Commit 91d3d4d6 authored by Himanshu's avatar Himanshu
Browse files

Update README.md

parent 5ada1905
# LandCoverClassification-Sentinel2 # LandCoverClassification-Sentinel2
Unsupervised classification over Sentinel-2 data using training labels from OSM landcover database Random Forest classification over Sentinel-2 data using training labels from OSM landcover database.
\ No newline at end of file
Prerequisites:
osm-lulc database dump and PostgreSQL (part of preprocessing script)
atleast 50GB RAM (for current subset size, or use lower subset size)
12 CPU cores (or change the values in script)
GDAL command line tools version >= 2.1.3
Python version 2.7 and associated libraries
R and associated libraries
Code structure:
--downloadScripts : scripts for download of Sentinel-2 data
--flowchart : for an overview of the workflow
--logs : preprocessing and RF logs for tiles in EU
--reports : pdf reports for the project (only for version 1 of code)
--scripts : classification scripts and others
Status:
Total tiles in EU : 865
Classified : 843
Not classified (NO scenes for download) : 22
Refer to the flowchart to understand the workflow.
For the whole process, two scripts need to be run separately:
downloadScripts/all_tiles_download.R : to download tiles
scripts/RandomForest_main.py : to run RF on downloaded tiles
After downloading the tiles, they need to be moved to RF script's input data location.
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment