[GRASS-user] classify image after i.segment

Dear all,

I got a set of i.segment output objects, and would like to classify the pixels within the regions.

how can I do that?

best wishes

Miltinho - mcr@rc.unesp.br
Laboratório de Ecologia Espacial e Conservação - LEEC
Depto de Ecologia - UNESP - Rio Claro
Av. 24A, 1515- Bela Vista
13506-900 Rio Claro, SP, Brasil

Fone: +55 19 3526-9647 (office) 19 3526-9680 (lab)
Cel: 19 9853-3220 / 19 9853-5430

Depto Ecologia http://ib.rc.unesp.br/#!/departamentos/ecologia/
PG ECO & BIODIV http://ib.rc.unesp.br/#!/departamentos/ecologia/pos-graduacao-em-ecologia-e-biodiversidade/

CV http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4792988H6&mostrarNroCitacoesISI=true&mostrarNroCitacoesScopus=true

Google citations http://scholar.google.com/citations?user=OWX_2eAAAAAJ

On 26/06/14 05:33, Milton Ribeiro wrote:

Dear all,

I got a set of i.segment output objects, and would like to classify the
pixels within the regions.

Check out the v.class.ml addon [1].

For a general procedure with modules in GRASS core see the script attached to this message [2]

And the web page that Martin Landa elaborated in czech based on that script [3] which you can run through Google translate to get it in your desired language [4].

Moritz

[1] https://svn.osgeo.org/grass/grass-addons/grass7/vector/v.class.ml/
[2] http://lists.osgeo.org/pipermail/grass-user/2013-October/069189.html
[3] http://geo.fsv.cvut.cz/gwiki/153ZODH_/_15._cvičení
[4] http://translate.google.com/translate?sl=cs&tl=en&js=n&prev=_t&hl=en&ie=UTF-8&u=http%3A%2F%2Fgeo.fsv.cvut.cz%2Fgwiki%2F153ZODH_%2F_15._cvi%25C4%258Den%25C3%25AD&act=url

Thanks Moritz,

I will check all the suggestions.

cheers

miltinho

···

2014-06-26 9:43 GMT-03:00 Moritz Lennert <mlennert@club.worldonline.be>:

On 26/06/14 05:33, Milton Ribeiro wrote:

Dear all,

I got a set of i.segment output objects, and would like to classify the
pixels within the regions.

Check out the v.class.ml addon [1].

For a general procedure with modules in GRASS core see the script attached to this message [2]

And the web page that Martin Landa elaborated in czech based on that script [3] which you can run through Google translate to get it in your desired language [4].

Moritz

[1] https://svn.osgeo.org/grass/grass-addons/grass7/vector/v.class.ml/
[2] http://lists.osgeo.org/pipermail/grass-user/2013-October/069189.html
[3] http://geo.fsv.cvut.cz/gwiki/153ZODH_/_15._cvi%C4%8Den%C3%AD
[4] http://translate.google.com/translate?sl=cs&tl=en&js=n&prev=t&hl=en&ie=UTF-8&u=http%3A%2F%2Fgeo.fsv.cvut.cz%2Fgwiki%2F153ZODH%2F_15._cvi%25C4%258Den%25C3%25AD&act=url

Miltinho - mcr@rc.unesp.br
Laboratório de Ecologia Espacial e Conservação - LEEC
Depto de Ecologia - UNESP - Rio Claro
Av. 24A, 1515- Bela Vista
13506-900 Rio Claro, SP, Brasil

Fone: +55 19 3526-9647 (office) 19 3526-9680 (lab)
Cel: 19 9853-3220 / 19 9853-5430

Depto Ecologia http://ib.rc.unesp.br/#!/departamentos/ecologia/
PG ECO & BIODIV http://ib.rc.unesp.br/#!/departamentos/ecologia/pos-graduacao-em-ecologia-e-biodiversidade/

CV http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4792988H6&mostrarNroCitacoesISI=true&mostrarNroCitacoesScopus=true

Google citations http://scholar.google.com/citations?user=OWX_2eAAAAAJ

On Wed, Jun 25, 2014 at 11:33 PM, Milton Ribeiro <
miltinho.astronauta@gmail.com> wrote:

Dear all,

I got a set of i.segment output objects, and would like to classify the
pixels within the regions.

how can I do that?

