Major Update: Semi-Automatic Classification Plugin v. 5.2.0

This post is about a major update for the Semi-Automatic Classification Plugin for QGIS, version 5.2.0.

Following the changelog:

-new tool for cross classification, calculating cross raster and cross area
between a classification and a reference shapefile or raster
-tif files allowed as input for Sentinel-2 preprocessing
-in Batch tool begin with # can be used for comments
-in Band calc new variables for output names, #BANDSET# for name of the first band in the bandset and #DATE# for the current date and time
-in Batch calc fixed NoData calculation

This update includes a new tool for the calculation of a cross classification raster and matrix. Classification is compared to a reference raster or reference shapefile (which is automatically converted to raster).

This tool is useful for calculating the area for every combination between reference classes and classification values.

A cross raster is created, where pixel values represents unique combinations between classification and reference.

Also, a report of pixel sum and area is calculated for each combination. An example of the output in the following image.

Other minor updates are:

• tif files are now allowed as input for Sentinel-2 preprocessing, which is useful in case of the conversion of already clipped .tif bands);
• the Batch tool can accept lines that begin with # for comments;

• In the tool Band calc it is now possible to use variables for the output names (after the @ in the expression) such as #BANDSET# for name of the first band in the bandset, and #DATE# for the current date and time, such as:

( "#NIR#" - "#RED#" ) / ( "#NIR#" + "#RED#" ) @NDVI_#BANDSET#

which would produce a raster named as NDVI_RT_S2A_OPER_MSI_L1C_TL_SGS__20160506T153005_A004552_T32TQM_B0.tif

For any comment or question, join the Facebook group and the Google+ Community about the Semi-Automatic Classification Plugin.