ngsford / range-image-based-dbscan-3d-lidar-ros

An ROS implementation of range image base dbscan clustering for 3D LiDAR point clouds

Fast range image based DBSCAN clustering for 3D LiDAR Point Clouds

An ROS implementation for dbscan clustering of 3D LiDAR point clouds

Reference

• Chen, Zhihui, et al. "Fast-spherical-projection-based point cloud clustering algorithm." Transportation research record 2676.6 (2022): 315-329.

Features

• faster comparing to traditional dbscan algorithm

TODOs

• imporove the segmentation accuracy

Dependencies

• semantic_kitti_loader
• obsdet_msgs

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/Range-image-based-DBSCAN-3D-LiDAR-ROS

cd ../
catkin_make

roslaunch ri_dbscan run_rviz.launch
roslaunch semantic_kitti run_semantic.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