Paper Info
Title
Feature Matching for Remote-Sensing Image Registration via Neighborhood Topological and Affine Consistency
Abstract
Feature matching is a key method of feature-based image registration, which refers to establishing reliable correspondence between feature points extracted from two images. In order to eliminate false matchings from the initial matchings, we propose a simple and efficient method. The key principle of our method is to maintain the topological and affine transformation consistency among the neighborhood matches. We formulate this problem as a mathematical model and derive a closed solution with linear time and space complexity. More specifically, our method can remove mismatches from thousands of hypothetical correspondences within a few milliseconds. We conduct qualitative and quantitative experiments on our method on different types of remote-sensing datasets. The experimental results show that our method is general, and it can deal with all kinds of remote-sensing image pairs, whether rigid or non-rigid image deformation or image pairs with various shadow, projection distortion, noise, and geometric distortion. Furthermore, it is two orders of magnitude faster and more accurate than state-of-the-art methods and can be used for real-time applications.
Year
DOI
Venue
2022
10.3390/rs14112606
REMOTE SENSING
Keywords
DocType
Volume
feature matching, topological and affine transformation consistency (TAT), registration, remote sensing
Journal
14
Issue
ISSN
Citations 
11
2072-4292
0
PageRank 
References 
Authors
0.34
40
7
Name
Order
Citations
PageRank
Xi Gong100.34
Feng Yao200.34
Jiayi Ma3130265.86
Junjun Jiang4113874.49
Tao Lu514926.63
Yanduo Zhang600.34
Huabing Zhou721615.18