This content presents how to classify satellite image by QGIS Semi-automatic classification plugin. It includes pre-processing, create a region of interest (AOI), and applying classification methods.
Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...
Image Classification
1. Center for Research and Application for Satellite Remote Sensing
Yamaguchi University
Image Classification
2. • The Semi-Automatic Classification Plugin (SCP) is a free open source
plugin for QGIS that allows for the semi-automatic classification (also
supervised and unsupervised classification) of remote sensing images.
Also, it provides several tools for the download of free images (Landsat,
Sentinel-2, Sentinel-3, ASTER, MODIS), the preprocessing of images, the
postprocessing of classifications, and the raster calculation.
Congedo Luca (2016). Semi-Automatic Classification Plugin Documentation.
DOI: http://dx.doi.org/10.13140/RG.2.2.29474.02242/1
Semi-Automatic Classification Plugin
8. • Go to icon of semi-automatic classification plugin → Preprocessing
• Or directly to preprocessing tool
Input
Run → select
directory
to save
Import image and pre-processing
9. • In band set will show image from preprocessing → click “RUN”
In band set will show image from preprocessing
12. Classes (MC ID)
• 1 Water
• 2 Tree and high vegetation
• 3 Low vegetation, grassland
• 4 Building, manmade
• 5 Openland, bareland
• # you can decide your own classes
• In this workshop, we will make just MC class
Optional → you can make sub-classes
SCP allows for the definition of Macroclass ID (i.e. MC
ID) and Class ID (i.e. C ID), which are the identification
codes of land cover classes. A Macroclass is a group of
ROIs having different Class ID, which is useful when one
needs to classify materials that have different spectral
signatures in the same land cover class.
Create ROI
30. There are 3 classification algorithm for this
plugin
1) Minimum distance
2) Maximum Likelihood
3) Spectral Angle Mapping
https://fromgistors.blogspot.com/p/user-manual.html
Select classification method