Climate Change Data Portal
DOI | 10.1109/JSTARS.2024.3354912 |
A Multiscale Dual Attention Network for the Automatic Classification of Polar Sea Ice and Open Water Based on Sentinel-1 SAR Images | |
发表日期 | 2024 |
ISSN | 1939-1404 |
EISSN | 2151-1535 |
起始页码 | 17 |
卷号 | 17 |
英文摘要 | Automatic classification of sea ice and open water plays a vital role in climate change research, polar shipping, and other applications. Many deep-learning-based methods are proposed to automatically classify sea ice and open water to address this issue. Even though these methods have achieved remarkable success, the noise phenomenon in synthetic aperture radar (SAR) images still causes considerable limitations in the model performance. Meanwhile, these existing methods ignore multiscale global information from large-scale SAR images, which tends to produce misclassification. In this article, we propose a novel multiscale dual attention network (MSDA-Net) for the task. To tackle the first drawback, we introduce the information of relative position and high-pass filtering as two extra channels to reduce the noisy effects. Moreover, we propose a patch dual attention mechanism and embed it into the ConvNeXt blocks to capture the multichannel and spatial features. To address the second problem, we propose a multiscale spatial attention module to capture multiscale global spatial information. The experiments show that the proposed method significantly outperforms state-of-the-art methods. In addition, comprehensive case studies are conducted, which verify the effectiveness of MSDA-Net in different SAR scenes. |
英文关键词 | Sea ice; Microwave radiometry; Feature extraction; Radar polarimetry; Transformers; Synthetic aperture radar; Microwave theory and techniques; Climate change; Deep learning; Noise measurement; Learning systems; sea ice classification; synthetic aperture radar (SAR) |
语种 | 英语 |
WOS研究方向 | Engineering ; Physical Geography ; Remote Sensing ; Imaging Science & Photographic Technology |
WOS类目 | Engineering, Electrical & Electronic ; Geography, Physical ; Remote Sensing ; Imaging Science & Photographic Technology |
WOS记录号 | WOS:001180713400004 |
来源期刊 | IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
![]() |
文献类型 | 期刊论文 |
条目标识符 | http://gcip.llas.ac.cn/handle/2XKMVOVA/288417 |
作者单位 | Harbin Institute of Technology; Harbin Institute of Technology; China Meteorological Administration |
推荐引用方式 GB/T 7714 | . A Multiscale Dual Attention Network for the Automatic Classification of Polar Sea Ice and Open Water Based on Sentinel-1 SAR Images[J],2024,17. |
APA | (2024).A Multiscale Dual Attention Network for the Automatic Classification of Polar Sea Ice and Open Water Based on Sentinel-1 SAR Images.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,17. |
MLA | "A Multiscale Dual Attention Network for the Automatic Classification of Polar Sea Ice and Open Water Based on Sentinel-1 SAR Images".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 17(2024). |
条目包含的文件 | 条目无相关文件。 |
个性服务 |
推荐该条目 |
保存到收藏夹 |
导出为Endnote文件 |
谷歌学术 |
谷歌学术中相似的文章 |
百度学术 |
百度学术中相似的文章 |
必应学术 |
必应学术中相似的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。