Deep Unfolding Network for Multi-Band Images Synchronous Fusion
This study proposes a new deep neural network to solve the multi-band image synchronous fusion problem (MBF-Net). Unlike other deep learning-based methods, our network architecture design combines the ideas of model-driven and data-driven methods, so it is more interpretable. First, a new multi-band...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10015736/ |
| _version_ | 1797866960788127744 |
|---|---|
| author | Dong Yu Suzhen Lin Xiaofei Lu Dawei Li Yanbo Wang |
| author_facet | Dong Yu Suzhen Lin Xiaofei Lu Dawei Li Yanbo Wang |
| author_sort | Dong Yu |
| collection | DOAJ |
| description | This study proposes a new deep neural network to solve the multi-band image synchronous fusion problem (MBF-Net). Unlike other deep learning-based methods, our network architecture design combines the ideas of model-driven and data-driven methods, so it is more interpretable. First, a new multi-band image synchronous fusion model is proposed. The source image in the data fidelity terms and the prior regularization are implicitly represented by the deep learning network and jointly learned from the training data. The proposed model is then solved using a half quadratic splitting (HQS) algorithm and unfolded into a deep fusion network. In addition, a new saliency loss function is proposed to retain thermal radiation information to enhance the fusion effect. Finally, the experimental results on the TNO dataset demonstrated the effectiveness of the proposed MBF-Net. |
| first_indexed | 2024-04-09T23:32:38Z |
| format | Article |
| id | doaj.art-29b089d21a634866b635c79d6ae017b6 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-09T23:32:38Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-29b089d21a634866b635c79d6ae017b62023-03-20T23:00:40ZengIEEEIEEE Access2169-35362023-01-0111251892520210.1109/ACCESS.2023.323631210015736Deep Unfolding Network for Multi-Band Images Synchronous FusionDong Yu0https://orcid.org/0000-0001-9837-602XSuzhen Lin1https://orcid.org/0000-0002-6418-5126Xiaofei Lu2Dawei Li3https://orcid.org/0000-0002-1441-8980Yanbo Wang4https://orcid.org/0000-0001-7997-434XDepartment of Data Science and Technology, North University of China, Taiyuan, ChinaDepartment of Data Science and Technology, North University of China, Taiyuan, ChinaJiuquan Satellite Launch Center, Jiuquan, ChinaDepartment of Electrical and Control Engineering, North University of China, Taiyuan, ChinaDepartment of Data Science and Technology, North University of China, Taiyuan, ChinaThis study proposes a new deep neural network to solve the multi-band image synchronous fusion problem (MBF-Net). Unlike other deep learning-based methods, our network architecture design combines the ideas of model-driven and data-driven methods, so it is more interpretable. First, a new multi-band image synchronous fusion model is proposed. The source image in the data fidelity terms and the prior regularization are implicitly represented by the deep learning network and jointly learned from the training data. The proposed model is then solved using a half quadratic splitting (HQS) algorithm and unfolded into a deep fusion network. In addition, a new saliency loss function is proposed to retain thermal radiation information to enhance the fusion effect. Finally, the experimental results on the TNO dataset demonstrated the effectiveness of the proposed MBF-Net.https://ieeexplore.ieee.org/document/10015736/Image fusionmulti-band imagestotal variationoptimization model |
| spellingShingle | Dong Yu Suzhen Lin Xiaofei Lu Dawei Li Yanbo Wang Deep Unfolding Network for Multi-Band Images Synchronous Fusion IEEE Access Image fusion multi-band images total variation optimization model |
| title | Deep Unfolding Network for Multi-Band Images Synchronous Fusion |
| title_full | Deep Unfolding Network for Multi-Band Images Synchronous Fusion |
| title_fullStr | Deep Unfolding Network for Multi-Band Images Synchronous Fusion |
| title_full_unstemmed | Deep Unfolding Network for Multi-Band Images Synchronous Fusion |
| title_short | Deep Unfolding Network for Multi-Band Images Synchronous Fusion |
| title_sort | deep unfolding network for multi band images synchronous fusion |
| topic | Image fusion multi-band images total variation optimization model |
| url | https://ieeexplore.ieee.org/document/10015736/ |
| work_keys_str_mv | AT dongyu deepunfoldingnetworkformultibandimagessynchronousfusion AT suzhenlin deepunfoldingnetworkformultibandimagessynchronousfusion AT xiaofeilu deepunfoldingnetworkformultibandimagessynchronousfusion AT daweili deepunfoldingnetworkformultibandimagessynchronousfusion AT yanbowang deepunfoldingnetworkformultibandimagessynchronousfusion |