NEURAL NETWORK HYPERSPECTRAL UNMIXING WITH SPECTRAL INFORMATION DIVERGENCE OBJECTIVE

被引：0

作者：

Palsson, Frosti ^{[1
]}

Sigurdsson, Jakob ^{[1
]}

Sveinsson, Johannes R. ^{[1
]}

Ulfarsson, Magnus O. ^{[1
]}

机构：

[1] Univ Iceland, Fac Elect & Comp Engn, Hjardarhagi 2-6, IS-107 Reykjavik, Iceland

来源：

2017 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS) | 2017年

关键词：

Hyperspectral unmixing; autoencoder; deep learning; neural network; spectral information divergence; SPARSE REGRESSION;

D O I：

暂无

中图分类号：

P [天文学、地球科学];

学科分类号：

07 ;

摘要：

Hyperspectral unmixing is a challenging inverse problem that involves determining the fractional abundances of the representive material (endmembers) in each pixel. In this paper, we develop a neural network autoencoder, that dynamically exploits the sparsity of the abundances and enforces the abundance sum constraint (ASC) for hyperspectral unmixing. Instead of using the conventional mean square error (MSE) objective function, we use the spectral information divergence (SID) measure. Experiments are performed using a real hyperspectral dataset and we compare results obtained using both MSE and SID. It is demonstrated by qualitative inspection that using SID gives significantly better results than using MSE.

引用

页码：755 / 758

页数：4

共 50 条

[21] An Improved Hyperspectral Unmixing Approach Based on a Spatial–Spectral Adaptive Nonlinear Unmixing Network [J].

Chen, Xiao ;

Zhang, Xianfeng ;

Ren, Miao ;

Zhou, Bo ;

Feng, Ziyuan ;

Cheng, Junyi .

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2023, 16 :10107-10123

[22] Spectral-Spatial Hyperspectral Unmixing Using Multitask Learning [J].

Palsson, Burkni ;

Sveinsson, Johannes R. ;

Ulfarsson, Magnus O. .

IEEE ACCESS, 2019, 7 (148861-148872) :148861-148872

[23] DSSFT: Dual branch spectral-spatial feature fusion transformer network for hyperspectral image unmixing [J].

Hadi, Fazal ;

Farooque, Ghulam ;

Shao, Yuantian ;

Yang, Jingxiang ;

Xiao, Liang .

EARTH SCIENCE INFORMATICS, 2025, 18 (02)

[24] Adversarial Autoencoder Network for Hyperspectral Unmixing [J].

Jin, Qiwen ;

Ma, Yong ;

Fan, Fan ;

Huang, Jun ;

Mei, Xiaoguang ;

Ma, Jiayi .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 34 (08) :4555-4569

[25] SNMF-Net: Learning a Deep Alternating Neural Network for Hyperspectral Unmixing [J].

Xiong, Fengchao ;

Zhou, Jun ;

Tao, Shuyin ;

Lu, Jianfeng ;

Qian, Yuntao .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60

[26] An Efficient Attention-Based Convolutional Neural Network That Reduces the Effects of Spectral Variability for Hyperspectral Unmixing [J].

Jin, Baohua ;

Zhu, Yunfei ;

Huang, Wei ;

Chen, Qiqiang ;

Li, Sijia .

APPLIED SCIENCES-BASEL, 2022, 12 (23)

[27] Hyperspectral Unmixing Based on Spectral and Sparse Deep Convolutional Neural Networks [J].

Wan, Lulu ;

Chen, Tao ;

Plaza, Antonio ;

Cai, Haojie .

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2021, 14 :11669-11682

[28] SSCU-Net: Spatial-Spectral Collaborative Unmixing Network for Hyperspectral Images [J].

Qi, Lin ;

Gao, Feng ;

Dong, Junyu ;

Gao, Xinbo ;

Du, Qian .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60

[29] HYPERSPECTRAL IMAGE RESOLUTION ENHANCEMENT BASED ON SPECTRAL UNMIXING AND INFORMATION FUSION [J].

Bieniarz, J. ;

Cerra, D. ;

Avbelj, J. ;

Reinartz, P. ;

Mueller, R. .

ISPRS HANNOVER WORKSHOP 2011: HIGH-RESOLUTION EARTH IMAGING FOR GEOSPATIAL INFORMATION, 2011, 39-4 (W19) :33-37

[30] CONVOLUTIONAL AUTOENCODER FOR SPATIAL-SPECTRAL HYPERSPECTRAL UNMIXING [J].

Palsson, Burkni ;

Ulfarsson, Magnus O. ;

Sveinsson, Johannes R. .

2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019), 2019, :357-360

← 1 2 3 4 5 →