E-Scooter Rider Detection and Classification in Dense Urban Environments
Partially Occluded E-Scooter Rider Detection Dataset used in "E-Scooter Rider Detection and Classification in Dense Urban Environments" Gilroy et al 2022.
This dataset contains 1,130 images including 543 e-scooter rider instances and 587 other vulnerable road user instances, for the characterization of detection and classification model performance for partially occluded e-scooter riders. Vulnerable road user instances are occluded by a diverse mix of objects across a range of occlusion levels from 0 to 99% occluded.
Images are annotated using the objective occlusion level annotation method described in “Pedestrian Occlusion Level Classification using Keypoint Detection and 2D Body Surface Area Estimation” Gilroy et al 2021.
@article{gilroy2022scooter,
title={E-Scooter Rider detection and classification in dense urban environments},
author={Gilroy, Shane and Mullins, Darragh and Jones, Edward and Parsi, Ashkan and Glavin, Martin},
journal={Results in Engineering},
volume={16},
pages={100677},
year={2022},
publisher={Elsevier}
}
Pattern Recognition Letters 2022
@article{gilroy2022objective,
title={An objective method for pedestrian occlusion level classification},
author={Gilroy, Shane and Glavin, Martin and Jones, Edward and Mullins, Darragh},
journal={Pattern Recognition Letters},
volume={164},
pages={96--103},
year={2022},
publisher={Elsevier}
}
@inproceedings{gilroy2021pedestrian,
title={Pedestrian Occlusion Level Classification using Keypoint Detection and 2D Body Surface Area Estimation},
author={Gilroy, Shane and Glavin, Martin and Jones, Edward and Mullins, Darragh},
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
pages={3833--3839},
year={2021}
}