A new affine invariant feature extraction method for SAR image registration

Abstract

To cope with the problem of automatic registration of synthetic aperture radar (SAR) images, a novel affine invariant feature extraction method is proposed. The proposed method adapts the salient image disks (SIDs) extraction method to accurately localize affine invariant features in SAR images. The contributions mainly include three aspects. First, a multi-scale isotropic matched filter (MIMF) operator is modified to detect salient features. Then, a multi-resolution search strategy is adopted for eliminating unstable features, and affine invariance is achieved by an affine adaptation process. Finally, a point-set registration method based on Coherent Point Drift (CPD) is applied to the SAR image registration problem. Experiment results show that the proposed method has great improvement compared with the original method.

Hybrid Invariant Local Features for Multiple Satellite Image Matching and Registration

“…Moreover for reducing the image dimension purpose Principal Component Analysis (PCA) algorithm was utilized, later hybrid feature technique was used to improve the classification accuracy, these outcomes have been matched for respective target satellite picture. Yang, et al [20] presented an IR for using affine method and invariant feature extraction methods. The advanced technique localize the features efficiently in Synthetic Aperture Radar (SAR) using extraction technique as Salient Image Disks (SIDs).…”

Optimal texture image reconstruction method for improvement of SAR image matching

“…Beside ABM methods which are usually applied for generating DEM or producing land deformation measurements, FBM methods are also used and are mostly applied in the registration process. Among FBM algorithms, scale‐invariant feature transform (SIFT) [1, 7, 18–23] and speeded‐up robust features (SURFs) [18] are the most common methods. Some geometrical constraints, such as epipolar geometry, can be considered in improving the precision and efficiency of the process [24].…”

Image Registration Using SIFT and Canonical Correlation Analysis

“…In feature based image registration methods, feature detection and feature matching are two key steps [2]. Some sophisticated feature detection methods have been applied successfully in image registration [3,4]. However, since there are usually areas with similar intensity distribution in the reference and sensed images, these local descriptor based matching process will result in mismatches inevitably.…”