Affine trackability for landmark selection in natural environment

Author

Vandapel, Nicolas ; Chatila, Raja

Author_Institution

Lab. d´´Autom. et d´´Anal. des Syst., CNRS, Toulouse, France

Volume

1

fYear

2002

fDate

2002

Firstpage

37

Abstract

In this article we propose a method for landmark selection and tracking in natural environments. Landmarks are not specific 3D objects, but an image area that can be tracked over a sequence of monocular images. No assumption is made a priori on landmarks. The algorithm selects areas in a monocular black and white image sequence that have an affine trackability property. A measure of affine trackability is proposed for selection and affine tracking. Initial experimental results are presented.

Keywords

computerised navigation; feature extraction; image sequences; mobile robots; parameter estimation; robot vision; tracking; 3D landmarks; affine trackability; affine transformation; homography; image sequence; landmark selection; landmark-based localization; mobile robot; natural environment; navigation; parameter estimation; tracking; Cameras; Data mining; Global Positioning System; Image reconstruction; Mobile robots; Navigation; Robot kinematics; Simultaneous localization and mapping; Stereo image processing; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Robots and Systems, 2002. IEEE/RSJ International Conference on

Print_ISBN

0-7803-7398-7

Type

conf

DOI

10.1109/IRDS.2002.1041359

Filename

1041359