Hi, recently I created:

[GRASS-user] Summary of object-based classification possibilities in GRASS
GIS (June 2014)
http://lists.osgeo.org/pipermail/grass-user/2014-June/070384.html

best wishes

--
Miltinho - mcr@rc.unesp.br
Laboratório de Ecologia Espacial e Conservação - LEEC
Depto de Ecologia - UNESP - Rio Claro
Av. 24A, 1515- Bela Vista
13506-900 Rio Claro, SP, Brasil

Fone: +55 19 3526-9647 (office) 19 3526-9680 (lab)
Cel: 19 9853-3220 / 19 9853-5430

Depto Ecologia http://ib.rc.unesp.br/#!/departamentos/ecologia/
PG ECO & BIODIV
http://ib.rc.unesp.br/#!/departamentos/ecologia/pos-graduacao-em-ecologia-e-biodiversidade/

CV
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4792988H6&mostrarNroCitacoesISI=true&mostrarNroCitacoesScopus=true

Google citations http://scholar.google.com/citations?user=OWX_2eAAAAAJ

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

Hi, recently I created:

[GRASS-user] Summary of object-based classification possibilities in GRASS

GIS (June 2014)

http://lists.osgeo.org/pipermail/grass-user/2014-June/070384.html

any chance to put this to the wiki?

-----
best regards
Helmut
--
View this message in context: http://osgeo-org.1560.x6.nabble.com/classify-image-after-i-segment-tp5147999p5148167.html
Sent from the Grass - Users mailing list archive at Nabble.com.

On Thu, Jun 26, 2014 at 11:44 AM, Helmut Kudrnovsky <hellik@web.de> wrote:

>Hi, recently I created:
>
>[GRASS-user] Summary of object-based classification possibilities in GRASS
GIS (June 2014)
>http://lists.osgeo.org/pipermail/grass-user/2014-June/070384.html

any chance to put this to the wiki?

There is "Image classification" page, so perhaps "Object-based

classification"? The topic is much broader if you consider lidar. But there
is certainly a overlap (once you classify based on attribute table).

But anyway, I'm not sure, I can copy and paste it there but it is just
bunch of links, nothing nice.

http://grasswiki.osgeo.org/wiki/Image_classification

-----
best regards
Helmut
--
View this message in context:
http://osgeo-org.1560.x6.nabble.com/classify-image-after-i-segment-tp5147999p5148167.html
Sent from the Grass - Users mailing list archive at Nabble.com.
_______________________________________________
grass-user mailing list
grass-user@lists.osgeo.org
http://lists.osgeo.org/mailman/listinfo/grass-user

But anyway, I'm not sure, I can copy and paste it there but it is just

bunch of links, nothing nice.

IMHO nice links to nice howto's are often lost in MLs and are some kind of
more persistent in wikis.

-----
best regards
Helmut
--
View this message in context: http://osgeo-org.1560.x6.nabble.com/classify-image-after-i-segment-tp5147999p5148216.html
Sent from the Grass - Users mailing list archive at Nabble.com.

Just one more question:

how can I use the objects output from i.segment in the steps to classify the image using i.maxlik?
I tried to find a step-by-step classification using the raster objects from i.segment by no luck.

best wishes

milton

···

2014-06-26 18:34 GMT-03:00 Helmut Kudrnovsky <hellik@web.de>:

But anyway, I’m not sure, I can copy and paste it there but it is just
bunch of links, nothing nice.

IMHO nice links to nice howto’s are often lost in MLs and are some kind of
more persistent in wikis.


best regards
Helmut

View this message in context: http://osgeo-org.1560.x6.nabble.com/classify-image-after-i-segment-tp5147999p5148216.html

Sent from the Grass - Users mailing list archive at Nabble.com.


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

Miltinho - mcr@rc.unesp.br
Laboratório de Ecologia Espacial e Conservação - LEEC
Depto de Ecologia - UNESP - Rio Claro
Av. 24A, 1515- Bela Vista
13506-900 Rio Claro, SP, Brasil

Fone: +55 19 3526-9647 (office) 19 3526-9680 (lab)
Cel: 19 9853-3220 / 19 9853-5430

Depto Ecologia http://ib.rc.unesp.br/#!/departamentos/ecologia/
PG ECO & BIODIV http://ib.rc.unesp.br/#!/departamentos/ecologia/pos-graduacao-em-ecologia-e-biodiversidade/

CV http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4792988H6&mostrarNroCitacoesISI=true&mostrarNroCitacoesScopus=true

Google citations http://scholar.google.com/citations?user=OWX_2eAAAAAJ

On Thu, Jun 26, 2014 at 5:34 PM, Helmut Kudrnovsky <hellik@web.de> wrote:

> But anyway, I'm not sure, I can copy and paste it there but it is just
bunch of links, nothing nice.

IMHO nice links to nice howto's are often lost in MLs and are some kind of
more persistent in wikis.

http://grasswiki.osgeo.org/wiki/Image_classification#Object-based_classification

On 26/06/14 23:54, Milton Ribeiro wrote:

Just one more question:

how can I use the objects output from i.segment in the steps to classify
the image using i.maxlik?
I tried to find a step-by-step classification using the raster objects
from i.segment by no luck.

If you really want to use i.maxlik, you have to create as many raster layers as you want to have variables characterizing your objects. Then you select a series of these objects as training areas and then you can run i.gensig + i.maxlik.

But I think that the machine learning approach, using Pietros addon-modules, is probably more efficient.

Moritz