Re: [GRASS-user] Image segmentation to separate object from background

[Markus Neteler]

On Mon, Jun 26, 2017 at 4:32 PM, Nikos Alexandris
 wrote:
...
> I was looking for, similarly, last week. What is the status of:
>
> - ann.create; ann.info; ann.data.rast; ann.learn; ann.run.rast? See
> doi:10.4172/2329-6755.1000145
> - see also related reference about "ann.*" at
> https://grasswiki.osgeo.org/wiki/AddOns
>  -- link is "broken".
> - http://www.uam.es/proyectosinv/Mclim/pdf/MBenito_EcoMod.pdf: broken
>  linke reference in our wiki (https://grasswiki.osgeo.org/wiki/R_statistics)

 I fixed in in the wiki:
 --> https://dx.doi.org/10.1016/j.ecolmodel.2006.03.015
   behind a paywall, though... (I can send an author's copy upon request).

Markus
___
grass-user mailing list
grass-user@lists.osgeo.org
https://lists.osgeo.org/mailman/listinfo/grass-user

Re: [GRASS-user] Image segmentation to separate object from background

[Nikos Alexandris]

* Moritz Lennert  [2017-06-26 15:38:53 +0200]:


On 26/06/17 15:01, Johannes Radinger wrote:

Hi GRASS users,

has anyone of you tried to use GRASS image tools (e.g. segmentation etc)
to identify an object in a picture. For example I have multiple photos
of fish and would like to separate the fish from its background in an
automatized way. The images look like:

http://fishbase.org/photos/PicturesSummary.php?ID=4730&what=species

http://fishbase.org/photos/PicturesSummary.php?StartRow=0&ID=4662&what=species&TotRec=5


So what I already know apriori: I would like two final classes (fish and
background), the fish is more or less centred within each picture, and
there is only one fish in each picture. I played already around with
i.segment but the results are not yet satisfying.


You will certainly have to go through a classification phase:
oversegment the image and then classify the resulting segments as fish
or non-fish. Probably results will be better if you classify into more
non-fish classes which you can then merge at the end.

Currently, we don't have semantic segmentation in GRASS GIS, i.e.
segmentation that "recognizes" real objects and it is difficult to get
complete real objects just through the segmentation methods we have
(check i.segment, i.superpixels.slic, but also edge detection, such as
i.zc).

For real semantic object recognition, neural network approaches seem the
way to go today, so you might want to look into those.

Moritz


I was looking for, similarly, last week. What is the status of:

- ann.create; ann.info; ann.data.rast; ann.learn; ann.run.rast? See 
doi:10.4172/2329-6755.1000145
- see also related reference about "ann.*" at 
https://grasswiki.osgeo.org/wiki/AddOns
 -- link is "broken".
- http://www.uam.es/proyectosinv/Mclim/pdf/MBenito_EcoMod.pdf: broken
 linke reference in our wiki
 (https://grasswiki.osgeo.org/wiki/R_statistics)

Nikos
___
grass-user mailing list
grass-user@lists.osgeo.org
https://lists.osgeo.org/mailman/listinfo/grass-user

Re: [GRASS-user] Image segmentation to separate object from background

[Moritz Lennert]

On 26/06/17 15:01, Johannes Radinger wrote:

Hi GRASS users,

has anyone of you tried to use GRASS image tools (e.g. segmentation etc)
to identify an object in a picture. For example I have multiple photos
of fish and would like to separate the fish from its background in an
automatized way. The images look like:

http://fishbase.org/photos/PicturesSummary.php?ID=4730&what=species

http://fishbase.org/photos/PicturesSummary.php?StartRow=0&ID=4662&what=species&TotRec=5


So what I already know apriori: I would like two final classes (fish and
background), the fish is more or less centred within each picture, and
there is only one fish in each picture. I played already around with
i.segment but the results are not yet satisfying.


