Parkseg12K: Parking Lot Segmentation Dataset with NIR-Enhanced Imagery

UTEL-UIUC created a dataset for parking lot segmentation, last updated in March 2025. The annotation masks were generated by correcting and processing data from the Parking Reform Network and OpenStreetMap to meet specific research requirements. The dataset is described in a 2024 article titled 'A Pipeline and NIR-Enhanced Dataset for Parking Lot Segmentation'.

Use Cases

• Train semantic segmentation models based on the annotated mask images for parking lots.
• Analyze urban land use and parking infrastructure based on processed geospatial data.
• Benchmark segmentation algorithms on near-infrared (NIR) enhanced imagery as referenced in the description.
• Study the spatial distribution of parking facilities using corrected OpenStreetMap and PRN data.

Strengths

• Annotations are derived from two established sources: Parking Reform Network (PRN) and OpenStreetMap (OSM) data.
• Dataset is associated with a specific 2024 research article detailing its creation pipeline.
• Last update timestamp is precisely recorded as 2025-03-10 21:46:02.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, file formats, and license information are unknown.

Provenance

Source

UTEL-UIUC, with annotations derived from Parking Reform Network (PRN) and OpenStreetMap (OSM) data.

Collection Method

Corrected and processed PRN and OSM data to create mask images suitable for a specific task.

Time Range

Associated with a 2024 article; specific temporal coverage of the underlying imagery is unknown.

Freshness

Last updated 2025-03-10 21:46:02; freshness should be verified.

Geography

Geographic coverage is not specified, but likely reflects the coverage of the source PRN and OSM data.