No version for distro dashing. Known supported distros are highlighted in the buttons above.
No version for distro crystal. Known supported distros are highlighted in the buttons above.
No version for distro bouncy. Known supported distros are highlighted in the buttons above.
No version for distro melodic. Known supported distros are highlighted in the buttons above.

velo2cam_calibration package from velo2cam_calibration repo

velo2cam_calibration

Package Summary

Tags No category tags.
Version 1.0.1
License GPLv2
Build type CATKIN
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/beltransen/velo2cam_calibration.git
VCS Type git
VCS Version master
Last Updated 2019-02-27
Dev Status MAINTAINED
Released UNRELEASED

Package Description

The velo2cam_calibration package

Additional Links

Maintainers

  • Jorge Beltran
  • Carlos Guindel

Authors

  • Jorge Beltran
  • Carlos Guindel

velo2cam_calibration Build Status

The velo2cam_calibration software implements an Automatic Calibration algorithm for Lidar-Stereo camera setups [1]. This software is provided as a ROS package.

Package developed at Intelligent Systems Laboratory, Universidad Carlos III de Madrid.

gazebo screenshot

Nodes

stereo_pattern

Subscribed Topics

cloud2 (sensor_msgs/PointCloud2)

    Stereo camera point cloud containing points belonging to edges in the left image

cam_plane_coeffs (pcl_msgs::ModelCoefficients)

    Coefficients of the calibration target plane model

Published Topics

/stereo_pattern/centers_cloud (velo2cam_calibration::ClusterCentroids)

    Target circles centers obtained from stereo camera data

laser_pattern

Subscribed Topics

cloud1 (sensor_msgs/PointCloud2)

    LIDAR pointcloud

Published Topics

/laser_pattern/centers_cloud (velo2cam_calibration::ClusterCentroids)

    Target circles centers obtained from LIDAR data <!-- ### Parameters ### -->

velo2cam_calibration

Subscribed Topics

~cloud1 (velo2cam_calibration::ClusterCentroids)

    Target circles centers obtained from LIDAR data

~cloud2 (velo2cam_calibration::ClusterCentroids)

    Target circles centers obtained from stereo camera data

~cloud3 (sensor_msgs/PointCloud2)

    Original LIDAR pointcloud

Published Topics

TF containing the transformation between both sensors (see TF info in ROS Wiki)

The node broadcasts the TF transformation between velodyne and stereo frames. The fixed transformation between stereo_camera and stereo is published by a static broadcaster in stereo_pattern.launch. The picture below shows the three coordinate frames:

gazebo screenshot

Note: Additionally, a .launch file called calibrated_tf.launch containing the proper TF broadcasters is created in the /launch folder of the velo2cam_calibration package so you can use the calibration just executing:

roslaunch velo2cam_calibration calibrated_tf.launch

Parameters

As described in the paper, different parameters can be selected. The ones that you will usually need are set in the launch files. For convenience, two sets of launch files are provided, with different parameters intended for the Gazebo environment, on the one hand, or the real wood pattern, on the other hand. The latter have real_ as a prefix.

Usage

Some sample .launch files are provided in this package. The simplest way to launch the algorithm is by running the three main ROS nodes as follows:

roslaunch velo2cam_calibration laser_pattern.launch

roslaunch velo2cam_calibration stereo_pattern.launch

roslaunch velo2cam_calibration velo2cam_calibration.launch

We also provide a launch file containing the three launch files above:

roslaunch velo2cam_calibration full_calibration.launch

In order to test the algorithm, you can download an example .bag file here.

Note: The .bag file above was generated using a simulator environment in Gazebo which is provided here. We use the simulator in order to test the algorithm with a proper ground truth.

Calibration target details

The following scheme shows the real size of the calibration target used by this algorithm. Measurements are given in centimeters (cm).

gazebo screenshot

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

Citation

[1] Guindel, C., Beltrán, J., Martín, D. and García, F. (2017). Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor Setups. IEEE International Conference on Intelligent Transportation Systems (ITSC), 674–679.

Pre-print available here.

CHANGELOG
No CHANGELOG found.

Wiki Tutorials

See ROS Wiki Tutorials for more details.