You will certainly have to go through a classification phase: 
oversegment the image and then classify the resulting segments as fish 
or non-fish. Probably results will be better if you classify into more 
non-fish classes which you can then merge at the end.


Currently, we don't have semantic segmentation in GRASS GIS, i.e. 
segmentation that "recognizes" real objects and it is difficult to get 
complete real objects just through the segmentation methods we have 
(check i.segment, i.superpixels.slic, but also edge detection, such as 
i.zc).


For real semantic object recognition, neural network approaches seem the 
way to go today, so you might want to look into those.


Moritz
___
grass-user mailing list
grass-user@lists.osgeo.org
https://lists.osgeo.org/mailman/listinfo/grass-user

[GRASS-user] Image segmentation to separate object from background

[Johannes Radinger]

Hi GRASS users,

has anyone of you tried to use GRASS image tools (e.g. segmentation etc) to
identify an object in a picture. For example I have multiple photos of fish
and would like to separate the fish from its background in an automatized
way. The images look like:

http://fishbase.org/photos/PicturesSummary.php?ID=4730&what=species
http://fishbase.org/photos/PicturesSummary.php?StartRow=
0&ID=4662&what=species&TotRec=5

So what I already know apriori: I would like two final classes (fish and
background), the fish is more or less centred within each picture, and
there is only one fish in each picture. I played already around with
i.segment but the results are not yet satisfying.

Any ideas?

/johannes
___
grass-user mailing list
grass-user@lists.osgeo.org
https://lists.osgeo.org/mailman/listinfo/grass-user

Re: [GRASS-user] Image segmentation

[Moritz Lennert]

Le Thu, 19 Jan 2017 11:08:13 -0500,
Giuseppe Amatulli  a écrit :

> Thanks Markus,
> the problem with the v.voronoi is that the polygon borders will be
> calculate based on point distance and not on the cost surface.
> Any other input?


Seems to me that "voronoi" is not what you are looking for.

Maybe you could have a look at some of the topographic modules like
r.param.scale or the addon r.geomorphon to extract the valleys.

Or you could you r.watershed but output the streams and/or the
accumulation map to identify the valleys. Then some magic to reduce
these to lines (r.reclass + r.thin maybe).


Moritz

> Best
> Giuseppe
> 
> 
> 
> On 19 January 2017 at 02:38, Markus Metz
>  wrote:
> 
>  [...]  
>  [...]  
>  [...]  
>  [...]  
>  [...]  
>  [...]  
>  [...]  
>  [...]  
>  [...]  
>  [...]  
>  [...]  
> 
> 

___
grass-user mailing list
grass-user@lists.osgeo.org
https://lists.osgeo.org/mailman/listinfo/grass-user

Re: [GRASS-user] Image segmentation

[Giuseppe Amatulli]

Thanks Markus,
the problem with the v.voronoi is that the polygon borders will be
calculate based on point distance and not on the cost surface.
Any other input?
Best
Giuseppe



On 19 January 2017 at 02:38, Markus Metz 
wrote:

>
>
> On Wed, Jan 18, 2017 at 8:16 PM, Giuseppe Amatulli <
> giuseppe.amatu...@gmail.com> wrote:
> >
> > Hi all,
> >
> > I would like to "segment" an image using a sort of Voronoi algorithm on
> a cost surface instead of distance between point.
> >
> > Below you can see an image where the black pixels identity areas with
> high cost value. I would like to identify the "valley" between theses black
> areas.
> >
> > In the second image I draft by hand an ideal solution for few high cost
> areas.
> >
> > Which grass command can do this kind of delineation?
>
> You can use v.voronoi: first extract the pixels with high cost values with
> e.g.
> r.mapcalc "high_cost = if(surface_map > threshold_value, 1, null())"
>
> Then convert to vector areas with
> r.to.vect input=high_cost output=high_cost type=area
>
> Now create Voronoi triangles for areas with
> v.voronoi input=high_cost output=high_cost_voronoi -a
>
> HTH,
>
> Markus M
> >
> > Thanks,
> >
> > Giuseppe
> >
> >
> >
> >
> >
> >
> > --
> > Giuseppe Amatulli, Ph.D.
> >
> > Research scientist at
> > Yale School of Forestry & Environmental Studies
> > Yale Center for Research Computing
> > Center for Science and Social Science Information
> > New Haven, 06511
> > Teaching: http://spatial-ecology.org
> > Work:  https://environment.yale.edu/profile/giuseppe-amatulli/
> >
> >
> >
> >
> > ___
> > grass-user mailing list
> > grass-user@lists.osgeo.org
> > https://lists.osgeo.org/mailman/listinfo/grass-user
>
>


