Thanks Jordi for answering, you are indeed right. Range radius is expressed in pixel values, so if they range in [0,1], range radius should be in that range to (and on the low end of it).

Regards,

Julien

Le 03/08/2015 08:34, Jordi Inglada a écrit :
Hi Thayse,

I don't know well how the framework is implemented, but since nobody
answered to your message, I will try to help here.

If you start the process with the MeanShift smoothing, you have to
bear in mind that the spatial radius parameter is related to the range of
the input values. The default value for this parameter in the
application is 15. Try to make it something like 0.1 and see what
happens.

Good luck.

Jordi

Thayse Nery <[email protected]> wrote:
Hi,

I have converted DN values of Landat 8 OLI to Top of Atmosphere (ToA) 
Reflectance using GRASS 7 and I would like to know if the Exact Large-Scale 
Mean-Shift segmentation (LSMS) from Orfeo Toolbox works
for TOA values.

I tried to apply all 4 steps of the LSMS using the bands with TOA values, which 
output range is 0-1, and it does not work. For example for the Band 4 I got a 
minimum value of -5.35928e+21 and max 0.01452.
And for LSMS step 2 a got only a black square.

Do I need to convert the values to DN in order to apply the LSMS using Orfeo 
toolbox in QGis 2.8.1? If yes, how can I convert from TOA value to DN?

Thanks for any advice.

Thayse Figueiredo


--


--
Julien MICHEL
CNES - DCT/SI/AP - BPI 1219
18, avenue Edouard Belin
31401 Toulouse Cedex 09 - France
Tel: +33 561 282 894 - Fax: +33 561 283 109

--
--
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