On the Appropriate Feature for General SAR Image Registration

Dong Li; Yunhua Zhang

doi:10.1117/12.970520

21 November 2012 On the appropriate feature for general SAR image registration

Dong Li, Yunhua Zhang

Proceedings Volume 8536, SAR Image Analysis, Modeling, and Techniques XII; 85360X (2012) https://doi.org/10.1117/12.970520
Event: SPIE Remote Sensing, 2012, Edinburgh, United Kingdom

Abstract

An investigation to the appropriate feature for SAR image registration is conducted. The commonly-used features such as tie points, Harris corner, the scale invariant feature transform (SIFT), and the speeded up robust feature (SURF) are comprehensively evaluated in terms of several criteria such as the geometrical invariance of feature, the extraction speed, the localization accuracy, the geometrical invariance of descriptor, the matching speed, the robustness to decorrelation, and the flexibility to image speckling. It is shown that SURF outperforms others. It is particularly indicated that SURF has good flexibility to image speckling because the Fast-Hessian detector of SURF has a potential relation with the refined Lee filter. It is recommended to perform SURF on the oversampled image with unaltered sampling step so as to improve the subpixel registration accuracy and speckle immunity. Thus SURF is more appropriate and competent for general SAR image registration.

Citation Download Citation

Dong Li and Yunhua Zhang "On the appropriate feature for general SAR image registration", Proc. SPIE 8536, SAR Image Analysis, Modeling, and Techniques XII, 85360X (21 November 2012); https://doi.org/10.1117/12.970520

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