26 October 2013 A novel SAR image precise-matching method based on SIFT algorithm
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.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Wenwen Yan, Bin Li, Dekun Yang, Jinwen Tian, 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); doi: 10.1117/12.2032027; https://doi.org/10.1117/12.2032027
PROCEEDINGS
7 PAGES


SHARE
Back to Top