Sentinel 1A监督分类

时间:2018-08-07 07:26:06

标签: google-earth-engine

// Load the Sentinel-1 ImageCollection.
var sentinel1 = ee.ImageCollection('COPERNICUS/S1_GRD');

// Filter by metadata properties.
var vh = sentinel1
   // Filter to get images with VV and VH dual polarization.
  .filter(ee.Filter.listContains('transmitterReceiverPolarisation', 'VV'))
  .filter(ee.Filter.listContains('transmitterReceiverPolarisation', 'VH'))
   // Filter to get images collected in interferometric wide swath mode.
  .filter(ee.Filter.eq('instrumentMode', 'IW'))
   //.filterDate('2016-01-01','2017-12-30')
   ;

 // Filter to get images from different look angles.
 var vhAscending = vh.filter(ee.Filter.eq('orbitProperties_pass', 'ASCENDING'));
 var vhDescending = vh.filter(ee.Filter.eq('orbitProperties_pass', 'DESCENDING'));

 // Create a composite from means at different polarizations and look angles.
 var composite = ee.Image.cat([
   vhAscending.select('VH').mean(),
   ee.ImageCollection(vhAscending.select('VV').merge(vhDescending.select('VV'))).mean(),
  vhDescending.select('VH').mean()
 ]).focal_median();
var clip = composite.clipToCollection(shimogga);
print(clip,'clip');

 // Display as a composite of polarization and backscattering characteristics.
 Map.addLayer(clip, {min: [-25, -20, -25], max: [0, 10, 0]}, 'clip');
 var band = ['VH','VV','VH_1'];
 var fc = forest.merge(WaterBody).merge(urban).merge(agriculture);
 print(fc,'fc');

 //var property = 'LULC';
 var training = clip.select(band).sampleRegions({collection:fc, properties:['LULC']});
 var classifier = ee.Classifier.cart().train({
   features:training,classproperty:'LULC',inputProprties:band
 });

 var classified = clip.select(band).classify(classifier);
Map.addLayer(classified,{min:0, max:3, palette:['1A4612','29468C','EC3316','E7EA0E']},'classified');

我进行了监督分类,但出现此错误

函数缺少必需的参数(classProperty):Classifier.train(分类器,功能,classProperty,inputProperty,子采样,子采样种子)

使用每个要素的指定数字属性作为训练数据,在要素集合上训练分类器。要素的几何将被忽略。

Args:

分类器(Classifier):输入分类器。   features(FeatureCollection):要进行训练的集合。   classProperty(字符串):包含类值的属性的名称。每个功能都必须具有此属性,并且其值必须是数字。   inputProperties(列表,可选):包括作为训练数据的属性名称的列表。每个功能都必须具有所有这些属性,并且它们的值必须是数字。如果输入集合包含'band_order'属性(由Image.sample生成),则此参数是可选的。   二次采样(浮点型,可选):可选的二次采样因子,在(0,1]之内。   subsamplingSeed(整数,可选):用于子采样的随机种子。     在,1837行     在第1854行

0 个答案:

没有答案