Geographic Information Systems Stack Exchange is a question and answer site for cartographers, geographers and GIS professionals. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

Is there any tool or plugin for QGIS/GRASS to make an automatic land cover classification from satellite imagery --- based on CLC nomenclature for example? Of course, it will not be 100% sure but it would be a first step of the classification process.

I have seen a similar tool expressed into a pdf file on the QGIS blog, but it seems the plugin has not been implemented (at least, not listed into the plugin repository).

I have also the existence of the Molusce plugin. I haven't tested it yet but the approach seems to be based on land use changes.

share|improve this question
Do you need land use or land cover? Land use cannot be derived from satellite imagery alone. – underdark Mar 14 '12 at 11:54
Indeed, I mean land cover of course – simo Mar 14 '12 at 13:28

It will be very difficult to perform an automatic Land Cover Classification based on the 44 class Corine Land Cover nomenclature. but as you say it could be a starting point.

You can use the GrassGIS plugin for QGIS - check this- namely for the spectral classification. Don't forget to integrate the ndvi.

Also you can try to perform a segmentation of the image first to have the image divided into 25ha polygons (MMU for CLC).

Then integrate the spectral classification into the polygons, i.e. classify the polygons accordingly to class of the majority of the matching pixels.

Regards, Vasco Nunes

share|improve this answer

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.