Le 24/01/2017 à 17:38, Sébastien G. a écrit :
*step 7- *otbgui_OGRLayerClassifier that takes as input the previous
shapefile and the image statistics and add a new "predicted"
attributes in the shapefile.
pb7.1 : The OGRLayerClassifier only seem to accept SVM models. It
worked for a SVM
Hi all,
Thanks for fixing pb 7.1. I'm looking forward to test it.
For very Basic OBIA classification (on OBIA my personal use is mainly
teaching, on a small areas , for the moment i make the student switch to
scikit-learn for the classification after the attributes are produced in
OTB...)
-
Hi Stephen,
just want to add that there is perhaps something else to try with the ITK
mechanism which allows to use pool of threads:
https://github.com/InsightSoftwareConsortium/ITK/blob/master/Modules/Core/Common/include/itkMultiThreader.h#L210
You can easily test this by setting the environmen
Hi Sinead,
in the input vector data list you should provide polygons which contains a
column in the attribute table which allows to identify the class associated
to the polygon. This column should contains integer values (1 for oats, 2
for wheat for instance etc...).
It's not require that polygon
Does the segmentation command works outside the batch script?
You need perhaps to call first the otbenv.cmd batch scrip which set all OTB
related variables (path, libraries...)
Hope it helps.
2017-05-12 12:15 GMT+02:00 celati Laurent :
> Good morning,
> I'm working on windows 7 with the last ve
On Fri 19-May-2017 at 10:39:13 +0200, Julien Michel
wrote:
> Given all the insightful comments here, I think we could plan a
> working group on this OBIA topic during next user days, to sum up what
> has been said in the thread, add more ideas and write a good RFC to
> capture all that. Then we
Hi Mary,
you probably have to set the environment LD_LIBRARY_PATH to the directory
where the OTB libraries are installed on your system. You should do
something like:
export LD_LIBRARY_PATH=*path_to_otb_libraries_directory*:$LD_LIBRARY_PATH
Settting this environment library is needed if you comp
Hi there,
I'm using OTB to co-register multi-temoral images (SPOT6/7) as documented
here:
https://www.orfeo-toolbox.org/CookBook/recipes/residual_registration.html
A question arises since the raw data is often distributed with separated
panchromatic and bands. At the moment I run the co-regist
Indeed, pansharpening before co-registration would be a better choice (at least
for Pleiades), since it corrects the slight offset that might happen between
PAN and XS. You can detect tie points with the pan image and then refine the
model from pansharpened image.
Regards,
Julien
De : otb-use
I'm not sure to understand which application you're talking about.
Is it the MeanShiftSmoothing application or the Segmentation application (I
think that there is no MeansShiftSegmentation application)?
2017-05-15 8:39 GMT+02:00 'Flint Freakwood' via otb-users <
otb-users@googlegroups.com>:
> He
Ok, I'll give it try with this order...thanks a lot!
André
On Friday, May 19, 2017 at 3:23:21 PM UTC+2, Julien Michel wrote:
>
> Indeed, pansharpening before co-registration would be a better choice (at
> least for Pleiades), since it corrects the slight offset that might happen
> between PAN an
Here is an interim summary of what I have found out so far:
- base starting case (10-15 Load average)
- converting the input file from .vrt to .tif improves performance a
little (12-17 Load average)
- ITK_USE_THREADPOOL=ON improves performance a little using .tif (17-28
Load avera
12 matches
Mail list logo