MorphologicalMultiScaleDecomposition¶
在输入图像通道上执行基于测地线形态的图像分析
描述¶
此应用程序递归地应用测地线分解。
此算法派生自以下出版物：
Martino Pesaresi和Jon Alti Benediktsson，IEEE成员：高分辨率卫星图像形态分割的新方法。《IEEE地球科学和遥感学报》，第39卷，第2期，2001年2月，第309-320页。
It provides a geodesic decomposition of the input image, with the following scheme. Let f_0 denote the input image, \stackrel{\smile}{\mu}_{N}(f) denote the convex membership function, \stackrel{\frown}{\mu}_{N}(f) denote the concave membership function and \psi_{N}(f) denote the leveling function, for a given radius N as defined in the documentation of the GeodesicMorphologyDecompositionImageFilter. Let [N_{1},\ldots, N_{n}] denote a range of increasing radius (or scales). The iterative decomposition is defined as follows:
f_i = \psi_{N_i}(f_{i-1})
\stackrel{\frown}{f}_i = \stackrel{\frown}{\mu}_{N_i}(f_i)
\stackrel{\smile}{f}_i = \stackrel{\smile}{\mu}_{N_i}(f_i)
The \stackrel{\smile}{f}_{i} and \stackrel{\frown}{f}_{i} are membership function for the convex (resp. concave) objects whose size is comprised between N_{i-1} and N_i
输出具有B波段的凸面、凹面和水平图像，其中n是层数。
这个应用程序有几个输出图像，并支持“多写”。不是独立地计算和写入每个图像，而是以同步的方式为每个输出写入流图像块。输出图像将逐条计算，使用可用的RAM计算条带大小，并且可以使用流扩展文件名(类型、模式和值)指定用户定义的流模式。请注意，可以使用多写扩展文件名选项禁用多写，在这种情况下，将逐个写入输出图像。请注意，MPI编写器不支持多重写入。
参数¶
Input Image -in image Mandatory
The input image to be classified.
Output Convex Image -outconvex image [dtype] Mandatory
The output convex image with N bands
Output Concave Image -outconcave image [dtype] Mandatory
The output concave concave with N bands
Output Image -outleveling image [dtype] Mandatory
The output leveling image with N bands
Selected Channel -channel int Default value: 1
The selected channel index for input image
Structuring Element Type -structype [ball|cross] Default value: ball
Choice of the structuring element type
- Ball
- Cross
Initial radius -radius int Default value: 5
Initial radius of the structuring element (in pixels)
Radius step -step int Default value: 1
Radius step along the profile (in pixels)
Number of levels use for multi scale -levels int Default value: 1
Number of levels use for multi scale
Available RAM (MB) -ram int Default value: 256
Available memory for processing (in MB).
实例¶
从命令行执行以下操作：
otbcli_MorphologicalMultiScaleDecomposition -in ROI_IKO_PAN_LesHalles.tif -structype ball -channel 1 -radius 2 -levels 2 -step 3 -outconvex convex.tif -outconcave concave.tif -outleveling leveling.tif
来自Python的评论：
import otbApplication
app = otbApplication.Registry.CreateApplication("MorphologicalMultiScaleDecomposition")
app.SetParameterString("in", "ROI_IKO_PAN_LesHalles.tif")
app.SetParameterString("structype","ball")
app.SetParameterInt("channel", 1)
app.SetParameterInt("radius", 2)
app.SetParameterInt("levels", 2)
app.SetParameterInt("step", 3)
app.SetParameterString("outconvex", "convex.tif")
app.SetParameterString("outconcave", "concave.tif")
app.SetParameterString("outleveling", "leveling.tif")
app.ExecuteAndWriteOutput()
局限性¶
多尺度分解的生成是不可流水化的，设置迭代层数时要注意这一点。