A Novel Spectral–Spatial Classification Method for Hyperspectral Image at Superpixel Level
Although superpixel segmentation provides a powerful tool for hyperspectral image (HSI) classification, it is still a challenging problem to classify an HSI at superpixel level because of the characteristics of adaptive size and shape of superpixels. Furthermore, these characteristics of superpixels...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-01-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/10/2/463 |
id |
doaj-0c71d7ca91e34d2b8e859b3a44408f6e |
---|---|
record_format |
Article |
spelling |
doaj-0c71d7ca91e34d2b8e859b3a44408f6e2020-11-25T03:35:38ZengMDPI AGApplied Sciences2076-34172020-01-0110246310.3390/app10020463app10020463A Novel Spectral–Spatial Classification Method for Hyperspectral Image at Superpixel LevelFuding Xie0Cunkuan Lei1Cui Jin2Na An3School of Geography, Liaoning Normal University, Dalian 116029, ChinaSchool of Geography, Liaoning Normal University, Dalian 116029, ChinaSchool of Geography, Liaoning Normal University, Dalian 116029, ChinaDepartment of Electronic and Optical Engineering, Space Engineering University, Beijing 101416, ChinaAlthough superpixel segmentation provides a powerful tool for hyperspectral image (HSI) classification, it is still a challenging problem to classify an HSI at superpixel level because of the characteristics of adaptive size and shape of superpixels. Furthermore, these characteristics of superpixels along with the appearance of noisy pixels makes it difficult to appropriately measure the similarity between two superpixels. Under the assumption that pixels within a superpixel belong to the same class with a high probability, this paper proposes a novel spectral−spatial HSI classification method at superpixel level (SSC-SL). Firstly, a simple linear iterative clustering (SLIC) algorithm is improved by introducing a new similarity and a ranking technique. The improved SLIC, specifically designed for HSI, can straightly segment HSI with arbitrary dimensionality into superpixels, without consulting principal component analysis beforehand. In addition, a superpixel-to-superpixel similarity is newly introduced. The defined similarity is independent of the shape of superpixel, and the influence of noisy pixels on the similarity is weakened. Finally, the classification task is accomplished by labeling each unlabeled superpixel according to the nearest labeled superpixel. In the proposed superpixel-level classification scheme, each superpixel is regarded as a sample. This obviously greatly reduces the data volume to be classified. The experimental results on three real hyperspectral datasets demonstrate the superiority of the proposed spectral−spatial classification method over several comparative state-of-the-art classification approaches, in terms of classification accuracy.https://www.mdpi.com/2076-3417/10/2/463hyperspectral imageimproved slicsuperpixelsuperpixel-to-superpixel similarityspectral–spatial classification |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Fuding Xie Cunkuan Lei Cui Jin Na An |
spellingShingle |
Fuding Xie Cunkuan Lei Cui Jin Na An A Novel Spectral–Spatial Classification Method for Hyperspectral Image at Superpixel Level Applied Sciences hyperspectral image improved slic superpixel superpixel-to-superpixel similarity spectral–spatial classification |
author_facet |
Fuding Xie Cunkuan Lei Cui Jin Na An |
author_sort |
Fuding Xie |
title |
A Novel Spectral–Spatial Classification Method for Hyperspectral Image at Superpixel Level |
title_short |
A Novel Spectral–Spatial Classification Method for Hyperspectral Image at Superpixel Level |
title_full |
A Novel Spectral–Spatial Classification Method for Hyperspectral Image at Superpixel Level |
title_fullStr |
A Novel Spectral–Spatial Classification Method for Hyperspectral Image at Superpixel Level |
title_full_unstemmed |
A Novel Spectral–Spatial Classification Method for Hyperspectral Image at Superpixel Level |
title_sort |
novel spectral–spatial classification method for hyperspectral image at superpixel level |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2020-01-01 |
description |
Although superpixel segmentation provides a powerful tool for hyperspectral image (HSI) classification, it is still a challenging problem to classify an HSI at superpixel level because of the characteristics of adaptive size and shape of superpixels. Furthermore, these characteristics of superpixels along with the appearance of noisy pixels makes it difficult to appropriately measure the similarity between two superpixels. Under the assumption that pixels within a superpixel belong to the same class with a high probability, this paper proposes a novel spectral−spatial HSI classification method at superpixel level (SSC-SL). Firstly, a simple linear iterative clustering (SLIC) algorithm is improved by introducing a new similarity and a ranking technique. The improved SLIC, specifically designed for HSI, can straightly segment HSI with arbitrary dimensionality into superpixels, without consulting principal component analysis beforehand. In addition, a superpixel-to-superpixel similarity is newly introduced. The defined similarity is independent of the shape of superpixel, and the influence of noisy pixels on the similarity is weakened. Finally, the classification task is accomplished by labeling each unlabeled superpixel according to the nearest labeled superpixel. In the proposed superpixel-level classification scheme, each superpixel is regarded as a sample. This obviously greatly reduces the data volume to be classified. The experimental results on three real hyperspectral datasets demonstrate the superiority of the proposed spectral−spatial classification method over several comparative state-of-the-art classification approaches, in terms of classification accuracy. |
topic |
hyperspectral image improved slic superpixel superpixel-to-superpixel similarity spectral–spatial classification |
url |
https://www.mdpi.com/2076-3417/10/2/463 |
work_keys_str_mv |
AT fudingxie anovelspectralspatialclassificationmethodforhyperspectralimageatsuperpixellevel AT cunkuanlei anovelspectralspatialclassificationmethodforhyperspectralimageatsuperpixellevel AT cuijin anovelspectralspatialclassificationmethodforhyperspectralimageatsuperpixellevel AT naan anovelspectralspatialclassificationmethodforhyperspectralimageatsuperpixellevel AT fudingxie novelspectralspatialclassificationmethodforhyperspectralimageatsuperpixellevel AT cunkuanlei novelspectralspatialclassificationmethodforhyperspectralimageatsuperpixellevel AT cuijin novelspectralspatialclassificationmethodforhyperspectralimageatsuperpixellevel AT naan novelspectralspatialclassificationmethodforhyperspectralimageatsuperpixellevel |
_version_ |
1724553254748028928 |