Heuristic method to extract building footprints

.gitignore

@@ -0,0 +1,166 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Custom
+.vscode
+data
+project_docs
+qgis

.python-version

@@ -0,0 +1 @@
+3.10.7

README.md

@@ -1,2 +1,3 @@
-# plantilla
-Plantilla de proyecto
+# Dencity
+
+

notebooks/heuristic_processing.py

@@ -0,0 +1,49 @@
+# %%
+import rasterio
+from rasterio.plot import show
+
+from preprocessing.utils import calculate_ndvi, mask_raster_band_by_value
+
+MDS_INPUT_FILE = "data/ideuy/K29D6P6_MDS_Remesa_01_MVD.tif"
+MDT_INPUT_FILE = "data/ideuy/K29D6P6_MDT_Remesa_01_MVD.tif"
+RGBI_INPUT_FILE = "data/ideuy/K29D6P6_RGBI_16_Remesa_01_MVD.tif"
+NDVI_OUTPUT_FILE = "data/ideuy/K29D6P6_NDVI_16_Remesa_01_MVD.tif"
+DIFF_OUTPUT_FILE = "data/ideuy/K29D6P6_MVD_diff.tif"
+
+# %%
+# Read data
+mds_raster = rasterio.open(MDS_INPUT_FILE)
+mdt_raster = rasterio.open(MDT_INPUT_FILE)
+rgbi_raster = rasterio.open(RGBI_INPUT_FILE)
+
+# %%
+# Plot rasters
+show(mds_raster)
+show(mdt_raster)
+show(rgbi_raster)
+
+# %%
+# Raster operations: MDS - MDT
+
+# Mask no-data values (value == -32767.0)
+mds_no_data_value = mds_raster.read(1).min()
+mdt_no_data_value = mdt_raster.read(1).min()
+
+mds_masked_raster = mask_raster_band_by_value(
+    raster_band=mds_raster.read(1), no_data_value=mds_no_data_value
+)
+mdt_masked_raster = mask_raster_band_by_value(
+    raster_band=mdt_raster.read(1), no_data_value=mdt_no_data_value
+)
+
+# diff_raster = mds_masked_raster - mdt_masked_raster
+
+# %%
+
+# Calculate NDVI
+ndvi_raster = calculate_ndvi(input_rgbi_raster_file=RGBI_INPUT_FILE, output_file=NDVI_OUTPUT_FILE)
+
+# Plot raster
+show(ndvi_raster)
+
+# %%

preprocessing/constants.py

@@ -0,0 +1,22 @@
+# System
+NUM_PARALLEL_JOBS = -2
+
+# Geographic
+CRS_EPSG = 5382
+
+# Raster
+RASTER_SCALE_FACTOR = 1 / 4
+
+# Data output
+OUTPUT_VECTORS = "data/outputs/vector"
+OUTPUT_RASTERS = "data/outputs/raster"
+MDS_OUTPUT_FILE = f"{OUTPUT_RASTERS}/K29D6P6_MDS_MVD_025x.tif"
+NDVI_OUTPUT_FILE = f"{OUTPUT_RASTERS}/K29D6P6_NDVI_16_Remesa_01_MVD.tif"
+
+# Data input
+INPUT_VECTORS = ""
+INPUT_RASTERS_IDEUY = "data/ideuy"
+
+MDS_INPUT_FILE = f"{INPUT_RASTERS_IDEUY}/K29D6P6_MDS_Remesa_01_MVD.tif"
+MDT_INPUT_FILE = f"{INPUT_RASTERS_IDEUY}/K29D6P6_MDT_Remesa_01_MVD.tif"
+RGBI_INPUT_FILE = f"{INPUT_RASTERS_IDEUY}/K29D6P6_RGBI_16_Remesa_01_MVD.tif"

preprocessing/raster_to_polygons.py

@@ -0,0 +1,29 @@
+# %%
+from pathlib import Path
+
+import rasterio
+from constants import MDT_INPUT_FILE, OUTPUT_VECTORS
+from rasterio import features
+from utils import mask_raster_band_by_value, raster_to_polygons
+
+# %%
+if __name__ == "__main__":
+    raster = rasterio.open(MDT_INPUT_FILE)
+    # Set mask based on no-data values
+    raster_no_data_value = raster.read(1).min()
+    mdt_masked_raster = mask_raster_band_by_value(
+        raster_band=raster.read(1), no_data_value=raster_no_data_value
+    )
+    # Get polygon and value from each raster cell:
+    masked_raster_polygons = features.shapes(mdt_masked_raster)
+    # Convert to polygons
+    masked_polygons_gdf = raster_to_polygons(
+        shapes_from_raster=masked_raster_polygons, parallel=True
+    )
+    # Write geodataframe
+    filename = Path(MDT_INPUT_FILE).name
+    output_file = Path(OUTPUT_VECTORS) / f"{filename}.geojson"
+    print(f"Saving output to {output_file}")
+    Path(OUTPUT_VECTORS).mkdir(parents=True, exist_ok=True)
+    masked_polygons_gdf.to_file(output_file, driver="GeoJSON")
+    print("Done!")

preprocessing/rgb_downsampling.py

@@ -0,0 +1,15 @@
+from pathlib import Path
+
+from constants import (
+    MDS_INPUT_FILE,
+    MDS_OUTPUT_FILE,
+    OUTPUT_RASTERS,
+    RASTER_SCALE_FACTOR,
+)
+from utils import save_raster, transform_raster
+
+if __name__ == "__main__":
+    Path(OUTPUT_RASTERS).mkdir(parents=True, exist_ok=True)
+    original_rgb, trans_rgb, transform = transform_raster(MDS_INPUT_FILE, RASTER_SCALE_FACTOR)
+    save_raster(original_rgb, trans_rgb, transform, MDS_OUTPUT_FILE)
+    print("Done!")