Parking Spot Detection¶

Install package¶

To use the geoai-py package, ensure it is installed in your environment. Uncomment the command below if needed.

In [ ]:

# %pip install geoai-py

# %pip install geoai-py

Import libraries¶

In [ ]:

import geoai

import geoai

Download sample data¶

We will download a sample image from Hugging Face Hub to use for parking spot detection. You can find more high-resolution images from OpenAerialMap.

In [ ]:

raster_url = (
    "https://huggingface.co/datasets/giswqs/geospatial/resolve/main/parking_spots.tif"
)

raster_url = ( "https://huggingface.co/datasets/giswqs/geospatial/resolve/main/parking_spots.tif" )

In [ ]:

raster_path = geoai.download_file(raster_url)

raster_path = geoai.download_file(raster_url)

Visualize the image¶

In [ ]:

geoai.view_raster(raster_url)

geoai.view_raster(raster_url)

Initialize the model¶

In [ ]:

detector = geoai.ParkingSplotDetector()

detector = geoai.ParkingSplotDetector()

Extract parking spots¶

Extract parking spots from the image using the model and save the output image.

In [ ]:

mask_path = detector.generate_masks(
    raster_path=raster_path,
    output_path="parking_masks.tif",
    confidence_threshold=0.5,
    mask_threshold=0.5,
    overlap=0.25,
    chip_size=(256, 256),
    min_object_area=10,
    # max_object_area=5000,
)

mask_path = detector.generate_masks( raster_path=raster_path, output_path="parking_masks.tif", confidence_threshold=0.5, mask_threshold=0.5, overlap=0.25, chip_size=(256, 256), min_object_area=10, # max_object_area=5000, )

Convert the image masks to polygons and save the output GeoJSON file.

In [ ]:

gdf = detector.vectorize_masks(
    masks_path="parking_masks.tif",
    output_path="parking.geojson",
    min_object_area=300,
    # max_object_area=5000,
)

gdf = detector.vectorize_masks( masks_path="parking_masks.tif", output_path="parking.geojson", min_object_area=300, # max_object_area=5000, )

Add geometric properties¶

In [ ]:

gdf = geoai.add_geometric_properties(gdf)

gdf = geoai.add_geometric_properties(gdf)

Visualize results¶

In [ ]:

geoai.view_vector_interactive(gdf, column="confidence", tiles=raster_url)

geoai.view_vector_interactive(gdf, column="confidence", tiles=raster_url)