Reference · built on requestCommons signalPlaces & geographic reference

Microsoft Global ML Building Footprints

Over one billion computer-vision building footprint polygons extracted from satellite and aerial imagery by Microsoft.

Request accessPricing ↗

About

Microsoft Global ML Building Footprints is an open geospatial dataset containing over one billion building outline polygons extracted from high-resolution satellite and aerial imagery. Using computer vision models applied to Bing Maps imagery, Microsoft digitized structural footprints across North America, South America, Europe, Africa, Asia, and Australia. The dataset is partitioned by country and Bing Maps quadkey tiles, distributed as line-delimited GeoJSON files.

Through Fibric, an operator queries physical building boundaries and structural footprints for facility sites, proposing delivery entrance coordinates or verifying property structures for asset management.

This is a reference listing. It documents what Fibric would read from Microsoft Global ML Building Footprints and what it could propose, based on the publisher's published interfaces. Fibric builds it under a managed deployment when you request it; selecting it here installs nothing.

Inputs

  • Building outline polygon geometries formatted in standard GeoJSON coordinates
  • Country-level dataset partitions and Bing Maps quadkey spatial indexing tiles
  • Structural presence verification derived from deep neural network imagery segmentation
  • Direct file access to open datasets hosted on public cloud storage
  • Geographic coverage spanning over one hundred and fifty countries worldwide

Proposed actions

Read-only. This feed informs operators; it changes nothing.

Proposed actions are target capabilities. Every action runs propose-first and needs a validated deployment and the appropriate permissions.

What you can build

  • Verify structural presence for new facility sites

    Check proposed commercial delivery or charging station coordinates against building footprints, proposing confirmed physical structure outlines for site plans.

    With Site Benchmark, Address Repair

  • Pinpoint delivery vehicle parking and dock doors

    Overlay building polygon perimeters with vehicle GPS breadcrumbs, proposing refined delivery dock drop-off points for freight drivers.

    With Field Dispatch, Route Deviation

  • Assess rooftop solar surface availability

    Extract building footprint surface areas across facility portfolios, proposing preliminary rooftop square footage estimates for solar evaluation teams.

    With Site Benchmark

Requirements

  • Spatial parsing capability for large line-delimited GeoJSON (GeoJSONL) files
  • Bing Maps quadkey tile conversion or spatial indexing to extract local areas of interest
  • Attribution under the Community Data License Agreement - Permissive - Version 2.0
Authentication
None. Microsoft Global ML Building Footprints are open datasets hosted on public Azure cloud storage with no registration or API keys required.

Limits

  • Building outlines are computer-vision extractions and may contain occasional visual artifacts or omit tree-covered structures
  • Footprints do not include building height, occupancy, or postal address metadata
  • Datasets are distributed as bulk downloadable files rather than an interactive REST point search API

Access and pricing

Reference listing. Public feed access is separate from Fibric integration. If you request this feed, your quote covers the build, usage, and support.

Request Microsoft Global ML Building Footprints ↗

Questions and answers

How were the building footprints generated?
Microsoft trained deep convolutional neural networks to perform semantic segmentation on high-resolution satellite and aerial imagery, followed by polygonization algorithms to extract crisp building outlines.
What license governs the Microsoft Building Footprints dataset?
The dataset is released under the Community Data License Agreement - Permissive - Version 2.0 (CDLA-Permissive-2.0), permitting open use, sharing, and commercial modification.
How are files partitioned for download?
Files are partitioned by country and administrative region, and further subdivided using Bing Maps quadkeys to enable downloading specific regional tiles without fetching entire national files.
Ask about Microsoft Global ML Building Footprints

Ask about the capabilities and requirements in this listing.

For project-specific requirements, contact Fibric.

This Commons signal listing is developed, published, and supported by Fibric. It reads public data published by Microsoft (github.com/microsoft/GlobalMLBuildingFootprints). Upstream agencies and projects are the property of their respective owners, who are not affiliated with Fibric and do not sponsor or endorse this listing. Trademark policy