Skip to content

An ROS implementation for paper "Curved-Voxel Clustering for Accurate Segmentation of 3D LiDAR Point Clouds with Real-Time Performance"

Notifications You must be signed in to change notification settings

HMX2013/CVC-ROS

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CVC ROS

An ROS implementation of paper "Curved-Voxel Clustering for Accurate Segmentation of 3D LiDAR Point Clouds with Real-Time Performance"

Ubuntu ROS C++

demo_1

Features

  • New Spatial Primitive. curved-voxel, a LiDAR-optimized spatial unit reflecting distinct characteristics of 3D LiDAR point clouds.
  • Algorithm. an efficient method for segmenting 3D LiDAR point clouds by utilizing LiDAR-optimized curved-voxels and efficient hashbased data structure.
  • ROS dynamic reconfigure, you can tune the parameters easily.

Reference

TODOs

  • imporove the efficiency of algorithm
  • imporove the segmentation accuracy

Known Issues

  • the segementation result is not very ideal.

Dependencies

How to use

# clone the repo
mkdir -p catkin_ws/src
cd catkin_ws/src
git clone https://github.com/HMX2013/SemanticKITTI_loader
git clone https://github.com/HMX2013/CVC-ROS
download obsdet_msgs from
"https://drive.google.com/file/d/1ztLk9Slm656CV-WJieUpBJPlz-Iw14Bk/view?usp=share_link"
cd ../
catkin_make
roslaunch semantic_kitti run_semantic.launch
roslaunch cvc_ros run_rviz.launch

Contribution

You are welcome contributing to the package by opening a pull-request

We are following: Google C++ Style Guide, C++ Core Guidelines, and ROS C++ Style Guide

License

MIT License

About

An ROS implementation for paper "Curved-Voxel Clustering for Accurate Segmentation of 3D LiDAR Point Clouds with Real-Time Performance"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published