Visual Position Tracking using Dual Quaternions with Hand-Eye Motion Constraints
Author
Summary, in English
In this paper a method for contour-based rigid body tracking with simultaneouscamera calibration is developed. The method works for a singleeye-in-hand camera with unknown hand-eye transformation,viewing a stationary object with unknown position. The method usesdual quaternions to express the relationship between the camera- andend-effector screws. It is shown how using the measured motion of therobot end-effector can improve the accuracy of theestimation, even if the relative position and orientation between sensorand actuator is completely unknown.The method is evaluated in simulations on images from a real-time 3D renderingsystem. The system is shown to be able to track the pose of rigid objects and changes in intrinsic camera parameters, using only rough initial values for the parameters. The method is finally validated in anexperiment using real images from a camera mounted on an industrial robot.
Department/s
Publishing year
2003
Language
English
Pages
3491-3496
Publication/Series
Proceedings. ICRA '03.
Volume
3
Full text
- Available as PDF - 371 kB
- Download statistics
Document type
Conference paper
Publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
Topic
- Control Engineering
Keywords
- motion estimation
- industrial robots
- real-time systems
- rendering (computer graphics)
- target tracking
- Kalman filters
- computer vision
- camera calibration
- extended Kalman filter
- end effector screws
- dual quaternions
- contour based rigid body tracking
- hand-eye motion constraints
- eye-in-hand camera
- motion measurement
- industrial robot
- real-time system
- visual position tracking
Status
Published
Project
- Sensor-based Integration and Task-level Programming, 1999-2002.
- Lund Research Programme in Autonomous Robotics, 1998-2001
- RobotLab LTH
ISBN/ISSN/Other
- ISSN: 1050-4729
- ISSN: 2152-4092
- ISBN: 0-7803-7736-2