many thanks Guillaume ,
see my code below ...
The number of the channels are good ? if yes , i don't see my
error
see you
Michel
otbcli_ConcatenateImages.bat -il LAND*.TIF -out
alldates2014_avignon_landsat.TIF uint16
for f in LAND*.TIF; do otbcli_RadiometricIndices.bat
-channels.blue 2 -channels.green 3 -channels.red 4 -channels.nir
5 -in "$f" -out "NDVI_$f" -list Vegetation:NDVI; done
(good number ???)
otbcli_ConcatenateImages.bat -il NDVI*.TIF -out
alldates2014_avignon_landsat_nvdi.TIF uint16
| otbcli_ConcatenateImages.bat
-il alldates2014_avignon_landsat.TIF
alldates2014_avignon_landsat_nvdi.TIF -out
alldates2014_avignon_landsat_bandes_et_nvdi.TIF uint16 |
otbcli_PolygonClassStatistics.bat -in
alldates2014_avignon_landsat.tif -vec training_range_rpg.shp
-field "code" -out test.xml
otbcli_SampleSelection.bat -in alldates2014_avignon_landsat.tif
-field code -vec training_range_rpg.shp -out
training_samples.sqlite -instats test.xml -strategy smallest
otbcli_SampleExtraction.bat -in
alldates2014_avignon_landsat.tif -vec training_samples.sqlite
-outfield prefix -outfield.prefix.name band_ -field code
otbcli_SampleExtraction.bat -in
alldates2014_avignon_landsat_nvdi.TIF -vec
training_samples.sqlite -outfield prefix -outfield.prefix.name
ndvi_ -field code
| for i in $(seq 1 7); do var=date$i;
otbcli_TrainVectorClassifier.bat -io.vd
training_samples.sqlite -cfield code -classifier rf
-classifier.rf.max 20 -io.out model.rf -feat ${bands} | grep Kappa; done |
OK |
for i in $(seq 1 7); do var=date$i;
otbcli_TrainVectorClassifier.bat -io.vd
training_samples.sqlite -cfield code -classifier rf
-classifier.rf.max 20 -io.out model.rf -feat ${bands}
${ndvi} | grep Kappa; done -- pas de NDVI !!!!
|
pas de ndvi |
Le mercredi 9 novembre 2016 15:17:40 UTC+1, Guillaume Pasero a
écrit :
Hi,
When you want to perform the training, the "feat"
parameter should be fed with field names from
training_samples.sqlite on which you want to train.
In your pipeline, you should concatenate your NDVI images
into one stack ( otbcli_ConcatenateImages) then use this
stack to extract the samples values
(otbcli_SampleExtraction).
Regards,
Guillaume
On 11/09/2016 11:08 AM, michel M wrote:
hello ,
I have a little question I have 7 images (7 months)
Landsat 8 (for a year)
i use this fonction
for f in LAND*.TIF; do otbcli_RadiometricIndices.bat
-channels.blue 2 -channels.green 3 -channels.red
4 -channels.nir 5 -in "$f" -out "NDVI_$f" -list
Vegetation:NDVI; done |
after i do
| ndvi=`for i in $(seq 0 6); do printf
"ndvi_$i "; done` |
and
| otbcli_TrainVectorClassifier.bat
-io.vd training_samples.sqlite -cfield code
-classifier rf -classifier.rf.max 20 -io.out
model.rf -feat ${ndvi} |
and i have
2016 Nov 09 11:04:36 : Application.logger (INFO)
Precision of class [28] vs all: 0.0697674
2016 Nov 09 11:04:36 : Application.logger (INFO)
Recall of class [28] vs all: 1
2016 Nov 09 11:04:36 : Application.logger (INFO)
F-score of class [28] vs all: 0.130435
2016 Nov 09 11:04:36 : Application.logger (INFO)
Global performance, Kappa index: 0
there is no vegetation very strange ????
is there the good numbers of channels ?
many thanks
--
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
otb-users+...@googlegroups.com
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 otb-users+...@googlegroups.com.
For more options, visit https://groups.google.com/d/optout.
--
![]() |
Guillaume
PASERO
Responsable technique
Business Unit E-SPACE & Geo Information -
Département Image & Applications
CS Systèmes d'Information
Parc de la Grande Plaine - 5, Rue Brindejonc des
Moulinais - BP 15872
31506 Toulouse Cedex 05 - FRANCE
+33 561 17 64 21 - [email protected] |
