HierU-Net: A Hierarchical Semantic Segmentation Method for Land Cover Mapping

首页 > 成果 > 详情

认领

导出

Link by DOI

反馈

作者信息关键词期刊信息基础信息归属信息摘要

成果类型：

期刊论文

作者：

Liu, Lanfa;Tong, Zichen;Cai, Zhanchuan;Wu, Hao;Zhang, Rongchun;...

通讯作者：

Cai, ZC

作者机构：

[Liu, Lanfa; Cai, Zhanchuan; Cai, ZC] Macau Univ Sci & Technol, State Key Lab Lunar & Planetary Sci, Macau, Peoples R China.

[Wu, Hao; Tong, Zichen; Liu, Lanfa] Cent China Normal Univ, Coll Urban & Environm Sci, Key Lab Geog Proc Anal & Simulat Hubei Prov, Wuhan 430079, Peoples R China.

[Cai, Zhanchuan; Cai, ZC] Macau Univ Sci & Technol, Sch Comp Sci & Engn, Macau, Peoples R China.

[Zhang, Rongchun] Nanjing Univ Posts & Telecommun, Coll Telecommun & Informat Engn, Sch Geog & Biol Informat, Nanjing 210023, Peoples R China.

[Olteanu-Raimond, Ana-Maria; Le Bris, Arnaud] Univ Gustave Eiffel, LASTIG, ENSG, IGN, F-94160 St Mande, France.

通讯机构：

[Cai, ZC ] M

Macau Univ Sci & Technol, State Key Lab Lunar & Planetary Sci, Macau, Peoples R China.

Macau Univ Sci & Technol, Sch Comp Sci & Engn, Macau, Peoples R China.

语种：

英文

关键词：

Land surface;Semantic segmentation;Task analysis;Remote sensing;Semantics;Training;Feature extraction;Hierarchical semantic segmentation;land cover mapping;U-Net;very high-resolution (VHR) imagery

期刊：

IEEE Transactions on Geoscience and Remote Sensing

ISSN：

0196-2892

年：

2024

卷：

页码：

1-14

DOI：

10.1109/TGRS.2024.3376432

基金类别：

National Natural Science Foundation of China#&#&#42271482#&#&#42101070#&#&#U23A2020 Knowledge Innovation Program of Wuhan-Shuguang Project#&#&#2022010801020284 International Science and Technology Cooperation Program of Hubei Province#&#&#2022EHB019 Macao Young Scholars Program#&#&#AM2022013 Science and Technology Development Fund of Macau#&#&#0059/2020/A2#&#&#0052/2020/AFJ Zhuhai Industry-University-Research Collaboration Program#&#&#ZH22017002210011PWC Fundamental Research Funds for the Central Universities#&#&#CCNU22QN018

机构署名：

本校为其他机构

院系归属：

城市与环境科学学院

摘要：

Land cover mapping is crucial for natural resource assessment, urban planning, and sustainable development. Land cover nomenclature often includes two or three hierarchical levels with tree-like hierarchical structures. This study aims to explore these hierarchical relationships and the potential of hierarchical semantic segmentation for land cover mapping. We propose a hierarchical semantic segmentation architecture by taking advantage of dual U-shaped network, named as HierU-Net. The coarse-level result is ingested to the fine-level segmentation functioned as soft constraints. The propagatio...

反馈

产权有误：本人成果被他人认领

数据有误：数据基本信息有误

归属有误：成果的院系归属、机构署名归属有误

其他原因：

验证码：

看不清楚，换一个

确定

取消

成果认领

标题：

用户	作者	通讯作者	--
	请选择	请选择	--

确定

取消

HierU-Net: A Hierarchical Semantic Segmentation Method for Land Cover Mapping

反馈

成果认领

提示

该栏目需要登录且有访问权限才可以访问