PKLot Segmentation by light condition

This is the dataset referenced in the publication, based on the PKLot dataset (Almeida et al., 2015). It includes the full set of images used in our training and validation processes, along with a segmented version where the images are categorized by lighting condition (cloudy, sunny, and shaded), as well as the models used in our experiment. Using original 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.Our training process involved various models, and the original repositories are listed below:YOLOv3-main.zippytorch-retinanet-master.zipyolov8-ultralytics-8.3.24.zipyolov9-main.zip The file segmented_pklot.zip provides the image split according to different lighting conditions: cloudy, sunny, and shaded. Meanwhile, full_dataset_pklot.zip contains the complete dataset used for training and validation.