Worldwide building footprints derived from satellite imagery
OTHER License
Bing Maps is releasing open building footprints around the world. We have detected 1.4B buildings from Bing Maps imagery between 2014 and 2024 including Maxar, Airbus, and IGN France imagery. The data is freely available for download and use under ODbL. This dataset includes our other releases.
You can download the layer above as GeoJSON here.
You can download the layer above as GeoJSON here.
This data is licensed by Microsoft under the Open Data Commons Open Database License (ODbL).
999M building footprint polygon geometries located around the world in line delimited GeoJSON format. Due to the way we process the data, file extensions are .csv.gz
see make-gis-friendly.py for an example of how to decompress and change file extension.
As of October 2022, we moved the location table to dataset-links.csv since it's over 19k records with country-quadkey partitioning.
GeoJSON is a format for encoding a variety of geographic data structures. For intensive documentation and tutorials, refer to this blog.
Microsoft has a continued interest in supporting a thriving OpenStreetMap ecosystem.
Maybe. Never overwrite the hard work of other contributors or blindly import data into OSM without first checking the local quality. While our metrics show that this data meets or exceeds the quality of hand-drawn building footprints, the data does vary in quality from place to place, between rural and urban, mountains and plains, and so on. Inspect quality locally and discuss an import plan with the community. Always follow the OSM import community guidelines.
Yes. The HOT Tasking Manager has integrated Facebook Rapid where the data has been made available.
The building extraction is done in two stages:
We trained a neural network to estimate height above ground using imagery paired with height measurements, and then we take the average height within a building polygon. Structures without height estimates are populated with a -1. Height estimates are in meters.
Confidence scores are between 0 and 1 and can be read as percent confidence. For structures released before this update, we use -1 as a placeholder value. A confidence value of 0.8 is read as "80% confidence." Higher values mean higher detection confidence. There are two stages in the building detection process -- first we use a model to classify pixels as either building or not and next we convert groups of pixels into polygons. Each pixel has a probability of being a building and a probability >0.5 is classified as "building pixel". When we generate the polygons, we then look at the pixels within and average the probability values to give and overall confidence score. The confidence scores are for the footprint and not height estimate.
We did not apply any modeling improvements for this release. Instead, we focused on scaling our approach to increase coverage, and trained models regionally.
The evaluation metrics are computed on a set of building polygon labels for each region. Note, we only have verification results for Mexico buildings since we did not train a model for the country.
Building match metrics on the evaluation set:
Region | Precision | Recall |
---|---|---|
Africa | 94.4% | 70.9% |
Caribbean | 92.2% | 76.8% |
Central Asia | 97.17% | 79.47% |
Europe | 94.3% | 85.9% |
Middle East | 95.7% | 85.4% |
South America | 95.4% | 78.0% |
South Asia | 94.8% | 76.7% |
We track the following metrics to measure the quality of matched building polygons in the evaluation set:
Region | IoU | Rotation error [deg] |
---|---|---|
Africa | 64.5% | 5.67 |
Caribbean | 64.0% | 6.64 |
Central Asia | 68.2% | 6.91 |
Europe | 65.1% | 10.28 |
Middle East | 65.1% | 9.3 |
South America | 66.7% | 6.34 |
South Asia | 63.1% | 6.25 |
False positives are estimated per country from randomly sampled building polygon predictions.
Region | Buildings Sampled | False Positive Rate | Run Date |
---|---|---|---|
Africa | 5,000 | 1.1% | Early 2022 |
Caribbean | 3,000 | 1.8% | Early 2022 |
Central Asia | 3,000 | 2.2% | Early 2022 |
Europe | 5,000 | 1.4% | Early 2022 |
Mexico | 2,000 | 0.1% | Early 2022 |
Middle East | 7,000 | 1.8% | Early 2022 |
South America | 5,000 | 1.7% | Early 2022 |
South Asia | 7,000 | 1.4% | Early 2022 |
North America | 4,000 | 1% | Oct 2022 |
Europe Maxar | 5,000 | 1.4% | July 2022 |
Vintage of extracted building footprints depends on the vintage of the underlying imagery. The underlying imagery is from Bing Maps including Maxar and Airbus between 2014 and 2021.
Our metrics show that in the vast majority of cases the quality is at least as good as hand digitized buildings in OpenStreetMap. It is not perfect, particularly in dense urban areas but it provides good recall in rural areas.
EPSG: 4326
Maybe. This is a work in progress. Also, check out our other building releases!
We excluded imagery from processing if tiles were dated before 2014 or there was a low-probability of detection. Detection probability is loosely defined here as proximity to roads and population centers. This filtering and tile exclusion results in squares of missing data.
Some files are very large but they are stored in line-delimited format so one could use parallel processing tools (e.g., Spark, Dask) or create a memory
efficient script to segment into smaller pieces. See scripts/read-large-files.py
for a Python example.
Check out our ML Road Detections project page!
This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.microsoft.com.
When you submit a pull request, a CLA-bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., label, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.
This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact [email protected] with any additional questions or comments.
Microsoft, Windows, Microsoft Azure and/or other Microsoft products and services referenced in the documentation may be either trademarks or registered trademarks of Microsoft in the United States and/or other countries. The licenses for this project do not grant you rights to use any Microsoft names, logos, or trademarks. Microsoft's general trademark guidelines can be found here.
Privacy information can be found here.
Microsoft and any contributors reserve all others rights, whether under their respective copyrights, patents, or trademarks, whether by implication, estoppel or otherwise.