Title
A method for stereo-vision-based tracking for robotic applications
Abstract
Vision-based tracking of an object using perspective projection inherently results in non-linear measurement equations in the Cartesian coordinates. The underlying object kinematics can be modelled by a linear system. In this paper we introduce a measurement conversion technique that analytically transforms the non-linear measurement equations obtained from a stereo-vision system into a system of linear measurement equations. We then design a robust linear filter around the converted measurement system. The state estimation error of the proposed filter is bounded and we provide a rigorous theoretical analysis of this result. The performance of the robust filter developed in this paper is demonstrated via computer simulation and via practical experimentation using a robotic manipulator as a target. The proposed filter is shown to outperform the extended Kalman filter (EKF).
Year
DOI
Venue
2010
10.1017/S0263574709005827
CDC
Keywords
Field
DocType
Kalman filters,manipulators,probability,robot vision,state estimation,stereo image processing,dynamic system,ellipsoidal set,extended Kalman filter,linear robust filter,measurement conversion techniques,probability,robotic applications,robotic manipulator,robust control,state estimation errors,stereo vision based tracking,stereo vision setting,vision sensors
Computer vision,Extended Kalman filter,Linear filter,Control theory,Stereopsis,Computer science,Perspective (graphical),Robustness (computer science),Kalman filter,Artificial intelligence,Robust control,Invariant extended Kalman filter
Journal
Volume
Issue
ISSN
28
4
0263-5747
ISBN
Citations 
PageRank 
978-1-4244-3124-3
1
0.35
References 
Authors
14
10