Supervised Classification using the Semi-Automatic Classification Plugin for QGIS, Version 2.1.0

An updated tutorial is available here. The Semi-Automatic Classification Plugin version 2.1.0 for QGIS 2.0 has been released. This post is a video tutorial that illustrates the features of the Semi-Automatic Classification Plugin, which allows for supervised classifications.

The version 2.1.0 of the plugin provides a new interface that better integrates in QGIS: two movable docks (or panels) for the ROI creation and the classification process; also, a main plugin interface contains several tools for expediting ROI creation, image post processing and advanced plugin settings.
For information about plugin installation and configuration see here.

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

Update: Semi-Automatic Classification Plugin v. 2.1.0

I have released a major update for the Semi-Automatic Classification Plugin for QGIS 2.0, version 2.1.0.
I have added several new features to the plugin and in particular to the interface: the ROI and classification commands are placed inside two movable docks, which allow for a better integration with the QGIS interface. This way, the map is better displayed for the ROI creation and the classification.

The Semi-Automatic Classification Plugin v. 2.1.0

Create a Virtual Machine based on Ubuntu, containing QGIS and the Semi-Automatic Classification Plugin

In this tutorial we are going to create a virtual machine based on Ubuntu.

The purpose of this virtual machine is to include the required GIS software for land cover classification: QGIS, Orfeo Toolbox, and SAGA GIS. Also, the intention is to produce a fast virtual machine that occupies little disk space and is adequate to low-spec computers.

The following steps are mainly the same ones that I have used for the creation of the Semi-Automatic OS.

Backup and Restore the Operating System with Clonezilla

There are several open source programs that allows for GIS and Remote Sensing analyses. Personally, I  often install several new programs and try them for a while. Sometimes I need to uninstall those programs in order to free hard disk space, but this can be a tedious process.
It can be useful to create a backup copy of the whole hard disk or partition (including operating system and data). This way, the operating system can be restored in a few minutes, along with all the programs and settings that were at the backup time.

This post is about how to create a backup of system partitions with Clonezilla, which is open source software and works with most file systems.

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

Flash update: Semi-Automatic Classification Plugin v. 2.0.2

This is a flash update to the Semi-Automatic Classification Plugin:

-update to new SAGA 2.1, classification codes
-version for QGIS 2.0

SAGA 2.1 has new codes for the algorithm choice, which I had to update in my plugin.

Users running a previous version of QGIS dev, which still requires SAGA 2.0.8, should use the Semi-Automatic Classification Plugin v. 2.0.0.
No update for the version 1.8.0 was needed, because SEXTANTE for QGIS 1.8 requires SAGA 2.0.8.

You can download this update from here.

Minor Update: Semi-Automatic Classification Plugin v. 2.0.1

I have updated the Semi-Automatic Classification Plugin for QGIS 2 to version 2.0.1.

This is the brief changelog:

-update to new SAGA 2.1, different output of csv table
-version for QGIS 2.0

A little explanation of the update: SEXTANTE for QGIS 2 uses the new SAGA 2.1; the new supervised classification module produces an output table for classifications, which has a different structure than the one produced by SAGA 2.0.8; therefore I have adapted the code to the new table structure, which is used during the classification process.

Users running a previous version of QGIS dev, which still requires SAGA 2.0.8, should use the Semi-Automatic Classification Plugin v. 2.0.0.
No update for the version 1.8.0 was needed, because SEXTANTE for QGIS 1.8 requires SAGA 2.0.8.

You can download the updated version of the Semi-Automatic Classification Plugin from here. However, this update will be soon available through the QGIS repository, in one or two weeks.

Apply a Mask to a Land Cover Classification in QGIS

An updated tutorial is available here . This post is a brief tutorial about how to mask a classification raster in QGIS using the Orfeo Toolbox provided by the SEXTANTE plugin.

The masking process is useful to clip a classification raster to a certain study area, as for example a municipal boundary. Obviously, this masking process can be applied to any raster file.
It is worth mentioning the QGIS tool Clipper (Menu Raster > Extraction > Clipper that is based on gdalwarp), which allows for the masking of rasters. However, in this tutorial I illustrate some SEXTANTE functions, which can also be used in python scripts for automatic processing.

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