3D motion tracking of a mobile robot in a natural environment

Title3D motion tracking of a mobile robot in a natural environment
Publication TypeConference Paper
Year of Publication2000
AuthorsSaeedi, P., P. Lawrence, and D. Lowe
Conference NameRobotics and Automation, 2000. Proceedings. ICRA '00. IEEE International Conference on
Pagination1682 -1687 vol.2
Keywords3D motion tracking, 3D representation, CCD cameras, computerised navigation, curve fitting, image matching, iterative method, iterative methods, Kalman filter, least squares approximations, least squares fit, mobile robot, mobile robots, motion estimation, optical tracking, robot vehicle guidance, robot vision, stereo image processing

This paper presents a vision-based tracking system suitable for autonomous robot vehicle guidance. The system includes a head with three on-board CCD cameras, which can be mounted anywhere on a mobile vehicle. By processing consecutive trinocular sets of precisely aligned and rectified images, the local 3D trajectory of the vehicle in an unstructured environment can be tracked. First, a 3D representation of stable features in the image scene is generated using a stereo algorithm. Next, motion is estimated by trading matched features over time. The motion equation with 6-DOF is then solved using an iterative least squares fit algorithm. Finally, a Kalman filter implementation is used to optimize the world representation of scene features


a place of mind, The University of British Columbia

Electrical and Computer Engineering
2332 Main Mall
Vancouver, BC Canada V6T 1Z4
Tel +1.604.822.2872
Fax +1.604.822.5949

Emergency Procedures | Accessibility | Contact UBC | © Copyright 2021 The University of British Columbia