公告:所有在
2025 年 4 月 15 日之前注册使用 Earth Engine 的非商业项目都必须
验证是否符合非商业性质的资格条件,才能继续使用 Earth Engine。
ee.Classifier.minimumDistance
使用集合让一切井井有条
根据您的偏好保存内容并对其进行分类。
为给定距离度量创建最小距离分类器。在分类模式下,系统会返回最接近的类。在“回归”模式下,系统会返回与最近类中心的距离。在 RAW 模式下,系统会返回到每个类中心的距离。
用法 | 返回 |
---|
ee.Classifier.minimumDistance(metric, kNearest) | 分类器 |
参数 | 类型 | 详细信息 |
---|
metric | 字符串,默认:“euclidean” | 要使用的距离指标。选项如下:
- 'euclidean' - 与未归一化的类均值的欧几里得距离。
- “cosine”- 与未归一化的类均值之间的谱角。
- “mahalanobis”- 与类均值的马氏距离。
- 'manhattan' - 与未归一化的类均值的曼哈顿距离。
|
kNearest | 整数,默认值:1 | 如果大于 1,则结果将包含 k 个最近邻或距离的数组,具体取决于输出模式设置。如果 kNearest 大于类别总数,则将其设为等于类别数。 |
示例
Code Editor (JavaScript)
// A Sentinel-2 surface reflectance image, reflectance bands selected,
// serves as the source for training and prediction in this contrived example.
var img = ee.Image('COPERNICUS/S2_SR/20210109T185751_20210109T185931_T10SEG')
.select('B.*');
// ESA WorldCover land cover map, used as label source in classifier training.
var lc = ee.Image('ESA/WorldCover/v100/2020');
// Remap the land cover class values to a 0-based sequential series.
var classValues = [10, 20, 30, 40, 50, 60, 70, 80, 90, 95, 100];
var remapValues = ee.List.sequence(0, 10);
var label = 'lc';
lc = lc.remap(classValues, remapValues).rename(label).toByte();
// Add land cover as a band of the reflectance image and sample 100 pixels at
// 10 m scale from each land cover class within a region of interest.
var roi = ee.Geometry.Rectangle(-122.347, 37.743, -122.024, 37.838);
var sample = img.addBands(lc).stratifiedSample({
numPoints: 100,
classBand: label,
region: roi,
scale: 10,
geometries: true
});
// Add a random value field to the sample and use it to approximately split 80%
// of the features into a training set and 20% into a validation set.
sample = sample.randomColumn();
var trainingSample = sample.filter('random <= 0.8');
var validationSample = sample.filter('random > 0.8');
// Train a minimum distance classifier (Mahalanobis distance metric) from
// the training sample.
var trainedClassifier = ee.Classifier.minimumDistance('mahalanobis').train({
features: trainingSample,
classProperty: label,
inputProperties: img.bandNames()
});
// Get information about the trained classifier.
print('Results of trained classifier', trainedClassifier.explain());
// Get a confusion matrix and overall accuracy for the training sample.
var trainAccuracy = trainedClassifier.confusionMatrix();
print('Training error matrix', trainAccuracy);
print('Training overall accuracy', trainAccuracy.accuracy());
// Get a confusion matrix and overall accuracy for the validation sample.
validationSample = validationSample.classify(trainedClassifier);
var validationAccuracy = validationSample.errorMatrix(label, 'classification');
print('Validation error matrix', validationAccuracy);
print('Validation accuracy', validationAccuracy.accuracy());
// Classify the reflectance image from the trained classifier.
var imgClassified = img.classify(trainedClassifier);
// Add the layers to the map.
var classVis = {
min: 0,
max: 10,
palette: ['006400' ,'ffbb22', 'ffff4c', 'f096ff', 'fa0000', 'b4b4b4',
'f0f0f0', '0064c8', '0096a0', '00cf75', 'fae6a0']
};
Map.setCenter(-122.184, 37.796, 12);
Map.addLayer(img, {bands: ['B11', 'B8', 'B3'], min: 100, max: 3500}, 'img');
Map.addLayer(lc, classVis, 'lc');
Map.addLayer(imgClassified, classVis, 'Classified');
Map.addLayer(roi, {color: 'white'}, 'ROI', false, 0.5);
Map.addLayer(trainingSample, {color: 'black'}, 'Training sample', false);
Map.addLayer(validationSample, {color: 'white'}, 'Validation sample', false);
Python 设置
如需了解 Python API 以及如何使用 geemap
进行交互式开发,请参阅
Python 环境页面。
import ee
import geemap.core as geemap
Colab (Python)
