RailPC: A large‐scale railway point cloud semantic segmentation dataset
Abstract Semantic segmentation in the context of 3D point clouds for the railway environment holds a significant economic value, but its development is severely hindered by the lack of suitable and specific datasets. Additionally, the models trained on existing urban road point cloud datasets demons...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-12-01
|
| Series: | CAAI Transactions on Intelligence Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cit2.12349 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841543316754137088 |
|---|---|
| author | Tengping Jiang Shiwei Li Qinyu Zhang Guangshuai Wang Zequn Zhang Fankun Zeng Peng An Xin Jin Shan Liu Yongjun Wang |
| author_facet | Tengping Jiang Shiwei Li Qinyu Zhang Guangshuai Wang Zequn Zhang Fankun Zeng Peng An Xin Jin Shan Liu Yongjun Wang |
| author_sort | Tengping Jiang |
| collection | DOAJ |
| description | Abstract Semantic segmentation in the context of 3D point clouds for the railway environment holds a significant economic value, but its development is severely hindered by the lack of suitable and specific datasets. Additionally, the models trained on existing urban road point cloud datasets demonstrate poor generalisation on railway data due to a large domain gap caused by non‐overlapping special/rare categories, for example, rail track, track bed etc. To harness the potential of supervised learning methods in the domain of 3D railway semantic segmentation, we introduce RailPC, a new point cloud benchmark. RailPC provides a large‐scale dataset with rich annotations for semantic segmentation in the railway environment. Notably, RailPC contains twice the number of annotated points compared to the largest available mobile laser scanning (MLS) point cloud dataset and is the first railway‐specific 3D dataset for semantic segmentation. It covers a total of nearly 25 km railway in two different scenes (urban and mountain), with 3 billion points that are finely labelled as 16 most typical classes with respect to railway, and the data acquisition process is completed in China by MLS systems. Through extensive experimentation, we evaluate the performance of advanced scene understanding methods on the annotated dataset and present a synthetic analysis of semantic segmentation results. Based on our findings, we establish some critical challenges towards railway‐scale point cloud semantic segmentation. The dataset is available at https://github.com/NNU‐GISA/GISA‐RailPC, and we will continuously update it based on community feedback. |
| format | Article |
| id | doaj-art-7ab3c84133df4097bfe8343096e924dc |
| institution | Kabale University |
| issn | 2468-2322 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | CAAI Transactions on Intelligence Technology |
| spelling | doaj-art-7ab3c84133df4097bfe8343096e924dc2025-01-13T14:05:51ZengWileyCAAI Transactions on Intelligence Technology2468-23222024-12-01961548156010.1049/cit2.12349RailPC: A large‐scale railway point cloud semantic segmentation datasetTengping Jiang0Shiwei Li1Qinyu Zhang2Guangshuai Wang3Zequn Zhang4Fankun Zeng5Peng An6Xin Jin7Shan Liu8Yongjun Wang9Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing Normal University Nanjing ChinaJiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing Normal University Nanjing ChinaJiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing Normal University Nanjing ChinaTianjin Key Laboratory of Rail Transit Navigation Positioning and Spatio‐temporal Big Data Technology Tianjin ChinaCollege of Computer Science and Engineering Northwest Normal University Lanzhou ChinaMckelvey School of Engineering Washington University in St. Louis St. Louis Missouri USASchool of Electronic and Information Engineering Ningbo University of Technology Ningbo ChinaEastern Institute of Technology (EIT) Ningbo ChinaJiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing Normal University Nanjing ChinaJiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing Normal University Nanjing ChinaAbstract Semantic segmentation in the context of 3D point clouds for the railway environment holds a significant economic value, but its development is severely hindered by the lack of suitable and specific datasets. Additionally, the models trained on existing urban road point cloud datasets demonstrate poor generalisation on railway data due to a large domain gap caused by non‐overlapping special/rare categories, for example, rail track, track bed etc. To harness the potential of supervised learning methods in the domain of 3D railway semantic segmentation, we introduce RailPC, a new point cloud benchmark. RailPC provides a large‐scale dataset with rich annotations for semantic segmentation in the railway environment. Notably, RailPC contains twice the number of annotated points compared to the largest available mobile laser scanning (MLS) point cloud dataset and is the first railway‐specific 3D dataset for semantic segmentation. It covers a total of nearly 25 km railway in two different scenes (urban and mountain), with 3 billion points that are finely labelled as 16 most typical classes with respect to railway, and the data acquisition process is completed in China by MLS systems. Through extensive experimentation, we evaluate the performance of advanced scene understanding methods on the annotated dataset and present a synthetic analysis of semantic segmentation results. Based on our findings, we establish some critical challenges towards railway‐scale point cloud semantic segmentation. The dataset is available at https://github.com/NNU‐GISA/GISA‐RailPC, and we will continuously update it based on community feedback.https://doi.org/10.1049/cit2.12349data benchmarkMLS point cloudsrailway scenesemantic segmentation |
| spellingShingle | Tengping Jiang Shiwei Li Qinyu Zhang Guangshuai Wang Zequn Zhang Fankun Zeng Peng An Xin Jin Shan Liu Yongjun Wang RailPC: A large‐scale railway point cloud semantic segmentation dataset CAAI Transactions on Intelligence Technology data benchmark MLS point clouds railway scene semantic segmentation |
| title | RailPC: A large‐scale railway point cloud semantic segmentation dataset |
| title_full | RailPC: A large‐scale railway point cloud semantic segmentation dataset |
| title_fullStr | RailPC: A large‐scale railway point cloud semantic segmentation dataset |
| title_full_unstemmed | RailPC: A large‐scale railway point cloud semantic segmentation dataset |
| title_short | RailPC: A large‐scale railway point cloud semantic segmentation dataset |
| title_sort | railpc a large scale railway point cloud semantic segmentation dataset |
| topic | data benchmark MLS point clouds railway scene semantic segmentation |
| url | https://doi.org/10.1049/cit2.12349 |
| work_keys_str_mv | AT tengpingjiang railpcalargescalerailwaypointcloudsemanticsegmentationdataset AT shiweili railpcalargescalerailwaypointcloudsemanticsegmentationdataset AT qinyuzhang railpcalargescalerailwaypointcloudsemanticsegmentationdataset AT guangshuaiwang railpcalargescalerailwaypointcloudsemanticsegmentationdataset AT zequnzhang railpcalargescalerailwaypointcloudsemanticsegmentationdataset AT fankunzeng railpcalargescalerailwaypointcloudsemanticsegmentationdataset AT pengan railpcalargescalerailwaypointcloudsemanticsegmentationdataset AT xinjin railpcalargescalerailwaypointcloudsemanticsegmentationdataset AT shanliu railpcalargescalerailwaypointcloudsemanticsegmentationdataset AT yongjunwang railpcalargescalerailwaypointcloudsemanticsegmentationdataset |