A Superpixel-Based Relational Auto-Encoder for Feature Extraction of Hyperspectral Images
Filter banks transferred from a pre-trained deep convolutional network exhibit significant performance in heightening the inter-class separability for hyperspectral image feature extraction, but weakening the intra-class consistency simultaneously. In this paper, we propose a new superpixel-based re...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-10-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/11/20/2454 |
id |
doaj-1e8609eaf4904d1eb15fc43d0b88fb21 |
---|---|
record_format |
Article |
spelling |
doaj-1e8609eaf4904d1eb15fc43d0b88fb212020-11-25T00:04:25ZengMDPI AGRemote Sensing2072-42922019-10-011120245410.3390/rs11202454rs11202454A Superpixel-Based Relational Auto-Encoder for Feature Extraction of Hyperspectral ImagesMiaomiao Liang0Licheng Jiao1Zhe Meng2School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, ChinaKey Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, Joint International Research Laboratory of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaKey Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, Joint International Research Laboratory of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaFilter banks transferred from a pre-trained deep convolutional network exhibit significant performance in heightening the inter-class separability for hyperspectral image feature extraction, but weakening the intra-class consistency simultaneously. In this paper, we propose a new superpixel-based relational auto-encoder for cohesive spectral−spatial feature learning. Firstly, multiscale local spatial information and global semantic features of hyperspectral images are extracted by filter banks transferred from the pre-trained VGG-16. Meanwhile, we utilize superpixel segmentation to construct the low-dimensional manifold embedded in the spectral domain. Then, representational consistency constraint among each superpixel is added in the objective function of sparse auto-encoder, which iteratively assist and supervisedly learn hidden representation of deep spatial feature with greater cohesiveness. Superpixel-based local consistency constraint in this work not only reduces the computational complexity, but builds the neighborhood relationships adaptively. The final feature extraction is accomplished by collaborative encoder of spectral−spatial feature and weighting fusion of multiscale features. A large number of experimental results demonstrate that our proposed method achieves expected results in discriminant feature extraction and has certain advantages over some existing methods, especially on extremely limited sample conditions.https://www.mdpi.com/2072-4292/11/20/2454hyperspectral images classification (hsic)convolutional neural network (cnn)relational auto-encoder (rae)transfer learningsuperpixelfeature fusion |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Miaomiao Liang Licheng Jiao Zhe Meng |
spellingShingle |
Miaomiao Liang Licheng Jiao Zhe Meng A Superpixel-Based Relational Auto-Encoder for Feature Extraction of Hyperspectral Images Remote Sensing hyperspectral images classification (hsic) convolutional neural network (cnn) relational auto-encoder (rae) transfer learning superpixel feature fusion |
author_facet |
Miaomiao Liang Licheng Jiao Zhe Meng |
author_sort |
Miaomiao Liang |
title |
A Superpixel-Based Relational Auto-Encoder for Feature Extraction of Hyperspectral Images |
title_short |
A Superpixel-Based Relational Auto-Encoder for Feature Extraction of Hyperspectral Images |
title_full |
A Superpixel-Based Relational Auto-Encoder for Feature Extraction of Hyperspectral Images |
title_fullStr |
A Superpixel-Based Relational Auto-Encoder for Feature Extraction of Hyperspectral Images |
title_full_unstemmed |
A Superpixel-Based Relational Auto-Encoder for Feature Extraction of Hyperspectral Images |
title_sort |
superpixel-based relational auto-encoder for feature extraction of hyperspectral images |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2019-10-01 |
description |
Filter banks transferred from a pre-trained deep convolutional network exhibit significant performance in heightening the inter-class separability for hyperspectral image feature extraction, but weakening the intra-class consistency simultaneously. In this paper, we propose a new superpixel-based relational auto-encoder for cohesive spectral−spatial feature learning. Firstly, multiscale local spatial information and global semantic features of hyperspectral images are extracted by filter banks transferred from the pre-trained VGG-16. Meanwhile, we utilize superpixel segmentation to construct the low-dimensional manifold embedded in the spectral domain. Then, representational consistency constraint among each superpixel is added in the objective function of sparse auto-encoder, which iteratively assist and supervisedly learn hidden representation of deep spatial feature with greater cohesiveness. Superpixel-based local consistency constraint in this work not only reduces the computational complexity, but builds the neighborhood relationships adaptively. The final feature extraction is accomplished by collaborative encoder of spectral−spatial feature and weighting fusion of multiscale features. A large number of experimental results demonstrate that our proposed method achieves expected results in discriminant feature extraction and has certain advantages over some existing methods, especially on extremely limited sample conditions. |
topic |
hyperspectral images classification (hsic) convolutional neural network (cnn) relational auto-encoder (rae) transfer learning superpixel feature fusion |
url |
https://www.mdpi.com/2072-4292/11/20/2454 |
work_keys_str_mv |
AT miaomiaoliang asuperpixelbasedrelationalautoencoderforfeatureextractionofhyperspectralimages AT lichengjiao asuperpixelbasedrelationalautoencoderforfeatureextractionofhyperspectralimages AT zhemeng asuperpixelbasedrelationalautoencoderforfeatureextractionofhyperspectralimages AT miaomiaoliang superpixelbasedrelationalautoencoderforfeatureextractionofhyperspectralimages AT lichengjiao superpixelbasedrelationalautoencoderforfeatureextractionofhyperspectralimages AT zhemeng superpixelbasedrelationalautoencoderforfeatureextractionofhyperspectralimages |
_version_ |
1725429497324371968 |