-- 
Giuseppe Amatulli, Ph.D.

Research scientist at
Yale School of Forestry & Environmental Studies
Yale Center for Research Computing
Center for Science and Social Science Information
New Haven, 06511
Teaching: http://spatial-ecology.org
Work:  https://environment.yale.edu/profile/giuseppe-amatulli/
___
grass-user mailing list
grass-user@lists.osgeo.org
https://lists.osgeo.org/mailman/listinfo/grass-user

Re: [GRASS-user] Image segmentation

[Markus Metz]

On Wed, Jan 18, 2017 at 8:16 PM, Giuseppe Amatulli <
giuseppe.amatu...@gmail.com> wrote:
>
> Hi all,
>
> I would like to "segment" an image using a sort of Voronoi algorithm on a
cost surface instead of distance between point.
>
> Below you can see an image where the black pixels identity areas with
high cost value. I would like to identify the "valley" between theses black
areas.
>
> In the second image I draft by hand an ideal solution for few high cost
areas.
>
> Which grass command can do this kind of delineation?

You can use v.voronoi: first extract the pixels with high cost values with
e.g.
r.mapcalc "high_cost = if(surface_map > threshold_value, 1, null())"

Then convert to vector areas with
r.to.vect input=high_cost output=high_cost type=area

Now create Voronoi triangles for areas with
v.voronoi input=high_cost output=high_cost_voronoi -a

HTH,

Markus M
>
> Thanks,
>
> Giuseppe
>
>
>
>
>
>
> --
> Giuseppe Amatulli, Ph.D.
>
> Research scientist at
> Yale School of Forestry & Environmental Studies
> Yale Center for Research Computing
> Center for Science and Social Science Information
> New Haven, 06511
> Teaching: http://spatial-ecology.org
> Work:  https://environment.yale.edu/profile/giuseppe-amatulli/
>
>
>
>
> ___
> grass-user mailing list
> grass-user@lists.osgeo.org
> https://lists.osgeo.org/mailman/listinfo/grass-user
___
grass-user mailing list
grass-user@lists.osgeo.org
https://lists.osgeo.org/mailman/listinfo/grass-user

Re: [GRASS-user] Image segmentation

[Giuseppe Amatulli]

Thanks Pedro,
yes I had already tried, but i do not get really what I want. Moreover, the
delineation of watersheds is based on a predefined threshold that can be
quite arbitrary give really different results.

Best Giuseppe


On 18 January 2017 at 14:27, Pedro Venâncio 
wrote:

