This post is about the supervised classification of hyperspectral data using the Semi-Automatic Classification Plugin for QGIS. In particular, we are going to classify a Hyperion image.
Hyperion is a NASA satellite launched in the frame of the EO-1 project. This hyperspectral satellite has hundreds of bands from the visible to the Short Wavelength Infrared, allowing for the identification of the spectral signatures of materials. Images have 30m resolution pixels (the same as Landsat) and cover a land area of 7.5 km by 100 km.
You can see an example of spectral signatures from Hyperion data in the following image.
|
Spectral signatures from an Hyperion image (available from the U.S. Geological Survey) |
For more information about the Hyperion sensor see
here. Hyperion images are freely available from the
USGS EarthExplorer website.
In this tutorial we are going to classify the following land cover classes:
- Class 1 = Vegetation (e.g. grassland or trees);
- Class 2 = Soil (e.g. soil without vegetation);
- Class 3 = Built-up (e.g. artificial areas, buildings and asphalt);
- Class 4 = Water (e.g. surface water).
The following are the main classification steps:
- Definition of the input;
- Creation of the ROIs and spectral signatures for the image;
- Classification of the image.