Classification with Orfeo Toolbox

Training per-pixel classifiers

Type into the search box of the Windows taskbar: mapla.bat. Click on mapla.bat to open Monteverdi Application Launcher.
In the search engine of mapla, type TrainImages and double click TrainImagesClassifer.
In the Input Image List click on + and select a (or optional: several) multispectral images: Subset_S2A_MSIL2A_20170619T_MUL.tif .
In the Input Vector Data List choose a vector polygon file with training areas: lab07_training_input.shp.
Activate the checkbox Validation Vector Data List and choose a vector polygon file with an independent sample of validation areas: lab07_validation_input.shp
In the Output model specify an output model file: e.g. svm.model
Activate the checkbox and save the Output confusion matrix or contingency table as ConfusionMatrixSVM.csv.
In the Bound sample number by minimum field type 0.
Set the training and validation sample ratio to 0. (0 = all training data).
Set Field containing the class integer label to C_ID (C_ID refers to the column that contains the LUC code in the training and validation vector file).
Choose LibSVM classifier from the drop down list as Classifier to use for the training.
The SVN Kernel Type is Gaussian radial basis function.
Switch the Parameters optimization to on.
Set user defined seed with an integer value.
Click on Execute.

Open Orfeo Toolbox --> Image Classification (see figure C).
Set Subset_S2A_MSIL2A_20170619T_MUL_BOA.tif as Input image.
Set SVM.model as Model file.
Set Subset_S2A_MSIL2A_20170619T_MUL_BOA.xml as Statistical file.
Save the Output image as su_svm.tif.
Evaluate classification results.
1. Add the classification result su_svm.tif to QGIS.
2. Right click su_svm.tif in the TOC and select Properties --> Style --> Style --> Load Style.
3. Load lab05_MinDist.qml.