Fast Spectral Clustering for Unsupervised Hyperspectral Image Classification
Hyperspectral image classification is a challenging and significant domain in the field of remote sensing with numerous applications in agriculture, environmental science, mineralogy, and surveillance. In the past years, a growing number of advanced hyperspectral remote sensing image classification...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-02-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/11/4/399 |
id |
doaj-3f9a0170459547afaecc57adf10f7ef0 |
---|---|
record_format |
Article |
spelling |
doaj-3f9a0170459547afaecc57adf10f7ef02020-11-24T20:47:25ZengMDPI AGRemote Sensing2072-42922019-02-0111439910.3390/rs11040399rs11040399Fast Spectral Clustering for Unsupervised Hyperspectral Image ClassificationYang Zhao0Yuan Yuan1Qi Wang2Key Laboratory of Spectral Imaging Technology CAS, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an 710119, ChinaSchool of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi’an 710072, ChinaSchool of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi’an 710072, ChinaHyperspectral image classification is a challenging and significant domain in the field of remote sensing with numerous applications in agriculture, environmental science, mineralogy, and surveillance. In the past years, a growing number of advanced hyperspectral remote sensing image classification techniques based on manifold learning, sparse representation and deep learning have been proposed and reported a good performance in accuracy and efficiency on state-of-the-art public datasets. However, most existing methods still face challenges in dealing with large-scale hyperspectral image datasets due to their high computational complexity. In this work, we propose an improved spectral clustering method for large-scale hyperspectral image classification without any prior information. The proposed algorithm introduces two efficient approximation techniques based on Nyström extension and anchor-based graph to construct the affinity matrix. We also propose an effective solution to solve the eigenvalue decomposition problem by multiplicative update optimization. Experiments on both the synthetic datasets and the hyperspectral image datasets were conducted to demonstrate the efficiency and effectiveness of the proposed algorithm.https://www.mdpi.com/2072-4292/11/4/399spectral clusteringhyperspectral image classificationremote sensingmanifold learningunsupervised learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yang Zhao Yuan Yuan Qi Wang |
spellingShingle |
Yang Zhao Yuan Yuan Qi Wang Fast Spectral Clustering for Unsupervised Hyperspectral Image Classification Remote Sensing spectral clustering hyperspectral image classification remote sensing manifold learning unsupervised learning |
author_facet |
Yang Zhao Yuan Yuan Qi Wang |
author_sort |
Yang Zhao |
title |
Fast Spectral Clustering for Unsupervised Hyperspectral Image Classification |
title_short |
Fast Spectral Clustering for Unsupervised Hyperspectral Image Classification |
title_full |
Fast Spectral Clustering for Unsupervised Hyperspectral Image Classification |
title_fullStr |
Fast Spectral Clustering for Unsupervised Hyperspectral Image Classification |
title_full_unstemmed |
Fast Spectral Clustering for Unsupervised Hyperspectral Image Classification |
title_sort |
fast spectral clustering for unsupervised hyperspectral image classification |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2019-02-01 |
description |
Hyperspectral image classification is a challenging and significant domain in the field of remote sensing with numerous applications in agriculture, environmental science, mineralogy, and surveillance. In the past years, a growing number of advanced hyperspectral remote sensing image classification techniques based on manifold learning, sparse representation and deep learning have been proposed and reported a good performance in accuracy and efficiency on state-of-the-art public datasets. However, most existing methods still face challenges in dealing with large-scale hyperspectral image datasets due to their high computational complexity. In this work, we propose an improved spectral clustering method for large-scale hyperspectral image classification without any prior information. The proposed algorithm introduces two efficient approximation techniques based on Nyström extension and anchor-based graph to construct the affinity matrix. We also propose an effective solution to solve the eigenvalue decomposition problem by multiplicative update optimization. Experiments on both the synthetic datasets and the hyperspectral image datasets were conducted to demonstrate the efficiency and effectiveness of the proposed algorithm. |
topic |
spectral clustering hyperspectral image classification remote sensing manifold learning unsupervised learning |
url |
https://www.mdpi.com/2072-4292/11/4/399 |
work_keys_str_mv |
AT yangzhao fastspectralclusteringforunsupervisedhyperspectralimageclassification AT yuanyuan fastspectralclusteringforunsupervisedhyperspectralimageclassification AT qiwang fastspectralclusteringforunsupervisedhyperspectralimageclassification |
_version_ |
1716810151016529920 |