aruco_detection

Detects the ArUco markers (cv::aruco), and their poses with the camera info and the size of the markers.

opencv_apps	3.0.0 and later
ROS	ROS One, jazzy, kilted, lyrical and later
OpenCV	OpenCV 4.7 or later, or the aruco module of opencv_contrib
Group	Codes and markers, the nodes of which publish `~/detections` (DetectionArrayStamped), with the decoded data and the corners

Usage

# ROS 2
ros2 launch opencv_apps aruco_detection.launch.xml image:=/camera/image_raw debug_view:=false
# ROS 1
roslaunch opencv_apps aruco_detection.launch image:=/camera/image_raw debug_view:=false

Try it with the demo video

Download the input video of the demo above, publish it as image with image_publisher, and run the node on it, in the terminals:

wget https://raw.githubusercontent.com/ros-perception/opencv_apps/indigo/test/codes.mp4
# terminal 1: publish the video as image in a loop
ros2 run image_publisher image_publisher_node codes.mp4 --ros-args -p publish_rate:=10.0 -r image_raw:=image
# terminal 2: run the node with the parameters of the demo
ros2 launch opencv_apps aruco_detection.launch.xml image:=image marker_length:=0.05 use_camera_info:=true
# terminal 3: view the result
ros2 run rqt_image_view rqt_image_view /aruco_detection/image

In ROS 1:

# terminal 1
rosrun image_publisher image_publisher codes.mp4 _publish_rate:=10 __name:=camera
# terminal 2
roslaunch opencv_apps aruco_detection.launch image:=camera/image_raw marker_length:=0.05 use_camera_info:=true

See Credits of the demo videos for the license of the video.

Subscribed topics

Topic	Type
`image`	`sensor_msgs/msg/Image`

Published topics

Topic	Type
`~/detections`	opencv_apps/msg/DetectionArrayStamped
`~/image`	`sensor_msgs/msg/Image`
`~/poses`	`geometry_msgs/msg/PoseArray`

Parameters

See also the common parameters.

Name	Type	Default (range)	Changed at run time	Description
`dictionary`	string	“DICT_4X4_50”	yes	Predefined dictionary of the markers, e.g. DICT_4X4_50, DICT_6X6_250, DICT_ARUCO_ORIGINAL, DICT_APRILTAG_36h11
`marker_length`	double	0.0 (0 - 100)	yes	Length of the side of the markers in meters, to publish their poses with the camera info, 0 not to publish
`queue_size`	int	3	no, restart the node	Specify queue_size of input image subscribers
`rectified`	bool	false	yes	The image is rectified (e.g. image_rect of image_proc), then the poses are estimated with the intrinsics of P of the camera info without distortion, instead of K and D
`use_camera_info`	bool	false	yes	Indicates that the camera_info topic should be subscribed to, to get the camera model for the poses of the markers. Otherwise the poses are not published.

Source

src/nodelet/aruco_detection_nodelet.cpp, launch/aruco_detection.launch.xml