Single Camera Calibrator App

Camera Calibrator Overview

You can use the Camera Calibrator app to estimate camera intrinsics, extrinsics, and lens distortion parameters. You can use these camera parameters for various computer vision applications. These applications include removing the effects of lens distortion from an image, measuring planar objects, or reconstructing 3-D scenes from multiple cameras.

The suite of calibration functions used by the Camera Calibrator app provide the workflow for camera calibration. You can use these functions directly in the MATLAB^® workspace. For a list of functions, see Single and Stereo Camera Calibration.

Single Camera Calibration

Follow this workflow to calibrate your camera using the app:

1. Prepare images, camera, and calibration pattern.

2. Add images and select standard or fisheye camera model.

3. Calibrate the camera.

4. Evaluate calibration accuracy.

5. Adjust parameters to improve accuracy (if necessary).

6. Export the parameters object.

In some cases, the default values work well, and you do not need to make any improvements before exporting parameters. You can also make improvements using the camera calibration functions directly in the MATLAB workspace. For a list of functions, see Single and Stereo Camera Calibration.

Open the Camera Calibrator

• MATLAB Toolstrip: On the Apps tab, in the Image Processing and Computer Vision section, click the Camera Calibrator icon.

• MATLAB command prompt: Enter cameraCalibrator

Prepare the Pattern, Camera, and Images

To better the results, use between 10 and 20 images of the calibration pattern. The calibrator requires at least three images. Use uncompressed images or lossless compression formats such as PNG. The calibration pattern and the camera setup must satisfy a set of requirements to work with the calibrator. For greater calibration accuracy, follow these instructions for preparing the pattern, setting up the camera, and capturing the images.

Note

The Camera Calibrator app supports only checkerboard patterns. If you are using a different type of calibration pattern, you can still calibrate your camera using the estimateCameraParameters function. Using a different type of pattern requires that you supply your own code to detect the pattern points in the image.

 Prepare the Checkerboard Pattern

The Camera Calibrator app uses a checkerboard pattern. A checkerboard pattern is a convenient calibration target. If you want to use a different pattern to extract key points, you can use the camera calibration MATLAB functions directly. See Single and Stereo Camera Calibration for the list of functions.

You can print (from MATLAB) and use the checkerboard pattern provided.

Tip

Use a checkerboard that contains an even number of squares along one edge and an odd number of squares along the other edge. Using a non-square pattern contains two black corners along one side and two white corners on the opposite side. This criteria enables the app to determine the orientation of the pattern and the origin. The calibrator assigns the longer side to be the x-direction. A square pattern can produce unexpected results for camera extrinsics.

To prepare the checkerboard pattern:

1. Attach the checkerboard printout to a flat surface. Imperfections on the surface can affect the accuracy of the calibration.

2. Measure one side of the checkerboard square. You need this measurement for calibration. The size of the squares can vary depending on printer settings.

   

3. To improve the detection speed, set up the pattern with as little background clutter as possible.

 Camera Setup

To calibrate your camera, follow these rules:

• Keep the pattern in focus, but do not use autofocus.

• If you change zoom settings between images, the focal length changes.

 Capture Images

For better results, use at least 10 to 20 images of the calibration pattern. The calibrator requires at least three images. Use uncompressed images or images in lossless compression formats such as PNG. For greater calibration accuracy:

• Capture the images of the pattern at a distance roughly equal to the distance from your camera to the objects of interest. For example, if you plan to measure objects from 2 meters, keep your pattern approximately 2 meters from the camera.

• Place the checkerboard at an angle less than 45 degrees relative to the camera plane.

  

• Do not modify the images, (for example, do not crop them).

• Do not use autofocus or change the zoom settings between images.

• Capture the images of a checkerboard pattern at different orientations relative to the camera.

• Capture a variety of images of the pattern so that you have accounted for as much of the image frame as possible. Lens distortion increases radially from the center of the image and sometimes is not uniform across the image frame. To capture this lens distortion, the pattern must appear close to the edges of the captured images.

  

The Calibrator works with a range of checkerboard square sizes. As a general rule, your checkerboard should fill at least 20% of the captured image. For example, the preceding images were taken with a checkerboard square size of 108 mm, as the following montage shows:

Add Images and Select Camera Model

To begin calibration, you must add images. You can add saved images from a folder or add images directly from a camera. The calibrator analyzes the images to ensure they meet the calibrator requirements. The calibrator then detects the points on the checkerboard.

 Add Images from File

On the Calibration tab, in the File section, click Add images, and then select From file. You can add images from multiple folders by clicking Add images for each folder.

