RANSAC L-shape Fitting for 3D LiDAR Point Clouds

An ROS implementation for RANSAC based L-shape fitting for 3D LiDAR point clouds

Reference

• L-Shape Fitting-Based Vehicle Pose Estimation and Tracking Using 3D-LiDAR. IEEE TRANSACTIONS ON INTELLIGENT VEHICLES. 2020

Features

• very fast comparing to the optimization-based L-shape fitting algorithm

TODOs

• complete ransac L shape fitting
• imporove the stability

Known Issues

• the fitting may be invalid if there are very few point clouds.

Dependencies

• the segementation part to output topic /segmentation/detected_objects
• autoware-msgs
• pcl

How to use

# clone the repo
mkdir -p catkin_ws/src
cd catkin_ws/src
git clone ...
cd ../
catkin_make 
roslaunch ransac_lshape_fitting ransac_lshape_fitting.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