I'm trying to make a supervised classification using QGIS and Semi-Automatic Classification Plugin using high resolution images (5 m). I wonder how many samples I need to have for an efficient classification and also if there's a standard for the height and width in pixels of the ROI (Region of interest). For example, if I have two areas of 10 square kilometers each, should I create only two ROIs or more small ROIs?

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.