hough_circles

Detects the circles with the Hough transform (cv::HoughCircles()).

opencv_apps	1.11 and later (ROS 1), 3.0.0 and later (ROS 2)
ROS	noetic, ROS One, jazzy, kilted, lyrical and later
OpenCV	any version of the distributions
Group	Features and shapes, the nodes of which publish `~/corners` (Point2DArrayStamped), `~/lines` (LineArrayStamped), `~/circles` (CircleArrayStamped) and `~/contours` (ContourArrayStamped, `~/hulls` of convex_hull), by the kind of the features

Usage

# ROS 2
ros2 launch opencv_apps hough_circles.launch.xml image:=/camera/image_raw debug_view:=false
# ROS 1
roslaunch opencv_apps hough_circles.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://ros-perception.github.io/opencv_apps/media/clips/pool_zoom.mp4
# terminal 1: publish the video as image in a loop
ros2 run image_publisher image_publisher_node pool_zoom.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 hough_circles.launch.xml image:=image accumulator_threshold:=40.0 canny_threshold:=200.0 max_circle_radius:=60 min_circle_radius:=15
# terminal 3: view the result
ros2 run rqt_image_view rqt_image_view /hough_circles/image

The radius range is tuned for the balls.

In ROS 1:

# terminal 1
rosrun image_publisher image_publisher pool_zoom.mp4 _publish_rate:=10 __name:=camera
# terminal 2
roslaunch opencv_apps hough_circles.launch image:=camera/image_raw accumulator_threshold:=40.0 canny_threshold:=200.0 max_circle_radius:=60 min_circle_radius:=15

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
`~/circles`	opencv_apps/msg/CircleArrayStamped
`~/debug_image`	`sensor_msgs/msg/Image`
`~/image`	`sensor_msgs/msg/Image`

Parameters

See also the common parameters.

Name	Type	Default (range)	Changed at run time	Description
`accumulator_threshold`	double	50.0 (1 - 200)	yes	Accumulator threshold
`canny_threshold`	double	200.0 (1 - 255)	yes	Canny threshold
`debug_image_type`	int	0 (0 - 2)	yes	Select image type for debug output, 0: Input, 1: Blur, 2: Canny
`dp`	double	2.0 (0 - 100)	yes	dp
`gaussian_blur_size`	int	9 (1 - 30)	yes	the size of gaussian blur (should be odd number)
`gaussian_sigma_x`	double	2.0 (1 - 10)	yes	sigma x of gaussian kernel
`gaussian_sigma_y`	double	2.0 (1 - 10)	yes	sigma y of gaussian kernel
`max_circle_radius`	int	0 (0 - 2000)	yes	the maximum size of the circle
`min_circle_radius`	int	0 (0 - 500)	yes	the minimum size of the circle
`min_distance_between_circles`	double	0.0 (0 - 1024)	yes	mnimum distance between the centers of the detected circles
`queue_size`	int	3	no, restart the node	Specigy queue_size of input image subscribers

Source

src/nodelet/hough_circles_nodelet.cpp, launch/hough_circles.launch.xml