Brad Dwyer


Object Detection


PKLot Computer Vision Project

Drop an image or


12416 images
Explore Dataset

Parking Lot Dataset

The PKLot dataset contains 12,416 images of parking lots extracted from surveilance camera frames. There are images on sunny, cloudy, and rainy days and the parking spaces are labeled as occupied or empty. We have converted the original annotations to a variety of standard object detection formats by enclosing a bounding box around the original dataset's rotated rectangle annotations.

Using this Dataset

The PKLot database is licensed under a Creative Commons Attribution 4.0 License and may be used provided you acknowledge the source by citing the PKLot paper in publications about your research:

Almeida, P., Oliveira, L. S., Silva Jr, E., Britto Jr, A., Koerich, A., PKLot – A robust dataset for parking lot classification, Expert Systems with Applications, 42(11):4937-4949, 2015.

Trained Model API

This project has a trained model available that you can try in your browser and use to get predictions via our Hosted Inference API and other deployment methods.

Cite this Project

If you use this dataset in a research paper, please cite it using the following BibTeX:

@misc{ pklot-1tros_dataset,
    title = { PKLot Dataset },
    type = { Open Source Dataset },
    author = { Universidade Federal do Parana },
    howpublished = { \url{ } },
    url = { },
    journal = { Roboflow Universe },
    publisher = { Roboflow },
    year = { 2022 },
    month = { jun },
    note = { visited on 2023-12-02 },

Find utilities and guides to help you start using the PKLot project in your project.


Brad Dwyer

Last Updated

a year ago

Project Type

Object Detection




space-empty, space-occupied

Views: 8597

Views in previous 30 days: 437

Downloads: 1485

Downloads in previous 30 days: 146


CC BY 4.0