Robust Registration of Multispectral Satellite Images Based on Structural and Geometrical Similarity

Abstract

Accurate registration of multispectral satellite images is a challenging task due to the significant and nonlinear radiometric differences between these data. To address this problem, this paper explores the strategy of geometrical similarity between triplets of feature points, and it is combined with the structural similarity between images in a feature-based image registration framework. The underlying principle is that the structural and geometrical similarities generally preserve across the images being registered. In this feature-based image registration framework, a set of control points are firstly detected. Then, the geometric similarity between triplets of control points is defined, followed by a ranking operation of these triplets of control points. The highly-ranked triplets are used to estimate a spatial transformation between images. Finally, initial matches obtained by a benchmark registration technique are refined by the estimated transformation. The experimental results demonstrate the great effectiveness of the proposed technique for registering multispectral satellite images.

Multi-temporal satellite image correction based on CNN features and adaptive contrast enhancement

“…Apart from that, correct registration of multispectral satellite images is a difficult task due to the substantial and nonlinear radiometric variations between these data. This is because the images being registered are captured at a variety of times, from a variety of angles, and with a variety of sensor types [2]. To overcome these constraints, image pre-processing and registration are required to increase the reliability of change detection results.…”

“…Because of the variation in sensor viewpoint and light stability during retrieving the satellite image, intensity changes occur. Image pre-processing types for satellite images [3] For geometric correction, it seeks to discover the correct spatial alignment among images of an identical scene captured under a variety of imaging circumstances [2]. As illustrated in Figure 2, the most prevalent methods for registering satellite pictures are area-based (intensity-based) and featurebased [4].…”