Lidar Radar 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 user's access to these datasets on this page.
Click on ‘New Calibration’ to create a new calibration dataset.
Upon clicking the ‘New Calibration’ button, the user can make a selection from the different calibrations. Select ‘Lidar Radar’ Calibration’ to create a new lidar-radar calibration dataset.
The page lists the important instructions and requirements that you need to follow in order to complete the calibration process.
Start the app by clicking on the “Get Started” button
You should fill all the details like board dimensions, edge length of trihedral corner reflector etc on this page
Calibration Name: This is the name you give to the present calibration to identify it when you visit it again.
Sensor name: provide the names of both radar and lidar sensors that you can refer to identify the camera when stats are shown.
Length: This is the length of the board which you are using in the calibration.
Breadth: This is the breadth of the board you are using in the calibration.
Thickness: This is the thickness of the board you are using in the calibration.
Edge Length: This is the edge length of the trihedral corner reflector which is used to collect radar data. ( Look at the preview to know exactly which is considered as edge length)
Once you have all the entries(i.e sensors, targets, and trihedral corner reflector), the top right button “Continue to Calibrate” is enabled. Click on that button to proceed.
Add the lidar point cloud files(.pcd files)
Once you upload all the lidar files, a button at the right bottom “Continue” is enabled. Click it to proceed.
On this page, you need to set the position of the reflector corner from the radar(in meters) for each lidar file which was uploaded in the earlier step.
Once radar data is entered for the corresponding lidar files, “Continue” button will be enabled in the bottom right corner. Please click it to proceed.
On this page you can see the point cloud in the middle of the screen, now you need to manually mark 4 corner points of the board in this point cloud with the order mentioned on the right side wooden board.
Please follow the ordering displayed on the right-panel wooden board, wrong ordering will lead to inaccurate results.
Such markings need to be done for all the uploaded point clouds.
Once marking is done in all the point cloud files, then the “Detect Board Points” button will be enabled at the bottom of the page. Click that button, which will detect the edge points of the target.
After this Continue button will be enabled at the right bottom of the pa, Click it to proceed.
Click the Run Calibration button at the bottom of the page to run your calibration.
After the Run Calibration algorithm is completed in the backend, it gives the extrinsic parameters and error stats on the right-side panel of the page.
Once Extrinsics are generated, you can visualize the results by clicking on the “Visualize” button to the top right.
You may also import a json file with all reflector positions by clicking on. Here is an example file:
