Reflectance Acquisition of Complex Dynamic Scenes
Amount £99,140 (GBP)
Funding ID EP/M021793/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Public
Country United Kingdom
Start 06/2015 
End 05/2017
 
Description TAPESTRY: Trust, Authentication and Privacy over a DeCentralised Social Registry
Amount £854,808 (GBP)
Funding ID EP/N02799X/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Public
Country United Kingdom
Start 01/2017 
End 09/2020
 
Title Multiview and 4D Video 
Description Multiple view video datasets and reconstructed 4D models 
Type Of Material Database/Collection of data 
Provided To Others? Yes  
Impact Data available is used by over 300 research groups worldwide. It is considered the benchmark dataset for research in this field. 
URL http://cvssp.org/data/cvssp3d/
 
Description Anthropics Technology Ltd 
Organisation Anthropics Technology
Country United Kingdom 
Sector Private 
Start Year 2005
 
Description Avatarme Ltd 
Organisation Avatarme
Country United Kingdom 
Sector Private 
Start Year 2004
 
Description BBC Research and Development 
Organisation British Broadcasting Corporation (BBC)
Country United Kingdom 
Sector Public 
PI Contribution Research in Computer Vision for broadcast production and Audio. Technologies for 3D production, free-view point video in sports, stereo production from monocular cameras, video annotation Member of the BBC Audio Research Partnership - developing the next generation of broadcast technology.
Collaborator Contribution In kind contribution (members of Steering/Advisory Boards) Use of the BBC lab and research/development facilities. Studentships (industrial case) funding and co-supervision of PhD students.
Impact Multi-disciplinary collaboration involves Computer Vision, Video Analysis, Psychoacoustics, Signal Processing and Spatial Audio
 
Description Snell & Wilcox Ltd 
Organisation Snell & Wilcox Ltd
Country United Kingdom 
Sector Private 
Start Year 2006
 
Description Sony Broadcast and Professional Europe 
Organisation SONY
Department Sony Broadcast and Professional Europe
Country United Kingdom 
Sector Private 
Start Year 2004