Point pattern registration method based on affine invariant

Xianwei Zhu; Yidan Xu; Qifeng Yu

doi:10.1117/12.835907

5 August 2009 Point pattern registration method based on affine invariant

Xianwei Zhu, Yidan Xu, Qifeng Yu

Proceedings Volume 7383, International Symposium on Photoelectronic Detection and Imaging 2009: Advances in Infrared Imaging and Applications; 73834K (2009) https://doi.org/10.1117/12.835907
Event: International Symposium on Photoelectronic Detection and Imaging 2009, 2009, Beijing, China

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.

Citation Download Citation

Xianwei Zhu, Yidan Xu, and Qifeng Yu "Point pattern registration method based on affine invariant", Proc. SPIE 7383, International Symposium on Photoelectronic Detection and Imaging 2009: Advances in Infrared Imaging and Applications, 73834K (5 August 2009); https://doi.org/10.1117/12.835907

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available