LiDAR-LiDAR Calibration
PreviousData Collection for LiDAR-LiDAR CalibrationNextData Collection for IMU Intrinsic calibration
Last updated
Last updated
Overview: Deepen Calibrate is a software tool that makes the critical task of sensor data calibration simple and quick.
This page allows the users to create, list, launch, and delete calibration datasets. Admins can manage users’ access to these datasets on this page.
Click on New Calibration to create a new calibration dataset.
Select the LiDAR-LiDAR Calibration button to create a new LiDAR-LiDAR calibration dataset.
Upon selecting LiDAR-LiDAR Calibration, the user is welcomed to the instructions page
Click on the Get started button after finishing with the instructions. The user has the choice of proceeding with Target or Targetless LiDAR-LiDAR calibration. Choose the appropriate option.
For a single target, Target count = Single
For multiple targets, Target count = Multi
Add files: Upload a single pcd file for each LiDAR sensor.
Mapping: Map the uploaded frames by picking four points from each frame.
Detect Ground Plane: Get ground planes for better optimization
Calibrate: Run the calibration and visualize the results.
A few other details :
The user can hit the Save changes option at any stage to prevent loss of work.
The user can navigate between the stages and update the details as per convenience.
Download the extrinsic parameters by using the Export option.
Click on the Help Center button (the top right corner) to get your doubts answered related to the calibration.
Upload a single file (.pcd format only) for the two LiDAR sensors. The calibration is calculated from LiDAR 1 to LiDAR 2. Click on Continue to proceed to the ‘Mapping’ stage.
Note: File name should NOT contain any whitespaces.
Mapping point clouds helps to determine where a point present in a frame from LiDAR 1 correlates to points in the frame from LiDAR 2. Our algorithm requires mapping exactly four points to get accurate results to proceed to calibration.
The different interactions with the point clouds are:
Add marker: enable the brush
Erase marker: enable the eraser
Clear markers: clear all the points selection
Toolbar: allows rotate, pan, zoom in/out operations
How to map point clouds using markers?
To start mapping the point clouds:
Click the Add Marker button, and click in the area of interest for LiDAR 1.
Map the exact points for LiDAR 2 by adding a marker.
Repeat the steps for all four markers.
To remove a misplaced marker, click the Erase Marker button and click on the incorrect marker. To remove all the added markers, click on the Clear Markers button.
The four markers selected for the Target based calibration will be the four corners of the target.
The order of the markers should correspond to the length and width configuration in the sample board, i.e., the length should be between the 1st and 2nd corners while the width should be between the 1st and 3rd corners. Please refer to the sample board in the right panel while marking the corner points.
Note: Please go ahead with this step only if your sensors capture ground points else click Continue and move to 'Calibrate' page.
First, Click on Detect ground plane button at the bottom to automatically get the planes in both the LiDARs.
If the user is not satisfied with the detected ground plane, they may use the Clear ground planes button to remove the detected ground planes and paint the ground points using Add sample button in the top center.
Click the Calibrate button at the bottom to trigger calibration. Upon completion, you can see the extrinsic parameters and the error statistics in the right panel. The extrinsic parameters are from LiDAR 1 to LiDAR 2, while the error stats indicate the rotation and translation error of the target boards in the two LiDARs.
The user can visualize the fused point clouds by clicking the Visualise button.
Rotation Error indicates the angle between the target planes
Translation Error indicates the distance between the center of the boards
Add files: Upload a single pcd file for each LiDAR sensor.
Mapping: Map the uploaded frames by picking four points from each frame.
Visualize quick estimates
Detect Ground Plane: This is an optional step, if you are using NDT or GICP algorithms to run the calibration step otherwise, it is mandatory for Custom GICP algorithm.
Calibrate: Run the calibration algorithm of your choice and visualize the results.
A few other details :
The user can hit the Save changes option at any stage to prevent loss of work.
The user can navigate between the stages and update the details as per convenience.
Download the extrinsic parameters by using the Export option.
Click on the Help Center button (the top right corner) to get your doubts answered related to the calibration.
Upload a single file (.pcd format only) for the two LiDAR sensors. The calibration is calculated from LiDAR 1 to LiDAR 2. Click on Continue to proceed to the ‘Mapping’ stage.
Note: File name should NOT contain any whitespaces.
Mapping point clouds helps to determine where a point present in a frame from LiDAR 1 correlates to points in the frame from LiDAR 2. Our algorithm requires mapping exactly four points to get accurate results to proceed to calibration.
The different interactions with the point clouds are:
Add marker: enable the brush
Erase marker: enable the eraser
Clear markers: clear all the points selection
Toolbar: allows rotate, pan, zoom in/out operations
How to map point clouds using markers?
To start mapping the point clouds:
Click the Add Marker button, and click in the area of interest for LiDAR 1.
Map the exact points for LiDAR 2 by adding a marker.
Repeat the steps for all four markers.
To remove a misplaced marker, click the Erase Marker button and click on the incorrect marker. To remove all the added markers, click on the Clear Markers button.
Note:
1.The user may mark any four areas in the LiDARs that correspond to each other since there is no specific target.
2.If the user have existing initial estimates, then those values can be entered directly in the right side panel and skip the mapping step.
Quick estimates will be generated once four points are mapped in both the lidar files. Users can visualize the results and, if satisfied, click on Continue to move forward or use Clear markers to redo the mapping.
Note:
1.Please go ahead with this step only if your sensors capture ground points else click Continue and move to 'Calibrate' page
2.If ground plane is not obtained in this page then the user can only use either NDT or GICP in the next step to perform calibration.
Click on the Add Sample button in the top center, paint the ground points in both the lidar frames, and click on the Detect ground plane button in the bottom center.
Calibrate your LiDAR sensors using the Generalized Iterative Closest Point(GICP), Custom GICP, or Normal Distributions Transform(NDT) algorithm. To find which one to use for your LiDAR sensors, please look in the Help Center (? on the top right) section.
Click on GICP, custom GICP, or NDT to fetch respective extrinsic parameters. This may take up to 2-3 minutes for us to get more accurate results, depending on the quality of point cloud files.
Validate the results in Visualize mode and mark the calibration process as complete. These extrinsic parameters can be exported by using the ‘Export’ option.
Please note that:
The error rate displayed for each algorithm represents the fitness score.
We provide a default value for voxel size in the case of the NDT algorithm based on heuristics. The user can wish to choose another value.
Similar to voxel size as mentioned above, we provide a default value for max correspondance in the Custom GICP algorithm which can be changed by the user if required.
roll, pitch, yaw, px, py, and pz are the extrinsic parameters downloaded from the calibration tool.
roll, pitch, and yaw are in degrees
px, py, and pz are in meters.
lidar1Point is the 3d coordinates of a point in the lidar1 coordinate system.
lidar2Point is the 3d coordinates of a point in the lidar2 coordinate system.