> Hi Giuseppe,
>
> Maybe you can use r.watershed [0] to get the "basins".
>
> Best regards,
> Pedro Venâncio
>
> [0] https://grass.osgeo.org/grass72/manuals/r.watershed.html
>
> 2017-01-18 19:16 GMT+00:00 Giuseppe Amatulli 
> :
>
>> Hi all,
>>
>>
>>
>> I would like to "segment" an image using a sort of Voronoi
>> 
>>  algorithm
>> on a cost surface instead of distance between point.
>>
>>
>>
>> Below you can see an image where the black pixels identity areas with
>> high cost value. I would like to identify the "valley" between theses black
>> areas.
>>
>>
>>
>> In the second image I draft by hand an ideal solution for few high cost
>> areas.
>>
>>
>>
>> Which grass command can do this kind of delineation?
>>
>>
>>
>> Thanks,
>>
>>
>> Giuseppe
>>
>>
>> [image: Inline images 1]
>>
>> [image: Inline images 2]
>>
>> --
>> Giuseppe Amatulli, Ph.D.
>>
>> Research scientist at
>> Yale School of Forestry & Environmental Studies
>> Yale Center for Research Computing
>> Center for Science and Social Science Information
>> New Haven, 06511
>> Teaching: http://spatial-ecology.org
>> 
>> Work:  https://environment.yale.edu/profile/giuseppe-amatulli/
>>
>>
>>
>>
>> ___
>> grass-user mailing list
>> grass-user@lists.osgeo.org
>> https://lists.osgeo.org/mailman/listinfo/grass-user
>>
>
>


-- 
Giuseppe Amatulli, Ph.D.

Research scientist at
Yale School of Forestry & Environmental Studies
Yale Center for Research Computing
Center for Science and Social Science Information
New Haven, 06511
Teaching: http://spatial-ecology.org
Work:  https://environment.yale.edu/profile/giuseppe-amatulli/
___
grass-user mailing list
grass-user@lists.osgeo.org
https://lists.osgeo.org/mailman/listinfo/grass-user

Re: [GRASS-user] Image segmentation

[Pedro Venâncio]

Hi Giuseppe,

Maybe you can use r.watershed [0] to get the "basins".

Best regards,
Pedro Venâncio

[0] https://grass.osgeo.org/grass72/manuals/r.watershed.html

2017-01-18 19:16 GMT+00:00 Giuseppe Amatulli :

> Hi all,
>
>
>
> I would like to "segment" an image using a sort of Voronoi
> 
>  algorithm
> on a cost surface instead of distance between point.
>
>
>
> Below you can see an image where the black pixels identity areas with high
> cost value. I would like to identify the "valley" between theses black
> areas.
>
>
>
> In the second image I draft by hand an ideal solution for few high cost
> areas.
>
>
>
> Which grass command can do this kind of delineation?
>
>
>
> Thanks,
>
>
> Giuseppe
>
>
> [image: Inline images 1]
>
> [image: Inline images 2]
>
> --
> Giuseppe Amatulli, Ph.D.
>
> Research scientist at
> Yale School of Forestry & Environmental Studies
> Yale Center for Research Computing
> Center for Science and Social Science Information
> New Haven, 06511
> Teaching: http://spatial-ecology.org
> 
> Work:  https://environment.yale.edu/profile/giuseppe-amatulli/
>
>
>
>
> ___
> grass-user mailing list
> grass-user@lists.osgeo.org
> https://lists.osgeo.org/mailman/listinfo/grass-user
>
___
grass-user mailing list
grass-user@lists.osgeo.org
https://lists.osgeo.org/mailman/listinfo/grass-user

[GRASS-user] Image segmentation

[Giuseppe Amatulli]

Hi all,



I would like to "segment" an image using a sort of Voronoi

algorithm
on a cost surface instead of distance between point.



Below you can see an image where the black pixels identity areas with high
cost value. I would like to identify the "valley" between theses black
areas.



In the second image I draft by hand an ideal solution for few high cost
areas.



Which grass command can do this kind of delineation?



Thanks,


Giuseppe


[image: Inline images 1]

[image: Inline images 2]

-- 
Giuseppe Amatulli, Ph.D.

Research scientist at
Yale School of Forestry & Environmental Studies
Yale Center for Research Computing
Center for Science and Social Science Information
New Haven, 06511
Teaching: http://spatial-ecology.org

Work:  https://environment.yale.edu/profile/giuseppe-amatulli/
___
grass-user mailing list
grass-user@lists.osgeo.org
https://lists.osgeo.org/mailman/listinfo/grass-user

Re: [GRASS-user] Image segmentation á-la eCog nition

[Marc Wieland]

Orfeo indeed seems to offer the most promising features at the moment. 
For a more user friendly but limited option, you could also try out the 
OTB plugin for QGIS 
(http://wiki.orfeo-toolbox.org/index.php/Quantum_GIS_plugins).

