a novel Ground-based Fast Approximate Least Squares (Ground-FALS) estimator for ground normal vectors
- NA-LOAM: NA-LOAM: Normal-based Adaptive LiDAR Odometry and Mapping
Tested under Ubuntu 18.04 with opencv4.0. Output point cloud with the topic "cloud_normal".
mkdir -p ground_fals_ws/src
cd ground_fals_ws/src
git clone https://github.com/BuaaYfl/Ground-FALS.git
set OpenCV_DIR in the CMakeLists.txt to your local path, and please compile the opencv-contrib module in advance.
cd .. & catkin_make
source devel/setup.bash
For the M2DGR dataset
roslaunch ground_fals normal_m2dgr.launch
For the KITTI datasets dataset
roslaunch ground_fals normal_kitti.launch
So far, we have only provided launch files for M2DGR and KITTI datasets
Set the parameters in the yaml file for the LiDAR carefully. compute_table must be set to true.
compute_table: true # true: compute only the lookup table
ring_table_dir: "/table_dir" # lookup table path, read or write
The lookup table will be saved to the path specified by ring_table_dir upon ros shutdown.
roslaunch ground_fals *.launch
rosbag play *.bag
Finally, run with your lookup table
roslaunch ground_fals *.launch