Nonlinear Unmixing of Hyperspectral Data via Deep Autoencoder Networks

作     者：Wang, Mou Zhao, Min Chen, Jie Rahardja, Susanto 

作者机构：Northwestern Polytech Univ Sch Marine Sci & Technol Xian 710072 Shaanxi Peoples R China Minist Ind & Informat Technol Key Lab Ocean Acoust & Sensing Xian 710072 Shaanxi Peoples R China Northwestern Polytech Univ Dev Inst Shenzhen 518057 Peoples R China 

出 版 物：《IEEE GEOSCIENCE AND REMOTE SENSING LETTERS》 (IEEE地球科学与遥感快报)

年 卷 期：2019年第16卷第9期

页      面：1467-1471页

核心收录：

学科分类：0808[工学-电气工程] 1002[医学-临床医学] 08[工学] 0708[理学-地球物理学] 0816[工学-测绘科学与技术] 

基　　金：NSFC [61671382, 61811530283] NSF of Shenzhen [JCYJ2017030155315873] 111 Project [B18041] 

主　　题：Autoencoder network deep learning hyperspectral imaging nonlinear spectral unmixing 

摘      要：Nonlinear spectral unmixing is an important and challenging problem in hyperspectral image processing. Classical nonlinear algorithms are usually derived based on specific assumptions on the nonlinearity. In recent years, deep learning shows its advantage in addressing general nonlinear problems. However, existing ways of using deep neural networks for unmixing are limited and restrictive. In this letter, we develop a novel blind hyperspectral unmixing scheme based on a deep autoencoder network. Both encoder and decoder of the network are carefully designed so that we can conveniently extract estimated endmembers and abundances simultaneously from the nonlinearly mixed data. Because an autoencoder is essentially an unsupervised algorithm, this scheme only relies on the current data and, therefore, does not require additional training. Experimental results validate the proposed scheme and show its superior performance over several existing algorithms.