Minor Update: Semi-Automatic Classification Plugin v. 4.5.1

This post is about a minor update for the Semi-Automatic Classification Plugin for QGIS, version 4.5.1.

Following the changelog:

-changed function for ROI display
-bug fixing

Major Update: Semi-Automatic Classification Plugin v. 4.5.0

This post is about a major update for the Semi-Automatic Classification Plugin for QGIS, version 4.5.0.

Following the changelog:

-added reflectance conversion for Landsat 1, 2, and 3 MSS
-improved the calculation of Band calc which now allows for calculation between
rasters with different size and resolution
-experimental version
-bug fixing

Major Update: Semi-Automatic Classification Plugin v. 4.4.0

This post is about a major update for the Semi-Automatic Classification Plugin for QGIS, version 4.4.0.

Following the changelog:

-added function for Landsat pan-sharpening
-added tooltips for classes and macroclasses in ROI and Signature tables
-bug fixing

New release: Semi-Automatic OS v. 4

I have released a new version of the Semi-Automatic OS v. 4, a free virtual machine based on Debian Linux, for the land cover classification of remote sensing images. It includes the Semi-Automatic Classification Plugin and QGIS, already configured along with all the required dependencies (OGR, GDAL, Numpy, SciPy, and Matplotlib).

The main features are:

• based on Debian 8;
• available as 32 bit and 64 bit;
• includes QGIS 2.8.2;
• includes the Semi-Automatic Classification Plugin v. 4.3.4;
• includes the PDF version of the User Manual of the Semi-Automatic Classification Plugin and a sample dataset of Landsat images (available from the U.S. Geological Survey).

Video Tutorial: Using the tool Band calc of the Semi-Automatic Classification Plugin

This is a tutorial about the use of the tool Band calc that allows for the raster calculation for bands. In particular, we are going to calculate the NDVI (Normalized Difference Vegetation Index) of a Landsat image, and then apply a condition in order to refine a land cover classification (see Tutorial 2: Land Cover Classification of Landsat Images ) basing on NDVI values (a sort of Decision Tree Classifier).

The Band calc can perform multiple calculations in sequence. We are going to apply a mask to every Landsat bands in order to exclude cirrus and cloud pixels from the NDVI calculation, and avoid anomalous values. In particular, Landsat 8 includes a Quality Assessment Band ) that can be used for masking cirrus and cloud pixels.

The values that indicate with high confidence cirrus or clouds pixels are (for the description of these codes see the table at http://landsat.usgs.gov/L8QualityAssessmentBand.php ):

• 61440;
• 59424;
• 57344;
• 56320;
• 53248;
• 31744;
• 28672 .

In particular, the Quality Assessment Band of the sample dataset includes mainly the value 53248 indicating clouds. Therefore, in this tutorial we are going to exclude the pixels with the value 53248 from all the Landsat bands.

Following the video of this tutorial.

Video Tutorial: Tutorial 2: Supervised Classification of Landsat Images for Land Cover

I have published the second video tutorial bout the use of the Semi-Automatic Classification Plugin (SCP) for the classification of a Landsat 8 image. It is recommended to read the Brief Introduction to Remote Sensing before this tutorial.