I'm also trying to do object-based image classification and am running in 
the same kind of trouble.

Can somebody help please ?

Le lundi 16 novembre 2015 11:00:53 UTC+1, Thayse Nery a écrit :
>
> I am trying to run an object-based classification using Orfeo and R. The 
> Landsat images were segmented using Monteverdi (Orfeo Toolbox).
> My problem is that the results (confusion matrix) are represented as the 
> total number of pixels per class instead of number of segments as training 
> object. 
> I applied the following steps: 
>    
>    1. The landsat images were segmented using the 4 steps of Large Scale 
>    Mean Shift Segmentation LSMS (Orfeo Toolbox). The segments generated in 
> the 
>    4th step of LSMS is a shapefile.
>    2. Training samples (segments) were selected from the LSMS 4.
>    3. Then I applied the classification using the original Landsat Image 
>    as input image.
>
> The classification doesn't allocate the whole segments per class, rather 
> it allocate number of pixels within a segment. Although I segmented the 
> images using the LSMS approach, the Landsat image are not considered an 
> object in the classification. For that reason my results are basically an 
> pixel based classification instead of object-based.
>
> It seems that I am missing a step in order to have an object based 
> classification. 
> I really appreciate any help.
>
>

-- 
-- 
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