/velo2cam_calibration

Automatic Extrinsic Calibration Method for LiDAR and Camera Sensor Setups. ROS Package.

Primary LanguageC++GNU General Public License v2.0GPL-2.0

velo2cam_calibration Build Status

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

real results

Setup

To install this ROS package:

  1. Clone the repository into your catkin_ws/src/ folder.
  2. Install run dependencies: sudo apt-get install ros-<distro>-opencv-apps
  3. Build your workspace as usual.

Usage

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.

Calibration target

The following picture shows a possible embodiment of the proposed calibration target used by this algorithm and its corresponding dimensional drawing.

calibration target

Note: Other size may be used for convenience. If so, please configure node parameters accordingly.

Citation

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.