CNN-TransNet: A Hybrid CNN-Transformer Network With Differential Feature Enhancement for Cloud Detection
文献类型：期刊论文
| 作者 | Ma, Nan1; Sun, Lin4; He, Yawen3; Zhou, Chenghu2; Dong, Chuanxiang4 |
| 刊名 | IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
 |
| 出版日期 | 2023 |
| 卷号 | 20页码:5 |
| 关键词 | Cloud detection convolutional neural network (CNN) differential feature dual branch transformer |
| ISSN号 | 1545-598X |
| DOI | 10.1109/LGRS.2023.3288742 |
| 通讯作者 | Sun, Lin(sunlin6@126.com) |
| 英文摘要 | Thin clouds detection and the difficulty in distinguishing between clouds and bright surface features have consistently presented challenges in optical remote sensing cloud detection tasks. Convolutional neural networks (CNNs) have made significant progress, however, CNNs perform weakly in capturing global information interactions due to the inherent limitation of network structure. To address these issues, we propose a hybrid CNN-transformer network with differential feature enhancement (DFE) for cloud detection (CNN-TransNet). CNN-TransNet adopts a dual-branch encoder consisting of a CNN-transformer module and a DFE module. CNN-TransNet combines the strengths of both transformer and CNN to enhance finer details and build long-range dependencies. CNN is considered a high-resolution feature extractor for capturing low-level features. The transformer module encodes image sequences by patch embedding to extract high-level features and relationships. DFE branch utilizes differential features and attention mechanism to further obtain effective information for distinguishing between clouds and nonclouds. The decoder upsamples features of the encoder and concatenates multiscale features from the CNN layers. Experimental results demonstrate that the proposed method achieves excellent performance on Landsat-8 and Sentinel-2 images, with a high cloud pixel precision of 92.94% and 93.04%. Moreover, it effectively reduces thin cloud omissions and the misclassifications of bright surface features. |
| WOS关键词 | DETECTION ALGORITHM ; VALIDATION |
| 资助项目 | National Natural Science Foundation of China[42271412] ; National Natural Science Foundation of China[41976184] |
| WOS研究方向 | Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:001025476100002 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Natural Science Foundation of China |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/195621]  |
| 专题 | 中国科学院地理科学与资源研究所 |
| 通讯作者 | Sun, Lin |
| 作者单位 | 1.China Univ Petr, Sch Geosci, Qingdao 266580, Peoples R China 2.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China 3.China Univ Petr, Coll Oceanog & Space Informat, Qingdao 266580, Peoples R China 4.Shandong Univ Sci & Technol, Coll Geomat, Qingdao 266590, Peoples R China |
| 推荐引用方式 GB/T 7714 | Ma, Nan,Sun, Lin,He, Yawen,et al. CNN-TransNet: A Hybrid CNN-Transformer Network With Differential Feature Enhancement for Cloud Detection[J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,2023,20:5. |
| APA | Ma, Nan,Sun, Lin,He, Yawen,Zhou, Chenghu,&Dong, Chuanxiang.(2023).CNN-TransNet: A Hybrid CNN-Transformer Network With Differential Feature Enhancement for Cloud Detection.IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,20,5. |
| MLA | Ma, Nan,et al."CNN-TransNet: A Hybrid CNN-Transformer Network With Differential Feature Enhancement for Cloud Detection".IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 20(2023):5. |
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。