Point Cloud Curb Detection Dataset

This dataset contains labeled point cloud data that was captured by a car equipped with a mobile laser scanner.

It is part of the ICMLA publication Large-Scale Curb Extraction Based on 3D Deep Learning and Iterative Refinement Post-Processing

The dataset is supposed to serve as a benchmark for automated large-scale point cloud curb detection approaches.

The dataset is derived from the publicly available KITTI360 dataset published in the paper

Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer by Jun Xie et al.

LICENSE

Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0) License

If you find this dataset useful, please cite the following publication:

@INPROCEEDINGS{9680221,  author={Schmitz, Jan-Christoph and Bauer, Adrian and Kummert, Anton},  booktitle={2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)},   title={Large-Scale Curb Extraction Based on 3D Deep Learning and Iterative Refinement Post-Processing},   year={2021},  volume={},  number={},  pages={558-563},  doi={10.1109/ICMLA52953.2021.00093}}

Supported by the State of North Rhine-Westphalia, Germany