Published April 19, 2024 | Version v2
Dataset Open

A Dynamic Points Removal Benchmark in Point Cloud Maps

Creators

  • 1. KTH

Description

Uniformat Dataset LiDAR Point Cloud Data [PCD format: with pose and points (x,y,z,/i)] 
We recommend you read this wiki page first to know about data: https://kth-rpl.github.io/DynamicMap_Benchmark/data/
For methods detail: DynamicMap_Benchmark repo, DUFOMap, BeautyMap.

  • 00: KITTI sequence 00 [VLP-64] from frame 4390 to 4530
  • 05: KITTI sequence 05 [VLP-64] from frame 2350 to 2670
  • av2: Argoverse 2.0 one sequence on 07YOTznatmYypvQYpzviEcU3yGPsyaGg__Spring_2020. [2 x VLP-32]
  • KTH campus: CVPR'24 MCD(Leica RTC360) For convenience teaser running, we include only 18 frames in data. Please check the MCD project page for more.
  • semindoor: semi-indoor dataset collected by [VLP-16], collected by ourselves. 
  • twofloor: complex structure with two floors[Livox mid-360], collected by ourselves.

 

Dataset Description Sensor Type Total Frame Number
KITTI sequence 00 in a small town with few dynamics (including one pedestrian around) VLP-64 141
KITTI sequence 05 in a small town straight way, one higher car, the benchmarking paper cover image from this sequence. VLP-64 321
Argoverse2 in a big city, crowded and tall buildings (including cyclists, vehicles, people walking near the building etc. 2 x VLP-32 575
KTH campus (no gt) Collected by us (Thien-Minh) on the KTH campus. Lots of people move around on the campus.  The DUFOMap paper cover image is from this one. Leica RTC360 18
Semi-indoor Collected by us (Qingwen & Mingkai), running on a small 1x2 vehicle with two people walking around the platform. VLP-16 960
Twofloor (no gt) Collected by us (Bowen Yang) in a quadruped robot. A two-floor structure environment with one pedestrian around. Livox-mid 360 3305

 

Cite as:

@inproceedings{zhang2023benchmark,
  author={Zhang, Qingwen and Duberg, Daniel and Geng, Ruoyu and Jia, Mingkai and Wang, Lujia and Jensfelt, Patric},
  booktitle={IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)}, 
  title={A Dynamic Points Removal Benchmark in Point Cloud Maps}, 
  year={2023},
  pages={608-614},
  doi={10.1109/ITSC57777.2023.10422094}
}
@article{jia2024beautymap,
  author={Jia, Mingkai and Zhang, Qingwen and Yang, Bowen and Wu, Jin and Liu, Ming and Jensfelt, Patric},
  journal={IEEE Robotics and Automation Letters}, 
  title={{BeautyMap}: Binary-Encoded Adaptable Ground Matrix for Dynamic Points Removal in Global Maps}, 
  year={2024},
  volume={9},
  number={7},
  pages={6256-6263},
  doi={10.1109/LRA.2024.3402625}
}
@article{daniel2024dufomap,
  author={Duberg, Daniel and Zhang, Qingwen and Jia, Mingkai and Jensfelt, Patric},
  journal={IEEE Robotics and Automation Letters}, 
  title={{DUFOMap}: Efficient Dynamic Awareness Mapping}, 
  year={2024},
  volume={9},
  number={6},
  pages={5038-5045},
  doi={10.1109/LRA.2024.3387658}
}

 

If you use this data, feel free to add your project to https://kth-rpl.github.io/DynamicMap_Benchmark/papers/

Files

00.zip

Files (4.2 GB)

Name Size Download all
md5:87f856c4dd1ad05d0ffd4171f92780a0
384.8 MB Preview Download
md5:6bed4fc1e19b7d3e3b08ed6da03ed664
864.0 MB Preview Download
md5:98005cb45457720a4361ef84b83eab39
1.3 GB Preview Download
md5:6263745a391e7ada169c82755b1c9d0b
256.4 MB Preview Download
md5:1f15b15fc0e8d649e176e3f8f95d05c7
620.8 MB Preview Download
md5:b8ac5b8c469b9a8a34096bcc3e20edfb
725.1 MB Preview Download