Feature matching in 360° waveforms for robot navigation

Author

Zhang, Zhongfei ; Weiss, Richard ; Riseman, Edward M.

Author_Institution

Dept. of Comput. & Inf. Sci., Massachusetts Univ., Amherst, MA, USA

fYear

1991

fDate

3-6 Jun 1991

Firstpage

742

Lastpage

743

Abstract

A target location is represented by compressing a 360° image from a spherical mirror into a circular waveform. Navigation tasks are specified as a sequence of homing tasks on target locations. This is accomplished by matching landmarks from the current view with the next target view. A method is provided for matching using qualitative geometric features of each of the waveforms. In addition, a geometric analysis allows one to do 3-D reasoning about the environment, which is sufficient for computing the rotation and translation between the current location and the target location. It eventually may allow acquisition of a 3-D model of the environment

Keywords

computer vision; computerised pattern recognition; mobile robots; spatial reasoning; 360° image; 3D reasoning; circular waveform; current view; feature matching; landmarks; motion analysis; qualitative geometric features; robot navigation; spherical mirror; target location; Algorithm design and analysis; Contracts; Image coding; Information science; Military computing; Mirrors; Motion analysis; Navigation; Robot kinematics; Robustness;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision and Pattern Recognition, 1991. Proceedings CVPR '91., IEEE Computer Society Conference on

Conference_Location

Maui, HI

ISSN

1063-6919

Print_ISBN

0-8186-2148-6

Type

conf

DOI

10.1109/CVPR.1991.139809

Filename

139809