/BeautyMap

[RA-L'24] BeautyMap: Binary-Encoded Adaptable Ground Matrix for Dynamic Points Removal in Global Maps

Primary LanguagePython

BeautyMap: Binary-Encoded Adaptable Ground Matrix for Dynamic Points Removal in Global Maps

Mingkai Jia1,*    Qingwen Zhang2,*    Bowen Yang1    Jin Wu1    Ming Liu1    Patric Jensfelt2   
*Co-first author    1HKUST    2KTH   

arXiv [video coming soon] [poster coming soon]. Accepted by RA-L'24.

0. Setup

Available in Ubuntu, Windows and MacOS.

Conda/Mamba is recommended.

wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
bash Miniconda3-latest-Linux-x86_64.sh

curl -L -O "https://github.com/conda-forge/miniforge/releases/latest/download/Mambaforge-$(uname)-$(uname -m).sh"
bash Mambaforge-$(uname)-$(uname -m).sh

Python version tested: 3.8, 3.9, 3.10.

mamba create -n beautymap python=3.8
mamba activate beautymap
pip install -r requirements.txt

1. Run

Prepare Data: Teaser data (KITTI 00: 384.4Mb) can be downloaded via follow commands, more data detail can be found in the dataset section or format your own dataset follow custom dataset section.

wget https://zenodo.org/records/8160051/files/00.zip
unzip 00.zip -d data

Run:

# kitti
python main.py --data_dir data/00 --dis_range 40 --xy_resolution 1 --h_res 0.5

# semi-indoor
python main.py --data_dir data/semindoor --dis_range 10 --xy_resolution 0.5 --h_res 0.2

Parameters explanation (Check our paper for more details):

  • range: from center point to an square.
  • resolution: resolution of the grid (x,y).
  • h_res: resolution of the grid (z).

beautymap

2. Evaluation

Please reference to DynamicMap_Benchmark for the evaluation of BeautyMap and comparison with other dynamic removal methods.

Evaluation Section link

Citation

This work was partially supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP) funded by the Knut and Alice Wallenberg Foundation.

Please cite our works if you find these useful for your research.

@ARTICLE{10533672,
  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}}

@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}
}