Please submit manuscripts in either of the following two submission systems

    ScholarOne Manuscripts

  • ScholarOne
  • 勤云稿件系统

  • 登录

Search by Issue

  • 2021 Vol.28
  • 2020 Vol.27
  • 2019 Vol.26
  • 2018 Vol.25
  • 2017 Vol.24
  • 2016 vol.23
  • 2015 vol.22
  • 2014 vol.21
  • 2013 vol.20
  • 2012 vol.19
  • 2011 vol.18
  • 2010 vol.17
  • 2009 vol.16
  • No.1
  • No.2

Supervised by Ministry of Industry and Information Technology of The People's Republic of China Sponsored by Harbin Institute of Technology Editor-in-chief Yu Zhou ISSNISSN 1005-9113 CNCN 23-1378/T

期刊网站二维码
微信公众号二维码
Related citation:Peiyuan Jia,Miao Zhang,Yi Shen.Robust Deep 3D Convolutional Autoencoder for Hyperspectral Unmixing with Hypergraph Learning[J].Journal of Harbin Institute Of Technology(New Series),2021,28(5):1-8.DOI:10.11916/j.issn.1005-9113.20059.
【Print】   【HTML】   【PDF download】   View/Add Comment  Download reader   Close
←Previous|Next→ Back Issue    Advanced Search
This paper has been: browsed 100times   downloaded 34times 本文二维码信息
码上扫一扫!
Shared by: Wechat More
Robust Deep 3D Convolutional Autoencoder for Hyperspectral Unmixing with Hypergraph Learning
Author NameAffiliation
Peiyuan Jia Department of Control Science and Engineering, Harbin Institute of Technology, Harbin 150001, China 
Miao Zhang Department of Control Science and Engineering, Harbin Institute of Technology, Harbin 150001, China 
Yi Shen Department of Control Science and Engineering, Harbin Institute of Technology, Harbin 150001, China 
Abstract:
Hyperspectral unmixing aims to acquire pure spectra of distinct substances (endmembers) and fractional abundances from highly mixed pixels. In this paper, a deep unmixing network framework is designed to deal with the noise disturbance. It contains two parts: a three-dimensional convolutional autoencoder (denoising 3D CAE) which recovers data from noised input, and a restrictive non-negative sparse autoencoder (NNSAE) which incorporates a hypergraph regularizer as well as a l2,1-norm sparsity constraint to improve the unmixing performance. The deep denoising 3D CAE network was constructed for noisy data retrieval, and had strong capacity of extracting the principle and robust local features in spatial and spectral domains efficiently by training with corrupted data. Furthermore, a part-based nonnegative sparse autoencoder with l2,1-norm penalty was concatenated, and a hypergraph regularizer was designed elaborately to represent similarity of neighboring pixels in spatial dimensions. Comparative experiments were conducted on synthetic and real-world data, which both demonstrate the effectiveness and robustness of the proposed network.
Key words:  deep learning  unsupervised unmixing  convolutional autoencoder  hypergraph  hyperspectral data
DOI:10.11916/j.issn.1005-9113.20059
CLC NUMBER:TP753
Fund:
Descriptions in Chinese:
  

基于超图学习的鲁棒深度3D卷积自动编码器高光谱解混方法

贾培源,张淼,沈毅

(哈尔滨工业大学 控制科学与工程系,哈尔滨 150001)

创新点说明:

1) 提出一种深度解混网络模型R3dCAE。深度学习能够通过深层非线性映射,实现高阶特征提取与数据变换,在解混领域展现出了巨大的应用价值。为去除影像内高噪声对解混带来的不利影响,通过去噪自编码网络与非负自编码网络级联,实现数据恢复与高精度解混工作。

2) 针对高光谱三维体数据特殊结构,将去噪自编码网络和三维卷积网络相结合,通过构建三维卷积层/反卷积层与三维池化/反池化层,深层解混模型R3dCAE能够无监督学习鲁棒的空谱联合特征信息;采用一系列噪声抽样的影像数据对网络参数进行训练优化,该模型能够对含噪数据输入实现高精度数据重建。

3) R3dCAE模型采用结合超图约束的自编码网络同步提取端元与丰度信息。通过邻域光谱相似性度量,超图结构能够描述物质分布的低维流形关系,从而表示物质分布的空间一致性信息;同时引入l2,1范数稀疏约束,在网络的迭代优化中实现精确的端元提取与丰度反演任务。

研究目的:

针对现有高光谱解混算法处理光谱混合数据,端元提取受噪声影响大,鲁棒性差,并且获得的丰度无法提现物质空间分布相关性信息,解混精度受限,探索一种基于深度学习的高光谱解混网络架构,通过网络的深层学习与优化,实现端元与丰度信息的高精度求取任务。

研究方法:

所提出深度解混框架R3dCAE由三维去噪卷积自编码网络与结合超图学习的非负稀疏自编码网络级联构成。三维去噪卷积自编码网络通过在编码层搭建卷积层与池化层,在解码层搭建反卷积层与反池化层,从而实现无监督提取光谱维与空间维的联合特征信息,通过学习含噪数据获得去噪影像光谱信息;非负稀疏自编码网络以三层网络映射的方式实现端元与丰度信息的联合优化,引入超图约束和稀疏约束,以更好实现端元特征提取和丰度信息求取。

研究结果:

采用仿真数据集对所提出解混框架和目前先进解混算法,包括MVSA, RCo-NMF, MVC-NMF, SGSNMF, 与uDAs等进行比较,对比各算法端元提取与丰度反演结果与参考端元和丰度信息的误差,结果显示R3dCAE在不同信噪比下都具有优异的性能表现;针对实际高光谱遥感数据集,对比各算法获得的端元信号误差,从而展示了所提出解混网络的有效性与鲁棒性。

结论:

本文针对高光谱图像数据光谱混合问题,提出一种新型的结合空间信息的高光谱深层自编码解混网络框架。该深度解混框架由三维去噪卷积自编码网络与结合超图学习的非负稀疏自编码网络级联构成。通过三维卷积与池化操作,三维去噪卷积自编码网络能够以无监督的方式提取光谱维与空间维的联合特征信息,并通过解码层的构建获得去噪影像数据;在非负稀疏自编码网络中,为保证丰度解的稀疏性和丰度在空间分布相关性,在网络上构建中引入超图学习和l2,1范数稀疏约束,从而使得求取的端元与丰度不仅满足非负性与和为一约束,同时丰度具有空间分布相关性信息。在实验验证中采用仿真数据集和真实高光谱影像对所提出解混框架和其他先进解混算法进行比较,展示了所提出解混网络的有效性与鲁棒性。

关键词:深度学习;无监督解混;卷积自编码网络;超图;高光谱图像;

LINKS