A Single Data Extraction Algorithm for Oblique Photographic Data Based on the U-Net
文献类型：期刊论文
| 作者 | Wang, Shaohua1,2; Li, Xiao1; Lin, Liming3; Lu, Hao4; Jiang, Ying3; Zhang, Ning5,6; Wang, Wenda1,7; Yue, Jianwei8; Li, Ziqiong9 |
| 刊名 | REMOTE SENSING
 |
| 出版日期 | 2024-03-01 |
| 卷号 | 16期号:6页码:16 |
| 关键词 | deep convolutional neural network dynamic virtual building monomer construction oblique photographic modeling |
| DOI | 10.3390/rs16060979 |
| 通讯作者 | Zhang, Ning(zhangning0496@163.com) |
| 英文摘要 | In the automated modeling generated by oblique photography, various terrains cannot be physically distinguished individually within the triangulated irregular network (TIN). To utilize the data representing individual features, such as a single building, a process of building monomer construction is required to identify and extract these distinct parts. This approach aids subsequent analyses by focusing on specific entities, mitigating interference from complex scenes. A deep convolutional neural network is constructed, combining U-Net and ResNeXt architectures. The network takes as input both digital orthophoto map (DOM) and oblique photography data, effectively extracting the polygonal footprints of buildings. Extraction accuracy among different algorithms is compared, with results indicating that the ResNeXt-based network achieves the highest intersection over union (IOU) for building segmentation, reaching 0.8255. The proposed "dynamic virtual monomer" technique binds the extracted vector footprints dynamically to the original oblique photography surface through rendering. This enables the selective representation and querying of individual buildings. Empirical evidence demonstrates the effectiveness of this technique in interactive queries and spatial analysis. The high level of automation and excellent accuracy of this method can further advance the application of oblique photography data in 3D urban modeling and geographic information system (GIS) analysis. |
| WOS关键词 | CONVOLUTIONAL NEURAL-NETWORKS ; 3D BUILDING MODELS |
| 资助项目 | Beijing Chaoyang District Collaborative Innovation Project |
| WOS研究方向 | Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:001193562500001 |
| 出版者 | MDPI |
| 资助机构 | Beijing Chaoyang District Collaborative Innovation Project |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/204171]  |
| 专题 | 中国科学院地理科学与资源研究所 |
| 通讯作者 | Zhang, Ning |
| 作者单位 | 1.Lanzhou Jiaotong Univ, Fac Geomatics, Lanzhou 730070, Peoples R China 2.Chinese Acad Sci, Aerosp Informat Res Inst, Beijing 100094, Peoples R China 3.STATE GRID Locat Based Serv Co Ltd, Beijing 100015, Peoples R China 4.SuperMap Software Co Ltd, Beijing 100015, Peoples R China 5.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China 6.China Acad Urban Planning & Design, Beijing 100044, Peoples R China 7.China Railway Construct Bridge Engn Bur Grp Co Ltd, Tianjin 300300, Peoples R China 8.Beijing Normal Univ, Fac Geog Sci, Beijing 100875, Peoples R China 9.UCL, Bartlett Ctr Adv Spatial Anal, London W1T 4TJ, England |
| 推荐引用方式 GB/T 7714 | Wang, Shaohua,Li, Xiao,Lin, Liming,et al. A Single Data Extraction Algorithm for Oblique Photographic Data Based on the U-Net[J]. REMOTE SENSING,2024,16(6):16. |
| APA | Wang, Shaohua.,Li, Xiao.,Lin, Liming.,Lu, Hao.,Jiang, Ying.,...&Li, Ziqiong.(2024).A Single Data Extraction Algorithm for Oblique Photographic Data Based on the U-Net.REMOTE SENSING,16(6),16. |
| MLA | Wang, Shaohua,et al."A Single Data Extraction Algorithm for Oblique Photographic Data Based on the U-Net".REMOTE SENSING 16.6(2024):16. |
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。