Hello, 

for large images, there is a four step process called "Large Scale Mean 
Shift segmentation. You can find a tutorial in here : 
https://www.orfeo-toolbox.org/CookBook/Applications/app_LargeScaleMeanShift.html

Note that mean shift segmentation is very time consuming, so it is 
difficult to accelerate. On the other hand, streaming is usually activated 
by default in OTB filters, but it works best for pixel based or block based 
analysis, while segmentation needs to keep information about the 
surrounding pixels at an undefined distance, so the memory handling is much 
more complex (if you don't want to see tiles). 

Le lundi 5 mars 2018 14:01:50 UTC+1, nouha touihri a écrit :
>
>
> Hello  all!
>
> I'm trying to segment a pléiade image and  my study area is 123 km^2 = 
> 22000 x 22000 pixels. The segmentation (meanshift) algorithm is taking more 
> than a week now and didn't bypasse 28% of the process! I'm using a work 
> station dell e5! on the otb cookbook documentation, the image size 
> limitation of OTB is mentioned and they said that this limitation can be 
> bypassed thanks to the streaming mechanism implemented within OTB’s 
> pipeline (actually ITK’s). does anyone know what OTB’s pipeline means ? how 
> to bypassed the processing time problem? 
>
> Best,
>
> Nouha,
>

-- 
-- 
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