The aruco_detector_osv (aruco_detector_opencv) uses the #include <opencv2/aruco.hpp> library instead of using #include <aruco/aruco.h> (ros-kinetic-aruco). This package was tested on ubuntu 16.04, ROS Kinetic with a Logitech C920 camera.
With this package you are able to:
- detect position and orientation of an aruco marker relatively to the camera. The corresponding tf is published.
- a certainty parameter of how robust the arcuco marker is detected.
- a result image with the detected markers highlighted is published.
Author: Markus Lamprecht
Maintainer: Markus Lamprecht, [email protected]
Video:
This software is built on the Robotic Operating System (ROS), which needs to be installed first. Additionally, this package depends on following software:
- [alfons_msgs]
- [cv_bridge]
- [opencv]
- [tf2_ros]
In order to install this package, clone the latest version from this repository into your catkin workspace and compile the package using catkin_tools
cd ~/Desktop
source /opt/ros/kinetic/setup.bash
mkdir -p catkin_ws/src
cd catkin_ws/src/
git clone [email protected]:CesMak/aruco_detector_ocv.git (takes some time due to included bag to test this package)
cd ..
catkin init -w .
catkin build
source devel/setup.bash
roscd roscd aruco_detector_ocv/data/
rosbag decompress 640x480_logitech_aruco3_compressed.orig.bag
roslaunch aruco_detector_ocv detector.launch
Please calibrate your camera first using: camera_calibration.
See all adjustments in the aruco_detector_osv/launch/detector.launch
There are many opencv parameters that can be adjusted internally to reduce the effect of lightening conditions. See opencv_tutorial
In order to adjust camera options use scripts/marker_filter.py
roslaunch aruco_detector_ocv detector.launch
If you want to use this package please contact: me.
If you get (when using the camera)
[ERROR] [1551630633.628039127]: Cannot identify '/dev/video0': 2, No such file or directory
do
sudo modprobe uvcvideo
- Reduce effect of motion blure if the camera is turned