Deep Autoencoders With Multitask Learning for Bilinear Hyperspectral Unmixing
Deep Autoencoders With Multitask Learning for Bilinear Hyperspectral Unmixing
复制标题
具有双线性高光谱分解多任务学习的深度自动编码器
DOI：
10.1109/tgrs.2020.3041157
复制
发表时间：
2021-10
影响因子：
8.2
通讯作者：
Plaza Antonio
中科院分区：
文献类型：
--
作者：
Su Yuanchao;Xu Xiang;Li Jun;Qi Hairong;Gamba Paolo;Plaza Antonio
Hyperspectral unmixing is an important problem for remotely sensed data interpretation. It amounts at estimating the spectral signatures of the pure spectral constituents in the scene (endmembers) and their corresponding subpixel fractional abundances. Although the unmixing problem is inherently nonlinear (due to multiple scattering), the nonlinear unmixing of hyperspectral data has been a very challenging problem. This is because nonlinear models require detailed knowledge about the physical interactions between the sunlight scattered by multiple materials. In turn, bilinear mixture models (BMMs) can reach good accuracy with a relatively simple model for scattering. In this article, we develop a new BMM and a corresponding unsupervised unmixing approach which consists of two main steps. In the first step, a deep autoencoder is used to linearly estimate the endmember signatures and their associated abundance fractions. The second step refines the initial (linear) estimates using a bilinear model, in which another deep autoencoder (with a low-rank assumption) is adapted to model second-order scattering interactions. It should be noted that in our developed BMM model, the two deep autoencoders are trained in a mutually interdependent manner under the multitask learning framework, and the relative reconstruction error is used as the stopping criterion. The effectiveness of the proposed method is evaluated using both synthetic and real hyperspectral data sets. Our experimental results indicate that the proposed approach can reasonably estimate the nature of nonlinear interactions in real scenarios. Compared with other state-of-the-art unmixing algorithms, the proposed approach demonstrates very competitive performance.
登录
查看更多内容
DOI：
10.1109/jstars.2012.2194696
发表时间：
2012-04-01
影响因子：
5.5
作者：
Bioucas-Dias, Jose M.;Plaza, Antonio;Chanussot, Jocelyn
通讯作者：
Chanussot, Jocelyn
DOI：
10.1109/whispers.2015.8075378
发表时间：
2015-06
期刊：
2015 7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)
影响因子：
--
作者：
Rui Guo;Wei Wang;H. Qi
通讯作者：
Rui Guo;Wei Wang;H. Qi
高光谱解混的结构化稀疏方法
DOI：
10.1016/j.isprsjprs.2013.11.014
发表时间：
2014
影响因子：
12.7
作者：
Zhu Feiyun;Wang Ying;Xiang Shiming;Fan Bin;Pan Chunhong
通讯作者：
Pan Chunhong
减轻共线性效应的两步约束非线性谱混合分析方法
DOI：
10.1109/tgrs.2015.2506725
发表时间：
2016-05-01
影响因子：
8.2
作者：
Ma, Lei;Chen, Jin;Chen, Xuehong
通讯作者：
Chen, Xuehong
影响因子：
8.2
作者：
Ying Qu;H. Qi
通讯作者：
Ying Qu;H. Qi