Siam-EMNet: A Siamese EfficientNet-MANet Network for Building Change Detection in Very High Resolution Images
文献类型:期刊论文
作者 | Huang, Liang2,3; Tian, Qiuyuan2; Tang, Bo-Hui1,2,3; Le, Weipeng2; Wang, Min2; Ma, Xianguang2,4 |
刊名 | REMOTE SENSING |
出版日期 | 2023-08-01 |
卷号 | 15期号:16页码:17 |
关键词 | change detection building VHR remote sensing images attention mechanism deep learning |
DOI | 10.3390/rs15163972 |
通讯作者 | Tian, Qiuyuan(20212201132@stu.kust.edu.cn) |
英文摘要 | As well as very high resolution (VHR) remote sensing technology and deep learning, methods for detecting changes in buildings have made great progress. Despite this, there are still some problems with the incomplete detection of change regions and rough edges. To this end, a change detection network for building VHR remote sensing images based on Siamese EfficientNet B4-MANet (Siam-EMNet) is proposed. First, a bi-branches pretrained EfficientNet B4 encoder structure is constructed to enhance the performance of feature extraction and the rich shallow and deep information is obtained; then, the semantic information of the building is input into the MANet decoder integrated by the dual attention mechanism through the skip connection. The position-wise attention block (PAB) and multi-scale fusion attention block (MFAB) capture spatial relationships between pixels in the global view and channel relationships between layers. The integration of dual attention mechanisms ensures that the building contour is fully detected. The proposed method was evaluated on the LEVIR-CD dataset, and its precision, recall, accuracy, and F1-score were 92.00%, 88.51%, 95.71%, and 90.21%, respectively, which represented the best overall performance compared to the BIT, CDNet, DSIFN, L-Unet, P2V-CD, and SNUNet methods. Verification of the efficacy of the suggested approach was then conducted. |
WOS关键词 | REMOTE-SENSING DATA ; CLASSIFICATION |
资助项目 | Yunnan Fundamental Research Project[202201AT070164] ; Hunan Provincial Natural Science Foundation of China[2023JJ60561] |
WOS研究方向 | Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology |
语种 | 英语 |
出版者 | MDPI |
WOS记录号 | WOS:001057643700001 |
资助机构 | Yunnan Fundamental Research Project ; Hunan Provincial Natural Science Foundation of China |
源URL | [http://ir.igsnrr.ac.cn/handle/311030/196540] |
专题 | 中国科学院地理科学与资源研究所 |
通讯作者 | Tian, Qiuyuan |
作者单位 | 1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China 2.Kunming Univ Sci & Technol, Fac Land & Resources Engn, Kunming 650093, Peoples R China 3.Yunnan Prov Dept Educ, Key Lab Plateau Remote Sensing, Kunming 650093, Peoples R China 4.Planning & Design Inst Land & Resources Yunnan Pro, Kunming 650224, Peoples R China |
推荐引用方式 GB/T 7714 | Huang, Liang,Tian, Qiuyuan,Tang, Bo-Hui,et al. Siam-EMNet: A Siamese EfficientNet-MANet Network for Building Change Detection in Very High Resolution Images[J]. REMOTE SENSING,2023,15(16):17. |
APA | Huang, Liang,Tian, Qiuyuan,Tang, Bo-Hui,Le, Weipeng,Wang, Min,&Ma, Xianguang.(2023).Siam-EMNet: A Siamese EfficientNet-MANet Network for Building Change Detection in Very High Resolution Images.REMOTE SENSING,15(16),17. |
MLA | Huang, Liang,et al."Siam-EMNet: A Siamese EfficientNet-MANet Network for Building Change Detection in Very High Resolution Images".REMOTE SENSING 15.16(2023):17. |
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。