You can find the simulation environment in this repo
thermal_range_calib is a robust, high-accuracy extrinsic calibration tool between thermal camera LiDAR (e.g. Livox) and RGBD-camera in targetless environment. If the scene is suitable, we can achieve high-level accuracy similar to the target-based method.
The system architecture is shown in the following diagram:
Related paper is coming soon...
Ubuntu 64-bit 16.04 or 18.04. ROS Kinetic or Melodic. ROS Installation and its additional ROS pacakge:
sudo apt-get install ros-XXX-cv-bridge ros-xxx-pcl-conversions
Follow Eigen Installation
Download Ceres 1.14.0 from here Follow Ceres Installation.
Follow PCL Installation. (Our code is tested with PCL1.7)
Clone the repository and catkin_make:
cd ~/catkin_ws/src
git clone https://github.com/allenthreee/thermal_range_calib.git
cd ../
catkin_make
source ~/catkin_ws/devel/setup.bash
our thermal camera intrinsic is shown below:
example data could be download here: google drive
Move it to your local path, and then change the file path in thermal_calib.yaml to your data path. Then directly run
roslaunch thermal_range_calib thermal_calib.launch
Following are some fusion examples:
Record thermal image files to png format and the point cloud to pcd files(you can record it from the simulation or hardware).
Change the data path to your local data path.
Provide the instrinsic matrix and distor coeffs for your thermal camera.
Thanks for Livox_Camera_calib(C. Yuan et al. Pixel-level extrinsic self calibration of high resolution lidar and camera in targetless environments).