Ordnance Survey - English
Microsoft and Ordnance Survey join forces to teach machines how to identify types of roofs
Machine goes from zero to 87% accuracy in five days.
The hack, featuring software engineers from Microsoft who had travelled from across Europe and Africa to work with OS’s machine learning team, used the city of Hull as a testbed. The trained machine model finished the week by correctly identifying 87% of the roof types it was shown.
In its training the model was shown 500 flat roofs and 500 hipped/gabled roofs, set a confidence limit of 90%, which means it must be 90% confident or more for its assessment to count.
Isabel Sargent, Senior Research and Development Scientist at OS, says: “Thanks to the excellence of the Microsoft team we have been able to work out together how to stream this machine captured data into our database for if and when we’re ready to put machine learning into production. It’s already very accurate, going from zero to 87% accuracy in just one week, but we need to increase its success rate. Although much slower, humans typically have an error rate of around 5%.”
In the time it takes a human to classify roof types in a single image, a machine can process thousands of images. It is thought it would take the machine less than a day to classify all 35,700,655 properties in Great Britain and their roof types. This enhanced level of detail could inform insurance companies to help them produce more accurate risk assessment.
Isabel continues: “We now have a machine training system that can be trained to classify almost anything, such as bodies of water for example, and on top of this, the machine can be set to run hundreds of these classification queries simultaneously.
“While it can take time to teach a machine, once that deep learning is done the classification algorithm is there ready to decode the landscape. This has the possibility to significantly increase the efficiency of our surveying operations – freeing up the surveyors we have on the ground to focus on those complex tasks for which there is no AI assistance. We would not have been able to achieve this breakthrough so quickly without Microsoft, and we’re thrilled for the future by the potential of what our collaboration has achieved.”
“The week-long hack we’ve conducted with Ordnance Survey demonstrates the potential benefits that artificial intelligence can bring to people in a broad mix of roles,” says Gina Dragulin, Audience Evangelist, Microsoft UK.
“Our own research (PDF) recently identified that workers believe that more than a third (36%) of tasks they carry out on a regular basis would benefit from intelligent automation. This hack is a perfect example of the value that could be created for Ordnance Survey surveyors if they were able to eliminate time-intensive tasks, such as roof-type identification, from their day-to-day activities, enabling them to focus on more complex tasks that require the type of high-level decision making and judgement calls that only an expert can make.”
This work follows on from a project for the Rural Payments Agency that saw OS utilise machine learning to automate the identification and mapping of 373,919km of England’s farmland hedges. The project produced consistent results and proved more cost effective and efficient than manual data capture. To help the UAE better manage Climate Change and its natural resources, OS has developed a machine learning process to identify palm trees from satellite imagery.
For more information:
Contact: Keegan Wilson, Senior Press Officer
Phone: (+44) 02380 055332
Latest News from
Ordnance Survey - English
Indispensable app for walkers to navigate Northern Ireland launched02/08/2022 12:20:00
Northern Irish walkers can plot and follow routes digitally around the nation’s loughs, hills and valleys using the most detailed topographic mapping for the first time on the OS Maps app.
Halifax pupil wins Ordnance Survey national Moon Map symbol competition27/07/2022 10:05:00
A year 10 pupil from Trinity Academy in Halifax has won our national Moon Map symbol competition.
OS research shows sustainability projects drive better opportunities for software developers13/07/2022 14:20:00
UK efforts to reduce transport emissions has driven up demand for developers who can support the roll out of electric vehicles (EVs) and other forms of sustainable transport.
Have we all lost our sense of direction?12/07/2022 12:20:00
With National Map Reading Week taking place from Monday July 11, latest survey results from OS reveal just how cautious British adults are about getting lost and exploring off the beaten track.
From Government to start-ups, the OS Data Hub delivers value to thousands of new customers08/07/2022 10:15:00
The OS Data Hub emerged from April 2020’s Geospatial Commissions Public Sector Geospatial Agreement (PSGA). It was developed with the aim of delivering a positive impact to all areas of government; as well as supporting businesses, developers, and new, emerging markets/users.
OS launches new virtual national work experience programme for year 10 students05/07/2022 16:05:00
OS has launched its inaugural geospatial virtual work experience programme that will be accessed by year 10 students across the country.
Ordnance Survey supports the British Heart Foundation’s national database of defibrillators04/07/2022 13:15:00
Ordnance Survey (OS) has supported the British Heart Foundation (BHF) in ensuring that the national database of defibrillators used by the UK’s ambulance services has access to complete and accurate address data including unique property reference numbers (UPRN) and additional attributes to identify a property and locate it on a map with precision.
Young people doing their Duke of Edinburgh’s Award (DofE) get new mapping boost from OS16/06/2022 13:15:00
Planning expeditions for Bronze, Silver and Gold Awards has never been easier as OS mapping is made available to young people doing their DofE.