microsoft / australiabuildingfootprints Goto Github PK

Bing Maps is releasing country wide open building footprints datasets in Australia. This dataset contains 11,334,866 computer generated building footprints derived using Bing Maps algorithms on satellite imagery. Satellite imagery used for extraction is from our imagery partners Maxar Technologies among others. The data is freely available for download and use under applicable license.

This data is licensed by Microsoft under the Open Data Commons Open Database License (ODbL).

11,334,866‬ building footprint polygon geometries in Australia in GeoJSON format. You may download the data in GeoJSON format here:

GeoJSON is a format for encoding a variety of geographic data structures. For intensive documentation and tutorials, refer to GeoJson 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. Currently Microsoft Open Buildings dataset is used in ml-enabler for task creation. You can try it out at AI assisted Tasking Manager. The data will also be made avaialble in Facebook RapiD.

The building extraction is done in two stages:

1. Semantic Segmentation – Recognizing building pixels on the aerial image using DNNs
2. Polygonization – Converting building pixel blobs into polygons

To train models for Australia we only had a few thousand building labels, which made it hard to rely only on supervised training. Typically we’ve used hundreds of thousands or best case tens of millions of building labels for training. In order to create a good and robust model for Australia we took advantage of self-supervised training and unsupervised domain adaptation techniques to leverage our training data from other countries and domains. We believe this is a good proof of concept to scale to building extraction to the whole world.

Australia evaluation set contains 6,785 buildings from several diverse and represenative regions.

Building match metrics on the evaluation set:

We track following metrics to measure the quality of matched buildings in the evaluation set:

1. Intersection over Union – This is a standard metric measuring the overlap quality against the labels
2. Shape distance – With this metric we measure the polygon outline similarity
3. Dominant angle rotation error – This measures the polygon rotation deviation

We estimate ~1% false postive ratio in 1000 randomly sampled buildings from the entire output corpus.

Correctly detecting connected buildings and small buildings are sometimes difficult tasks, even for a human labeller. There are often ambiguities in whether one is looking at multiple connected buildings or a single fragmented building. Similarly, it is sometimes hard to estimate for a small object if it should be classified as a building or not.

Output precision and recall metrics are calculated after optimal 1-to-1 matching between output polygons and labels scored by polygons intersection over union. The labels are usually very granular whilst it is sometimes very hard for DNN model to separate connected buildings. This results with significant ratio of unmatched false negatives which are pushing the recall down.

Small building example:

Connected buildings example:

Vintage of extracted building footprints depends on vintage of the underlying imagery. Bing Imagery is a composite of multiple sources, therefore it is difficult to know the exact dates for individual pieces of data. However we believe the vintage is anywhere from 2013 to 2018, with majority being from 2018.

Our metrics show that in the vast majority of cases the quality is at least as good as data 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.

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.