Unsupervised hyperspectral unmixing based on robust nonnegative dictionary learning

作     者：LI Yang JIANG Bitao LI Xiaobin TIAN Jing SONG Xiaorui LI Yang;JIANG Bitao;LI Xiaobin;TIAN Jing;SONG Xiaorui

作者机构：Department of Space InformationSpace Engineering UniversityBeijing 101400China Beijing Institute of Remote Sensing InformationBeijing 100192China 

出 版 物：《Journal of Systems Engineering and Electronics》 (系统工程与电子技术（英文版）)

年 卷 期：2022年第33卷第2期

页      面：294-304页

核心收录：

学科分类：0810[工学-信息与通信工程] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 0808[工学-电气工程] 08[工学] 081002[工学-信号与信息处理] 0811[工学-控制科学与工程] 

基　　金：supported by the National Natural Science Foundation of China(61801513). 

主　　题：hyperspectral image(HSI) nonnegative dictionary learning norm loss function unsupervised unmixing 

摘      要：Considering the sparsity of hyperspectral images(HSIs),dictionary learning frameworks have been widely used in the field of unsupervised spectral unmixing.However,it is worth mentioning here that existing dictionary learning method-based unmixing methods are found to be short of robustness in noisy contexts.To improve the performance,this study specifically puts forward a new unsupervised spectral unmixing solution.For the reason that the solution only functions in a condition that both endmembers and the abundances meet non-negative con-straints,a model is built to solve the unsupervised spectral un-mixing problem on the account of the dictionary learning me-thod.To raise the screening accuracy of final members,a new form of the target function is introduced into dictionary learning practice,which is conducive to the growing robustness of noisy HSI statistics.Then,by introducing the total variation(TV)terms into the proposed spectral unmixing based on robust nonnega-tive dictionary learning(RNDLSU),the context information under HSI space is to be cited as prior knowledge to compute the abundances when performing sparse unmixing operations.Ac-cording to the final results of the experiment,this method makes favorable performance under varying noise conditions,which is especially true under low signal to noise conditions.