Building footprint dataset uses AI to map structure outlines across US
Powered by deep neural networks, the National Building Map product also includes accurate locations and addresses to support enhanced routing and rooftop-accurate geocoding for millions of properties across the country. The AI-based approach, says the company, allows it to repeatedly extract building footprints from newer imagery that removes older buildings and adds newer construction to create a consistently updated snapshot of the built environment in the US.
The building polygon data has an average accuracy of 98% and is updated every three months. The Geographic Information System (GIS)-ready building footprints, says the company, will help support better decision making in applications like insurance risk assessment and 911 response and routing that need accurate location data on built-up areas.
In addition to providing universal addresses and geographic coordinates for all structures, the company says it can also extract additional property attributes on demand such as roof form, building elevation, eave height etc., by exploiting available Lidar for most regions in the US.
“Our goal is to create and maintain state/national level building data with a unique and consistent attribute set,” says EarthDefine CEO, Vikalpa Jetly. “We are achieving this best-in-class building footprint dataset through applying advancements in artificial intelligence (AI) to high resolution aerial imagery.”
“By constantly refining our algorithms and applying them to newer imagery every few months, we are able to provide building location intelligence that will remain current and useful for a range of GIS applications. For example, in our upcoming quarterly update, we will revise and re-map the majority of the buildings in the country using aerial imagery flown within the last 12 months.”
The company says it also has the largest archive of high-resolution tree canopy and land cover data for the US that can be used to geo-enrich the building polygons in unique ways.
Related articles:
DARPA taps geospatial analytics startup for cloud data marketplace
New IBM analytics service takes geospatial-temporal data ‘out of the dark’
Street-level analytics startup accelerates 3D reality capture plans
Linux urban computing effort targets connected cities
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
