Can anyone provide some guidance on how to set the convergence threshold 
and max iteration parameters for the LSMS Smoothing application.
I notice that the source code defaults these to threshold=0.001 and 
maxIteration=4, but the example doc [1] sets these to 0.1 and 100 
respectively.
It seems that the optimal choice of these parameters impacts the trade off 
between segmentation quality and algorithm performance.

While searching for some information on this, I came across a paper "A new 
stopping criterion for the mean shift iterative algorithm", by Rodrıguez et 
al [2] that might be of interest.

[1] https://www.orfeo-toolbox.org/Applications/MeanShiftSmoothing.html
[2] https://arxiv.org/pdf/1311.2014.pdf

-- 
-- 
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