No version for distro crystal. Known supported distros are highlighted in the buttons above.

No version for distro bouncy. Known supported distros are highlighted in the buttons above.

visp_auto_tracker package from vision_visp repo

vision_visp visp_auto_tracker visp_bridge visp_camera_calibration visp_hand2eye_calibration visp_tracker

Package Summary

Tags	No category tags.
Version	0.9.3
License	GPLv2
Build type	CATKIN
Use	RECOMMENDED

Repository Summary

Checkout URI	https://github.com/lagadic/vision_visp.git
VCS Type	git
VCS Version	melodic-devel
Last Updated	2019-05-24
Dev Status	MAINTAINED
Released	UNRELEASED

Package Description

Online automated pattern-based object tracker relying on visual servoing. visp_auto_tracker wraps model-based trackers provided by ViSP visual servoing library into a ROS package. The tracked object should have a QRcode of Flash code pattern. Based on the pattern, the object is automaticaly detected. The detection allows then to initialise the model-based trackers. When lost of tracking achieves a new detection is performed that will be used to re-initialize the tracker. This computer vision algorithm computes the pose (i.e. position and orientation) of an object in an image. It is fast enough to allow object online tracking using a camera.

Additional Links

Website

Maintainers

Fabien Spindler

Authors

Filip Novotny

visp_auto_tracker/README.md

visp_auto_tracker

visp_auto_tracker wraps model-based trackers provided by ViSP visual servoing library into a ROS package. The tracked object should have a QRcode of Flash code pattern. Based on the pattern, the object is automaticaly detected. The detection allows then to initialise the model-based trackers. When lost of tracking achieves a new detection is performed that will be used to re-initialize the tracker.

This computer vision algorithm computes the pose (i.e. position and orientation) of an object in an image. It is fast enough to allow object online tracking using a camera.

This package is composed of one node called 'visp_auto_tracker'. The node tries first to detect the QRcode or the Flash code associated to the object. Once the detection is performed, the node tracks the object. When a lost of tracking occurs the node tries to detect once again the object and then restart a tracking.

The viewer comming with visp_tracker package can be used to monitor the tracking result.

Setup

This package contains submodules. It can be compiled like any other ROS package using catkin_make.

Prerequisities

visp_auto_tracker depends on visp_bridge and visp_tracker packages available from https://github.com/lagadic/vision_visp (indigo-devel branches).

visp_auto_tracker depends also on libdmtx-dev and libzbar-dev system dependencies. To install them run:

$ sudo apt-get install libdmtx-dev libzbar-dev

How to get and build visp_tracker

Supposed you have a catkin work space just run:

$ cd ~/catkin_ws/src 
$ git clone -b indigo-devel https://github.com/lagadic/vision_visp.git
$ cd ..
$ catkin_make --pkg visp_auto_tracker

Documentation

The documentation is available on the project ROS homepage.

For more information, refer to the ROS tutorial.

CHANGELOG

Could not convert RST to MD: No such file or directory - pandoc

Wiki Tutorials

See ROS Wiki Tutorials for more details.

Source Tutorials

Not currently indexed.

Package Dependencies

Deps		Name
	2	geometry_msgs
	3	message_filters
	2	resource_retriever
	2	roscpp
	2	sensor_msgs
	2	std_msgs
	0	visp
	1	visp_bridge
	1	visp_tracker
	1	catkin

System Dependencies

Name
libdmtx-dev
zbar

Dependant Packages

Name	Repo	Deps
vision_visp	github-lagadic-vision_visp

Launch files

launch/tracklive_usb.launch
- -*- xml -*- This tutorial relies on a live video sequence acquired with an usb camera in front of a QR code planar target. The model corresponding to this target is given into the models directory of this package. Camera parameters are set as rosparam parameters. They need to be changed to be the one of your camera. See http://www.ros.org/wiki/visp_auto_tracker for more information.
launch/tutorial.launch
- -*- xml -*- This tutorial relies on a recorded video sequence where the camera is fixed in front of QR code planar target. The model corresponding to this target is given into the models directory of this package. See http://www.ros.org/wiki/visp_auto_tracker for more information.
launch/tracklive_firewire.launch
- -*- xml -*- This tutorial relies on a live video sequence acquired with a firewire camera in front of a QR code planar target. The model corresponding to this target is given into the models directory of this package. Camera parameters are read from models/calibration.ini file. They need to be the one of your camera. Here we use the viewer coming with visp_tracker package to display the pose estimation results. See http://www.ros.org/wiki/visp_auto_tracker for more information.

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged `visp_auto_tracker` at answers.ros.org

API Docs Browse Code Wiki