An Interband Registration Method for Hyperspectral Images Based on Adaptive Iterative Clustering
In the context of the problem of image blur and nonlinear reflectance difference between bands in the registration of hyperspectral images, the conventional method has a large registration error and is even unable to complete the registration. This paper proposes a robust and efficient registration...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/13/8/1491 |
_version_ | 1797537847192846336 |
---|---|
author | Shiyong Wu Ruofei Zhong Qingyang Li Ke Qiao Qing Zhu |
author_facet | Shiyong Wu Ruofei Zhong Qingyang Li Ke Qiao Qing Zhu |
author_sort | Shiyong Wu |
collection | DOAJ |
description | In the context of the problem of image blur and nonlinear reflectance difference between bands in the registration of hyperspectral images, the conventional method has a large registration error and is even unable to complete the registration. This paper proposes a robust and efficient registration algorithm based on iterative clustering for interband registration of hyperspectral images. The algorithm starts by extracting feature points using the scale-invariant feature transform (SIFT) to achieve initial putative matching. Subsequently, feature matching is performed using four-dimensional descriptors based on the geometric, radiometric, and feature properties of the data. An efficient iterative clustering method is proposed to perform cluster analysis on the proposed descriptors and extract the correct matching points. In addition, we use an adaptive strategy to analyze the key parameters and extract values automatically during the iterative process. We designed four experiments to prove that our method solves the problem of blurred image registration and multi-modal registration of hyperspectral images. It has high robustness to multiple scenes, multiple satellites, and multiple transformations, and it is better than other similar feature matching algorithms. |
first_indexed | 2024-03-10T12:22:05Z |
format | Article |
id | doaj.art-546051320af846799a940abf9eff6e48 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-10T12:22:05Z |
publishDate | 2021-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-546051320af846799a940abf9eff6e482023-11-21T15:21:54ZengMDPI AGRemote Sensing2072-42922021-04-01138149110.3390/rs13081491An Interband Registration Method for Hyperspectral Images Based on Adaptive Iterative ClusteringShiyong Wu0Ruofei Zhong1Qingyang Li2Ke Qiao3Qing Zhu4Key Laboratory of 3D Information Acquisition and Application Ministry of Education, Capital Normal University, Beijing 100048, ChinaKey Laboratory of 3D Information Acquisition and Application Ministry of Education, Capital Normal University, Beijing 100048, ChinaKey Laboratory of 3D Information Acquisition and Application Ministry of Education, Capital Normal University, Beijing 100048, ChinaState Key Laboratory of Media Convergence Production Technology and Systems, Beijing 100048, ChinaFaculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu 610000, ChinaIn the context of the problem of image blur and nonlinear reflectance difference between bands in the registration of hyperspectral images, the conventional method has a large registration error and is even unable to complete the registration. This paper proposes a robust and efficient registration algorithm based on iterative clustering for interband registration of hyperspectral images. The algorithm starts by extracting feature points using the scale-invariant feature transform (SIFT) to achieve initial putative matching. Subsequently, feature matching is performed using four-dimensional descriptors based on the geometric, radiometric, and feature properties of the data. An efficient iterative clustering method is proposed to perform cluster analysis on the proposed descriptors and extract the correct matching points. In addition, we use an adaptive strategy to analyze the key parameters and extract values automatically during the iterative process. We designed four experiments to prove that our method solves the problem of blurred image registration and multi-modal registration of hyperspectral images. It has high robustness to multiple scenes, multiple satellites, and multiple transformations, and it is better than other similar feature matching algorithms.https://www.mdpi.com/2072-4292/13/8/1491feature matchinginterband registrationspatial clusteringhyperspectral satellitek-means |
spellingShingle | Shiyong Wu Ruofei Zhong Qingyang Li Ke Qiao Qing Zhu An Interband Registration Method for Hyperspectral Images Based on Adaptive Iterative Clustering Remote Sensing feature matching interband registration spatial clustering hyperspectral satellite k-means |
title | An Interband Registration Method for Hyperspectral Images Based on Adaptive Iterative Clustering |
title_full | An Interband Registration Method for Hyperspectral Images Based on Adaptive Iterative Clustering |
title_fullStr | An Interband Registration Method for Hyperspectral Images Based on Adaptive Iterative Clustering |
title_full_unstemmed | An Interband Registration Method for Hyperspectral Images Based on Adaptive Iterative Clustering |
title_short | An Interband Registration Method for Hyperspectral Images Based on Adaptive Iterative Clustering |
title_sort | interband registration method for hyperspectral images based on adaptive iterative clustering |
topic | feature matching interband registration spatial clustering hyperspectral satellite k-means |
url | https://www.mdpi.com/2072-4292/13/8/1491 |
work_keys_str_mv | AT shiyongwu aninterbandregistrationmethodforhyperspectralimagesbasedonadaptiveiterativeclustering AT ruofeizhong aninterbandregistrationmethodforhyperspectralimagesbasedonadaptiveiterativeclustering AT qingyangli aninterbandregistrationmethodforhyperspectralimagesbasedonadaptiveiterativeclustering AT keqiao aninterbandregistrationmethodforhyperspectralimagesbasedonadaptiveiterativeclustering AT qingzhu aninterbandregistrationmethodforhyperspectralimagesbasedonadaptiveiterativeclustering AT shiyongwu interbandregistrationmethodforhyperspectralimagesbasedonadaptiveiterativeclustering AT ruofeizhong interbandregistrationmethodforhyperspectralimagesbasedonadaptiveiterativeclustering AT qingyangli interbandregistrationmethodforhyperspectralimagesbasedonadaptiveiterativeclustering AT keqiao interbandregistrationmethodforhyperspectralimagesbasedonadaptiveiterativeclustering AT qingzhu interbandregistrationmethodforhyperspectralimagesbasedonadaptiveiterativeclustering |