OTB TrainImageClassifiers in QGIS

i have installed the OTB 5.10.1 version and when i want to use train images classifier for the random forest it doesn’t create any output model file. and the library give me this error message:
ERROR: Waiting for at least one parameter…
This is the TrainImagesClassifier application, version 5.10.1
Train a classifier from multiple pairs of images and training vector data.

Complete documentation: http://www.orfeo-toolbox.org/Applications/TrainImagesClassifier.html

-progress Report progress
MISSING -io.il Input Image List (mandatory)
MISSING -io.vd Input Vector Data List (mandatory)
-io.valid Validation Vector Data List (optional, off by default)
-io.imstat Input XML image statistics file (optional, off by default)
-io.confmatout Output confusion matrix (optional, off by default)
MISSING -io.out Output model (mandatory)
-elev.dem DEM directory (optional, off by default)
-elev.geoid Geoid File (optional, off by default)
-elev.default Default elevation (mandatory, default value is 0)
-sample.mt Maximum training sample size per class (mandatory, default value is 1000)
-sample.mv Maximum validation sample size per class (mandatory, default value is 1000)
-sample.bm Bound sample number by minimum (mandatory, default value is 1)
-sample.vtr Training and validation sample ratio (mandatory, default value is 0.5)
-sample.vfn Field Name (mandatory, default value is )
-classifier Classifier to use for the training [libsvm] (mandatory, default value is libsvm)
-classifier.libsvm.k SVM Kernel Type [linear/rbf/poly/sigmoid] (mandatory, default value is linear)
-classifier.libsvm.m SVM Model Type [csvc/nusvc/oneclass] (mandatory, default value is csvc)
-classifier.libsvm.c Cost parameter C (mandatory, default value is 1)
-classifier.libsvm.opt Parameters optimization (optional, off by default)
-classifier.libsvm.prob Probability estimation (optional, off by default)
-rand set user defined seed (optional, off by default)
-ram Available RAM (Mb) (optional, off by default, default value is 128)
-cleanup Temporary files cleaning (optional, on by default)
-inxml Load otb application from xml file (optional, off by default)

it give me only the libsvm classification.
i would be grateful if you help me.

Dear Syrine,
this is not the right forum for your question. I suggest to subscribe to OTB forum hosted as Google forum.
What I’d say here you use quite old version of OTB the current is 6.0

Good luck.


If you are interested in performing classification using the random forest algorithm , you can use the one implemented in SNAP