Shouldn't we use spectral, spatial, and contextual attributes of our 
objects (segments) while we are classifying our image? Isn't this the 
difference between the object-based and pixel-based classifications? 

I'm not sure if I'm on the right track or not but I thought I should 
calculate the spectral, spatial, and contextual attributes of the objects 
both in segmented image and training vector file and by the algorithms like 
RandomForest find the resemblance and finally generate the classified map.

On Thursday, March 2, 2017 at 5:06:01 AM UTC-3:30, Arnaud Durand wrote:
>
> The application ObjectsRadiometricStatistics only put shape and 
> radiometric information in the attribute table of a Shapefile representing 
> a segmentation.
> The idea is to permit in a further step a selection by attributes with a 
> GIS software.
>
>

-- 
-- 
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