D-TNet: Category-Awareness Based Difference-Threshold Alternative Learning Network for Remote Sensing Image Change Detection
文献类型：期刊论文
| 作者 | Wan, Ling1,2 ; Tian, Ye1,2; Kang, Wenchao1,2; Ma, Lei1,2
|
| 刊名 | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
 |
| 出版日期 | 2022 |
| 卷号 | 60页码:16 |
| 关键词 | Feature extraction Task analysis Remote sensing Semantics Convolutional neural networks Deep learning Visualization Category-awareness change detection optical remote sensing image threshold learning |
| ISSN号 | 0196-2892 |
| DOI | 10.1109/TGRS.2022.3213925 |
| 通讯作者 | Ma, Lei(lei.ma@ia.ac.cn) |
| 英文摘要 | Deep-learning-based change detection methods have achieved remarkable success through the feature learning capability of deep convolutions. However, the network structures of existing methods are simply modified from the semantic segmentation models, ignoring the essential characteristics of change detection, thereby limiting their applications. In this work, we propose a category-awareness-based difference-threshold alternative-learning network (D-TNet) for remote sensing image change detection. Our motivation is to characterize the different change magnitudes for different land cover changes, and represent the semantic content differences of various objects. Thus, our D-TNet consists of a difference map (DM) learning path and a threshold map (TM) learning path, realizing self-adapting threshold selection by assigning each pixel a unique threshold. The two paths are alternatively optimized to make the DM more discriminative, as well as making the TM more adaptive. In addition, a category-awareness attention mechanism is introduced in D-TNet, which learns a pixel-to-category relationship to benefit in representing the heterogeneity of land covers. Finally, experimental results on three change detection datasets verify the effectiveness of our D-TNet in both visual and quantitative analyses. Code will be available at: https://www.researchgate.net/profile/Ling-Wan-4. |
| WOS关键词 | CHANGE VECTOR ANALYSIS ; FUSION NETWORK |
| 资助项目 | National Natural Science Foundation of China[62071466] ; National Natural Science Foundation of China[61901439] ; Fund of National Key Laboratory of Science and Technology on Remote Sensing Information and Imagery Analysis, Beijing Research Institute of Uranium Geology[6142A010402] ; Guangxi Natural Science Foundation[2018GXNSFBA281086] |
| WOS研究方向 | Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:000882005800005 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Natural Science Foundation of China ; Fund of National Key Laboratory of Science and Technology on Remote Sensing Information and Imagery Analysis, Beijing Research Institute of Uranium Geology ; Guangxi Natural Science Foundation |
| 源URL | [http://ir.ia.ac.cn/handle/173211/51242]  |
| 专题 | 类脑芯片与系统研究 |
| 通讯作者 | Ma, Lei |
| 作者单位 | 1.Univ Chinese Acad Sci, Beijing 100039, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wan, Ling,Tian, Ye,Kang, Wenchao,et al. D-TNet: Category-Awareness Based Difference-Threshold Alternative Learning Network for Remote Sensing Image Change Detection[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2022,60:16. |
| APA | Wan, Ling,Tian, Ye,Kang, Wenchao,&Ma, Lei.(2022).D-TNet: Category-Awareness Based Difference-Threshold Alternative Learning Network for Remote Sensing Image Change Detection.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,60,16. |
| MLA | Wan, Ling,et al."D-TNet: Category-Awareness Based Difference-Threshold Alternative Learning Network for Remote Sensing Image Change Detection".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 60(2022):16. |
入库方式： OAI收割
来源：自动化研究所
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。