DAAN: A Deep Autoencoder-Based Augmented Network for Blind Multilinear Hyperspectral Unmixing

• 全文链接
• 请求原文

作   者：

Yuanchao Su;  Zhiqing Zhu;  Lianru Gao;  Antonio Plaza;  Pengfei Li;  Xu Sun;  Xiang Xu; 

作者机构：

College of Geomatics;  Escuela Politécnica;  University of Electronic Science and Technology of China;  College of GeomaticsCollege of Geology and Environment;  Department of Technology of Computers and Communications;  Xi’an University of Science and Technology;  Zhongshan Institute;  University of Extremadura;  Cáceres;  Zhongshan;  Chinese Academy of Sciences;  Hyperspectral Computing Laboratory;  Spain;  China;  Aerospace Information Research Institute;  Beijing;  Xi’an;  Artificial Intelligence and Computer Vision Laboratory;  China|Key Laboratory of Computational Optical Imaging Technology;  Department of Remote Sensing;  Key Laboratory of Computational Optical Imaging Technology; 

关键词：

Correlation;  Scattering;  Mixture models;  Convolutional neural networks;  Spatial resolution;  Hyperspectral imaging;  Photonics; 

期刊名称：

IEEE Transactions on Geoscience and Remote Sensing

i s s n：

0196-2892

年卷期：

2024 年 62 卷

页   码：

1-15

页   码：

摘   要：

In recent years, deep learning (DL) has accelerated the development of hyperspectral image (HSI) processing, expanding the range of applications further. As a typical model of unsupervised DL, the autoencoder framework has been extensively applied for spectral unmixing due to its strong representation ability and scalability. Nowadays, most DL-based unmixing approaches adopt the linear mixture model (LMM) to estimate pure spectral signatures (endmembers) and their corresponding abundance fractions. However, since sunlight scattering is an inevitable physical phenomenon, the spectral mixture problem is inherently nonlinear. Moreover, most existing nonlinear unmixing approaches focus exclusively on spectral information, neglecting the spatial distribution of materials and the intrinsic correlation between pixels, making it challenging to explore latent features. To address these issues, this article develops a new deep autoencoder-based augmented network (DAAN). The proposed DAAN employs the multilinear mixture model (MLMM) to handle the nonlinear influence caused by multiple scattering. Meanwhile, the proposed DAAN constraints homogenous smoothing in the autoencoder architecture, enabling the aggregation of intrinsic correlations by means of spatial relationships to enhance the performance of abundance estimation. We achieve unsupervised nonlinear hyperspectral unmixing by combining spectral and spatial information. The effectiveness and advantages of DAAN are confirmed by several experiments with synthetic and real HSI datasets. The results indicate that the proposed method outperforms other DL-based unmixing approaches. The source codes of the proposed DAAN will be provided in the following link https://github.com/yuanchaosu/TGRS-daan.