 Acquire Live Images

To begin calibration, you must add images. You can acquire live images from a webcam using the MATLAB Webcam support. To use this feature, you must install MATLAB Support Package for USB Webcams. See Install the MATLAB Support Package for USB Webcams (Image Acquisition Toolbox) for information on installing the support package. To add live images, follow these steps.

1. On the Calibration tab, in the File section, click Add Images, then select From camera.

   This action opens the Camera tab opens. If you have only one webcam connected to your system, it is selected by default and a live preview window opens. If you have multiple cameras connected and want to use one different from the default, select that specific camera in the Camera list.

2. Set properties for the camera to control the image (optional). Click the Camera Properties to open a menu of the properties for the selected camera. This list varies depending on your device.

   Use the sliders or drop-down list to change any available property settings. The Preview window updates dynamically when you change a setting. When you are done setting properties, click anywhere outside of the menu box to dismiss the properties list.

3. Enter a location for the acquired image files in the Save Location box by typing the path to the folder or using the Browse button. You must have permission to write to the folder you select.

4. Set the capture parameters.

   • To set the number of seconds between image captures, use the Capture Interval box or slider. The default is 5 seconds, the minimum is 1 second, and the maximum is 60 seconds.

   • To set the number of image captures, use the Number of images to capture box or slider. The default is 20 images, the minimum is 2 images, and the maximum is 100 images.

   In the default configuration, a total of 20 images are captured, one every 5 seconds.

5. The Preview window shows the live images streamed as RGB data. After you adjust any device properties and capture settings, use the Preview window as a guide to line up the camera to acquire the checkerboard pattern image you want to capture.

6. Click the Capture button. The number of images you set are captured and the thumbnails of the snapshots appear in the Data Browser pane. They are automatically named incrementally and are captured as .png files.

   You can optionally stop the image capture before the designated number of images are captured by clicking Stop Capture.

   When you are capturing images of a checkerboard, after the designated number of images are captured, a Checkerboard Square Size dialog box displays. Specify the size of the checkerboard square, then click OK.

   

   The detection results are then calculated and displayed. For example:

   

7. Click OK to dismiss the Detection Results dialog box.

8. When you have finished acquiring live images, click Close Image Capture to close the Camera tab.

 Analyze Images

After you add the images, the Checkerboard Square Size dialog box appears. Specify size of the checkerboard square by entering the length of one side of a square from the checkerboard pattern.

The calibrator attempts to detect a checkerboard in each of the added images, displaying an Analyzing Images progress bar window, indicating detection progress. If any of the images are rejected, the Detection Results dialog box appears, which contains diagnostic information. The results indicate how many total images were processed, and of those processed, how many were accepted, rejected, or skipped. The calibrator skips duplicate images.

To view the rejected images, click View images. The calibrator rejects duplicate images. It also rejects images where the entire checkerboard could not be detected. Possible reasons for no detection are a blurry image or an extreme angle of the pattern. Detection takes longer with larger images and with patterns that contain a large number of squares.

 View Images and Detected Points

The Data Browser pane displays a list of images with IDs. These images contain a detected pattern. To view an image, select it from the Data Browser pane.

The Image window displays the selected checkerboard image with green circles to indicate detected points. You can verify that the corners were detected correctly using the zoom controls. The yellow square indicates the (0,0) origin. The X and Y arrows indicate the checkerboard axes orientation.

Calibrate

Once you are satisfied with the accepted images, click the Calibrate button on the Calibration tab. The default calibration settings assume the minimum set of camera parameters. Start by running the calibration with the default settings. After evaluating the results, you can try to improve calibration accuracy by adjusting the settings and adding or removing images and then calibrating again. If you switch between standard and fisheye camera model, you must recalibrate.

 Select Camera Model

You can select either a standard or fisheye camera model on the Calibration tab, in the Camera Model section, select Standard or Fisheye.

You can switch camera models at any point in the session. You must calibrate again after any changes you make to the app's settings. Click Options to access settings and optimizations for either camera model.

 Standard Model Options

When the camera has severe lens distortion, the app can fail to compute the initial values for the camera intrinsics. If you have the manufacturer’s specifications for your camera and know the pixel size, focal length, or lens characteristics, you can manually set initial guesses for camera intrinsics and radial distortion. To set initial guesses, click Options > Optimization Options.

• Select the top checkbox and then enter a 3-by-3 matrix to specify initial intrinsics. If you do not specify an initial guess, the function computes the initial intrinsic matrix using linear least squares.

• Select the bottom checkbox and then enter a 2- or 3-element vector to specify the initial radial distortion. If you do not provide a value, the function uses 0 as the initial value for all the coefficients.

 Fisheye Model Options

In the Camera Model section, with Fisheye selected, click Options. Select Estimate Alignment to enable estimation of the axes alignment when the optical axis of the fisheye lens is not perpendicular to the image plane.

