Clovis Didry <[email protected]> wrote: > Hello > > Is there someone here who made a SOM classification to classify linear > and unlinear woody area. I found this solutions of SOM classification, > is it the good way to make this type of classification ? If it's the > good method, could you explain me how can I make it on monteverdi/OTB > with the application. > > Thanks a lot
Hi, The Self Organizing Map (SOM) is an unsupervised classification method. You can see it as a non-linear version of the k-means approach which is more flexible and has also the advantage of giving a spatial representation of the clusters (the "Map" in the name of the method). OTB has an application for that: otbcli_SOMClassification. However, there is nothing particular in the SOM method which makes it specially a good solution for the discrimination of elongated vegetation areas with respect to other types of vegetation. If you want to make this distinction using unsupervised classification, you will have to find the appropriate features that can be extracted from the images. In you case, I would suggest the SFS (structural feature set, using the otbcli_SFSTextureExtraction application). You can combine these features with vegetation indices and textures and perform the classification. Jordi -- -- Check the OTB FAQ at http://www.orfeo-toolbox.org/FAQ.html You received this message because you are subscribed to the Google Groups "otb-users" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/otb-users?hl=en --- You received this message because you are subscribed to the Google Groups "otb-users" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. For more options, visit https://groups.google.com/d/optout.
