The OTB 3.18 release candidate 1 has been tagged, and is available for testing!
Some of the major changes in this release are:
- Bridge to OpenCV classifiers: the architecture of the machine learning framework has been redesigned. It provides a simple and generic interface to create bridges with existing machine learning algorithms implementation. This new framework has been used to include OpenCV machine learning algorithms. So in addition to LibSVM, you can now use 8 other algorithms for your images classification tasks, such as bayesian, k-nearest neighbors, random forests, artificial neural network… All these classifiers can be reached directly from the TrainImagesClassifier and ImageClassifier applications (read this note to learn about migrating to these new applications).
- Dempster-Shafer based fusion of classifications: A new method based on Dempster-Shafer theory has been developed to fuse multiple classification maps. This method will take advantage of the per-class strengh and weaknesses of each input classification (estimated from confusion matrices) to produce a robust output map combining the best of each input. It is available as an alternative choice to majority voting fusion in the FusionOfClassifications application.
- Improvement of the StereoFramework application: a whole set of filters has been developed to enhance this application, including line-of-sight interesction, left-right / right-left coherency checking and fusion of several 3D clouds into one raster DSM. The application now allows to input several views of the same scene and build a single raster DSM from them combining the information from all pairs, which is most useful for tri-stereoscopic Pleiades data for instance.
- Access to Gdal overviews and writing of output image subsets throughout the library using the box and resol parameters of the extended filenames.
There are a lot more new things coming with this release! For more information, please read the complete release note available here.
Source code can be downloaded here.
You can also obtain the source code using Mercurial:
hg clone http://hg.orfeo-toolbox.org/OTB cd OTB hg update -r 3.18-rc1
Feel free to test the release candidate and share your experiences on the mailing list. And if you run into a bug, please file it into our issues tracker.
You can also help to identify other issues by submitting an Experimental build to the dashboard with:
ctest -D Experimental
For more details please see:
OTB Dev Team
11 thoughts on “OTB 3.18 Release Candidate 1 ready for testing!”
the new update is not yet available with window installer (click and install type) ? if not what is a easiest way to install in a window? i am dumb ; )
there is a Windows installer for Monteverdi but for the library we’ll provide Windows installer through OSGeo4W for the release (here is the release candidate). The release will be out next week if no blocking issues happened in the meantime.
thx manuel for answering.
In the mean time, i tried to compile myself as i want to test OTB during the weekend.
Following error occurs while configuring with Cmake
Disabling build shared lib option on windows like OS.
Found OSGeo4W (C:/OSGeo4W/bin)
Could NOT find GDAL (missing: GDAL_LIBRARY)
CMake Error at CMake/ImportGdal.cmake:14 (MESSAGE):
Cannot find GDAL. Set GDAL_INCLUDE_DIR and GDAL_LIBRARY
Call Stack (most recent call first):
I have GDAL already installed in my system. Any info how to proceed?
I am not familiar with OTB compilation on Windows,
you should ask on otb-users mailing list where people should be able to give you some tips regarding the compilation.
There are also cmake script from platforms which submit tests to the OTB dashboard available on the OTB website. For example one example of cmake configuration on Windows7:
Hope it helps.
thankx for you help. i really dont know what to do with the file you pointed out. Seems like i will have to wait till you guys provide binary executable file next week.
Just the follow up. I managed to compile it with CMAKE and build my solution with visual studio. Now the dumb question, how do i run QTB?
It depends what you want to do, OTB is firstly a library so you can write your own code in C++ based on the API and compile it.
Secondly OTB is shipped with a set of executables (called applications) that you can run in command line or access through a GUI.
Try to open the OSGEO4W shell and type for example otbcli_Orthorectification for example.
thx for the quick answer. I am not good at C++ so i will stick with trying to use with command line or with GUI. I have scoured the net with related information. It seems OTB can be used within the QGIS with the help of Sextante. I sextante add on in Qgis comes with only previous version of QTB (65 algo). I tried to change the OTB application folder with Sexante options and pointed it the folder where i have exe generated after building the solution. However, the new algorithm are not apprearing. What i am doing wrong?
thx for the help so far
I will attempt to build and package on win64. Do you have an NSIS CPack definition in there. I will try to publish an x64 installer as Osgeo4W is not in the x64 land yet.
its me again bothering you, after much struggle i managed to compile it as i said in my previous post. Now, the dumb question: How to i access it.
I open my cmd window, pointed to bin folder within OTB_BINARY_DIR and typed: otbcli
The error it throws back is otbApplicationLauncherCommandLine.exe is not recognized as an internal or external comand, operable program or batch file.
Help me !
Mickael has posted yesterday on the mailing list a message with lots of useful and up to date information to compile and use OTB on Windows platform. See:
Please try using thios info and ask to the mailing list if yuo still got issues: