Contour-based multisensor image registration using gradient vector features

Delie Ming; Mi Wang; Pengfei Gao

doi:10.1117/12.832594

30 October 2009 Contour-based multisensor image registration using gradient vector features

Delie Ming, Mi Wang, Pengfei Gao

Author Affiliations +

Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 74954A (2009) https://doi.org/10.1117/12.832594
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China

Abstract

Multi-sensor image registration plays an important role in the automatic targets acquirement (ATA). In this paper, two kinds of new multi-sensor image registration methods based on contour feature are put forward. One is gradient vector correlation coefficient method which is based on contour characteristics of the image, the other is called relative gradient difference method which is in fact a measurement of differences between out-contour area and inner area of the target. Lots of experimental data composed of satellite images and real-time infrared images are used to verify the above two algorithms, and the results show that the two proposed methods can have good performances for both day and night infrared images.

Citation Download Citation

Delie Ming, Mi Wang, and Pengfei Gao "Contour-based multisensor image registration using gradient vector features", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 74954A (30 October 2009); https://doi.org/10.1117/12.832594

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