Thanks, but please specify that ranger refers to an euclidean spectral
distance in the doc.
Agus


On Mon, Dec 15, 2014 at 2:46 PM, Julien Michel <[email protected]> wrote:
> Le 15/12/2014 10:08, Agustin Lobo a écrit :
>>
>> Consider the workflow provided in
>> http://www.orfeo-toolbox.org/CookBook/CookBooksu42.html
>>
>> 1. Which metric is the one being used as "ranger" in
>> otbcli_MeanShiftSmoothing
>> and otbcli_LSMSSegmentation? is it just a range
>> of DN to be applied to each single band? is it an euclidean distance
>> in the space of all bands?
>
> It is a spectral euclidean distance.
>
>>
>> 2. For otbcli_LSMSSegmentation: how are pixels included in one cluster
>> in the case of multi-spectral images? The manual sates
>> "This application will produce a labeled image where neighbor pixels
>> whose range distance is below range radius (and optionally spatial
>> distance below spatial radius) will be grouped together into the same
>> cluster."
>> but this is unambiguous just in the case of one single band. How is
>> the multi-band case managed? Are pixels grouped if their range
>> distance is <= ranger for all bands?
>
> Since range distance is euclidean it is a R^n -> R application, so there is
> no ambiguity.
>
>>
>> 4. Are images normalized before the "range distance" is calculated?
>
> No, it is the responsibility of the user to provide an input feature space
> where euclidean distance is (at least a bit) meaningful.
>>
>>
>> Thanks for clarifying these details, they do matter for the user to
>> select the appropriate ranger parameter.
>
>
> If you did not already read it, you can read our paper which explains into
> details this method :
>
> http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6849524&queryText%3DArbitrarily+large+remote+sensing+images
>
> Regards,
>
> Julien
>
> --
> 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.

-- 
-- 
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