[GRASS-user] Clustering process in i.segment

Giuseppe Esposito peppegeo84 at gmail.com
Tue May 8 07:31:36 PDT 2018


Thanks for your explanation Marcus.

It was very useful for better understanding results of my segmentation.

Giuseppe

2018-05-08 8:22 GMT+02:00 Markus Metz <markus.metz.giswork a gmail.com>:

>
>
> On Mon, May 7, 2018 at 4:03 PM, Giuseppe Esposito <peppegeo84 a gmail.com>
> wrote:
> >
> > Dear GRASS GIS experts,
> >
> > I’m approaching segmentation in GRASS GIS and some doubts arised when
> reading the manual of the i.segment module (https://grass.osgeo.org/
> grass74/manuals/i.segment.html). For this reason, I would like to ask if
> someone may provide me further explanations about the following point.
> >
> > I understood that the mean shift image segmentation consists of 2 steps:
> anisotrophic filtering and clustering. It is non immediatelly clear to me
> how the second step (clustering) is working and I can't find help from the
> manual. I am not understanding how this process is performed in the
> i.segment module, as well as if I can set it somehow. Do someone can help
> me with some explanation or reference about the clustering process in
> i.segment?
>
> The clustering is the same like in r.clump: it identifies connected
> components by grouping neighboring cells together that are similar to each
> other with regard to hr (spectral bandwidth). Each group of cells becomes
> an object in the final output.
>
> Markus M
>
> >
> > Thanks in advance for your help.
> >
> > Giuseppe Esposito
> >
> >
> >
> > _______________________________________________
> > grass-user mailing list
> > grass-user a lists.osgeo.org
> > https://lists.osgeo.org/mailman/listinfo/grass-user
>
>
-------------- parte successiva --------------
Un allegato HTML è stato rimosso...
URL: <http://lists.osgeo.org/pipermail/grass-user/attachments/20180508/b6d4c1f7/attachment-0001.html>


More information about the grass-user mailing list