A structure-from-motion algorithm for robot vehicle guidance

Author

Wang, Han ; Brady, Michael

Author_Institution

Oxford Univ., UK

fYear

1992

fDate

29 Jun-1 Jul 1992

Firstpage

30

Lastpage

35

Abstract

Reports a new structure-from-motion algorithm designed for autonomous robot vehicle guidance. This algorithm takes input from a binocular image sequence obtained from cameras mounted on the robot, and extracts feature points using a corner detection algorithm developed at Oxford. 3D information is instantiated from feature disparities given by feature-point matching using normalised correlation and disparity gradient techniques. Vehicle motion is estimated from the tracked feature points in the image sequence using a Kalman filter. The algorithm is partly implemented on a heterogeneous parallel machine PARADOX commissioned at Oxford

Keywords

Kalman filters; computer vision; computerised navigation; feature extraction; image sequences; mobile robots; motion estimation; Kalman filter; autonomous robot vehicle guidance; binocular image sequence; computer vision; disparity gradient; feature disparities; feature extraction; feature-point matching; heterogeneous parallel machine PARADOX; mobile robots; motion estimation; navigation; normalised correlation; structure-from-motion algorithm; Algorithm design and analysis; Cameras; Data mining; Detection algorithms; Feature extraction; Image sequences; Mobile robots; Navigation; Remotely operated vehicles; Robot vision systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Vehicles '92 Symposium., Proceedings of the

Conference_Location

Detroit, MI

Print_ISBN

0-7803-0747-X

Type

conf

DOI

10.1109/IVS.1992.252229

Filename

252229