Google Earth Engine——BigEarthNet是一个新的耕地Sentinel-2数据，由590,326个Sentinel-2图像斑块组成的土地覆盖高清数据集

BigEarthNet is a new large-scale Sentinel-2 benchmark archive, consisting of 590,326 Sentinel-2 image patches. To construct BigEarthNet, 125 Sentinel-2 tiles acquired between June 2017 and May 2018 over the 10 countries (Austria, Belgium, Finland, Ireland, Kosovo, Lithuania, Luxembourg, Portugal, Serbia, Switzerland) of Europe were initially selected. All the tiles were atmospherically corrected by the Sentinel-2 Level 2A product generation and formatting tool (sen2cor). Then, they were divided into 590,326 non-overlapping image patches. Each image patch was annotated by the multiple land-cover classes (i.e., multi-labels) that were provided from the CORINE Land Cover database of the year 2018 (CLC 2018).

BigEarthNet是一个新的大规模Sentinel-2基准档案，由590,326个Sentinel-2图像斑块组成。为了构建BigEarthNet，最初选择了2017年6月至2018年5月期间在欧洲10个国家（奥地利、比利时、芬兰、爱尔兰、科索沃、立陶宛、卢森堡、葡萄牙、塞尔维亚、瑞士）获得的125张Sentinel-2瓦片。所有的瓦片都通过Sentinel-2 2A级产品生成和格式化工具（sen2cor）进行了大气校正。然后，它们被划分为590,326个不重叠的图像斑块。每个图像斑块都由2018年CORINE土地覆盖数据库（CLC 2018）提供的多个土地覆盖类别（即多标签）进行注释。

Dataset Availability

2017-06-01T00:00:00 - 2018-05-31T00:00:00

Dataset Provider

BigEarthNet

Collection Snippet

ee.ImageCollection("TUBerlin/BigEarthNet/v1")

Bands Table

影像属性：

使用说明：The BigEarthNet Archive is licensed under the Community Data License Agreement – Permissive, Version 1.0. For more information, please refer to the (http://bigearth.net/downloads/documents/License.pdf).

引用：

G. Sumbul, M. Charfuelan, B. Demir, V. Markl, BigEarthNet: A Large-Scale Benchmark Archive for Remote Sensing Image Understanding, IEEE International Conference on Geoscience and Remote Sensing Symposium, pp. 5901-5904, Yokohama, Japan, 2019.

代码：

var geometry = ee.Geometry.Polygon(
    [[
      [16.656886757418057, 48.27086673747943],
      [16.656886757418057, 48.21359065567954],
      [16.733276070162198, 48.21359065567954],
      [16.733276070162198, 48.27086673747943]
    ]],
    null, false);
var ic = ee.ImageCollection('TUBerlin/BigEarthNet/v1');
var filtered = ic.filterBounds(geometry);
var tiles = filtered.map(function(i) {
  var labels = ee.List(i.get('labels'));
  var urban = labels.indexOf('Discontinuous urban fabric').gte(0);
  var highlight_urban = ee.Image(urban).toInt().multiply(1000);
  return i.addBands(
      {srcImg: i.select(['B4']).add(highlight_urban), overwrite: true});
});
var image = tiles.mosaic().clip(geometry);
var visParams = {bands: ['B4', 'B3', 'B2'], min: 0, max: 3000};
Map.addLayer(image, visParams);
Map.centerObject(image, 13);