A novel SAR image precise-matching method based on SIFT algorithm

Wenwen Yan; Bin Li; Dekun Yang; Jinwen Tian; Qiong Yu

doi:10.1117/12.2032027

26 October 2013 A novel SAR image precise-matching method based on SIFT algorithm

Wenwen Yan, Bin Li, Dekun Yang, Jinwen Tian, Qiong Yu

Author Affiliations +

Proceedings Volume 8921, MIPPR 2013: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications; 89210U (2013) https://doi.org/10.1117/12.2032027
Event: Eighth International Symposium on Multispectral Image Processing and Pattern Recognition, 2013, Wuhan, China

Abstract

As for SAR image, it has a relatively great geometric distortion, and contains a lot of speckle noise. So a lot of research has been done to find a good method for SAR image matching. SIFT (Scale Invariant Feature Transform) has been proved to a good algorithm for the SAR image matching. This operator can dispose of matching problem such as rotation, affine distortion and noise. In this passage, firstly, in the preprocessing process, we use BM3D to denoise the image which can perform well comparing to other denoise method. Then, regardless of traditional SIFT-RANSAC method, SIFT-TC is used to complete image matching. By using this method, the image matching is proved to have better predominance in the matching efficiency, speed and robustness.

Citation Download Citation

Wenwen Yan, Bin Li, Dekun Yang, Jinwen Tian, and Qiong Yu " A novel SAR image precise-matching method based on SIFT algorithm", Proc. SPIE 8921, MIPPR 2013: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications, 89210U (26 October 2013); https://doi.org/10.1117/12.2032027

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