goodfeature_track

Detects the strong corners to track with the Shi-Tomasi method (cv::goodFeaturesToTrack()), and publishes their positions.

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 goodfeature_track.launch.xml image:=/camera/image_raw debug_view:=false
# ROS 1
roslaunch opencv_apps goodfeature_track.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/street.mp4
# terminal 1: publish the video as image in a loop
ros2 run image_publisher image_publisher_node street.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 goodfeature_track.launch.xml image:=image max_corners:=50
# terminal 3: view the result
ros2 run rqt_image_view rqt_image_view /goodfeature_track/image

In ROS 1:

# terminal 1
rosrun image_publisher image_publisher street.mp4 _publish_rate:=10 __name:=camera
# terminal 2
roslaunch opencv_apps goodfeature_track.launch image:=camera/image_raw max_corners:=50

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
`~/corners`	opencv_apps/msg/Point2DArrayStamped
`~/image`	`sensor_msgs/msg/Image`

Parameters

Source

src/nodelet/goodfeature_track_nodelet.cpp, launch/goodfeature_track.launch.xml

Name	Type	Default (range)	Changed at run time	Description
`max_corners`	int	23 (1 - 100)	yes	Max Number of Corners
`queue_size`	int	3	no, restart the node	Specigy queue_size of input image subscribers