Parking Space Occupancy

The PKLot dataset contains 12,417 images of parking lots and 695,899 images of parking spaces segmented from them, which were manually checked and labeled. All images were acquired at the parking lots of the Federal University of Parana (UFPR) and the Pontificial Catholic University of Parana (PUCPR), both located in Curitiba, Brazil.

The Action-Camera Parking Dataset contains 293 images captured at a roughly 10-meter height using a GoPro Hero 6 camera. It can be used for training machine learning models that perform image-based parking space occupancy classification. Image credit: https://github.com/martin-marek/parking-space-occupancy

The SPKL dataset contains 1203 images of parking lots divided into 11 categories regarding vision conditions (including the 'winter' category absent in other datasets at the time of publishing). Parking lot annotations: lists of parking lot coordinates (4 points per lot) Vision categories: sunny, overcast, rainy, winter, fog, glare, night, infrared, occlusion (car), occlusion (tree), distortion Labels: binary (occupied/non-occupied)