Share Email Print
cover

Proceedings Paper

Point pattern registration method based on affine invariant
Author(s): Xianwei Zhu; Yidan Xu; Qifeng Yu
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In the procedure of multi-source image registration, the invariance between image intensity is not existed. So, nearly all the methods based on the grey level face many problems. Even on visible satellite images, the problem also exists when the images were taken in different season or at different time. Point Pattern Relaxation matching as a method to match features is a promising way, because only the localization of feature point is used. As known, in a plane, any point's coordinate can linear described with other three non-collinear point' coordinate, and the linear description is invariant to affine transformation. This paper brings forward a new method to solve the problem of registration between two point patterns with affine transformation. Badly effect brought by "disturbed points" is removed through changing the way to compute the support measure. The correctness and validity of the algorithm are verified through simulated patterns and real images.

Paper Details

Date Published: 5 August 2009
PDF: 6 pages
Proc. SPIE 7383, International Symposium on Photoelectronic Detection and Imaging 2009: Advances in Infrared Imaging and Applications, 73834K (5 August 2009); doi: 10.1117/12.835907
Show Author Affiliations
Xianwei Zhu, National Univ. of Defense Technology (China)
Yidan Xu, National Univ. of Defense Technology (China)
Qifeng Yu, National Univ. of Defense Technology (China)


Published in SPIE Proceedings Vol. 7383:
International Symposium on Photoelectronic Detection and Imaging 2009: Advances in Infrared Imaging and Applications
Jeffery Puschell; Hai-mei Gong; Yi Cai; Jin Lu; Jin-dong Fei, Editor(s)

© SPIE. Terms of Use
Back to Top