# A Sentinel-2 surface reflectance image, reflectance bands selected,
# serves as the source for training and prediction in this contrived example.
img = ee.Image(
'COPERNICUS/S2_SR/20210109T185751_20210109T185931_T10SEG'
).select('B.*')
# ESA WorldCover land cover map, used as label source in classifier training.
lc = ee.Image('ESA/WorldCover/v100/2020')
# Remap the land cover class values to a 0-based sequential series.
class_values = [10, 20, 30, 40, 50, 60, 70, 80, 90, 95, 100]
remap_values = ee.List.sequence(0, 10)
label = 'lc'
lc = lc.remap(class_values, remap_values).rename(label).toByte()
# Add land cover as a band of the reflectance image and sample 100 pixels at
# 10 m scale from each land cover class within a region of interest.
roi = ee.Geometry.Rectangle(-122.347, 37.743, -122.024, 37.838)
sample = img.addBands(lc).stratifiedSample(
numPoints=100, classBand=label, region=roi, scale=10, geometries=True
)
# Add a random value field to the sample and use it to approximately split 80%
# of the features into a training set and 20% into a validation set.
sample = sample.randomColumn()
training_sample = sample.filter('random <= 0.8')
validation_sample = sample.filter('random > 0.8')
# Train a minimum distance classifier (Mahalanobis distance metric) from
# the training sample.
trained_classifier = ee.Classifier.minimumDistance('mahalanobis').train(
features=training_sample,
classProperty=label,
inputProperties=img.bandNames(),
)
# Get information about the trained classifier.
display('Results of trained classifier', trained_classifier.explain())
# Get a confusion matrix and overall accuracy for the training sample.
train_accuracy = trained_classifier.confusionMatrix()
display('Training error matrix', train_accuracy)
display('Training overall accuracy', train_accuracy.accuracy())
# Get a confusion matrix and overall accuracy for the validation sample.
validation_sample = validation_sample.classify(trained_classifier)
validation_accuracy = validation_sample.errorMatrix(label, 'classification')
display('Validation error matrix', validation_accuracy)
display('Validation accuracy', validation_accuracy.accuracy())
# Classify the reflectance image from the trained classifier.
img_classified = img.classify(trained_classifier)
# Add the layers to the map.
class_vis = {
'min': 0,
'max': 10,
'palette': [
'006400',
'ffbb22',
'ffff4c',
'f096ff',
'fa0000',
'b4b4b4',
'f0f0f0',
'0064c8',
'0096a0',
'00cf75',
'fae6a0',
],
}
m = geemap.Map()
m.set_center(-122.184, 37.796, 12)
m.add_layer(
img, {'bands': ['B11', 'B8', 'B3'], 'min': 100, 'max': 3500}, 'img'
)
m.add_layer(lc, class_vis, 'lc')
m.add_layer(img_classified, class_vis, 'Classified')
m.add_layer(roi, {'color': 'white'}, 'ROI', False, 0.5)
m.add_layer(training_sample, {'color': 'black'}, 'Training sample', False)
m.add_layer(
validation_sample, {'color': 'white'}, 'Validation sample', False
)
m
如未另行说明,那么本页面中的内容已根据知识共享署名 4.0 许可获得了许可,并且代码示例已根据 Apache 2.0 许可获得了许可。有关详情,请参阅 Google 开发者网站政策。Java 是 Oracle 和/或其关联公司的注册商标。
最后更新时间 (UTC):2025-07-25。
[null,null,["最后更新时间 (UTC):2025-07-25。"],[[["\u003cp\u003eCreates a classifier using the minimum distance to class centers based on a specified distance metric ('euclidean', 'cosine', 'mahalanobis', or 'manhattan').\u003c/p\u003e\n"],["\u003cp\u003eOffers three output modes: CLASSIFICATION (returns nearest class), REGRESSION (returns distance to nearest class), and RAW (returns distances to all class centers).\u003c/p\u003e\n"],["\u003cp\u003eOptionally considers the 'kNearest' neighbors, returning an array of nearest neighbors or distances if 'kNearest' is greater than 1.