For details about the fisheye camera model calibration algorithm, see Fisheye Calibration Basics.

 Calibration Algorithm

For fisheye camera model calibration, see Fisheye Calibration Basics.

The standard camera model calibration algorithm assumes a pinhole camera model:

$$w\left[\begin{array}{ccc}x& y& 1\end{array}\right]=\left[\begin{array}{cccc}X& Y& Z& 1\end{array}\right]\left[\begin{array}{c}R\\ t\end{array}\right]K$$

• (X,Y,Z): world coordinates of a point.

• (x,y): image coordinates of the corresponding image point in pixels.

• w: arbitrary homogeneous coordinates scale factor.

• K: camera intrinsic matrix, defined as.

  $$\left[\begin{array}{ccc}{f}_x& 0& 0\\ s& f_y& 0\\ c_x& c_y& 1\end{array}\right]$$

  The coordinates (c_x c_y) represent the optical center (the principal point), in pixels. When the x- and y-axes are exactly perpendicular, the skew parameter, s, equals 0. The matrix elements are defined as:

  fx = F*sx

  fy = F*sy

  F is the focal length in world units, typically expressed in millimeters.

  [sx, sy] are the number of pixels per world unit in the x and y direction respectively.

  fx and fy are expressed in pixels.

• R: matrix representing the 3-D rotation of the camera .

• t: translation of the camera relative to the world coordinate system.

The camera calibration algorithm estimates the values of the intrinsic parameters, the extrinsic parameters, and the distortion coefficients. Camera calibration involves these steps:

1. Solve for the intrinsics and extrinsics in closed form, assuming that lens distortion is zero. [1]

2. Estimate all parameters simultaneously, including the distortion coefficients, using nonlinear least-squares minimization (Levenberg–Marquardt algorithm). Use the closed-form solution from the preceding step as the initial estimate of the intrinsics and extrinsics. Set the initial estimate of the distortion coefficients to zero. [1][2]

Evaluate Calibration Results

You can evaluate calibration accuracy by examining the reprojection errors, examining the camera extrinsics, or viewing the undistorted image. For best calibration results, use all three methods of evaluation.

 Examine Reprojection Errors

The reprojection errors are the distances, in pixels, between the detected and the reprojected points. The Camera Calibrator app calculates reprojection errors by projecting the checkerboard points from world coordinates, defined by the checkerboard, into image coordinates. The app then compares the reprojected points to the corresponding detected points. As a general rule, mean reprojection errors of less than one pixel are acceptable.

The Camera Calibrator app displays, in pixels, the reprojection errors as a bar graph. The graph helps you to identify which images that adversely contribute to the calibration. Select the bar graph entry and remove the image from the list of images in the Data Browser pane.

Reprojection Errors Bar Graph
The bar graph displays the mean reprojection error per image, along with the overall mean error. The bar labels correspond to the image IDs. The highlighted bars correspond to the selected images.

Select an image in one of these ways:

• Click a corresponding bar in the graph.

• Select an image from the list of images in the Data Browser pane.

• Adjust the overall mean error. Click and slide the red line up or down to select outlier images.

 Examine Extrinsic Parameter Visualization

The 3-D extrinsic parameters plot provides a camera-centric view of the patterns and a pattern-centric view of the camera. The camera-centric view is helpful if the camera was stationary when the images were captured. The pattern-centric view is helpful if the pattern was stationary. You can click the cursor and hold down the mouse button with the rotate icon to rotate the figure. Click a checkerboard (or camera) to select it. The highlighted data in the visualizations correspond to the selected image in the list. Examine the relative positions of the pattern and the camera to determine if they match what you expect. For example, a pattern that appears behind the camera indicates a calibration error.

 View Undistorted Image

To view the effects of removing lens distortion, click Show Undistorted in the View section of the Calibration tab. If the calibration was accurate, the distorted lines in the image become straight.

Checking the undistorted images is important even if the reprojection errors are low. For example, if the pattern covers only a small percentage of the image, the distortion estimation might be incorrect, even though the calibration resulted in few reprojection errors. The following image shows an example of this type of incorrect estimation for a single camera calibration.

While viewing the undistorted images, you can examine the fisheye images more closely by selecting Fisheye Scale in the View section of the Calibration tab. Use the slider in the Scale Factor window to adjust the scale of the image.

Improve Calibration

To improve the calibration, you can remove high-error images, add more images, or modify the calibrator settings.

 Add or Remove Images

Consider adding more images if:

• You have less than 10 images.

• The patterns do not cover enough of the image frame.

• The patterns do not have enough variation in orientation with respect to the camera.

