版权说明 操作指南
首页 > 成果 > 详情

A pipeline defect trajectory tracking method based on the combination of prototype iterative correction and global dilated attention

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:
Cui, Wentao;Liu, Weihua;Zeng, Shan;Zhu, Chenwei;Chen, Liangyan;...
通讯作者:
Liu, WH
作者机构:
[Zhu, Chenwei; Chen, Liangyan; Liu, Weihua; Duan, Zhaoyan; Cui, Wentao] Wuhan Polytech Univ, Sch Elect & Elect Engn, 36 Huanhu Rd, Wuhan 430023, Hubei, Peoples R China.
[Zeng, Shan] Wuhan Polytech Univ, Sch Math & Comp Sci, 36 Huanhu Rd, Wuhan 430023, Hubei, Peoples R China.
通讯机构:
[Liu, WH ] W
Wuhan Polytech Univ, Sch Elect & Elect Engn, 36 Huanhu Rd, Wuhan 430023, Hubei, Peoples R China.
语种:
英文
关键词:
Pipeline defect;Multi-target tracking;Deep learning;Prototype learning;Global attention;Pipeline defect;Multi-target tracking;Deep learning;Prototype learning;Global attention;Pipeline defect;Multi-target tracking;Deep learning;Prototype learning;Global attention
期刊:
Measurement
ISSN:
0263-2241
年:
2026
卷:
257
页码:
118752
基金类别:
CRediT authorship contribution statement Wentao Cui: Writing – review & editing, Writing – original draft, Validation, Software, Investigation. Weihua Liu: Writing – review & editing, Supervision, Project administration. Shan Zeng: Project administration, acquisition. Chenwei Zhu: Writing – review & editing, Methodology. Liangyan Chen: Methodology. Zhaoyan Duan: Visualization, Investigation, Data curation.
机构署名:
本校为第一且通讯机构
院系归属:
电气与电子工程学院
数学与计算机学院
摘要:
In the industrial routine inspection process, accurately tracking pipeline defects is essential for ensuring safe operation. However, this accuracy is adversely affected by the complexity of pipeline internal environment, similarity in the appearance of different defects, and difference in the appearance of the same defect with the movement of the camera used. Herein, we present a novel model called global prototype tracking network (GP-Net), which integrates prototype learning, global attention, and global tracking to accurately track the defects. The proposed model mitigates the feature bias...

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