HR-MM Segformer: Enhancing land use and land cover semantic segmentation through transformer-based multisource remote sensing feature fusion
文献类型：期刊论文
| 作者 | Fan, Junfu2,3; Shi, Zongwen1,2; Du, Yujie2; Zhuang, Can2 |
| 刊名 | ENVIRONMENTAL MODELLING & SOFTWARE
 |
| 出版日期 | 2026-02-01 |
| 卷号 | 197页码:106848 |
| 关键词 | LULC Multimodal Multispectral Multisource feature fusion Vision transformer Deep learning |
| ISSN号 | 1364-8152 |
| DOI | 10.1016/j.envsoft.2025.106848 |
| 产权排序 | 2 |
| 文献子类 | Article |
| 英文摘要 | Automatic land use and land cover (LULC) semantic segmentation is constrained by spectral confusion and the semantic gap inherent in independent-branch multisource and multisensor (MM) data fusion architectures. To address these limitations, this study proposes HR-MM SegFormer, a framework incorporating a unified transformer encoder. Unlike conventional dual-stream approaches, the architecture projects heterogeneous high-resolution (HR) optical imagery and MM auxiliary data (multispectral/DSM) into a shared semantic manifold via a feature correction (FC) layer. Additionally, a multimodal cross-attention fusion (MCAF) module dynamically retrieves complementary spectral and geometric contexts guided by HR spatial structures. Experimental evaluations of the HR-MS LULC and HR-DSM Potsdam datasets yield mean intersection over union (mIoU) scores of 88.50 % and 87.84 %, respectively. These results correspond to improvements of 8.89 % and 12.67 % over single-modal baselines, accompanied by a 6.3 % increase in computational overhead. This study substantiates that the unified full-attention paradigm bridges cross-modal disparities, providing an effective solution for finegrained Earth observations. |
| URL标识 | 查看原文 |
| WOS关键词 | NETWORK ; IMAGES |
| WOS研究方向 | Computer Science ; Engineering ; Environmental Sciences & Ecology ; Water Resources |
| 语种 | 英语 |
| WOS记录号 | WOS:001657505600001 |
| 出版者 | ELSEVIER SCI LTD |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/219708]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 通讯作者 | Shi, Zongwen |
| 作者单位 | 1.Nanjing Univ Informat Sci & Technol, Sch Geog Sci, Nanjing 210044, Peoples R China 2.Shandong Univ Technol, Sch Civil Engn & Geomat, Zibo 255000, Peoples R China; 3.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Fan, Junfu,Shi, Zongwen,Du, Yujie,et al. HR-MM Segformer: Enhancing land use and land cover semantic segmentation through transformer-based multisource remote sensing feature fusion[J]. ENVIRONMENTAL MODELLING & SOFTWARE,2026,197:106848. |
| APA | Fan, Junfu,Shi, Zongwen,Du, Yujie,&Zhuang, Can.(2026).HR-MM Segformer: Enhancing land use and land cover semantic segmentation through transformer-based multisource remote sensing feature fusion.ENVIRONMENTAL MODELLING & SOFTWARE,197,106848. |
| MLA | Fan, Junfu,et al."HR-MM Segformer: Enhancing land use and land cover semantic segmentation through transformer-based multisource remote sensing feature fusion".ENVIRONMENTAL MODELLING & SOFTWARE 197(2026):106848. |
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。