The new documentation is great! I have a question though for
Orthorectification I saw you listed it as thus for parameters io.out image
[dtype]
Is it possible to set the output datatype in this same step? If so how? I
have WV data that needs to be orthoed and the data type keeps getting
Hi Agustin,
Thanks a lot for the feedback. Actually I've been working on a new version of
the CookBook which improves many things, including showing default parameter
values. It will be available for the next release, but you can see it here
already:
Hi,
2 suggestions regarding the doc:
1. The tables for parameters lack a column with Default values
(e.g. Table in
https://www.orfeo-toolbox.org/CookBook/Applications/app_DimensionalityReduction.html)
2. In general, a very simple case is provided as example, e.g.
otbcli_DimensionalityReduction
Hi!
Happy new year to everyone!
is there a way to ignore no-data values in otbcli_DimensionalityReduction?
Despite having 3.4028234663852886e+38 value set as no-data in the
geotif input image, the application uses pixels with that value as if
it were actual data, which considerably disrupts the
Hi!
Having an operation such as im1/im2
where both im1 and im2 are tif multi-spectral images with 0 set as
no-data value, otbcli_BandMathX complains about
"Generated 0 Underflow(s) And 836 Overflow(s)"
and the resulting tif image does not have the 3.4028234663852886e+38
value set as no-data
TrainImagesClassifier and TrainVectorClassifier perform training but on
different inputs.
TrainImagesClassifier takes as input one or multiple images and separately
polygons with class label associated to each polygon. Pixels inside those
polygons will be used to create the training set
The
If you want to change the nodata value you can use the ManageNoData
application:
https://www.orfeo-toolbox.org/CookBook/Applications/app_ManageNoData.html
If you want to change the value of a pixel in a image you can use the
BandMath application with the expression: "im1b1 ==
Statistics shoud be computed on the same features as the one you use for
the training (in your case you'll need mean and variance for all geometric
features).
Note also that statistics are used to normalize samples between [0,1] to
deal with features with different amplitude. Nevertheless this is
