Vehicle-Camera Calibration

  1. Calibration list page, where the users can load existing dataset or create a new one.

2. New calibration selection modal.

3. Get started page of vehicle-camera setup.

4. Calibration settings modal.

  • Dataset name can be added here.

  • The user has to select the shape of the vehicle. Either rectangle or isosceles trapezoid.

5. For rectangle-shaped vehicle, users can input the measured values

6. For isosceles trapezoid-shaped vehicles, users can input the following measured values.

7. Enter the intrinsic parameters for the mounted camera.

  • Intrinsic parameters for the camera are to be added here. Users have three options.

  • Users can use the intrinsic calibration tool and calibrate the results. Save them to profile and then load them here.

  • Or users can also load the JSON file.

8. Add images related to the mounted camera. One for the left view and the other for the right view.

9. Configure the checkerboard pattern and the square size at the top right corner.

10. Detect the checkerboard corners for both the mounted camera images.

11. Enter the intrinsic parameters for the external camera.

  • Intrinsic parameters for the camera are to be added here. Users have three options.

  • Users can use the intrinsic calibration tool and calibrate the results. Save them to profile and then load them here.

  • Or users can also load the JSON file.

12. Upload images taken from the external camera for left view.

13. Detect the checkerboard corners for both the left view external camera images.

14. Mark both the front wheel and rear wheel points in all the images.

  • Wheel points can be auto-detected by clicking on the detect corners button.

  • Now select the wheel points and tag them as either the front wheel or the rear wheel.

15. Upload images taken from the external camera for the right view.

16. Detect the checkerboard corners for both the right view external camera images.

17. Mark both the front wheel and rear wheel points in all the images.

  • Wheel points can be auto-detected by clicking on the detect corners button.

  • Now select the wheel points and tag them as either the front wheel or the rear wheel.

18. Click on the run calibration button. This takes all the input configuration and the file data to get the calibrated results.

19. Top right bar shows the extrinsic parameters.

20. Visualize button shows the 3d representation of the car and its wheels. Along with the camera center and its frustum.

21. Export option helps the user to export the calibrated data for the mounted camera with the vehicle.

22. Users can check the error stats and add more images to see the change in error stats.

  • Reprojection Error: It’s value is the mean delta of the marked wheel point and the reprojection of the calibrated wheel position. It's measured in pixels.

  • Ray distance Error: It’s value is the mean delta of the distance between the ray produced from marked wheel points and the calibrated wheel position in 3d space. It's measured in meters.

Save calibration dataset:

We have a save option on the top right corner. A user can click on the Save button to save the calibration dataset at any time during the calibration process.

Checkboard Inner Corner Detection:

If the checkerboard corners are not auto-detected. Users can select four boundary points in order (top-left, top-right , bottom-left, bottom-right). And then click on retry corner detection, to get the remaining inner corners of the checkerboard.

Extrinsic Calibration Output:

  • roll, pitch, yaw, px, py, pz are the extrinsic parameters downloaded from the calibration tool.

  • vehiclePoint3D is the 3d coordinates of a point in the vehicle coordinate system.

  • imagePoint3D is the 3d coordinates of a point in the camera coordinate system.