Land Cover Classifier for Pléiades/SPOT

Classifies imagery into discrete land cover classes.


Description

A processing block that assigns each of the input image pixels to a discrete land cover class.

See this block on the marketplace.

Compatibility

Catalog collections

Use in combination with Processing from Storage.

How it works

ParameterOverview
nclassesinteger / required
The number of land cover classes. The allowed values:
  • 4 — Barren land and Urban will be treated as a single class.
  • 5 — All the classes are included.
The default value is 4.

Land cover classes

ClassOverview
1Water
2High vegetation (including trees)
3Low vegetation (including bushes and grass)
4Barren land
5Urban (including roads and buildings)

Accuracy assessment

Accuracy metricsWith 4 classesWith 5 classes
Accuracy0.750.64
Jaccard0.220.51

Capabilities

Input

raster
up42_standard
bands
[
  "red",
  "green",
  "blue",
  "nir"
]
dtypeuint16
formatGTiff
sensor
{
  "or": [
    "Pleiades",
    "SPOT"
  ]
}
processing_levell2

Output

To know more please check the block capabilities specifications.

Learn more