Training data selection (SCP)

From AWF-Wiki
(Difference between revisions)
Jump to: navigation, search
(Defining land cover classes)
(Defining land cover classes)
Line 1: Line 1:
 
=Defining land cover classes=
 
=Defining land cover classes=
 
Before starting to map land cover classes using Sentinel-2 satellite images we need clear definitions and a classification scheme.  
 
Before starting to map land cover classes using Sentinel-2 satellite images we need clear definitions and a classification scheme.  
An example of a hierarchical land use and land cover (LUC) classification scheme is the European Urban Atlas.
+
An example for a hierarchical land use and land cover (LUC) classification scheme is the European Urban Atlas.
 
The scheme defines 5 main meta-classes where the class ''1. Artificial surfaces'' has many sub classes as shown in the following figure.
 
The scheme defines 5 main meta-classes where the class ''1. Artificial surfaces'' has many sub classes as shown in the following figure.
 
+
The specification other metaclasses is not as detailed. If we are more interested in forest and open area classes we need to adapt and modify this scheme.
 
[[File:qgis_urban_atlas_scheme.png|900px]]
 
[[File:qgis_urban_atlas_scheme.png|900px]]
 
On the lowest level not all classes defined in the European Urban Atlas do also appear in the surroundings of Göttingen:  
 
On the lowest level not all classes defined in the European Urban Atlas do also appear in the surroundings of Göttingen:  
 
[[File:qgis_goe_luc_classes.png|400px]]   
 
[[File:qgis_goe_luc_classes.png|400px]]   
The specification other metaclasses is not as detailed. If we are more interested in forest and open area classes we need to adapt and modify this scheme.
 
 
In addition we need to consider pheneolgical developments of vegetation at specific acquisiton dates and to specify more classes which  can possibly be identified in the multispectral feature space of the satellite image.
 
In addition we need to consider pheneolgical developments of vegetation at specific acquisiton dates and to specify more classes which  can possibly be identified in the multispectral feature space of the satellite image.
 
   
 
   
 
[[category:QGIS Tutorial]]
 
[[category:QGIS Tutorial]]

Revision as of 10:52, 19 April 2018

Defining land cover classes

Before starting to map land cover classes using Sentinel-2 satellite images we need clear definitions and a classification scheme. An example for a hierarchical land use and land cover (LUC) classification scheme is the European Urban Atlas. The scheme defines 5 main meta-classes where the class 1. Artificial surfaces has many sub classes as shown in the following figure. The specification other metaclasses is not as detailed. If we are more interested in forest and open area classes we need to adapt and modify this scheme. Qgis urban atlas scheme.png On the lowest level not all classes defined in the European Urban Atlas do also appear in the surroundings of Göttingen: Qgis goe luc classes.png In addition we need to consider pheneolgical developments of vegetation at specific acquisiton dates and to specify more classes which can possibly be identified in the multispectral feature space of the satellite image.

Personal tools
Namespaces

Variants
Actions
Navigation
Development
Toolbox
Print/export