I was wondering if there is a way to conduct Land Cover Signature Classification, as specified on page 122 of the following user manual: https://buildmedia.readthedocs.org/media/pdf/semiautomaticclassificationmanual/latest/semiautomaticclassificationmanual.pdf, on Google Earth Engine.

Essentially, my problem consists of the following: using a single image, I am trying to find pixels whose spectral curves are contained within a certain threshold from my training ROI's spectral curve. It is almost equivalent to performing a one-class supervised classification, but a bit more rigorous due to the threshold requirement. This is similar to Parallelepiped Classification, with the exception that spectral regions are defined by user, and can be assigned independently for the upper and lower bounds.

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.