This article comes from: Nav2 Chinese Network Tutorial
For complete Nav2 documentation and tutorials please visit: http://nav2.fishros.com
Nav2 communication group: 139707339
WeChat public account: Yuxiang ROS
Camera calibration
Overview
This tutorial demonstrates how to obtain the parameters of a monocular camera through calibration.
Require
1- Use the package manager of the operating system to install the software packages required for camera calibration
sudo apt install ros-<ros2-distro>-camera-calibration-parsers
sudo apt install ros-<ros2-distro>-camera-info-manager
sudo apt install ros-<ros2-distro>-launch-testing-ament-cmake
2- The Image Pipeline package needs to be built from source in your workspace with the following command:
git clone – b <ros2-distro> [email protected]:ros-perception/image_pipeline.git
Also, make sure you have the following:
A large chessboard of known size. This tutorial uses a 200mm x 200mm square chessboard. ** Since the camera calibration uses the inner vertices of the checkerboard, an "8x10" checkerboard is required. So using the internal vertex parameter is exactly "7x9" as shown in the example below. ** Can be downloaded from here .
A well-lit 5m x 5m area to clear obstacles and check the checkerboard pattern
A monocular camera that can publish images on ROS
Tutorial Steps
1- Start a terminal in the GUI
2- Launch the ROS driver for the camera being used.
3- Make sure the camera is publishing images via ROS. This can be tested by running:
ros2 topic list
4- This will show all your posted threads, make sure there is an image thread inside /camera/image_raw. Make sure the image_raw topic is a real topic and is posting images, you need to check how often the topic is posted:
ros2 topic hz /camera/image_raw
5- Start the camera calibration node
ros2 run camera_calibration cameracalibrator --size 7x9 --square 0.20 image:=/my_camera/image_raw camera:=/my_camera
Camera Name:
-c, --camera_name
name of the camera to appear in the calibration file
Chessboard Options:
You must specify one or more chessboards as pairs of --size and--square options.
-p PATTERN, --pattern=PATTERN
calibration pattern to detect - 'chessboard','circles', 'acircles','charuco'
-s SIZE, --size=SIZE
chessboard size as NxM, counting interior corners (e.g. a standard chessboard is 7x7)
-q SQUARE, --square=SQUARE
chessboard square size in meters
ROS Communication Options:
--approximate=APPROXIMATE
allow specified slop (in seconds) when pairing images from unsynchronized stereo cameras
--no-service-check
disable check for set_camera_info services at startup
Calibration Optimizer Options:
--fix-principal-point
fix the principal point at the image center
--fix-aspect-ratio
enforce focal lengths (fx, fy) are equal
--zero-tangent-dist
set tangential distortion coefficients (p1, p2) to
zero
-k NUM_COEFFS, --k-coefficients=NUM_COEFFS
number of radial distortion coefficients to use (up to
6, default 2)
--disable_calib_cb_fast_check
uses the CALIB_CB_FAST_CHECK flag for findChessboardCorners
This will open a calibration window which highlight the checkerboard.
6 In order to get better calibration results, it is necessary to continuously move the checkerboard within the camera's field of view:
Make the checkerboard reach the left, right, top, and bottom of the camera's field of view
◦ X-left/right orientation in camera field of view
Y - up and down in the camera's field of view
◦ Size - approach/away from the camera and tilt relative to the camera
checkerboard filling the whole field of view
Skew the checkerboard to the left, right, up, and down (Skew)
7 As the checkerboard moves continuously, the length of the 4 horizontal bars on the sidebar of the calibration window will continue to grow. The "CALIBRATE" button will illuminate when all 4 bars are green and there is enough data available for calibration. Click to view the results. Calibration takes about a minute.
8- When the calibration is complete, the save and submit buttons are illuminated. The calibration results can also be seen in the terminal.
9- The result can be viewed after pressing the save button. Data is saved to "/tmp/calibrationdata.tar.gz"
10- To use the camera calibration result file, execute the following command to unzip the file (calibration.tar.gz)
tar -xvf calibration.tar.gz
11- In the calibration results folder, you can see all the images used for the calibration along with the "ost.yaml" and "ost.txt" files. You can use a yaml file that contains calibration parameters for the camera driver.