Coarse-to-Fine Image Registration for Multi-Temporal High Resolution Remote Sensing Based on a Low-Rank Constraint

Abstract

For multi-temporal high resolution remote sensing images, the image registration is important but difficult due to the high resolution and low-stability land-cover. Especially, the changing of land-cover, solar altitude angle, radiation intensity, and terrain fluctuation distortion in the overlapping areas can represent different image characteristics. These time-varying properties cause traditional registration methods with known reference information to fault. Therefore, in this paper we propose a comprehensive coarse-to-fine registration (CCFR) algorithm. First, we design a low-rank constraint-based batch reference extraction (LRC-BRE) method. Under the low-rank constraint, the stable features with highly spatial co-occurrence can be reconstructed via matrix decomposition, and are set as reference images to batch registration. Second, we improve the general feature registration with block feature matching and local linear transformation (BFM-LLT) operators including match outlier filtering (MOF) on regional mutual information and dual-weighted block fitting (DWBF). Finally, based on combining LRC-BRE and BFM-LLT, CCFR is integrated. Experimental results show that the proposed method has a good batch alignment effect, especially in the registration of large difference image pairs. The proposed CCFR achieves a significant performance improvement over many state-of-the-art registration algorithms.

FPGA Implementation of Image Registration Using Accelerated CNN

“…MAX ı is the maximum valid value for the image pixels. SSIM, as illustrated in Equation (10), measures the similarity of images in three parts: luminance (l), contrast (c), and structure (s). The variables α, β, and γ in the function represent the effect ratios of the comparisons.…”

“…IR is the process of combining images side-by-side or on top of each other by determining the transformation matrix between two or more images taken from different angles, times, or modalities for the same region of interest [ 6 ]. The IR process is performed using classical and deep learning (DL)-based methods [ 7 , 8 , 9 , 10 ]. DL is widely recognized as a state-of-the-art technique for a broad range of applications, particularly in computer vision [ 11 ], natural language processing [ 12 ], bioinformatics [ 13 ], robotics and control [ 14 ], biomedical signal processing [ 15 ], and IR processes [ 16 , 17 , 18 ].…”

A Hybrid approach for Image Acquisition Methods based on Feature Based Image Registration (FBIR)

“…A hybrid feature extraction technique is proposed in [28], for medical images. A robust "coarse-to-fine registration (CCFR)" image registration algorithm is proposed [29]. A feature matching algorithm using the combination of FAST feature points and SURF descriptors is proposed in [30].…”