Road Extraction Convolutional Neural Network with Embedded Attention Mechanism for Remote Sensing Imagery

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：

Shao, Shiwei;Xiao, Lixia;Lin, Liupeng;Ren, Chang;Tian, Jing

通讯作者：

Shao, SW

作者机构：

[Shao, Shiwei; Shao, SW] Cent China Normal Univ, Natl Res Ctr Cultural Ind, Wuhan 430056, Peoples R China.

[Shao, Shiwei; Shao, SW] Zhongzhi Software Technol Co Ltd, Wuhan 430013, Peoples R China.

[Xiao, Lixia] Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan 430079, Peoples R China.

[Xiao, Lixia] Wuhan Nat Resources & Planning Informat Ctr, Wuhan 430014, Peoples R China.

[Tian, Jing; Lin, Liupeng] Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Peoples R China.

通讯机构：

[Shao, SW ] C

Cent China Normal Univ, Natl Res Ctr Cultural Ind, Wuhan 430056, Peoples R China.

Zhongzhi Software Technol Co Ltd, Wuhan 430013, Peoples R China.

语种：

英文

关键词：

road extraction;U-Net;attention mechanism;residual densely connected blocks;dilated convolution

期刊：

Remote Sensing

ISSN：

2072-4292

年：

2022

卷：

期：

页码：

2061-

DOI：

10.3390/rs14092061

基金类别：

This research received no external funding.

机构署名：

本校为第一且通讯机构

院系归属：

国家文化产业研究中心

摘要：

Roads are closely related to people’s lives, and road network extraction has become one of the most important remote sensing tasks. This study aimed to propose a road extraction network with an embedded attention mechanism to solve the problem of automatic extraction of road networks from a large number of remote sensing images. Channel attention mechanism and spatial attention mechanism were introduced to enhance the use of spectral information and spatial information based on the U-Net framework. Moreover, residual densely connected blocks w...

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

Road Extraction Convolutional Neural Network with Embedded Attention Mechanism for Remote Sensing Imagery

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