Article(id=1251893514771055168, tenantId=1146029695717560320, journalId=1251234473337991274, issueId=1251893504037831074, articleNumber=null, orderNo=null, doi=10.3969/j.issn.1003-3114.2025.05.013, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1745769600000, receivedDateStr=2025-04-28, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1776404272978, onlineDateStr=2026-04-17, pubDate=1758124800000, pubDateStr=2025-09-18, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1776404272978, onlineIssueDateStr=2026-04-17, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1776404272978, creator=13701087609, updateTime=1776404272978, updator=13701087609, issue=Issue{id=1251893504037831074, tenantId=1146029695717560320, journalId=1251234473337991274, year='2025', volume='51', issue='5', pageStart='877', pageEnd='1134', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1776404270419, creator=13701087609, updateTime=1776404832543, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1251895861849043019, tenantId=1146029695717560320, journalId=1251234473337991274, issueId=1251893504037831074, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1251895861849043020, tenantId=1146029695717560320, journalId=1251234473337991274, issueId=1251893504037831074, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1008, endPage=1015, ext={EN=ArticleExt(id=1251893516767543932, articleId=1251893514771055168, tenantId=1146029695717560320, journalId=1251234473337991274, language=EN, title=Detection Research of Dam Seepage Areas in Infrared Images Based on the Improved Mask R-CNN, columnId=1251893508886446519, journalTitle=Radio Communications Technology, columnName=Special Topic:Frontiers in Intelligent Communication, Storage, and Information Processing Technologies, runingTitle=null, highlight=null, articleAbstract=

Seepage monitoring is crucial for the safe operation and maintenance of dams. Traditional dam observation methods suffer from significant random errors and insufficient inspection frequency during flood seasons. To address these limitations, this study proposes an infrared thermography-based unmanned aerial vehicle inspection system for detecting surface seepage on dam bodies. First, an image dataset of seepage-affected areas on the dam surface was collected and established using an infrared camera. Then, an improved Mask Region-based Convolutional Neural Network(Mask R-CNN) framework was employed to extract seepage region data, enabling rapid detection of surface seepage. Subsequently, binary processing was applied to quantify the seepage area. Finally, the proposed method was validated on the downstream face of a hydropower station. Experimental results demonstrate that the proposed approach reduces the inspection cycle by 80% compared to traditional methods while maintaining sufficient accuracy for routine dam monitoring. This study provides a novel technique for seepage detection and quantitative analysis, offering a new solution for dam leakage inspection and seepage-related damage assessment.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Jiayi HUANG), CN=ArticleExt(id=1251893530617135225, articleId=1251893514771055168, tenantId=1146029695717560320, journalId=1251234473337991274, language=CN, title=基于改进Mask R-CNN的红外图像坝体渗水区域检测研究, columnId=1251893509079384505, journalTitle=无线电通信技术, columnName=专题:智能通信、存储与信息处理技术前沿, runingTitle=null, highlight=null, articleAbstract=

渗水病害监测是大坝安全运行及运维的重点。针对传统大坝观测方法偶然误差大、汛期检测频次无法满足要求等缺点,提出以无人机搭载红外测温相机对坝体表面进行渗水检测。通过红外相机采集坝体表面影像,建立渗水病害区域影像集,将Swin Transformer架构整合到基于区域掩码的卷积神经网络(Mask Region-based Convolutional Neural Network,Mask R-CNN)中,提升该掩码区域检测网络的性能,据此提取渗水区域数据,实现坝体表面渗水区域的快速检测。通过对渗水区域数据二值化处理,统计坝体表面渗水区域面积。以某电站下游坝面为试验对象,结果表明,该方法相比传统大坝观测方法,检测周期缩短80%,渗水区域检测准确率达97%,满足大坝日常观测需求,有效实现大坝渗漏水定量分析。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=yq0fZsFV+FOZ+CiuBDz1mw==, magXml=qWgz7nDkD75P/4t7eUccng==, pdfUrl=null, pdf=izzTDrkNAJSBKVRMuWBKog==, pdfFileSize=6598743, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=0OIsrHDt9V/Vigy+k9MPPA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=wH9YvMVzwWrYBkXJz4+rLQ==, mapNumber=null, authorCompany=null, fund=null, authors=

黄佳一 女,(1996—),工程师。主要研究方向:水利工程水工建筑物观测。

, authorsList=黄佳一)}, authors=[Author(id=1251895523221913968, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1251895524891246971, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, authorId=1251895523221913968, language=EN, stringName=Jiayi HUANG, firstName=Jiayi, middleName=null, lastName=HUANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Fujian Shuikou Power Generation Group Co , Ltd , Fuzhou 350004, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251895525004493186, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, authorId=1251895523221913968, language=CN, stringName=黄佳一, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=福建水口发电集团有限公司,福建 福州 350004, bio={"content":"

