Nonlinear Unmixing via Deep Autoencoder Networks for Generalized Bilinear Model

作     者：Zhang, Jinhua Zhang, Xiaohua Meng, Hongyun Sun, Caihao Wang, Li Cao, Xianghai 

作者机构：Xidian Univ Sch Artificial Intelligence Xian 710071 Peoples R China Xidian Univ Sch Math & Stat Xian 710071 Peoples R China 

出 版 物：《REMOTE SENSING》 (遥感)

年 卷 期：2022年第14卷第20期

页      面：5167页

核心收录：

学科分类：0830[工学-环境科学与工程（可授工学、理学、农学学位）] 1002[医学-临床医学] 070801[理学-固体地球物理学] 07[理学] 08[工学] 0708[理学-地球物理学] 0816[工学-测绘科学与技术] 

基　　金：National Natural Science Foundation of China Aero-Science Fund Science and technology plan project of Xi'an [21RGZN0010] 

主　　题：unsupervised nonlinear spectral unmixing generalized bilinear model deep learning autoencoder network 

摘      要：Hyperspectral unmixing decomposes the observed mixed spectra into a collection of constituent pure material signatures and the associated fractional abundances. Because of the universal modeling ability of neural networks, deep learning (DL) techniques are gaining prominence in solving hyperspectral analysis tasks. The autoencoder (AE) network has been extensively investigated in linear blind source unmixing. However, the linear mixing model (LMM) may fail to provide good unmixing performance when the nonlinear mixing effects are nonnegligible in complex scenarios. Considering the limitations of LMM, we propose an unsupervised nonlinear spectral unmixing method, based on autoencoder architecture. Firstly, a deep neural network is employed as the encoder to extract the low-dimension feature of the mixed pixel. Then, the generalized bilinear model (GBM) is used to design the decoder, which has a linear mixing part and a nonlinear mixing one. The coefficient of the bilinear mixing part can be adjusted by a set of learnable parameters, which makes the method perform well on both nonlinear and linear data. Finally, some regular terms are imposed on the loss function and an alternating update strategy is utilized to train the network. Experimental results on synthetic and real datasets verify the effectiveness of the proposed model and show very competitive performance compared with several existing algorithms.