\u003c/p\u003e\n"]]],[],null,["# ee.Classifier.minimumDistance\n\nCreates a minimum distance classifier for the given distance metric. In CLASSIFICATION mode, the nearest class is returned. In REGRESSION mode, the distance to the nearest class center is returned. In RAW mode, the distance to every class center is returned.\n\n\u003cbr /\u003e\n\n| Usage | Returns |\n|------------------------------------------------------------|------------|\n| `ee.Classifier.minimumDistance(`*metric* `, `*kNearest*`)` | Classifier |\n\n| Argument | Type | Details |\n|------------|------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `metric` | String, default: \"euclidean\" | The distance metric to use. Options are: - 'euclidean' - Euclidean distance from the unnormalized class mean. - 'cosine' - spectral angle from the unnormalized class mean. - 'mahalanobis' - Mahalanobis distance from the class mean. - 'manhattan' - Manhattan distance from the unnormalized class mean. |\n| `kNearest` | Integer, default: 1 | If greater than 1, the result will contain an array of the k nearest neighbors or distances, based on the output mode setting. If kNearest is greater than the total number of classes, it will be set equal to the number of classes. |\n\nExamples\n--------\n\n### Code Editor (JavaScript)\n\n```javascript\n// A Sentinel-2 surface reflectance image, reflectance bands selected,\n// serves as the source for training and prediction in this contrived example.\nvar img = ee.Image('COPERNICUS/S2_SR/20210109T185751_20210109T185931_T10SEG')\n .select('B.*');\n\n// ESA WorldCover land cover map, used as label source in classifier training.\nvar lc = ee.Image('ESA/WorldCover/v100/2020');\n\n// Remap the land cover class values to a 0-based sequential series.\nvar classValues = [10, 20, 30, 40, 50, 60, 70, 80, 90, 95, 100];\nvar remapValues = ee.List.sequence(0, 10);\nvar label = 'lc';\nlc = lc.remap(classValues, remapValues).rename(label).toByte();\n\n// Add land cover as a band of the reflectance image and sample 100 pixels at\n// 10 m scale from each land cover class within a region of interest.\nvar roi = ee.Geometry.Rectangle(-122.347, 37.743, -122.024, 37.838);\nvar sample = img.addBands(lc).stratifiedSample({\n numPoints: 100,\n classBand: label,\n region: roi,\n scale: 10,\n geometries: true\n});\n\n// Add a random value field to the sample and use it to approximately split 80%\n// of the features into a training set and 20% into a validation set.\nsample = sample.randomColumn();\nvar trainingSample = sample.filter('random \u003c= 0.8');\nvar validationSample = sample.filter('random \u003e 0.8');\n\n// Train a minimum distance classifier (Mahalanobis distance metric) from\n// the training sample.\nvar trainedClassifier = ee.Classifier.minimumDistance('mahalanobis').train({\n features: trainingSample,\n classProperty: label,\n inputProperties: img.bandNames()\n});\n\n// Get information about the trained classifier.\nprint('Results of trained classifier', trainedClassifier.explain());\n\n// Get a confusion matrix and overall accuracy for the training sample.\nvar trainAccuracy = trainedClassifier.confusionMatrix();\nprint('Training error matrix', trainAccuracy);\nprint('Training overall accuracy', trainAccuracy.accuracy());\n\n// Get a confusion matrix and overall accuracy for the validation sample.\nvalidationSample = validationSample.classify(trainedClassifier);\nvar validationAccuracy = validationSample.errorMatrix(label, 'classification');\nprint('Validation error matrix', validationAccuracy);\nprint('Validation accuracy', validationAccuracy.accuracy());\n\n// Classify the reflectance image from the trained classifier.\nvar imgClassified = img.classify(trainedClassifier);\n\n// Add the layers to the map.