Home

Awesome

Ground Segmentation Benchmark

This repository contains various Ground Segmentation baseline methods. Currently, 7 projects are organized for SemanticKITTI dataset:

The repository consists of C++ and ROS. But, for python users, we also provide all the previously extracted ground label files. Please check the explanations below.

Citation

If our open sources have been helpful, please cite the below papers published by our research group:

@inproceedings{oh2022travel,
    title={{TRAVEL: Traversable ground and above-ground object segmentation using graph representation of 3D LiDAR scans}},
    author={Oh, Minho and Jung, Euigon and Lim, Hyungtae and Song, Wonho and Hu, Sumin and Lee, Eungchang Mason and Park, Junghee and Kim, Jaekyung and Lee, Jangwoo and Myung, Hyun},
    booktitle={IEEE Robotics and Automation Letters},
    year={2022},
    note={{Submitted}}
}

@inproceedings{lee2022patchworkpp,
    title={{Patchwork++: Fast and robust ground segmentation solving partial under-segmentation using 3D point cloud}},
    author={Lee, Seungjae and Lim, Hyungtae and Myung, Hyun},
    booktitle={Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst.},
    year={2022},
    note={{Submitted}} 
}

@article{lim2021patchwork,
    title={Patchwork: Concentric Zone-based Region-wise Ground Segmentation with Ground Likelihood Estimation Using a 3D LiDAR Sensor},
    author={Lim, Hyungtae and Oh, Minho and Myung, Hyun},
    journal={IEEE Robot. Autom. Lett.},
    volume={6},
    number={4},
    pages={6458--6465},
    year={2021},
    }

Contents

  1. Description
  2. Requirements
  3. Preparing DataSet
  4. Getting Started
  5. Python visualization / Provided result files

Description

This benchmark provides:

Performance Calculation

Image text

RVIZ

Requirements

Test Environment

The code wass tested successfully at

Settings

sudo apt update
sudo apt-get install ros-melodic-jsk-recognition
sudo apt-get install ros-melodic-jsk-common-msgs
sudo apt-get install ros-melodic-jsk-rviz-plugins

sudo apt-get install libpcl-dev

Install Package

$ cd ~/catkin_ws/src
$ git clone git@github.com:url-kaist/Ground-Segmentation-Benchmark.git
$ catkin build gseg_benchmark

Preparing Dataset

Offline KITTI dataset

  1. Download SemanticKITTI Odometry dataset including Velodyne point clouds, calibration data, and label data.
  2. Set data_path parameter in shellscripts/common.sh for your machine.

The data_path consists of velodyne folder and labels folder as follows:

${data_path}
    |___00
        |___labels
        |    |___000000.label
        |    |___000001.label
        |    |___ ...
        |___velodyne
            |___000000.bin
            |___000001.bin
            |___ ...
    |___01
        |___labels
        |    |___ ...
        |___velodyne
            |___ ...

Getting Started

Set Parameters of Benchmark

rosparam set /data_path "/home/user/data/SemanticKITTI/"  # absolute path of downloaded KITTI dataset. It must include '/' at the end part
rosparam set /stop_for_each_frame false                   # set as 'true' to make it stop every frame 
rosparam set /init_idx 0                                  # index of first frame to run
rosparam set /save_csv_file true                          # set as 'false' if csv output files are not needed
rosparam set /save_pcd_flag false                         # set as 'false' if csv output files are not needed
rosparam set /output_path "/data/"                        # reltive path of output files to be generated

Run Ground Segmentation Algorithms

$ roscore

$ roslaunch gseg_benchmark gseg_benchmark.launch alg:=${name of algorithm} seq:=${sequence}

For example,

$ roslaunch gseg_benchmark gseg_benchmark.launch alg:=patchwork seq:=05

$ roslaunch gseg_benchmark gseg_benchmark.launch alg:=all seq:=all

If you are not familiar with ROS/C++...

Provided Result Files

We provide csv files of binary estimated results of sequences from "00" to "10". The value 1 denotes the corresponding point is estimated as the ground, whereas 0 denotes the point is considered as the non-ground.

The previously extracted ground labels can be downloaded via the below commands:

wget https://urserver.kaist.ac.kr/publicdata/GroundSegBenchmark/cascaded_gseg_ground_labels.zip
wget https://urserver.kaist.ac.kr/publicdata/GroundSegBenchmark/gpf_ground_labels.zip
wget https://urserver.kaist.ac.kr/publicdata/GroundSegBenchmark/gpregression_ground_labels.zip
wget https://urserver.kaist.ac.kr/publicdata/GroundSegBenchmark/linefit_ground_labels.zip
wget https://urserver.kaist.ac.kr/publicdata/GroundSegBenchmark/patchwork_ground_labels.zip
wget https://urserver.kaist.ac.kr/publicdata/GroundSegBenchmark/ransac_ground_labels.zip
wget https://urserver.kaist.ac.kr/publicdata/GroundSegBenchmark/r_gpf_ground_labels.zip

Visualization with Python

We provide Python code to visualize estimated results in binary form.

pip install open3d

alg = "patchwork"
seq = "04"
kittiraw_dir = "/home/user/data/SemanticKITTI/"       # absolute path of KITTI dataset folder
label_csv_dir = "/home/user/data/"                    # absolute path of directory to save csv files
frame_num ="000010"                                   # needed only in viz_one_frame.py

$ cd ~/catkin_ws/src/Ground-Segmentation-Benchmark/src/utils
$ python3 viz_one_frame.py
$ python3 viz_all_frames.py

Image text

Contributors

Errors

If the following error occurs in flann

/usr/include/flann/util/serialization.h:35:14: error: ‘class std::unordered_map<unsigned int, std::vector<unsigned int> >’ has no member named ‘serialize’

then open header file

sudo gedit /usr/include/flann/util/serialization.h

and change all terms of "map" into "unordered_map".

License

<a rel="license" href="http://creativecommons.org/licenses/by-nc-sa/4.0/"><img alt="Creative Commons License" style="border-width:0" src="https://i.creativecommons.org/l/by-nc-sa/4.0/88x31.png" /></a><br />This work is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by-nc-sa/4.0/">Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License</a>.

Copyright