Semi-Automatic OS: a Virtual Machine for Semi-Automatic Classifications

This post is to inform you about the availability of the virtual machine Semi-Automatic OS.

The Semi-Automatic OS is a lightweight virtual machine for the land cover classification of remote sensing images and GIS analyses. It includes the Semi-Automatic Classification Plugin for QGIS 1.8, already configured along with all the required dependencies (SEXTANTE plugin, Orfeo Toolbox, SAGA GIS, and Matplotlib).

The Semi-Automatic OS is based on Ubuntu 12.04 Precise 32-bit, and it is designed to require very little hardware resources. It uses LXDE and Openbox as main desktop environment.
This virtual machine can be useful for testing the Semi-Automatic Classification Plugin, or when the installation of the required programs in the host system is problematic.

The following is a guide for the installation of the Semi-Automatic OS in the open source program of virtualization VirtualBox.

Bug in QGIS dev which affects the Semi-Automatic Classification Plugin v. 2.0.0: FIXED

This post is to inform you that the issue affecting QGIS dev, related to the supervised classification module of SEXTANTE plugin (saga:supervisedclassification) has been fixed. Many thanks to the SEXTANTE developer for solving this issue.

Therefore, the Semi-Automatic Classification Plugin v. 2.0.0 should work as expected in QGIS dev. Also, I remind you that SEXTANTE plugin requires the new SAGA 2.1.0 in QGIS dev for Windows.

News about the bug in QGIS dev which affects the Semi-Automatic Classification Plugin v. 2.0.0

UPDATE 24/07/2013: this bug has been fixed. See here.

---

This post is a rapid update about the bug in QGIS dev that affects the Semi-Automatic Classification Plugin v.2.0.0, which is related to the supervised classification module of SEXTANTE (saga:supervisedclassification).

The SEXTANTE plugin in QGIS dev (for Windows) has switched to the new SAGA 2.1.0 (http://lists.osgeo.org/pipermail/qgis-developer/2013-July/027097.html); the new SAGA module for the supervised classification has changed, and now it requires some new inputs from the command line. In particular, it appears that the supervised classification module requires always an input table (which should be optional) containing the statistics of ROIs, even when the statistics should be calculated by the module, using the ROI shapefile as input. 

The SEXTANTE developer is working to adapt his plugin to this strange input requirement, and I hope he will find soon a solution. In the meanwhile, if you run a supervised classification from the SEXTANTE plugin it produces an error; that error precludes the Semi-Automatic Classification Plugin v.2.0.0 from classifying images.

Therefore, if you need the Semi-Automatic Classification Plugin do not update to any QGIS dev version higher than 1.9.0-327; alternatively, use the Semi-Automatic Classification Plugin v.1.8.0 for QGIS 1.8, which has exactly the same abilities of the version 2.0.0.

I will keep you posted.

Supervised Classification using the Semi-Automatic Classification Plugin for QGIS - version 1.8.0 and 2.0.0

An updated tutorial is available here.

Working with Multispectral Bands in QGIS

An updated tutorial is available here. This post is a quick tutorial about how to handle multispectral images in QGIS.

In this tutorial we are going to split the dataset that you can download from here (data available from the U.S. Geological Survey), using the functions provided by the SEXTANTE plugin and Orfeo Toolbox. For information about how to install and configure this plugin see here. In addition, we are going to create a multispectral image from single bands

At the end of this post you can find the video of this tutorial.

Semi-Automatic Classification Plugin: bug in QGIS dev 1.9.0-327

UPDATE 24/07/2013: this bug has been fixed. See here.

---

This post is to inform you that the Semi-Automatic Classification Plugin 2.0 has an issue with QGIS dev 1.9.0-327 that causes the error: "Classification failed. Possible reason: ROIs are outside the image extent" when performing a classification or calculating the spectral signature.
Thanks to the report of a cooperative user, I can say that the error is not caused by ROIs.
This issues is related to the supervised classification provided by SEXTANTE plugin and I have already reported it to the QGIS hub.
Therefore, until it is fixed please use QGIS 1.8 or do not update to QGIS dev 1.9.0-327.
I will keep you posted.

Calculate Classification Error in QGIS with GRASS

An updated tutorial is available here. We have seen how to perform a land cover classification using the Semi-Automatic Classification Plugin for QGIS. This post is about the calculation of classification error in QGIS; this is useful to assess the accuracy of land cover classifications, in order to identify and measure map errors. For more information about accuracy assessment see my previous post here.

Major Update for the Semi-Automatic Classification Plugin for QGIS

This post is to inform you of a major update for the Semi-Automatic Classification Plugin for QGIS. Following the changes of the QGIS API, I have released two plugin versions:

• version 1.8 is compatible with QGIS 1.8;
• version 2.0 is compatible with QGIS 2.0.

Both versions have the same functionalities, and the code of the version 2.0 has been updated to the API changes of the new QGIS 2.0.

The major changes from the previous version 1.5.1 of the plugin are:

• Improved interface layout;
• The plugin can calculate the spectral signatures of ROIs;
• A new "Spectral signature" tab allows for the visualization of the spectral signatures in a chart;
• A new "Band set" tab allows for the definition of a group of single bands as image input.

Following, more details about these improvements.