The velo2cam_calibration software implements a state-of-the-art automatic calibration algorithm for pair of sensors composed of LiDAR and camera devices in any possible combination [1]. This software is provided as a ROS package.
Package co-developed by Carlos Guindel
To install this ROS package:
- Clone the repository into your catkin_ws/src/ folder.
- Install run dependencies:
sudo apt-get install ros-<distro>-opencv-apps - Build your workspace as usual.
See HOWTO.md for detailed instructions on how to use this software.
To test the algorithm in a virtual environment, you can launch any of the calibration scenarios included in our Gazebo validation suite.
The following picture shows a possible embodiment of the proposed calibration target used by this algorithm and its corresponding dimensional drawing.
Note: Other size may be used for convenience. If so, please configure node parameters accordingly.
If you use this work in your research, please consider citing the following paper:
[1] Beltrán, J., Guindel, C., and García, F. (2021). Automatic Extrinsic Calibration Method for LiDAR and Camera Sensor Setups. arXiv:2101.04431 [cs.RO]. Submitted to IEEE Transactions on Intelligent Transportation Systems.
A previous version of this tool is available here and was described on this paper:
[2] Guindel, C., Beltrán, J., Martín, D., and García, F. (2017). Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor Setup. IEEE International Conference on Intelligent Transportation Systems (ITSC), 674–679.