Semi-Automatic Classification Plugin is a QGIS tool for supervised classification of remote-sensing imagery and land-cover mapping. This plugin provides a comprehensive suite of tools for processing satellite and aerial imagery directly within the QGIS environment. It streamlines complex workflows by managing band sets, calculating spectral signatures, and executing supervised classification algorithms. The interface integrates natively into the software, allowing for systematic preprocessing of raw data, atmospheric correction, and refined pixel-based classification. Designed to bridge the gap between raw raster inputs and actionable vector outputs, the toolset includes advanced options for training sample development, signature analysis, and post-classification processing, ensuring precise land-cover characterisation for large-scale geographic data projects.

The download is a 1.1 MB file containing .ZIP files.

Users install the plugin via the QGIS repository to access the specialized toolbar and dock panels. The workflow typically begins by defining a band set from loaded raster layers, followed by collecting training areas to build a spectral library. Once signatures are defined, users run the classification algorithm to generate categorical maps. The results can be further refined through post-processing tools, exported as standard raster files, or converted into vector polygons for subsequent spatial analysis.

Ideal for urban planners, environmental scientists, and landscape architects, this tool is essential for projects requiring land-use analysis, environmental impact assessments, or urban expansion studies. It is frequently employed during the site analysis phase of large-scale infrastructure or masterplanning projects where existing land-cover data is outdated or unavailable. Professionals often pair this plugin with high-resolution satellite imagery to derive accurate site context, enabling data-driven design decisions in complex geographical settings where precise terrain and vegetation mapping are critical.