Scribd
Upload
53 views8 pages

Image Classification Unsupervised

This document provides a step-by-step guide for detecting land use and land cover changes using unsupervised classification in QGIS with the SEMI AUTOMATIC CLASSIFICATION plug-in. It details the processes of pre-processing satellite images, creating regions of interest (ROIs), and performing classification to generate land cover maps for different years. Finally, it explains how to analyze changes between the generated maps by using the Land cover change tool in QGIS.

Uploaded by

shashank kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
53 views8 pages

Image Classification Unsupervised

This document provides a step-by-step guide for detecting land use and land cover changes using unsupervised classification in QGIS with the SEMI AUTOMATIC CLASSIFICATION plug-in. It details the processes of pre-processing satellite images, creating regions of interest (ROIs), and performing classification to generate land cover maps for different years. Finally, it explains how to analyze changes between the generated maps by using the Land cover change tool in QGIS.

Uploaded by

shashank kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 8

Land Use Land Cover Change Detection with Unsupervised classification in

QGIS
1. open QGIS and install SEMI AUTOMATIC CLASSIFICATION plug-in from the plugin option. After installation of the plugin if
toolbox on the screen of the same is not showing by default then, then click view and click panels. And Check both the
panels SCP: ROI creation and SCP: classification.

2. Now click toolbar and activate SCP toolbar


3. Your Desktop QGIS screen will look like this below image

4. Now Click on pre-processing tool and Select the folder in which all the images and MTL file is present

5. Check these two options i.e Apply DOS1 Atmospheric Correction and Create Virtual Raster as shown below
6. Now click on perform conversion. The processing may
take too much time

7. All the images are loaded into Layers and virtual raster with
name landsat.vrt is also created
8. We can remove image 8,9, 10 and 11. Click on band set icon and select all raster

9. Add rasters to band set

10. Select landsat 8 only because we have downloaded a landsat 8 image

11. Now Right click on landsat virtual raster and click properties
16. Create a shape file in the same folder with name roi or as per your wish. Click on ‘+’ sign and then Click on create a ROI

17. Now as per your knowledge of the location zoom in and create a polygon. We are creating polygon because it will take
pixels of same colour with slightly difference in the value. Right click to end the polygon

18. Give Macroclass name and class name

19. Click on save ROI and check add sigg. List


20. The roi is added to the signature list

21. Save this signature list in the same folder, and create new ROI’s for different classes. You can also change the color. Within
same class you can have different Macroclass so that you can classify precisely. You can see the color convention for classes
that are used generally on internet

22. Save all the roi. Select algorithm for classification


22. Before going for classification you can see a preview with the option provided as classification preview. Now Click on
the plus sign and click on the area where you want to see the preview

23. Click on perform classification for final classification. This process will take time for classification. After the classification
is done. Click on post processing tool icon and generate classification report
Change Detection
• After following the steps and creating the land cover maps. We now have two distinct land cover maps for years 2015 and
2024 respectively. To observe the notable changes between the two years, navigate to the SCP panel, and click on post-
processing and Land cover change.

• Within the Land cover change panel, the reference layer is the old classification layer which here is the 2015 Land cover
while the new classification is the new land cover, which is the 2021 layer. Ensure the unchanged “Report unchanged pixel”
is ticked also. Click “RUN”... The Land cover change tool produces an image depicting changes in the layer and a table
showing the pixels that have been transformed from one class to another.

You might also like