Dear otb-users:
I'm trying to get fractional cover by unmixing using Hyperspectral Unmixing 
application. The inputs I'm using are a Landsat 7 images and a raster of 
endmembers derived from field data in the required format, 1 row x c clases 
x b bands.
My problem is while trying to interpret the outputs. I was expecting to get 
as many layers as endmembers classes, with values ranging 0-1 and summing 1 
(unmix1+unmix2+unixN=1), but the resulting raster as you can see in the 
attached histogram are varying between -20 and 20
And the values depends on the method used (ucls, isra, etc). Where can I 
found more information about the methods and how to interpret the results?

Regards.

Dr. Leonardo Hardtke

-- 
-- 
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.

Reply via email to