Visual Position Tracking using Dual Quaternions with Hand-Eye Motion Constraints

• 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.

Ämnesord

TEKNIK OCH TEKNOLOGIER  -- Elektroteknik och elektronik -- Reglerteknik (hsv//swe)

ENGINEERING AND TECHNOLOGY  -- Electrical Engineering, Electronic Engineering, Information Engineering -- Control Engineering (hsv//eng)

Nyckelord

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

Publikations- och innehållstyp

kon (ämneskategori)

ref (ämneskategori)