• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Ding, Lei (Ding, Lei.) | Lin, Dong (Lin, Dong.) | Lin, Shaofu (Lin, Shaofu.) | Zhang, Jing (Zhang, Jing.) | Cui, Xiaojie (Cui, Xiaojie.) | Wang, Yuebin (Wang, Yuebin.) | Tang, Hao (Tang, Hao.) | Bruzzone, Lorenzo (Bruzzone, Lorenzo.)

收录:

EI Scopus SCIE

摘要:

Long-range contextual information is crucial for the semantic segmentation of high-resolution (HR) remote sensing images (RSIs). However, image cropping operations, commonly used for training neural networks, limit the perception of long-range contexts in large RSIs. To overcome this limitation, we propose a wide-context network (WiCoNet) for the semantic segmentation of HR RSIs. Apart from extracting local features with a conventional convolutional neural network (CNN), the WiCoNet has an extra context branch to aggregate information from a larger image area. Moreover, we introduce a context transformer to embed contextual information from the context branch and selectively project it onto the local features. The context transformer extends the vision transformer, an emerging kind of neural networks, to model the dual-branch semantic correlations. It overcomes the locality limitation of CNNs and enables the WiCoNet to see the bigger picture before segmenting the land-cover/land-use (LCLU) classes. Ablation studies and comparative experiments conducted on several benchmark datasets demonstrate the effectiveness of the proposed method. In addition, we present a new Beijing Land-Use (BLU) dataset. This is a large-scale HR satellite dataset with high-quality and fine-grained reference labels, which can facilitate future studies in this field.

关键词:

vision transformer (ViT) Task analysis Transformers semantic segmentation Semantics Context modeling Convolutional neural networks Feature extraction Convolutional neural network Image segmentation remote sensing

作者机构:

  • [ 1 ] [Ding, Lei]PLA Strateg Force Informat Engn Univ, Zhengzhou 450001, Peoples R China
  • [ 2 ] [Lin, Dong]Space Engn Univ, Beijing 102249, Peoples R China
  • [ 3 ] [Lin, Dong]Xian Inst Surveying & Mapping, State Key Lab Geoinformat Engn, Xian 710054, Peoples R China
  • [ 4 ] [Lin, Shaofu]Beijing Univ Technol, Fac Informat Technol, Beijing 100022, Peoples R China
  • [ 5 ] [Zhang, Jing]Univ Trento, Dept Informat Engn & Comp Sci, I-38123 Trento, Italy
  • [ 6 ] [Bruzzone, Lorenzo]Univ Trento, Dept Informat Engn & Comp Sci, I-38123 Trento, Italy
  • [ 7 ] [Cui, Xiaojie]Beijing Inst Remote Sensing Informat, Beijing 100011, Peoples R China
  • [ 8 ] [Wang, Yuebin]China Univ Geosci Beijing, Sch Land Sci & Technol, Beijing 100084, Peoples R China
  • [ 9 ] [Tang, Hao]Swiss Fed Inst Technol, Dept Informat Technol & Elect Engn, CH-8092 Zurich, Switzerland

通讯作者信息:

查看成果更多字段

相关关键词:

相关文章:

来源 :

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING

ISSN: 0196-2892

年份: 2022

卷: 60

8 . 2

JCR@2022

8 . 2 0 0

JCR@2022

ESI学科: GEOSCIENCES;

ESI高被引阀值:38

JCR分区:1

中科院分区:1

被引次数:

WoS核心集被引频次:

SCOPUS被引频次:

ESI高被引论文在榜: 12 展开所有

  • 2024-11
  • 2024-11
  • 2024-9
  • 2024-9
  • 2024-7
  • 2024-5
  • 2024-3
  • 2024-1
  • 2023-11
  • 2023-9
  • 2023-7
  • 2023-5

万方被引频次:

中文被引频次:

近30日浏览量: 3

归属院系:

在线人数/总访问数:465/4940567
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司