Cheers,
Marc

Am 26.03.2010 13:29, schrieb Leo Hardtke:

Hello,
maybe there are more options, but I only found Orfeo Toolbox. It s 
very complete but not user friendly.

Hope it helps.

http://www.orfeo-toolbox.org/otb/

joel dinis escribió:

Hello fellow GRASS users,

Can anyone tell if is possible to
do image segmentation, like
eCognition or SPRING, in GRASS.

I did some reasearch, but I couldn't
find anything about it.

Thank you 



___
grass-user mailing list
grass-user@lists.osgeo.org
http://lists.osgeo.org/mailman/listinfo/grass-user


___
grass-user mailing list
grass-user@lists.osgeo.org
http://lists.osgeo.org/mailman/listinfo/grass-user



___
grass-user mailing list
grass-user@lists.osgeo.org
http://lists.osgeo.org/mailman/listinfo/grass-user

Re: [GRASS-user] Image segmentation á-la eCog nition

[Leo Hardtke]

Hello,
maybe there are more options, but I only found Orfeo Toolbox. It s very 
complete but not user friendly.

Hope it helps.

http://www.orfeo-toolbox.org/otb/

joel dinis escribió:

Hello fellow GRASS users,

Can anyone tell if is possible to
do image segmentation, like
eCognition or SPRING, in GRASS.

I did some reasearch, but I couldn't
find anything about it.

Thank you 



___
grass-user mailing list
grass-user@lists.osgeo.org
http://lists.osgeo.org/mailman/listinfo/grass-user
  


___
grass-user mailing list
grass-user@lists.osgeo.org
http://lists.osgeo.org/mailman/listinfo/grass-user

[GRASS-user] Image segmentation á-la eCognition

[joel dinis]

Hello fellow GRASS users,

Can anyone tell if is possible to
do image segmentation, like
eCognition or SPRING, in GRASS.

I did some reasearch, but I couldn't
find anything about it.

Thank you
___
grass-user mailing list
grass-user@lists.osgeo.org
http://lists.osgeo.org/mailman/listinfo/grass-user

Re: [GRASS-user] image segmentation in GRASS

[Dylan Beaudette]

On Mon, Oct 6, 2008 at 6:51 AM, Davide Fornacca <[EMAIL PROTECTED]> wrote:
>
> Hello everybody,
>
> I'm new in Grass and I'm trying the image segmentation and classification
> with the i.smap module. This, with spot imagery 5 and 10 meters resolution.
>
> Can I see the segmented image before the classification?
> What do you think about the grass opportunities on image segmentation?
> Do you know other good, open source image segmentation softwares like
> SPRING?
>
> Thank you and have a nice week!
>
> Dade Send

If the image stack is small enough to fit into memory, check out the
clara() function from the cluster package in R.

Cheers,

Dylan
___
grass-user mailing list
grass-user@lists.osgeo.org
http://lists.osgeo.org/mailman/listinfo/grass-user

[GRASS-user] image segmentation in GRASS

[Davide Fornacca]

Hello everybody,

I'm new in Grass and I'm trying the image segmentation and classification with 
the i.smap module. This, with spot imagery 5 and 10 meters resolution.

Can I see the segmented image before the classification?
What do you think about the grass opportunities on image segmentation?
Do you know other good, open source image segmentation softwares like SPRING? 

Thank you and have a nice week!

Dade
Send
_
News, entertainment and everything you care about at Live.com. Get it now!
http://www.live.com/getstarted.aspx___
grass-user mailing list
grass-user@lists.osgeo.org
http://lists.osgeo.org/mailman/listinfo/grass-user