黄佳一 女,(1996—),工程师。主要研究方向:水利工程水工建筑物观测。

"}, bioImg=null, bioContent=

黄佳一 女,(1996—),工程师。主要研究方向:水利工程水工建筑物观测。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251895523129639273, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, xref=null, ext=[AuthorCompanyExt(id=1251895523133833578, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, companyId=1251895523129639273, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Fujian Shuikou Power Generation Group Co , Ltd , Fuzhou 350004, China), AuthorCompanyExt(id=1251895523142222187, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, companyId=1251895523129639273, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=福建水口发电集团有限公司,福建 福州 350004)])])], keywords=[Keyword(id=1251895525193236877, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=EN, orderNo=1, keyword=dam), Keyword(id=1251895525281317267, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=EN, orderNo=2, keyword=seepage feature extraction algorithm), Keyword(id=1251895525381980569, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=EN, orderNo=3, keyword=unmanned aerial vehicle photogrammetry), Keyword(id=1251895525512003999, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=EN, orderNo=4, keyword=DCNN), Keyword(id=1251895525600084390, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=EN, orderNo=5, keyword=seepage identification), Keyword(id=1251895525788828074, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=CN, orderNo=1, keyword=大坝), Keyword(id=1251895525889491376, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=CN, orderNo=2, keyword=渗水特征提取算法), Keyword(id=1251895525969183157, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=CN, orderNo=3, keyword=无人机摄影测量), Keyword(id=1251895526074040763, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=CN, orderNo=4, keyword=深度卷积神经网络), Keyword(id=1251895526157926845, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=CN, orderNo=5, keyword=渗水识别)], refs=[Reference(id=1251895530872324751, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2001, volume=null, issue=3, pageStart=9, pageEnd=12, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=方卫华, journalName=水利水文自动化, refType=null, unstructuredReference=方卫华.纵论大坝安全监测[J].水利水文自动化, 2001(3):9-12., articleTitle=纵论大坝安全监测, refAbstract=null), Reference(id=1251895530981376663, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2006, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=杨杰, journalName=大坝安全监控中若干不确定性问题的分析方法与应用研究, refType=null, unstructuredReference=杨杰.大坝安全监控中若干不确定性问题的分析方法与应用研究[D].南京:河海大学,2006., articleTitle=null, refAbstract=null), Reference(id=1251895531140760224, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2023, volume=7, issue=2, pageStart=58, pageEnd=62, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=王周萼, 王小波, 杜国平, journalName=长江技术经济, refType=null, unstructuredReference=王周萼,王小波,杜国平.基于声呐技术的霍林河水库大坝渗漏区分析[J].长江技术经济,2023,7(2):58-62., articleTitle=基于声呐技术的霍林河水库大坝渗漏区分析, refAbstract=null), Reference(id=1251895531224646309, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2025, volume=31, issue=7, pageStart=145, pageEnd=149, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=杭辉, journalName=水利科技与经济, refType=null, unstructuredReference=杭辉.地球物理计算在大坝渗漏检测中的应用[J].水利科技与经济,2025,31(7):145-149., articleTitle=地球物理计算在大坝渗漏检测中的应用, refAbstract=null), Reference(id=1251895531300143789, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2009, volume=25, issue=6, pageStart=38, pageEnd=42, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=陈文燕, 朱林, 王文韬, journalName=电力环境保护, refType=null, unstructuredReference=陈文燕,朱林,王文韬.大坝安全监测的现状与发展趋势[J].电力环境保护,2009,25(6):38-42., articleTitle=大坝安全监测的现状与发展趋势, refAbstract=null), Reference(id=1251895531388224180, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=6154, pageEnd=6162, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=CAI Z W, VASCONCELOS N, journalName=null, refType=null, unstructuredReference=CAI Z W,VASCONCELOS N. Cascade R-CNN:Delving into High Quality Object Detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City:IEEE,2018:6154-6162., articleTitle=Cascade R-CNN:Delving into High Quality Object Detection, refAbstract=null), Reference(id=1251895531463721657, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2023, volume=51, issue=3, pageStart=74, pageEnd=79, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=郭磊, 王洋, 靳正轩, journalName=毛纺科技, refType=null, unstructuredReference=郭磊,王洋,靳正轩,.基于改进Faster RCNN的化纤丝缺陷检测[J].