版权说明 操作指南
首页 > 成果 > 成果详情

DUCTNet: An Effective Road Crack Segmentation Method in UAV Remote Sensing Images Under Complex Scenes

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Sun, Lixiang;Yang, Yixin;Yang, Zaichun;Zhou, Guoxiong;Li, Liujun
通讯作者:
Zhou, GX
作者机构:
[Yang, Yixin; Sun, Lixiang; Zhou, Guoxiong; Yang, Zaichun] Cent South Univ Forestry & Technol, Coll Comp & Informat Engn, Changsha 410004, Peoples R China.
[Li, Liujun] Univ Idaho, Dept Soil & Water Syst, Moscow, ID 83844 USA.
通讯机构:
[Zhou, GX ] C
Cent South Univ Forestry & Technol, Coll Comp & Informat Engn, Changsha 410004, Peoples R China.
语种:
英文
关键词:
Feature extraction;Roads;Image segmentation;Data mining;Interference;Autonomous aerial vehicles;Training;Complex scenes;road crack segmentation;DUCTNet;DeepCFB;HDF-FAM;UAV remote sensing image
期刊:
IEEE Transactions on Intelligent Transportation Systems
ISSN:
1524-9050
年:
2024
卷:
25
期:
9
页码:
12682-12695
基金类别:
Scientific Research Project of Education Department of Hunan Province (Grant Number: 21A0179) Changsha Municipal Natural Science Foundation (Grant Number: kq2014160) 10.13039/501100004735-Natural Science Foundation of Hunan Province (Grant Number: 2021JJ41087) 10.13039/501100001809-Natural Science Foundation of China (Grant Number: 61902436) Hunan Key Laboratory of Intelligent Logistics Technology (Grant Number: 2019TP1015)
机构署名:
本校为第一且通讯机构
院系归属:
计算机与信息工程学院
摘要:
Road crack detection in complex scenarios is challenged by vehicles, traffic facilities, road printed signs and fine cracks. In order to better solve these problems, a novel dense nested depth U-shaped structure for crack image segmentation network named DUCTNet is proposed. Firstly, a depth dense nested structure is designed by combining the superior performance of the Unet $++$ dense nested structure and the deep nested structure of U2Net. This structure improves the ability of the model to extract crack features in depth. Second, a novel deep competitive fusion feature extraction block is p...

反馈

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

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com