Details can be found here :
http://hg.orfeo-toolbox.org/OTB/file/13189e3b03df/Modules/Filtering/Smoothing/include/otbMeanShiftSmoothingImageFilter.txx#l711

The threshold is applied on the squared norm of the mean shift vector.
This vector is in a joint space : (2 spatial dimensions + 'nbBands'
radiometric dimensions). So the threshold is in a composite unit where 1
DN ~ 1 pixel size.

Regards,
Guillaume

On 06/19/2015 09:45 AM, Agustin Lobo wrote:
> Are you sure? is it not DN**2 ? Note we have geographic and radiometric 
> spaces.
> Agus
> 
> On Thu, Jun 18, 2015 at 11:35 AM, Guillaume Pasero
> <[email protected]> wrote:
> 
>>> The convergence threshold is expressed in the same numbers as the
>>> spatial radius (e.g. default o 0.10 pixels), right?
>> According to otbMeanShiftSmoothingImageFilter.h, the threshold is
>> compared to the squared norm of the mean shift vector (so units should
>> be pixel²)
> 

-- 
<www.c-s.fr>    *Guillaume PASERO*
Ingénieur d'études et développement
*Business Unit E-SPACE & Geo Information*
<https://thor.si.c-s.fr/blogs/cs-blogs-business/>*- Département
APPLICATIONS*

*CS Systèmes d'Information*
Parc de la Grande Plaine - 5, Rue Brindejonc des Moulinais - BP 15872
31506 Toulouse Cedex 05 - FRANCE
+33 561 17 64 21 - [email protected]

-- 
-- 
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