Open Buildings V3 Polygons

GOOGLE/Research/open-buildings/v3/polygons
Dataset Availability
2023-05-30T00:00:00Z–2023-05-30T00:00:00
Dataset Provider
Earth Engine Snippet
FeatureCollection
ee.FeatureCollection("GOOGLE/Research/open-buildings/v3/polygons")
FeatureView
ui.Map.FeatureViewLayer("GOOGLE/Research/open-buildings/v3/polygons_FeatureView")
Tags
africa building
asia
built-up
open-buildings
south-asia
southeast-asia
structure

Description

This large-scale open dataset consists of outlines of buildings derived from high-resolution 50 cm satellite imagery. It contains 1.8B building detections in Africa, Latin America, Caribbean, South Asia and Southeast Asia. The inference spanned an area of 58M km².

For each building in this dataset we include the polygon describing its footprint on the ground, a confidence score indicating how sure we are that this is a building, and a Plus Code corresponding to the center of the building. There is no information about the type of building, its street address, or any details other than its geometry.

Building footprints are useful for a range of important applications: from population estimation, urban planning and humanitarian response to environmental and climate science. The project is based in Ghana, with an initial focus on the continent of Africa and new updates on South Asia, South-East Asia, Latin America and the Caribbean.

Inference was carried out during May 2023.

For more details see the official website of the Open Buildings dataset.

Table Schema

Table Schema

Name Type Description
area_in_meters DOUBLE

Area in square meters of the polygon.

confidence DOUBLE

Confidence score [0.65;1.0] assigned by the model.

full_plus_code STRING

The full Plus Code at the building polygon centroid.

longitude_latitude GEOMETRY

Centroid of the polygon.

Terms of Use

Terms of Use

CC-BY-4.0

Citations

Citations:
  • W. Sirko, S. Kashubin, M. Ritter, A. Annkah, Y.S.E. Bouchareb, Y. Dauphin, D. Keysers, M. Neumann, M. Cisse, J.A. Quinn. Continental-scale building detection from high resolution satellite imagery. arXiv:2107.12283, 2021.

Explore with Earth Engine

Code Editor (JavaScript)

// Visualization of GOOGLE/Research/open-buildings/v3/polygons.

var t = ee.FeatureCollection('GOOGLE/Research/open-buildings/v3/polygons');

var t_065_070 = t.filter('confidence >= 0.65 && confidence < 0.7');
var t_070_075 = t.filter('confidence >= 0.7 && confidence < 0.75');
var t_gte_075 = t.filter('confidence >= 0.75');

Map.addLayer(t_065_070, {color: 'FF0000'}, 'Buildings confidence [0.65; 0.7)');
Map.addLayer(t_070_075, {color: 'FFFF00'}, 'Buildings confidence [0.7; 0.75)');
Map.addLayer(t_gte_075, {color: '00FF00'}, 'Buildings confidence >= 0.75');
Map.setCenter(3.389, 6.492, 17);  // Lagos, Nigeria
Map.setOptions('SATELLITE');
Open in Code Editor

Visualize as a FeatureView

A FeatureView is a view-only, accelerated representation of a FeatureCollection. For more details, visit the FeatureView documentation.

Code Editor (JavaScript)

var fvLayer = ui.Map.FeatureViewLayer(
  'GOOGLE/Research/open-buildings/v3/polygons_FeatureView');

var visParams = {
  rules: [
    {
      filter: ee.Filter.expression('confidence >= 0.65 && confidence < 0.7'),
      color: 'FF0000'
    },
    {
      filter: ee.Filter.expression('confidence >= 0.7 && confidence < 0.75'),
      color: 'FFFF00'
    },
    {
      filter: ee.Filter.expression('confidence >= 0.75'),
      color: '00FF00'
    },
  ]
};

fvLayer.setVisParams(visParams);
fvLayer.setName('Buildings');

Map.setCenter(3.389, 6.492, 17);  // Lagos, Nigeria
Map.add(fvLayer);
Map.setOptions('SATELLITE');
Open in Code Editor