Abstract | ||
---|---|---|
In this letter, we propose an adapted anisotropic Gaussian scale-invariant feature transform (AAG-SIFT) method to find feature matches for synthetic aperture radar (SAR) image registration. First, features are detected and described in an AAG scale space. The scale space is built adaptively to local structures. Noises are blurred, but details and edges remain unaffected in this scale space. Compared with traditional SIFT-based matching methods, features extracted by AAG-SIFT are more stable and precise. Then, the dominant orientation consistency (DOC) property is analyzed and adopted to improve the matching stability. The correct matching rate is significantly increased by DOC matching. Experiments on various SAR images demonstrate the applicability of AAG-SIFT to find stable and precise feature matches for SAR registration. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/LGRS.2014.2330593 | IEEE Geosci. Remote Sensing Lett. |
Keywords | Field | DocType |
aag-sift applicability,matching stability improvement,aag-sift method,adapted anisotropic gaussian sift matching strategy,synthetic aperture radar,scale-invariant feature transform (sift),anisotropic gaussian scale space,image processing,doc property,doc matching,noise,sar registration,sar image,traditional sift-based matching method,dominant orientation consistency property,synthetic aperture radar (sar) image registration,blurred noise,synthetic aperture radar image registration feature match,stable feature match,precise feature match,adapted anisotropic gaussian scale-invariant feature transform method,transforms,image registration,correct matching rate,local structure,aag scale space | Computer vision,Scale-invariant feature transform,Anisotropy,Pattern recognition,Synthetic aperture radar,Remote sensing,Scale space,Gaussian,Artificial intelligence,Feature transform,Image registration,Mathematics | Journal |
Volume | Issue | ISSN |
12 | 1 | 1545-598X |
Citations | PageRank | References |
12 | 0.63 | 7 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Feng Wang | 1 | 19 | 3.05 |
Hongjian You | 2 | 103 | 17.44 |
Xingyu Fu | 3 | 12 | 0.63 |