.. _MorphologicalMultiScaleDecomposition: 

MorphologicalMultiScaleDecomposition
====================================





Perform a geodesic morphology based image analysis on an input image channel

Description
-----------

This application recursively apply geodesic decomposition. 

This algorithm is derived from the following publication:

Martino Pesaresi and Jon Alti Benediktsson, Member, IEEE: A new approach for the morphological segmentation of high resolution satellite imagery.
IEEE Transactions on geoscience and remote sensing, vol. 39, NO. 2, February 2001, p. 309-320.

It provides a geodesic decomposition of the input image, with the following scheme. Let :math:`f_0` denote the input image, :math:`\stackrel{\smile}{\mu}_{N}(f)` denote the convex membership function, :math:`\stackrel{\frown}{\mu}_{N}(f)` denote the concave membership function and :math:`\psi_{N}(f)` denote the leveling function, for a given radius :math:`N` as defined in the documentation
of the GeodesicMorphologyDecompositionImageFilter. Let :math:`[N_{1},\ldots, N_{n}]` denote a range of increasing radius (or scales). The iterative decomposition is defined as follows:

:math:`f_i` = :math:`\psi_{N_i}(f_{i-1})` 

:math:`\stackrel{\frown}{f}_i` = :math:`\stackrel{\frown}{\mu}_{N_i}(f_i)` 

:math:`\stackrel{\smile}{f}_i` = :math:`\stackrel{\smile}{\mu}_{N_i}(f_i)` 

The :math:`\stackrel{\smile}{f}_{i}` and :math:`\stackrel{\frown}{f}_{i}` are membership function for the convex
(resp. concave) objects whose size is comprised between :math:`N_{i-1}` and :math:`N_i`

Output convex, concave and leveling images with B bands, where n is the number of levels.

This application has several output images and supports "multi-writing". Instead of computing and writing each image independently, the streamed image blocks are written in a synchronous way for each output. The output images will be computed strip by strip, using the available RAM to compute the strip size, and a user defined streaming mode can be specified using the streaming extended filenames (type, mode and value). Note that multi-writing can be disabled using the multi-write extended filename option: &multiwrite=false, in this case the output images will be written one by one. Note that multi-writing is not supported for MPI writers.

Parameters
----------

.. contents:: :local:

.. |br| raw:: html

   <br />

.. |em| raw:: html

   &emsp;

**Input Image** :code:`-in image` *Mandatory* |br|
The input image to be classified.

**Output Convex Image** :code:`-outconvex image [dtype]` *Mandatory* |br|
The output convex image with N bands

**Output Concave Image** :code:`-outconcave image [dtype]` *Mandatory* |br|
The output concave concave with N bands

**Output Image** :code:`-outleveling image [dtype]` *Mandatory* |br|
The output leveling image with N bands

**Selected Channel** :code:`-channel int` *Default value: 1* |br|
The selected channel index for input image

**Structuring Element Type** :code:`-structype [ball|cross]` *Default value: ball* |br|
Choice of the structuring element type

* **Ball** |br| 

* **Cross** |br| 



**Initial radius** :code:`-radius int` *Default value: 5* |br|
Initial radius of the structuring element (in pixels)

**Radius step** :code:`-step int` *Default value: 1* |br|
Radius step along the profile (in pixels)

**Number of levels use for multi scale** :code:`-levels int` *Default value: 1* |br|
Number of levels use for multi scale

**Available RAM (MB)** :code:`-ram int` *Default value: 256* |br|
Available memory for processing (in MB).



Examples
--------

From the command-line:

.. code-block:: bash

    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


From Python:

.. code-block:: python

	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()



Limitations
-----------

Generation of the multi scale decomposition is not streamable, pay attention to this fact when setting the number of iterating levels.

See also
--------

| otbGeodesicMorphologyDecompositionImageFilter class