Refining multi-modal remote sensing image matching with repetitive feature optimization

Existing methods for matching multi-modal remote sensing images (MRSI) demonstrate considerable adaptability. However, high-precision matching for rectification remains challenging due to differing imaging mechanisms in cross-modal remote sensing images, leading to numerous non-repeated detailed fea...

Full description

Saved in:
Bibliographic Details
Main Authors: Yifan Liao, Ke Xi, Huijin Fu, Lai Wei, Shuo Li, Qiang Xiong, Qi Chen, Pengjie Tao, Tao Ke
Format: Article
Language:English
Published: Elsevier 2024-11-01
Series:International Journal of Applied Earth Observations and Geoinformation
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1569843224005429
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846166214779338752
author Yifan Liao
Ke Xi
Huijin Fu
Lai Wei
Shuo Li
Qiang Xiong
Qi Chen
Pengjie Tao
Tao Ke
author_facet Yifan Liao
Ke Xi
Huijin Fu
Lai Wei
Shuo Li
Qiang Xiong
Qi Chen
Pengjie Tao
Tao Ke
author_sort Yifan Liao
collection DOAJ
description Existing methods for matching multi-modal remote sensing images (MRSI) demonstrate considerable adaptability. However, high-precision matching for rectification remains challenging due to differing imaging mechanisms in cross-modal remote sensing images, leading to numerous non-repeated detailed feature points. Additionally, assuming linear transformations between images conflicts with the complex aberrations present in remote sensing images, limiting matching accuracy. This paper aims to elevate matching accuracy by implementing a detailed texture removal strategy that effectively isolates repeatable structural features. Subsequently, we construct a radiation-invariant similarity function within a generalized gradient framework for least-squares matching, specifically designed to mitigate nonlinear geometric and radiometric distortions across MRSIs. Comprehensive qualitative and quantitative evaluations across multiple datasets, employing substantial manual checkpoints, demonstrate that our method significantly enhances matching accuracy for image data involving multiple modal combinations and outperforms the current state-of-the-art solutions in matching accuracy. Additionally, rectification experiments employing WorldView and TanDEM-X images validate our method’s ability to achieve a matching accuracy of 1.05 pixels, thereby indicating its practical utility and generalization capacity. Access to experiment-related data and codes will be provided at https://github.com/LiaoYF001/refinement/.
format Article
id doaj-art-965bab8cda9246d0aac93c7abd2b12d8
institution Kabale University
issn 1569-8432
language English
publishDate 2024-11-01
publisher Elsevier
record_format Article
series International Journal of Applied Earth Observations and Geoinformation
spelling doaj-art-965bab8cda9246d0aac93c7abd2b12d82024-11-16T05:10:08ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322024-11-01134104186Refining multi-modal remote sensing image matching with repetitive feature optimizationYifan Liao0Ke Xi1Huijin Fu2Lai Wei3Shuo Li4Qiang Xiong5Qi Chen6Pengjie Tao7Tao Ke8School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, ChinaKey Laboratory of Smart Earth, Beijing 100094, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, ChinaSchool of Geography and Information Engineering, China University of Geosciences (Wuhan), Wuhan 430074, China; Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, 315200, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China; Key Laboratory of Smart Earth, Beijing 100094, China; Hubei Luojia Laboratory, Wuhan 430079, China; Corresponding authors at: School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China.School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China; Hubei Luojia Laboratory, Wuhan 430079, China; Corresponding authors at: School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China.Existing methods for matching multi-modal remote sensing images (MRSI) demonstrate considerable adaptability. However, high-precision matching for rectification remains challenging due to differing imaging mechanisms in cross-modal remote sensing images, leading to numerous non-repeated detailed feature points. Additionally, assuming linear transformations between images conflicts with the complex aberrations present in remote sensing images, limiting matching accuracy. This paper aims to elevate matching accuracy by implementing a detailed texture removal strategy that effectively isolates repeatable structural features. Subsequently, we construct a radiation-invariant similarity function within a generalized gradient framework for least-squares matching, specifically designed to mitigate nonlinear geometric and radiometric distortions across MRSIs. Comprehensive qualitative and quantitative evaluations across multiple datasets, employing substantial manual checkpoints, demonstrate that our method significantly enhances matching accuracy for image data involving multiple modal combinations and outperforms the current state-of-the-art solutions in matching accuracy. Additionally, rectification experiments employing WorldView and TanDEM-X images validate our method’s ability to achieve a matching accuracy of 1.05 pixels, thereby indicating its practical utility and generalization capacity. Access to experiment-related data and codes will be provided at https://github.com/LiaoYF001/refinement/.http://www.sciencedirect.com/science/article/pii/S1569843224005429Multi-modal remote sensing imagesMatching refinementRepetitive featureLeast-squares matchingNonlinear radiometric distortion
spellingShingle Yifan Liao
Ke Xi
Huijin Fu
Lai Wei
Shuo Li
Qiang Xiong
Qi Chen
Pengjie Tao
Tao Ke
Refining multi-modal remote sensing image matching with repetitive feature optimization
International Journal of Applied Earth Observations and Geoinformation
Multi-modal remote sensing images
Matching refinement
Repetitive feature
Least-squares matching
Nonlinear radiometric distortion
title Refining multi-modal remote sensing image matching with repetitive feature optimization
title_full Refining multi-modal remote sensing image matching with repetitive feature optimization
title_fullStr Refining multi-modal remote sensing image matching with repetitive feature optimization
title_full_unstemmed Refining multi-modal remote sensing image matching with repetitive feature optimization
title_short Refining multi-modal remote sensing image matching with repetitive feature optimization
title_sort refining multi modal remote sensing image matching with repetitive feature optimization
topic Multi-modal remote sensing images
Matching refinement
Repetitive feature
Least-squares matching
Nonlinear radiometric distortion
url http://www.sciencedirect.com/science/article/pii/S1569843224005429
work_keys_str_mv AT yifanliao refiningmultimodalremotesensingimagematchingwithrepetitivefeatureoptimization
AT kexi refiningmultimodalremotesensingimagematchingwithrepetitivefeatureoptimization
AT huijinfu refiningmultimodalremotesensingimagematchingwithrepetitivefeatureoptimization
AT laiwei refiningmultimodalremotesensingimagematchingwithrepetitivefeatureoptimization
AT shuoli refiningmultimodalremotesensingimagematchingwithrepetitivefeatureoptimization
AT qiangxiong refiningmultimodalremotesensingimagematchingwithrepetitivefeatureoptimization
AT qichen refiningmultimodalremotesensingimagematchingwithrepetitivefeatureoptimization
AT pengjietao refiningmultimodalremotesensingimagematchingwithrepetitivefeatureoptimization
AT taoke refiningmultimodalremotesensingimagematchingwithrepetitivefeatureoptimization