GEE边缘检测（canny）

canny边缘检测

主要功能

使用landsat5数据计算归一化植被指数，之后对植被指数计算结果执行canny边缘检测，输出检测出的边缘

代码

// Canny Edge Detector example.

// Load an image and compute NDVI from it.
var image = ee.Image('LANDSAT/LT05/C01/T1_TOA/LT05_031034_20110619');
var ndvi = image.normalizedDifference(['B4','B3']);

// Detect edges in the composite.
var canny = ee.Algorithms.CannyEdgeDetector(ndvi, 0.7);

// Mask the image with itself to get rid of areas with no edges.
canny = canny.updateMask(canny);

Map.setCenter(-101.05259, 37.93418, 13);
Map.addLayer(ndvi, {min: 0, max: 1}, 'Landsat NDVI');
Map.addLayer(canny, {min: 0, max: 1, palette: 'FF0000'}, 'Canny Edges');

步骤分析

1. 创建ee对象，获取landsat05数据
2. 指定特定波段，计算归一化植被指数（NDVI）
3. canny边缘检测
4. 剔除检测出的非边缘部分
5. 设置地图显示中心，缩放等级
6. 添加计算出的NDVI图层
7. 添加检测出的边缘图层

主要方法

1. ee.Image.normalizeDifference()

Computes the normalized difference between two bands. If the bands to use are not specified, uses the first two bands. The normalized difference is computed as (first − second) / (first + second).
Arguments:
this:input (Image):
The input image.
bandNames (List, default: null):
A list of names specifying the bands to use. If not specified, the first and second bands are used.
Returns: Image

计算归一化差值指数，若没有指定波段，则计算前两个波段。

2. ee.Algorithms.CannyEdgeDetector()
   Applies the Canny edge detection algorithm to an image. The output is an image whose bands have the same names as the input bands, and in which non-zero values indicate edges, and the magnitude of the value is the gradient magnitude.
   Arguments:
   image (Image):
   The image on which to apply edge detection.
   threshold (Float):
   Threshold value. The pixel is only considered for edge detection if the gradient magnitude is higher than this threshold.
   sigma (Float, default: 1):
   Sigma value for a gaussian filter applied before edge detection. 0 means apply no filtering.
   Returns: Image

对影像对象执行canny边缘检测。输出的结果影像中具有输入影像相同波段名称，非零区域指示为边缘区域。值为梯度值。
输入参数：
输入影像对象，阈值（浮点型，梯度值的阈值），sigma表示在边缘检测之前，对影像进行高斯平滑的大小。0表示不执行平滑。

3. ee.Image.updateMask()
   Updates an image's mask at all positions where the existing mask is not zero. The output image retains the metadata and footprint of the input image.
   Arguments:
   this:image (Image):
   Input image.
   mask (Image):
   New mask for the image, as a floating-point value in the range [0, 1] (invalid = 0, valid = 1). If this image has a single band, it is used for all bands in the input image; otherwise, must have the same number of bands as the input image.
   Returns: Image

对影像进行掩膜，非零区域得到保留，影像外边界得到保留。
输入参数：
输入影像对象，掩膜影像。

本例中，为了显示边缘检测的结果，需要增加掩膜这一步骤，然后使用一种颜色（红色）来展示结果