Geoscience Reference
In-Depth Information
INFO: Open of 'vector_32629.sqlite'
using driver 'SQLite' successful.
Layer name: SELECT
Geometry: None
Feature Count: 1
Layer SRS WKT:
(unknown)
natural: String (0.0)
count(*): Integer (0.0)
OGRFeature(SELECT):0
natural (String) = wood
count(*) (Integer) = 4621
To train the classifier, we also need a sample for the non-forest class. We masked
non-vegetated areas, sowe only concentrate on polygons that cover vegetation. Based
on the information from the OpenStreetMap web page on tagging vegetation,
6
we
select the multipolygons that delineate scrub, heath, grass and meadow. The first two
are defined by the key “natural”. Multipolygons for grass and meadow are defined by
the key “landuse”. Our training sample will thus consist of a subset of the available
multipolygons, based on different keys. We create this training sample as a new
vector of multipolygons, with a separate layer for forest and non-forest.
ogr2ogr -f SQLite -nln forest -where "natural='wood'" -select
ₒ
natural,type,landuse training.sqlite vector_32629.sqlite
-f SQLite
Output vector type is SQLite.
-nln forest
New layer name of the output vector dataset.
-where "natural='wood'"
Select the subset of features where key 'natural' equals 'wood'.
-select natural,type,landuse
Selection of attributes to copy from input to output vector dataset.
training.sqlite
Output vector dataset.
vector_32629.sqlite
Input vector dataset.
Search WWH ::
Custom Search