Enhanced hyperspectral image classification for coastal wetlands using a hybrid CNN-transformer approach with cross-attention mechanism
文献类型：期刊论文
| 作者 | Li, Zhongmei1,2; Liu, Tang1; Lu, Yuxiang1; Tian, Jing2; Zhang, Meng2; Zhou, Chenghu1 |
| 刊名 | FRONTIERS IN MARINE SCIENCE
 |
| 出版日期 | 2025-06-26 |
| 卷号 | 12页码:1613565 |
| 关键词 | convolutional neural network transformer cross attention mechanism hyperspectral image classification coastal wetland classification |
| DOI | 10.3389/fmars.2025.1613565 |
| 产权排序 | 1 |
| 文献子类 | Article |
| 英文摘要 | Coastal wetlands play a vital role in shoreline protection, material cycling, and biodiversity conservation. Utilizing hyperspectral remote sensing technology for wetland monitoring can enhance scientific management of these ecosystems. However, the complex water-land interactions and vegetation mixtures in wetlands often lead to significant spectral confusion and complicated spatial structures, posing challenges for fine classification. This paper proposes a novel hyperspectral image classification method that combines the strengths of Convolutional Neural Networks (CNNs) for local feature extraction and Transformers for modeling long-range dependencies. The method utilizes both 3D and 2D convolution operations to effectively capture spectral and spatial features of coastal wetlands. Additionally, dual-branch Transformers equipped with cross-attention mechanisms are employed to explore deep features from multiple perspectives and model the interrelationships between various characteristics. Comprehensive experiments conducted on two typical coastal wetland hyperspectral datasets demonstrate that the proposed method achieves an overall accuracy (OA) of 96.52% and 85.72%, surpassing other benchmarks by 1.0-8.64%. Notably, challenging categories such as mudflats and mixed vegetation area benefit significantly. This research provides valuable insights for the application of hyperspectral imagery in coastal wetland classification. |
| URL标识 | 查看原文 |
| WOS研究方向 | Environmental Sciences & Ecology ; Marine & Freshwater Biology |
| 语种 | 英语 |
| WOS记录号 | WOS:001524701000001 |
| 出版者 | FRONTIERS MEDIA SA |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/215413]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 作者单位 | 1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res IGSNRR, State Key Lab Resources & Environm Informat Syst, Beijing, Peoples R China; 2.Beijing Inst Remote Sensing Informat, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Li, Zhongmei,Liu, Tang,Lu, Yuxiang,et al. Enhanced hyperspectral image classification for coastal wetlands using a hybrid CNN-transformer approach with cross-attention mechanism[J]. FRONTIERS IN MARINE SCIENCE,2025,12:1613565. |
| APA | Li, Zhongmei,Liu, Tang,Lu, Yuxiang,Tian, Jing,Zhang, Meng,&Zhou, Chenghu.(2025).Enhanced hyperspectral image classification for coastal wetlands using a hybrid CNN-transformer approach with cross-attention mechanism.FRONTIERS IN MARINE SCIENCE,12,1613565. |
| MLA | Li, Zhongmei,et al."Enhanced hyperspectral image classification for coastal wetlands using a hybrid CNN-transformer approach with cross-attention mechanism".FRONTIERS IN MARINE SCIENCE 12(2025):1613565. |
入库方式： OAI收割
来源：地理科学与资源研究所
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。