This worksheet covers the first approach of an actual land-cover classification based on the comprehensive data set and training sites from the last session. After completing this worksheet you should have gained some feeling for the modelling approach and for an eyeball analysis.
QGIS and OTB — For remote sensing related tasks, we recommend to use the capabilities of QGIS including the Orfeo ToolBox (OTB) plugin. Regarding the installation, the unstable repository of the Ubuntu GIS package is a good choice for Linux while we strongly recommend the OSGeo4W environment as installation source for Windows users. Please have a look at the actual OTB download options prior your installation of QGIs. If you experience troubles with the OTB plugins in QGis, you can also install Monteverdi2 which is a stand alone GUI for OTB.
Now that we have (i) a comprehensive explanatory data set and (ii) training sites at hand, we are ready to actually perform a supervised land-cover classification.
Compute a land-cover classification with a random forest classifier.
Perform an eyeball-analysis of the classification results and identify at least 2 regions per land-cover class where the classification results are sub-optimal.
Based on your impression, decide if it would be more productive to test another classifier or to change your training areas or the baseline data set.
If you need the 1m RGB data set, use this link (works only from within the university network)