I-Lab: Visual Search and Understanding
Deep learning for visual analysis and semantic understanding.
Impact: World-leading image/video recognition/AI technology
- Visual search technologies used by the BBC, RAI television, Metropolitan Police
- Underpin international standards (ISO MPEG) for fast media search (CVDS and CDVA)
- Spin-out Visual Atoms (face verification)
- Gold medal in Google-Kaggle YouTube video understanding challenge (#7 out of 680 teams
- globally).
Current activities
- Ultra fast recognition of any object, landmark, pattern in billion-scale databases
- Video semantic understanding
- Big Visual Data Analysis (security, media, industry, cyber)
- Applications to medical image/video analysis.
Current larger projects
- InnovateUK: iTravel (2017-2019) - Surrey-Visual Atoms - iGeolise (£893k) “A Virtual Journey Assistant”
- InnovateUK: RetinaScan (2018-2020) – Surrey – Retinopathy Answer Ltd.(£993k) “RetinaScan: AI enabled automated image assessment system for diabetic retinopathy screening”
- BRIDGET H2020: (2014-2017) – Surrey–Huawei-RAI-Telecom Italia (£3.8m) “Bridging the gap for enhanced broadcast.”
Example applications
- Visual recognition for RAI/BBC (mentioned in our impact at the top of the page)
- Suspect search for Scotland Yard.
Research lead
Partners
