This section is aimed at users with no previous EnMAP-Box experience. You will get a brief introduction into the main functionalities, i.e. you will
- Load some testdata
- Get to know the GUI (especially using multiple map views)
- View and extract spectral profiles from a hyperspectral image
- Use a Processing Algorithm
Launching the EnMAP-Box¶
Once you successfully installed the EnMAP-Box, you can access the plugin via the icon in the QGIS Toolbar. Furthermore, the EnMAP-Box Processing Algorithms should also appear in the QGIS Processing Toolbox.
Go toto load example datasets into you project. The following datasets will be added (now they are listed in the
By default the example data is loaded into a single Map View. Let’s rearrange those for better visualisation and in order to get to know the GUI functionalities:
We want to arrange the windows so that they are next to each other (horizontally). Click and hold on the blue area of Map #2 and drag it to the right of Map #1 (see figure below). The translucent blue rectangle indicates where the map window will be docked once you stop holding the left mouse button.
Now, in the
Data Viewswindow, expand the Map #1 list, so that you can see the individual layers. Select HighResolution_BerlinUrbanGradient.bsq and LandCov_BerlinUrbanGradient.shp (hold Strg and click on layers) and drag them into Map #2 (you can drag them directly into the map views or the respective menu item under
In the next step we link both map views, so that zoom and center are synchronized between both. First, click the button in the Map #1 window. Now three options become selectable in Map #2: Select , which will link both, zoomlevel and map center.
Right-click into one of the map views and select Show Crosshair. Repeat this also for the other map view.
- In Map #1 (EnMAP image), navigate to a pixel which is mostly covered by vegetation (use the higher resolution image in Map #2 to identify such a pixel)
- Click on Select pixel profile from map and then click on this vegetated pixel in Map #1.
- Click to add this spectrum to the spectral library.
- Now select another pixel profile, e.g. red roof to have a direct comparison.
Hello World for Processing Algorithms¶
Up to now we mainly had a glimpse at the GUI of the EnMAP-Box. Let’s take a look at the Processing Algorithms.
In the Processing Toolbox panel, go toand double-click on the algorithm (alternatively you might directly type “Classification from Vector” into the search bar to find the algorithm).
Mind the help sidebar on the right of the window, where the algorithm and each of its parameters are described.
In the algorithm window, set the following parameters:
Class id attribute: Level_2_ID
ClassDefinition(classes=6, names=['Roof', 'Pavement', 'Low vegetation', 'Tree', 'Soil', 'Other'], colors=['#e60000', '#9c9c9c', '#98e600', '#267300', '#a87000', '#f5f57a'])
Minimal overall coverage: 0.9
Minimal winner class coverage: 0.7
Oversampling factor: 2
Click Run in Background
Data Sourcesyou should now find the layer outClassification.bsq
- Drag it onto Map #2 (i.e. where your vector layer is), and compare the vector dataset with the classification you just derived from it.
- You might want to activate/deactivate the top layer in the
Data Viewspanel, in order to switch back and forth between both layers.
- Are all pixels that were covered by the vector layer assigned a class? Or are some labeled as unclassified?
- You might want to have a look at the help window again, especially at the parameters Minimal overall coverage and Minimal winner class coverage, and see if you find out why not all pixels are included, given the settings we used.
Feel comfortable with the EnMAP-Box interface now…?
… then have a look at our User Guide section, and dive deeper into the matter!