Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2000 | 10.1109/ROBOT.2000.844838 | ICRA |
Keywords | Field | DocType |
kalman filter,least square,natural environment,ccd camera,motion tracking,tracking system,layout,curve fitting,mobile robots,least squares fit,motion estimation,tracking,head,remotely operated vehicles,mobile robot,navigation,iterative method,iterative methods | Computer vision,Iterative method,Computer science,Tracking system,Control engineering,Kalman filter,Artificial intelligence,Motion estimation,Autonomous robot,Match moving,Trajectory,Mobile robot | Conference |
Volume | Issue | ISSN |
2 | 1 | 1050-4729 |
Citations | PageRank | References |
6 | 0.67 | 3 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Parvaneh Saeedi | 1 | 183 | 20.02 |
Peter D. Lawrence | 2 | 111 | 40.88 |
D. G. Lowe | 3 | 15718 | 1413.60 |