Source Tutorials

Not currently indexed.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged velo2cam_calibration at answers.ros.org

velo2cam_calibration package from velo2cam_calibration repo

velo2cam_calibration

Package Summary

Tags No category tags.
Version 1.0.1
License GPLv2
Build type CATKIN
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/beltransen/velo2cam_calibration.git
VCS Type git
VCS Version master
Last Updated 2019-02-27
Dev Status MAINTAINED
Released UNRELEASED

Package Description

The velo2cam_calibration package

Additional Links

Maintainers

  • Jorge Beltran
  • Carlos Guindel

Authors

  • Jorge Beltran
  • Carlos Guindel

velo2cam_calibration Build Status

The velo2cam_calibration software implements an Automatic Calibration algorithm for Lidar-Stereo camera setups [1]. This software is provided as a ROS package.

Package developed at Intelligent Systems Laboratory, Universidad Carlos III de Madrid.

gazebo screenshot

Nodes

stereo_pattern

Subscribed Topics

cloud2 (sensor_msgs/PointCloud2)

    Stereo camera point cloud containing points belonging to edges in the left image

cam_plane_coeffs (pcl_msgs::ModelCoefficients)

    Coefficients of the calibration target plane model

Published Topics

/stereo_pattern/centers_cloud (velo2cam_calibration::ClusterCentroids)

    Target circles centers obtained from stereo camera data

laser_pattern

Subscribed Topics

cloud1 (sensor_msgs/PointCloud2)

    LIDAR pointcloud

Published Topics

/laser_pattern/centers_cloud (velo2cam_calibration::ClusterCentroids)

    Target circles centers obtained from LIDAR data <!-- ### Parameters ### -->

velo2cam_calibration

Subscribed Topics

~cloud1 (velo2cam_calibration::ClusterCentroids)

    Target circles centers obtained from LIDAR data

~cloud2 (velo2cam_calibration::ClusterCentroids)

    Target circles centers obtained from stereo camera data

~cloud3 (sensor_msgs/PointCloud2)

    Original LIDAR pointcloud

Published Topics

TF containing the transformation between both sensors (see TF info in ROS Wiki)

The node broadcasts the TF transformation between velodyne and stereo frames. The fixed transformation between stereo_camera and stereo is published by a static broadcaster in stereo_pattern.launch. The picture below shows the three coordinate frames:

gazebo screenshot

Note: Additionally, a .launch file called calibrated_tf.launch containing the proper TF broadcasters is created in the /launch folder of the velo2cam_calibration package so you can use the calibration just executing:

roslaunch velo2cam_calibration calibrated_tf.launch

Parameters

As described in the paper, different parameters can be selected. The ones that you will usually need are set in the launch files. For convenience, two sets of launch files are provided, with different parameters intended for the Gazebo environment, on the one hand, or the real wood pattern, on the other hand. The latter have real_ as a prefix.

Usage

Some sample .launch files are provided in this package. The simplest way to launch the algorithm is by running the three main ROS nodes as follows:

roslaunch velo2cam_calibration laser_pattern.launch

roslaunch velo2cam_calibration stereo_pattern.launch

roslaunch velo2cam_calibration velo2cam_calibration.launch

We also provide a launch file containing the three launch files above:

roslaunch velo2cam_calibration full_calibration.launch

In order to test the algorithm, you can download an example .bag file here.

Note: The .bag file above was generated using a simulator environment in Gazebo which is provided here. We use the simulator in order to test the algorithm with a proper ground truth.

Calibration target details

The following scheme shows the real size of the calibration target used by this algorithm. Measurements are given in centimeters (cm).

gazebo screenshot

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

Citation

[1] Guindel, C., Beltrán, J., Martín, D. and García, F. (2017). Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor Setups. IEEE International Conference on Intelligent Transportation Systems (ITSC), 674–679.

Pre-print available here.

CHANGELOG
No CHANGELOG found.

Wiki Tutorials

See ROS Wiki Tutorials for more details.

Source Tutorials

Not currently indexed.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged velo2cam_calibration at answers.ros.org

No version for distro ardent. Known supported distros are highlighted in the buttons above.
No version for distro jade. Known supported distros are highlighted in the buttons above.
No version for distro indigo. Known supported distros are highlighted in the buttons above.
No version for distro hydro. Known supported distros are highlighted in the buttons above.