Using aerial photography and AI to classify buildings

48
aerial photography,

A new joint venture between the University of Leicester and Bluesky International will harness aerial photography and AI to develop new geospatial data products

Project team: Bluesky International, University of Leicester

Location: UK

Completion: Ongoing

The University of Leicester and aerial mapping company Bluesky International are partnering in a joint venture to develop a new portfolio of geospatial data products.

Using machine learning and Artificial Intelligence, combined with satellite imagery and aerial survey data, it is hoped the project, which is funded by the Space Research & Innovation Network for Technology (SPRINT), will improve the analysis of key urban environmental data to automatically recognise building classifications and structure detail.

“We were keen to explore the potential of AI and machine learning for the automatic identification and classification of data for use within the insurance sector,” said James Eddy, technical director of Bluesky International.

“So, having strong ties with the academic community having worked alongside university and higher education organisations on other projects, we approached the University of Leicester.

“Directed to the School of Mathematics & Actuarial Science, we were introduced to SPRINT. The space-based aspect means we can use mathematical methods to look at data in different forms and, by the end of this project, we hope to develop a technique to extract data and produce it commercially for a range of sectors.”

Satellite datasets

Ivan Tyukin, professor of applied mathematics at the University of Leicester, said: “Satellite data is an extremely valuable resources, and the volume of this data grows very fast. It is hence important to develop methods enabling organisations to utilise this wealth of resources in the most efficient and reliable way.

“In our project, we will employ state-of-the-art machine learning techniques to extract information from available satellite datasets and fuse this extracted information with Bluesky’s own proprietary data to increase Bluesky’s data analysis capabilities.”

Bluesky is an established provider of geospatial data including nationwide coverage of high-resolution aerial photography and 3D height models. Working alongside academics from the mathematics department, it is hoped this project will leverage the University of Leicester’s deep expertise in object classification systems, as applied to satellite remotely sensed data. Aerial imagery, from visible and infrared sensors, can then be used, in isolation and combination, to deliver a robust, high confidence intelligence service.

The Bluesky/University of Leicester project will be funded by a grant from the £4.8m SPRINT programme. SPRINT provides unprecedented access to university space expertise and facilities, helping business with the commercial exploitation of space data and technologies.

 

SPRINT (Space Research & Innovation Network for Technology) is supported by Research England and the Scottish Funding Council. It is being delivered by a consortium of five of the UK’s leading space universities; led by the University of Leicester and including the University of Edinburgh, The Open University, University of South and University of Surrey. A Connecting Capability Fund, SPRINT enables SMEs to access the Higher Education Knowledge base and resources.

 

 

James Eddy

Technical director

Bluesky International

Tel: +44 (0)1530 518 518

info@bluesky-world.com

www.bluesky-world.com

 

Ivan Tyukin

Professor of applied mathematics

University of Leicester

Tel: +44 (0)116 229 7407

I.Tyukin@le.ac.uk

www.le.ac.uk

LEAVE A REPLY

Please enter your comment!
Please enter your name here