中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 复杂系统认知与决策实验室
CLDRNet: A Difference Refinement Network Based on Category Context Learning 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 JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
出版日期2024
卷号17页码:2133-2148
ISSN号1939-1404
关键词Feature extraction Task analysis Remote sensing Transformers Deep learning Semantics Support vector machines Category context learning (CCL) clustering learning (CL) difference map refinement (DMR) optical remote sensing image change detection (CD)
DOI10.1109/JSTARS.2023.3327340
通讯作者Ma, Lei(lei.ma@ia.ac.cn)
英文摘要In recent years, change detection (CD) of optical remote sensing images has made remarkable progress through using deep learning. However, current CD deep learning methods are usually improved from the semantic segmentation models, and focus on enhancing the separability of changed and unchanged features. They ignore the essential characteristics of CD, i.e., different land cover changes exhibit different change magnitudes, resulting in limited accuracy and serious false alarms. To address this limitation, in this article, a category context learning-based difference refinement network (CLDRNet) based on our previous work is proposed. Considering the semantic content differences of heterogeneous land covers, a category context learning module is designed, which introduces a clustering learning procedure to generate an overall representation for each category, guiding the category context modeling. The clustering learning process is differentiable and can be integrated into the end-to-end trainable CD network, so it considers the semantic content differences from the CD perspective, thereby improving the CD performance. In addition, to address the magnitude differences of different land cover changes, a two-stage CD strategy is introduced. The two stages correspond to difference map learning and difference map refinement, aiming at ensuring high detection rates and revising false alarms, respectively. Finally, experimental results on three CD datasets verify the effectiveness of our CLDRNet in both visual and quantitative analysis.
WOS关键词CHANGE VECTOR ANALYSIS ; CLASSIFICATION
资助项目Research Funding of Satellite Information Intelligent Processing and Application Research Laboratory
WOS研究方向Engineering ; Physical Geography ; Remote Sensing ; Imaging Science & Photographic Technology
语种英语
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号WOS:001136788300007
资助机构Research Funding of Satellite Information Intelligent Processing and Application Research Laboratory
源URL[http://ir.ia.ac.cn/handle/173211/54777]  
专题复杂系统认知与决策实验室
通讯作者Ma, Lei
作者单位1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100039, Peoples R China
推荐引用方式
GB/T 7714		 Wan, Ling,Tian, Ye,Kang, Wenchao,et al. CLDRNet: A Difference Refinement Network Based on Category Context Learning for Remote Sensing Image Change Detection[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,2024,17:2133-2148.
APA Wan, Ling,Tian, Ye,Kang, Wenchao,&Ma, Lei.(2024).CLDRNet: A Difference Refinement Network Based on Category Context Learning for Remote Sensing Image Change Detection.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,17,2133-2148.
MLA Wan, Ling,et al."CLDRNet: A Difference Refinement Network Based on Category Context Learning for Remote Sensing Image Change Detection".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 17(2024):2133-2148.

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。