\nvar classVis = {\n min: 0,\n max: 10,\n palette: ['006400' ,'ffbb22', 'ffff4c', 'f096ff', 'fa0000', 'b4b4b4',\n 'f0f0f0', '0064c8', '0096a0', '00cf75', 'fae6a0']\n};\nMap.setCenter(-122.184, 37.796, 12);\nMap.addLayer(img, {bands: ['B11', 'B8', 'B3'], min: 100, max: 3500}, 'img');\nMap.addLayer(lc, classVis, 'lc');\nMap.addLayer(imgClassified, classVis, 'Classified');\nMap.addLayer(roi, {color: 'white'}, 'ROI', false, 0.5);\nMap.addLayer(trainingSample, {color: 'black'}, 'Training sample', false);\nMap.addLayer(validationSample, {color: 'white'}, 'Validation sample', false);\n```\nPython setup\n\nSee the [Python Environment](/earth-engine/guides/python_install) page for information on the Python API and using\n`geemap` for interactive development. \n\n```python\nimport ee\nimport geemap.core as geemap\n```\n\n### Colab (Python)\n\n```python\n# A Sentinel-2 surface reflectance image, reflectance bands selected,\n# serves as the source for training and prediction in this contrived example.\nimg = ee.Image(\n 'COPERNICUS/S2_SR/20210109T185751_20210109T185931_T10SEG'\n).select('B.*')\n\n# ESA WorldCover land cover map, used as label source in classifier training.\nlc = ee.Image('ESA/WorldCover/v100/2020')\n\n# Remap the land cover class values to a 0-based sequential series.\nclass_values = [10, 20, 30, 40, 50, 60, 70, 80, 90, 95, 100]\nremap_values = ee.List.sequence(0, 10)\nlabel = 'lc'\nlc = lc.remap(class_values, remap_values).rename(label).toByte()\n\n# Add land cover as a band of the reflectance image and sample 100 pixels at\n# 10 m scale from each land cover class within a region of interest.\nroi = ee.Geometry.Rectangle(-122.347, 37.743, -122.024, 37.838)\nsample = img.addBands(lc).stratifiedSample(\n numPoints=100, classBand=label, region=roi, scale=10, geometries=True\n)\n\n# Add a random value field to the sample and use it to approximately split 80%\n# of the features into a training set and 20% into a validation set.\nsample = sample.randomColumn()\ntraining_sample = sample.filter('random \u003c= 0.8')\nvalidation_sample = sample.filter('random \u003e 0.8')\n\n# Train a minimum distance classifier (Mahalanobis distance metric) from\n# the training sample.\ntrained_classifier = ee.Classifier.minimumDistance('mahalanobis').train(\n features=training_sample,\n classProperty=label,\n inputProperties=img.bandNames(),\n)\n\n# Get information about the trained classifier.\ndisplay('Results of trained classifier', trained_classifier.explain())\n\n# Get a confusion matrix and overall accuracy for the training sample.\ntrain_accuracy = trained_classifier.confusionMatrix()\ndisplay('Training error matrix', train_accuracy)\ndisplay('Training overall accuracy', train_accuracy.accuracy())\n\n# Get a confusion matrix and overall accuracy for the validation sample.\nvalidation_sample = validation_sample.classify(trained_classifier)\nvalidation_accuracy = validation_sample.errorMatrix(label, 'classification')\ndisplay('Validation error matrix', validation_accuracy)\ndisplay('Validation accuracy', validation_accuracy.accuracy())\n\n# Classify the reflectance image from the trained classifier.\nimg_classified = img.classify(trained_classifier)\n\n# Add the layers to the map.\nclass_vis = {\n 'min': 0,\n 'max': 10,\n 'palette': [\n '006400',\n 'ffbb22',\n 'ffff4c',\n 'f096ff',\n 'fa0000',\n 'b4b4b4',\n 'f0f0f0',\n '0064c8',\n '0096a0',\n '00cf75',\n 'fae6a0',\n ],\n}\nm = geemap.Map()\nm.set_center(-122.184, 37.796, 12)\nm.add_layer(\n img, {'bands': ['B11', 'B8', 'B3'], 'min': 100, 'max': 3500}, 'img'\n)\nm.add_layer(lc, class_vis, 'lc')\nm.add_layer(img_classified, class_vis, 'Classified')\nm.add_layer(roi, {'color': 'white'}, 'ROI', False, 0.5)\nm.add_layer(training_sample, {'color': 'black'}, 'Training sample', False)\nm.add_layer(\n validation_sample, {'color': 'white'}, 'Validation sample', False\n)\nm\n```"]]