中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 视频内容安全团队
LG-DBNet: Local and Global Dual-Branch Network for SAR Image Denoising

文献类型：期刊论文

作者Liu, Shuaiqi1,2; Tian, Shikang1; Zhao, Yuhang1; Hu, Qi1; Li, Bing2; Zhang, Yu-Dong3
刊名IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
出版日期2024
卷号62页码:15
关键词Noise reduction Radar polarimetry Feature extraction Speckle Transforms Filtering Transformers Convolutional neural network (CNN) dual-branch network hybrid attention module self-attention mechanisms synthetic aperture radar (SAR) image denoising
ISSN号0196-2892
DOI10.1109/TGRS.2024.3362510
通讯作者Tian, Shikang(sktian_hbu@163.com) ; Hu, Qi(qihu_hbu@163.com)
英文摘要Synthetic aperture radar (SAR) tends to be seriously affected by speckle noise due to its inherent imaging characteristics, which brings great challenges to the high-level visualization task of SAR images. Speckle suppression, therefore, plays a crucial role in remote sensing image processing. Attention-based SAR image denoising algorithms frequently struggle to capture rich feature information and face challenges in balancing the trade-off between denoising and preserving texture details. To solve the above problems, this article constructs a local and global dual-branch network (LG-DBNet) for SAR image denoising. This network can effectively suppress speckle noise while fully retaining the detailed information of the original image. First, the shallow features are extracted through simple convolution. Then, a dual-branch structure constructed using different attention modules is used to extract deep features from SAR images. Specifically, one branch performs local deep feature extraction of an image through a hybrid attention module built by a convolutional neural network (CNN), while the other branch uses a superposition of self-attention mechanisms for global deep feature extraction of the image. Finally, the final denoised image is generated through global residual learning. LG-DBNet can effectively extract the local and global image information through the dual-branch structure and further focus on the noise information, which can better retain the texture information of the image while effectively denoising. The experimental results show that compared with the state-of-the-art SAR image denoising algorithms, the proposed algorithm not only improves on various objective indexes but also shows great advantages in the visual effect after denoising.
WOS关键词ALGORITHM
资助项目National Natural Science Foundation of China
WOS研究方向Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
语种英语
WOS记录号WOS:001173263900031
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/57989]  
专题自动化研究所_模式识别国家重点实验室_视频内容安全团队
通讯作者Tian, Shikang; Hu, Qi
作者单位1.Hebei Univ, Coll Elect & Informat Engn, Machine Vis Technol Innovat Ctr Hebei Prov, Baoding 071002, Peoples R China
2.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence, Beijing 100190, Peoples R China
3.Univ Leicester, Sch Comp & Math, Leicester LE1 7RH, England
推荐引用方式
GB/T 7714		 Liu, Shuaiqi,Tian, Shikang,Zhao, Yuhang,et al. LG-DBNet: Local and Global Dual-Branch Network for SAR Image Denoising[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2024,62:15.
APA Liu, Shuaiqi,Tian, Shikang,Zhao, Yuhang,Hu, Qi,Li, Bing,&Zhang, Yu-Dong.(2024).LG-DBNet: Local and Global Dual-Branch Network for SAR Image Denoising.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,62,15.
MLA Liu, Shuaiqi,et al."LG-DBNet: Local and Global Dual-Branch Network for SAR Image Denoising".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 62(2024):15.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。