Supervised classification (Tutorial)
Revision as of 09:02, 4 July 2019 by Hfuchs
Per pixel classification with QGIS and OTB processing plugin
- In the search engine of Processing Toolbox, type TrainImages and open TrainImagesClassifer.
Per pixel classification with OTB standalone
- 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 click on and select a (or optional: several) multispectral images: Subset_S2A_MSIL2A_20170619T_MUL.tif .
- In the choose a vector polygon file with training areas: lab07_training_input.shp.
- Activate the checkbox and choose a vector polygon file with an independent sample of validation areas: lab07_validation_input.shp
- In the specify an output model file: e.g. SVM.model
- Activate the checkbox and save the as ConfusionMatrixSVM.csv.
- In the 1. field type
- Set the 0. (0 = all training data). to
- Set to C_ID (C_ID refers to the column that contains the LUC code in the training and validation vector file).
- Choose from the drop down list as Classifier to use for the training.
- The SVM Kernel Type is .
- Switch the Parameters optimization to .
- Set user defined seed with an integer value.
- Click on .
- In the search engine of mapla, type ImageClassifier and double click ImageClassifier
- Set Subset_S2A_MSIL2A_20170619T_MUL.tif as .
- Set SVM.model as .
- Save the as svm_classification.tif.
- Evaluate classification results:
- Load the multispectral Sentinel-2 image Subset_S2A_MSIL2A_20170619T_MUL.tif into QGIS.
- Data source Manager --> Browser --> XYZ Tiles. Select Google Satellite as background layer.
- Load the European Urban Atlas as vector layer Subset-Goe_DE021L1_GOTTINGEN_UA2012_UTM32N.shp
- Add svm_classification.tif to the QGIS project.
- Download the style file classifcation.qml from Stud.IP.
- Right click svm_classification.tif in the TOC and select Properties --> Style --> Style --> Load Style.
- Select the style file classification.qml. .
- Open the text file ConfusionMatrixSVM.csv and calculate overall, user and producer accuracies.