Difference between revisions of "Request for Changes-97: KMeansClassification reimplemented (Shark KMeans composite application)"

From OTBWiki
Jump to: navigation, search
(Applications)
 
(6 intermediate revisions by the same user not shown)
Line 1: Line 1:
== [Request for Changes - 97] KMeansClassification reimplemented (Shark KMeans composite application) ==
+
== [Request for Changes - 97] KMeansClassification reimplemented ==
  
 
=== Status ===  
 
=== Status ===  
Line 12: Line 12:
 
=== Summary ===
 
=== Summary ===
  
Gives a short summary of the changes.
+
Reimplement using Shark KMeans composite application.
  
 
=== Rationale ===
 
=== Rationale ===
 +
Implement KMeansClassification as a composite application using an existing training and classification application.
  
Explain the rationale for the changes (possible link to a [Request For Comments] or to a mantis ticket).
+
The SharkKMeans model is used instead of ITK classes.
  
 
=== Implementation details ===
 
=== Implementation details ===
Line 33: Line 34:
 
</pre>
 
</pre>
  
==== Tests ====
 
  
List impacted tests, and explain the changes that were made.
+
The applications pipeline for this composite application is :
 +
<pre>
 +
ImageEnveloppe => PolygonClassStatistics => SampleSelection => SamplesExtraction => TrainVectorClassifier => ImageClassifier.
 +
</pre>
  
Consider grouping changes by module names if several modules are impacted.
+
Use this application for:
 +
* ImageEnveloppe: create an image envelope,
 +
* PolygonClassStatistics : create the statistics,
 +
* SampleSelection : select the samples by constant strategy in the shapefile,
 +
* SamplesExtraction : extract the samples descriptors,
 +
* TrainVectorClassifier : train the model,
 +
* ImageClassifier: performs the classification of the input image according to a model file.
  
Link to dashboard pages of impacted if possible.
+
The parameters of the internal applications have been initialized such as:
  
==== Documentation ====
+
(TODO list)
  
List documentation modification that were made (doxygen, example, software guide, application documentation, cookbook).
+
The rest of the settings are by default.
 +
 
 +
==== Documentation ====
 +
None
  
 
=== Additional notes ===
 
=== Additional notes ===
  
 
List remaining open issues if any, and additional notes.
 
List remaining open issues if any, and additional notes.

Latest revision as of 16:31, 7 July 2017

[Request for Changes - 97] KMeansClassification reimplemented

Status

  • Author: Marina Bertolino
  • Submitted on 07.07.2017
  • Proposed target release : 6.2
  • Adopted:
  • Link to a public git branch or pull request corresponding to the changes.
  • Merged : (put merge commit when merged)

Summary

Reimplement using Shark KMeans composite application.

Rationale

Implement KMeansClassification as a composite application using an existing training and classification application.

The SharkKMeans model is used instead of ITK classes.

Implementation details

Classes and files

A       Modules/Applications/AppClassification/include/otbClassKMeansBase.h
A       Modules/Applications/AppClassification/include/otbClassKMeansBase.txx

Applications

M       Modules/Applications/AppClassification/app/otbKMeansClassification.cxx


The applications pipeline for this composite application is :

ImageEnveloppe => PolygonClassStatistics => SampleSelection => SamplesExtraction => TrainVectorClassifier => ImageClassifier.

Use this application for:

  • ImageEnveloppe: create an image envelope,
  • PolygonClassStatistics : create the statistics,
  • SampleSelection : select the samples by constant strategy in the shapefile,
  • SamplesExtraction : extract the samples descriptors,
  • TrainVectorClassifier : train the model,
  • ImageClassifier: performs the classification of the input image according to a model file.

The parameters of the internal applications have been initialized such as:

(TODO list)

The rest of the settings are by default.

Documentation

None

Additional notes

List remaining open issues if any, and additional notes.