Invariant features and the registration of rigid bodies

Author

Sharp, Gregory C. ; Lee, Sang W. ; Wehe, David E.

Author_Institution

Dept. of Electr. Eng. & Comput. Sci., Michigan Univ., Ann Arbor, MI, USA

Volume

2

fYear

1999

fDate

1999

Firstpage

932

Abstract

Investigates the use of Euclidean invariants in the iterative closest point registration of range images. Invariants are used in a modified distance function for the selection of point correspondences. Theoretical results show that under ideal conditions, using invariants can only improve the chance of a making correct correspondences. In addition, monotonic convergence to a local minimum is preserved. Experimental results show that using invariant features accelerates the registration and decreases the probability of being trapped in a local minimum

Keywords

convergence; distance measurement; image registration; invariance; iterative methods; probability; Euclidean invariants; invariant features; iterative closest point registration; local minimum; monotonic convergence; range images; rigid bodies; Accelerated aging; Convergence; Image registration; Iterative algorithms; Iterative closest point algorithm; Iterative methods; Layout; Mean square error methods; Object recognition; Shape;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics and Automation, 1999. Proceedings. 1999 IEEE International Conference on

Conference_Location

Detroit, MI

ISSN

1050-4729

Print_ISBN

0-7803-5180-0

Type

conf

DOI

10.1109/ROBOT.1999.772424

Filename

772424