View source for Per pixel supervised classification

=Using QGIS and OTB processing toolbox=

* Using OTB version > 7.2.0, input vector file format of training data can be GeoPackage GPKG or ESRI Shapefile.
* The column containing class label needs to be an integer (whole number).

==Training phase==
* In the search engine of Processing Toolbox, type {{typed|text=TrainImages}} and open '''TrainImagesClassifer'''.
* In the {{button|text=Input Image List}} select one (or optional: several) multi-band raster (multispectral images).
* In the {{button|text=Input Vector Data List}} select a file containing training area polygons in format GPKG or SHP.
* If you do not have independent validation data: leave {{button|text=Validation Vector Data List}} empty.
* Bound sample number ba minimum: {{typed|text=1}}. The class with the minimum number of pixels determines the sample  size of all other classes. Changing this value to {{typed|text=0}} does not have an effect (current bug in QGIS3.16). 
* Training and validation sample ratio: {{typed|text=0.25}}. This is a 4-fold cross-validation with split 0.75 per cent  for training and 0.25 per cent for testing.
* Type {{typed|text=Code}} in the {{button|text=Field containing the class integer label for supervision}} text field.
* As Classifier to use for training choose Support Vector Machine {{button|text=libsvm}} from the drop down list.
* The SVM Kernel Type is {{button|text=Linear}}.
* SVM Model Type is {{button|text=csvc}}
* Switch checkbox {{button|text=Parameters optimization}} '''off'''. The optimization results in a higher accuracy but takes much time (> 1 hour computation).
* In the {{button|text=Output model}} specify a model file: e.g. '''svm.model'''
* Click {{button|text=Run}}.
* Click on the {{button|text=Log}} tab and inspect the '''model quality''' measures: Precision, Recall, F-score and Kappa index.
[[File:qgis_otb_trainimages.png|400px]]

==Classification phase==
* In the search engine of Processing Toolbox, type {{typed|text=ImageClassifier}} and double click '''ImageClassifier'''.
* Set an multiband image as {{button|text=Input image}}.
* Set {{button|text=Input _mask}} to blank (top of drop-down list).
* Set '''svm.model''' as {{button|text=Model file}}.
* Set the number of classes in your model: this is the number of unique classes in your training vector file.
* Set {{button|text=Output pixel type}} to '''uint16'''
* Save the {{button|text=Output image}} as '''svm_classification.tif'''.
* Uncheck Confidence map: ''Open output file after running algorithm''.
* Uncheck Probability map: ''Open output file after running algorithm''. {{button|text=Run}}.

[[File:qgis_otb_imageclassifier.png|400px]]

* Find the output ''svm_classification.tif'' in the QGIS map canvas.
* Right click on the layer ''svm_classification'' and select {{mitem|text=Properties --> Symbology --> Style --> Load Style}}.
* Select the style file  '''classified.qml'''. {{button|text=OK}}.

==Postprocessing==
"Sieve" removes raster polygons smaller than a provided threshold size (in pixels) and replaces them with the pixel value of the largest neighbour polygon. This is useful if you want to generalize a map and have a large amount of very small areas on your raster map

This application uses a the "Sieve" algorithm.
* In the search engine of Processing Toolbox, type {{typed|text=sieve}} and double click '''Gedal > Raster analysis > Sieve'''.
* Define {{button|text=Input layer}} as an thematic raster map.
* Only raster polygons smaller than the size defined by {{button|text=Trheshold}} will be removed. Set to {{typed|text=2}} pixels.
* Save the {{button|text=Sieved}} as '''svm_classification_sieve.tif'''.
* Click {{button|text=Run}}.

[[File:qgis_gdal_sieve.png|400px]]

* Find the output ''svm_classification_sieve.tif'' in the QGIS map canvas.
* Right click on the layer ''svm_classification_sieve'' in the and select {{mitem|text=Properties --> Symbology --> Style --> Load Style}}.
* Select the style file  '''rast_classified.qml'''. {{button|text=OK}}.

=Using OTB standalone=
==Training phase==
* Navigate in the Windows explorer to your Folder OTB-7.2.0-Win64. Double click the Windows-Batchdatei mapla to open Monteverdi Application Launcher.
* In the search engine of mapla, type {{typed|text=TrainImages}} and double click '''TrainImagesClassifer'''.
* In the {{button|text=Input Image List}} click on {{button|text=+}} and select a (or optional: several) multispectral images: '''Subset_S2A_MSIL2A_20170619T_MUL.tif '''.
* In the {{button|text=Input Vector Data List}} choose a vector polygon file with training areas in file format GPKG or SHP.
* In the {{button|text=Output model}} specify an output model file: e.g. '''lucc_rf.model'''
* In the {{button|text=Bound sample number by minimum}} field type {{typed|text=0}}. 
* Set the {{button|text=training and validation sample ratio}} to {{typed|text=0.25}}.
* Mark  ''C_ID''  in the {{button|text=Field containing the class integer label}} (C_ID refers to the column that contains the LUC code in the training and validation vector file).
* Choose {{button|text=Shark Random forests classifier}} from the drop down list as Classifier to use for the training.
* Check user defined Random seed and enter any positive integer value. This initializes a pseudorandom number generator which may be used to reproduce results.
* Click on {{button|text=Execute}}.
* Click on the {{button|text=Log}} tab and inspect the model quality measures: Precision, Recall, F-score and Kappa index.
[[File:otb_Trainrf.png|500px]]

==Classification phase==
* In the search engine of mapla, type {{typed|text=ImageClassifier}} and double click '''ImageClassifier'''
* Set ''Subset_S2A_MSIL2A_20170619T_MUL.tif'' as {{button|text=Input image}}.
* Set '''lucc_rf.model''' as {{button|text=Model file}}.
* Save the {{button|text=Output image}} as '''rf_classification.tif'''.
* Adjust the {{button|text=Number of classes in the model}} to the number of unique classes in the training vector file.

[[File:otb_imageclassifier.png|500px]]

* Add ''rf_classification.tif'' to QGIS canvas.
* Download the style file '''classified.qml''' from Stud.IP.
* Right click on the layer ''rf_classification'' and select {{mitem|text=Properties --> Style --> Style --> Load Style}}.
* Select the style file '''classified.qml'''. {{button|text=OK}}.

==Postprocessing==
This application uses a majority with a circular structure element.
* In the search engine of mapla, type, {{typed|text=regular}} and double click '''ClassifcationMapRegularization'''.
* As the{{button|text=Input classification image}} define the output raster file of the classification phase.
* Save the {{button|text=Output regularizd image}} as '''rf_classification_majority.tif'''.
* Set {{button|text=Structuring element radius}} to {{typed|text=2}} pixels.
* Set {{button|text=Output pixel type}} to {{button|text=uint8}}.
* Click {{button|text=Execute}}.

[[File:otb_majority.png|400px]]

* Add ''rf_classification_majority.tif'' to QGIS canvas.
* Download the style file '''classified.qml''' from Stud.IP.
* Right click on the layer ''rf_classification_majority'' and select {{mitem|text=Properties --> Style --> Style --> Load Style}}.
* Select the style file '''classified.qml'''. {{button|text=OK}}.

[[Category:QGIS Tutorial]]