Edicíos disponibilizados pela Microsoft para o Mapeamento No Brasil.

O Bing Maps está lançando pegadas de edifícios abertos em todo o mundo. Detectamos 777 milhões de edifícios de imagens do Bing Maps entre 2014 e 2021, incluindo imagens Maxar e Airbus. Os dados estão disponíveis gratuitamente para download e uso no ODbL. Este conjunto de dados complementa nossos outros lançamentos.

Qual é a safra desses dados? A safra das pegadas de construção extraídas depende da safra das imagens subjacentes. As imagens subjacentes são do Bing Maps, incluindo Maxar e Airbus entre 2014 e 2021.

Quão bons são os dados? Nossa mostra que, na grande maioria dos casos, a qualidade é pelo menos tão boa quanto as métricas digitalizadas à mão no OpenStreetMap. Não é perfeito, particularmente em áreas urbanas densas, mas fornece boa memória nas áreas rurais.

O que é o sistema de referência de coordenadas? EPSG: 4326

Haverá mais dados chegando para outras geografias? Pode ser. Este é um trabalho em progresso. Além disso, confira nossos outros lançamentos de construção!

NÓS Austrália Canadá Uganda e Tanzânia América do Sul Quênia e Nigéria Indonésia, Malásia e Filipinas

Contribuindo Este projeto aceita contribuições e sugestões. A maioria das contribuições exige que você concorde com um Contributor License Agreement (CLA) declarando que você tem o direito de, e realmente tem, nos conceder os direitos de usar sua contribuição. Para obter detalhes, visite https://cla.microsoft.com.

Quando você envia a solicitação pull, o CLA-bot determinará automaticamente se você precisa fornecer o CLA e decorar o PR adequadamente (por exemplo, rótulo, comentário). Basta seguir as instruções fornecidas pelo bot. Você só precisará fazer isso uma vez em todos os repositórios usando nosso CLA.

Este projeto adotou o Código de Conduta de Código Aberto da Microsoft. Para obter mais informações, consulte as Perguntas frequentes sobre o Código de Conduta ou entre em contato com opencode@microsoft.com com perguntas ou comentários adicionais.

Noticias legais Microsoft, Windows, Microsoft Azure e/ou outros produtos e serviços da Microsoft mencionados na documentação podem ser marcas comerciais ou marcas registradas da Microsoft nos Estados Unidos e/ou em outros países. As licenças para este projeto não concedem a você direitos de uso de quaisquer nomes, logotipos ou marcas registradas da Microsoft. As diretrizes gerais de marca registrada da Microsoft podem ser encontradas aqui.

Informações de privacidade podem ser encontradas aqui.

A Microsoft e quaisquer contribuidores reservam-se todos os outros direitos, seja sob seus respectivos direitos autorais, patentes ou marcas registradas, seja por implicação, preclusão ou de outra forma. https://github.com/microsoft/GlobalMLBuildingFootprints

Bing Maps is releasing open building footprints around the world. We have detected 777M buildings from Bing Maps imagery between 2014 and 2021 including Maxar and Airbus imagery. The data is freely available for download and use under ODbL. This dataset complements our other releases.

What is the GeoJSON format? GeoJSON is a format for encoding a variety of geographic data structures. For intensive documentation and tutorials, refer to this blog.

Why is the data being released? Microsoft has a continued interest in supporting a thriving OpenStreetMap ecosystem.

Should we import the data into OpenStreetMap? 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.

Will the data be used or made available in the larger OpenStreetMap ecosystem? Yes. The HOT Tasking Manager has integrated Facebook RapiD where the data has been made available.

How did we create the data? The building extraction is done in two stages:

Semantic Segmentation – Recognizing building pixels on an aerial image using deep neural networks (DNNs) Polygonization – Converting building pixel detections into polygons

Were there any modeling improvements used for this release? We did not apply any modeling improvements for this release. Instead, we focused on scaling our approach to increase coverage, and trained models regionally.

Evaluation set metrics 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:

Intersection over Union – This is a standard metric measuring the overlap quality against the labels Dominant angle rotation error – This measures the polygon rotation deviation 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 positive ratio in the corpus False positives are estimated per country from randomly sampled building polygon predictions.

Region Buildings Sampled False Positive Rate Africa 5,000 1.1% Caribbean 3,000 1.8% Central Asia 3,000 2.2% Europe 5,000 1.4% Mexico 2,000 0.1% Middle East 7,000 1.8% South America 5,000 1.7% South Asia 7,000 1.4% What is the vintage of this data? 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.

How good is the data? 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.

What is the coordinate reference system? EPSG: 4326

Will there be more data coming for other geographies? Maybe. This is a work in progress. Also, check out our other building releases!

US Australia Canada Uganda and Tanzania South America Kenya and Nigeria Indonesia, Malaysia, and the Philippines

Contributing 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 opencode@microsoft.com with any additional questions or comments.

Legal Notices 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.

https://github.com/microsoft/GlobalMLBuildingFootprints