Nonlocal feature learning based on a variational graph auto-encoder network for small area change detection using SAR imagery
文献类型：期刊论文
| 作者 | Su, Hang2; Zhang, Xinzheng2,3; Luo, Yuqing2; Zhang, Ce4,5; Zhou, Xichuan2; Atkinson, Peter M.1,4,6 |
| 刊名 | ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
 |
| 出版日期 | 2022-11-01 |
| 卷号 | 193页码:137-149 |
| 关键词 | Synthetic aperture radar Change detection Difference image Graph auto -encoder network Deep learning |
| ISSN号 | 0924-2716 |
| DOI | 10.1016/j.isprsjprs.2022.09.006 |
| 通讯作者 | Zhang, Xinzheng() ; Zhang, Ce() |
| 英文摘要 | Synthetic aperture radar (SAR) image change detection is a challenging task due to inherent speckle noise, imbalanced class occurrence and the requirement for discriminative feature learning. The traditional handcrafted feature extraction and current convolution-based deep learning techniques have some advantages, but suffer from being limited to neighborhood-based spatial information. The nonlocally observable imbalance phenom-enon that exists naturally in small area change detection has presented a huge challenge to methods that focus on local features only. In this paper, an unsupervised method based on a variational graph auto-encoder (VGAE) network was developed for object-based small area change detection using SAR images, with the advantages of alleviating the negative impact of class imbalance and suppressing speckle noise. The main steps include: 1) Three types of difference image (DI) are combined to establish a three-channel fused DI (TCFDI), which lays the data-level foundation for subsequent analysis. 2) Simple linear iterative clustering (SLIC) is used to divide the TCFDI into superpixels regarded as nodes. Two functions are proposed and developed to measure the similarity between nodes to build a weighted undirected graph. 3) A VGAE network is designed and trained using the graph and nodes, and high-level nonlocal feature representations of each node are extracted. The network, with a Gaussian Radial Basis Function constrained by geospatial distances, establishes the connection among nonlocal, but similar superpixels in the process of feature learning, which leads to speckle noise suppression and distin-guishable features learned in latent space. The nodes are then identified as changed or unchanged classes via k -means clustering. Five real SAR datasets were used in comparative experiments. Up to 99.72% accuracy was achieved, which is superior to state-of-the-art methods that pay attention only to local information, thus, demonstrating the effectiveness and robustness of the proposed approach. |
| WOS关键词 | AUTOMATIC CHANGE DETECTION ; REMOTELY-SENSED IMAGES |
| 资助项目 | National Natural Science Foundation of China ; Natural Science Foundation of Chongqing ; Natural Environment Research Council ; [61301224] ; [cstc2021jcyj-msxmX0174] ; [NE/T004002/1] |
| WOS研究方向 | Physical Geography ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:000876743000002 |
| 出版者 | ELSEVIER |
| 资助机构 | National Natural Science Foundation of China ; Natural Science Foundation of Chongqing ; Natural Environment Research Council |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/186451]  |
| 专题 | 中国科学院地理科学与资源研究所 |
| 通讯作者 | Zhang, Xinzheng; Zhang, Ce |
| 作者单位 | 1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, 11A Datun Rd, Beijing 100101, Peoples R China 2.Chongqing Univ, Sch Microelect & Commun Engn, Chongqing 400044, Peoples R China 3.Chongqing Key Lab Space Informat Network & Intelli, Chongqing 400044, Peoples R China 4.Univ Lancaster, Lancaster Environm Ctr, Lancaster LA1 4YQ, Lancashire, United Kingdom 5.UK Ctr Ecol & Hydrol, Lib Ave, Lancaster LA1 4AP, Lancashire, United Kingdom 6.Univ Southampton, Geog & Environm Sci, Southampton SO17 1BJ, Hampshire, England |
| 推荐引用方式 GB/T 7714 | Su, Hang,Zhang, Xinzheng,Luo, Yuqing,et al. Nonlocal feature learning based on a variational graph auto-encoder network for small area change detection using SAR imagery[J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING,2022,193:137-149. |
| APA | Su, Hang,Zhang, Xinzheng,Luo, Yuqing,Zhang, Ce,Zhou, Xichuan,&Atkinson, Peter M..(2022).Nonlocal feature learning based on a variational graph auto-encoder network for small area change detection using SAR imagery.ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING,193,137-149. |
| MLA | Su, Hang,et al."Nonlocal feature learning based on a variational graph auto-encoder network for small area change detection using SAR imagery".ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 193(2022):137-149. |
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。