Vision-Based Multiscale Construction Object Detection under Limited Supervision

IF 4.6 2区 工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY Structural Control & Health Monitoring Pub Date : 2024-02-16 DOI:10.1155/2024/1032674
Yapeng Guo, Yang Xu, Hongtao Cui, Shunlong Li
{"title":"Vision-Based Multiscale Construction Object Detection under Limited Supervision","authors":"Yapeng Guo,&nbsp;Yang Xu,&nbsp;Hongtao Cui,&nbsp;Shunlong Li","doi":"10.1155/2024/1032674","DOIUrl":null,"url":null,"abstract":"<div>\n <p>Contemporary multiscale construction object detection algorithms rely predominantly on fully-supervised deep learning, requiring arduous and time-consuming labeling process. This paper presents a novel semisupervised multiscale construction objects detection (SS-MCOD) by harnessing nearly infinite unlabeled images along with limited labels, achieving more accurate and robust detection results. SS-MCOD uses a deformable convolutional network (DCN)-based teacher-student joint learning framework. DCN uses deformable advantages to extract and fuse multiscale construction object features. The teacher module generates pseudolabels for construction objects in unlabeled images, while the student module learns the location and classification of construction objects in both labeled images and unlabeled images with pseudolabels. Experimental validation using commonly used construction datasets demonstrates the accuracy and generalization performance of SS-MCOD. This research can provide insights for other detection tasks with limited labels in the construction domain.</p>\n </div>","PeriodicalId":49471,"journal":{"name":"Structural Control & Health Monitoring","volume":null,"pages":null},"PeriodicalIF":4.6000,"publicationDate":"2024-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/2024/1032674","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Structural Control & Health Monitoring","FirstCategoryId":"5","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1155/2024/1032674","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CONSTRUCTION & BUILDING TECHNOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Contemporary multiscale construction object detection algorithms rely predominantly on fully-supervised deep learning, requiring arduous and time-consuming labeling process. This paper presents a novel semisupervised multiscale construction objects detection (SS-MCOD) by harnessing nearly infinite unlabeled images along with limited labels, achieving more accurate and robust detection results. SS-MCOD uses a deformable convolutional network (DCN)-based teacher-student joint learning framework. DCN uses deformable advantages to extract and fuse multiscale construction object features. The teacher module generates pseudolabels for construction objects in unlabeled images, while the student module learns the location and classification of construction objects in both labeled images and unlabeled images with pseudolabels. Experimental validation using commonly used construction datasets demonstrates the accuracy and generalization performance of SS-MCOD. This research can provide insights for other detection tasks with limited labels in the construction domain.

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
有限监督下基于视觉的多尺度建筑物体检测
当代的多尺度建筑物体检测算法主要依赖于全监督深度学习,需要艰苦耗时的标记过程。本文提出了一种新颖的半监督多尺度建筑物体检测(SS-MCOD),利用近乎无限的无标签图像和有限的标签,实现更准确、更稳健的检测结果。SS-MCOD 采用基于可变形卷积网络(DCN)的师生联合学习框架。DCN 利用可变形优势提取和融合多尺度建筑物体特征。教师模块为未标记图像中的建筑物体生成伪标签,而学生模块则通过伪标签学习标记图像和未标记图像中建筑物体的位置和分类。使用常用建筑数据集进行的实验验证证明了 SS-MCOD 的准确性和泛化性能。这项研究可为建筑领域其他标签有限的检测任务提供启示。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Structural Control & Health Monitoring
Structural Control & Health Monitoring 工程技术-工程:土木
CiteScore
9.50
自引率
13.00%
发文量
234
审稿时长
8 months
期刊介绍: The Journal Structural Control and Health Monitoring encompasses all theoretical and technological aspects of structural control, structural health monitoring theory and smart materials and structures. The journal focuses on aerospace, civil, infrastructure and mechanical engineering applications. Original contributions based on analytical, computational and experimental methods are solicited in three main areas: monitoring, control, and smart materials and structures, covering subjects such as system identification, health monitoring, health diagnostics, multi-functional materials, signal processing, sensor technology, passive, active and semi active control schemes and implementations, shape memory alloys, piezoelectrics and mechatronics. Also of interest are actuator design, dynamic systems, dynamic stability, artificial intelligence tools, data acquisition, wireless communications, measurements, MEMS/NEMS sensors for local damage detection, optical fibre sensors for health monitoring, remote control of monitoring systems, sensor-logger combinations for mobile applications, corrosion sensors, scour indicators and experimental techniques.
期刊最新文献
Vision Transformer–Based Anomaly Detection Method for Offshore Platform Monitoring Data Investigation of the Mechanism of Hidden Defects in Epoxy Asphalt Pavement on Steel Bridge Decks Under Moisture Diffusion Using Nondestructive Detection Techniques Multidamage Detection of Breathing Cracks in Plate-Like Bridges: Experimental and Numerical Study Designing a Distributed Sensing Network for Structural Health Monitoring of Concrete Tunnels: A Case Study Detection of Delamination in Composite Laminate Using Mode Shape Processing Method and YOLOv8
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1