Stack content
This stack contains the following packages
visp_bridge provides conversion tools between ROS and ViSP.
visp_camera_calibration estimates camera intrinsic paremeters.
visp_hand2eye_calibration estimates camera extrinsic paremeters.
visp_tracker wraps the model-based tracker provided by ViSP into a ROS node.
visp_auto_tracker provides a tracker with automatic initialisation and reinitialisation after tracking loss (with help of specific patterns textured on the object).
These packages depend on visp package that corresponds to the Open Source Visual Servoing Library last stable release packaged for ROS.
Installation
Installation from prebuild packages
vision_visp stack could be installed from prebuilt packages.
sudo apt-get install ros-$ROS_DISTRO-vision-visp
Installation from source
vision_visp stack could also be build and installed from source code following the steps described next.
Install ROS and create a catkin workspace
mkdir -p ~/catkin_ws/src cd ~/catkin_ws/src catkin_init_workspace cd ~/catkin_ws catkin_make
Bring the source
cd ~/catkin_ws/src
Get vision_visp stack:
git clone https://github.com/lagadic/vision_visp.git
Checkout the branch that matches your ROS distro:
cd vision_visp git checkout $ROS_DISTRO
Install dependencies
cd ~/catkin_ws sudo rosdep init rosdep update rosdep install --from-paths src --ignore-src --rosdistro $ROS_DISTRO
Build the source
cd ~/catkin_ws catkin_make -j4 -DCMAKE_BUILD_TYPE=Release
You can also build a specific package
cd ~/catkin_ws catkin_make -j4 -DCMAKE_BUILD_TYPE=Release --pkg visp_tracker
Test installation
roslaunch visp_tracker tutorial.launch roslaunch visp_auto_tracker tutorial.launch
Getting started
This stack allows you to track objects in real-time.
The next video shows how to track an object using ViSP model-based tracker. To learn how to achieve this, look at the visp_tracker tutorials.
The next video shows how to track a specific pattern textured with a QRcode. ViSP model-based tracker detects when it fails and recover the object position thanks to QRcode detection. To learn how to achieve this, look at the visp_auto_tracker package.
Report a bug
Use GitHub to report a bug or submit an enhancement.
References
E. Marchand, F. Spindler, F. Chaumette. ViSP for visual servoing: a generic software platform with a wide class of robot control skills. IEEE Robotics and Automation Magazine, Special Issue on "Software Packages for Vision-Based Control of Motion", P. Oh, D. Burschka (Eds.), 12(4):40-52, December 2005. [ PDF ]