Consider removing images if the images:

• The images have a high mean reprojection error.

• The images are blurry.

• The images contain a checkerboard at an angle greater than 45 degrees relative to the camera plane.

  

• The images contain incorrectly detected checkerboard points.

 Standard Model: Change the Number of Radial Distortion Coefficients

You can specify two or three radial distortion coefficients. On the Calibrations tab, in the Camera Model section, with Standard selected, click Options. Select the Radial Distortion as either 2 Coefficients or 3 Coefficients. Radial distortion occurs when light rays bend more near the edges of a lens than they do at its optical center. The smaller the lens, the greater the distortion.

The radial distortion coefficients model this type of distortion. The distorted points are denoted as (x_distorted, y_distorted):

x_distorted = x(1 + k₁*r² + k₂*r⁴ + k₃*r⁶)

y_distorted= y(1 + k₁*r² + k₂*r⁴ + k₃*r⁶)

• x, y — Undistorted pixel locations. x and y are in normalized image coordinates. Normalized image coordinates are calculated from pixel coordinates by translating to the optical center and dividing by the focal length in pixels. Thus, x and y are dimensionless.

• k₁, k₂, and k₃ — Radial distortion coefficients of the lens.

• r²: x² + y²

Typically, two coefficients are sufficient for calibration. For severe distortion, such as in wide-angle lenses, you can select 3 coefficients to include k₃.

The undistorted pixel locations are in normalized image coordinates, with the origin at the optical center. The coordinates are expressed in world units.

 Standard Model: Compute Skew

When you select the Compute Skew check box, the calibrator estimates the image axes skew. Some camera sensors contain imperfections that cause the x- and y-axes of the image to not be perpendicular. You can model this defect using a skew parameter. If you do not select the check box, the image axes are assumed to be perpendicular, which is the case for most modern cameras.

 Standard Model: Compute Tangential Distortion

Tangential distortion occurs when the lens and the image plane are not parallel. The tangential distortion coefficients model this type of distortion.

The distorted points are denoted as (x_distorted, y_distorted):

x_distorted = x + [2 * p₁ * x * y + p₂ * (r² + 2 * x²)]

y_distorted = y + [p₁ * (r² + 2 *y²) + 2 * p₂ * x * y]

• x, y — Undistorted pixel locations. x and y are in normalized image coordinates. Normalized image coordinates are calculated from pixel coordinates by translating to the optical center and dividing by the focal length in pixels. Thus, x and y are dimensionless.

• p₁ and p₂ — Tangential distortion coefficients of the lens.

• r²: x² + y²

When you select the Compute Tangential Distortion check box, the calibrator estimates the tangential distortion coefficients. Otherwise, the calibrator sets the tangential distortion coefficients to zero.

 Fisheye Model: Estimate Alignment

In the Camera Model section, with Fisheye selected, click Options. Select Estimate Alignment to enable estimation of the axes alignment when the optical axis of the fisheye lens is not perpendicular to the image plane.

Export Camera Parameters

When you are satisfied with calibration accuracy, click Export Camera Parameters. You can either save and export the camera parameters to an object by selecting Export Camera Parameters or generate the camera parameters as a MATLAB script.

 Export Camera Parameters

Select Export Camera Parameters > Export Parameters to Workspace to create a cameraParameters object in your workspace. The object contains the intrinsic and extrinsic parameters of the camera and the distortion coefficients. You can use this object for various computer vision tasks, such as image undistortion, measuring planar objects, and 3-D reconstruction. See Measuring Planar Objects with a Calibrated Camera. You can optionally export the cameraCalibrationErrors object, which contains the standard errors of estimated camera parameters, by selecting the Export estimation errors check box.

 Generate MATLAB Script

Select Export Camera Parameters > Generate MATLAB script to save your camera parameters to a MATLAB script, enabling you to reproduce the steps from your calibration session.

References

[1] Zhang, Z. “A Flexible New Technique for Camera Calibration.” IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 22, Number. 11, 2000, pp. 1330–1334.

[2] Heikkila, J. and O. Silven. “A Four-step Camera Calibration Procedure with Implicit Image Correction.” IEEE International Conference on Computer Vision and Pattern Recognition. 1997.

[3] Scaramuzza, D., A. Martinelli, and R. Siegwart. "A Toolbox for Easy Calibrating Omindirectional Cameras." Proceedings to IEEE International Conference on Intelligent Robots and Systems (IROS 2006). Beijing, China, October 7–15, 2006.

[4] Urban, S., J. Leitloff, and S. Hinz. "Improved Wide-Angle, Fisheye and Omnidirectional Camera Calibration." ISPRS Journal of Photogrammetry and Remove Sensing. Vol. 108, 2015, pp.72–79.