毛纺科技,2023,51(3):74-79., articleTitle=基于改进Faster RCNN的化纤丝缺陷检测, refAbstract=null), Reference(id=1251895531564384962, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=83, pageEnd=89, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=CHERPANATH E D, NASREEN P R F, PRADEEP K, journalName=null, refType=null, unstructuredReference=CHERPANATH E D,NASREEN P R F,PRADEEP K, et al. Food Iage Rcognition and Calorie Prediction Using Faster R-CNN and Mask R-CNN[C]//2023 9th International Conference on Smart Computing and Communications (ICSCC). Kharagpur:IEEE,2023:83-89., articleTitle=Food Iage Rcognition and Calorie Prediction Using Faster R-CNN and Mask R-CNN, refAbstract=null), Reference(id=1251895531656659654, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2019, volume=32, issue=4, pageStart=103, pageEnd=105, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=汪宋, 费树岷, journalName=工业控制计算机, refType=null, unstructuredReference=汪宋,费树岷. SSD(Single Shot MultiBox Detector)目标检测算法的研究与改进[J].工业控制计算机,2019, 32(4):103-105., articleTitle=SSD(Single Shot MultiBox Detector)目标检测算法的研究与改进, refAbstract=null), Reference(id=1251895531816043213, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=7263, pageEnd=7271, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=REDMON J, FARHADI A, journalName=null, refType=null, unstructuredReference=REDMON J, FARHADI A. YOLO9000: Better, Faster, Stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu:IEEE,2017:7263-7271., articleTitle=YOLO9000: Better, Faster, Stronger, refAbstract=null), Reference(id=1251895531962843859, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=779, pageEnd=788, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=REDMON J, DIVVALA S, GIRSHICK R, journalName=null, refType=null, unstructuredReference=REDMON J,DIVVALA S,GIRSHICK R,et al. You Only Look Once:Unified,Real-time Object Detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas:IEEE,2016:779-788., articleTitle=You Only Look Once:Unified,Real-time Object Detection, refAbstract=null), Reference(id=1251895532050924249, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=6995, pageEnd=7003, url=null, language=null, rfNumber=[12], rfOrder=11, authorNames=ZHANG S S, YANG J, SCHIELE B, journalName=null, refType=null, unstructuredReference=ZHANG S S,YANG J,SCHIELE B. Occluded Pedestrian Detection Through Guided Attention in CNNs[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City:IEEE,2018:6995-7003., articleTitle=Occluded Pedestrian Detection Through Guided Attention in CNNs, refAbstract=null), Reference(id=1251895532113838813, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=9, pageStart=29, pageEnd=33, url=null, language=null, rfNumber=[13], rfOrder=12, authorNames=田有良, 樊廷立, 唐超, journalName=测绘通报, refType=null, unstructuredReference=田有良,樊廷立,唐超.面向地铁隧道表面渗漏水的快速检测技术[J].测绘通报,2022(9):29-33., articleTitle=面向地铁隧道表面渗漏水的快速检测技术, refAbstract=null), Reference(id=1251895532243862245, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=8, pageStart=34, pageEnd=39, url=null, language=null, rfNumber=[14], rfOrder=13, authorNames=周宝定, 谢沛瑶, 郭文浩, journalName=测绘通报, refType=null, unstructuredReference=周宝定,谢沛瑶,郭文浩,.基于激光点云灰度图像的隧道渗水病害检测[J].测绘通报,2023(8):34-39., articleTitle=基于激光点云灰度图像的隧道渗水病害检测, refAbstract=null), Reference(id=1251895533799949037, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2022, volume=12, issue=1, pageStart=11519, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=14, authorNames=LI J Q, HE Z Y, LI D X, journalName=Scientific Reports, refType=null, unstructuredReference=LI J Q,HE Z Y,LI D X,et al. Research on Water Seepage Detection Technology of Tunnel Asphalt Pavement Based on Deep Learning and Digital Image Processing[J]. Scientific Reports,2022,12(1):11519., articleTitle=Research on Water Seepage Detection Technology of Tunnel Asphalt Pavement Based on Deep Learning and Digital Image Processing, refAbstract=null), Reference(id=1251895533955138293, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2023, volume=13, issue=10, pageStart=6231, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=15, authorNames=ZHAO L, WANG J W, LIU S P, journalName=Applied Sciences, refType=null, unstructuredReference=ZHAO L,WANG J W,LIU S P,et al. An Adaptive Multitask Network for Detecting the Region of Water Leakage in Tunnels[J]. Applied Sciences,2023,13(10):6231., articleTitle=An Adaptive Multitask Network for Detecting the Region of Water Leakage in Tunnels, refAbstract=null), Reference(id=1251895534127104764, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=1, pageStart=70, pageEnd=73, url=null, language=null, rfNumber=[17], rfOrder=16, authorNames=肖翠翠, 远航, journalName=北方建筑, refType=null, unstructuredReference=肖翠翠,远航.基于红外热成像技术的建筑外墙渗漏及空鼓检测研究[J].北方建筑,2025(1):70-73., articleTitle=基于红外热成像技术的建筑外墙渗漏及空鼓检测研究, refAbstract=null), Reference(id=1251895534215185154, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2025-04-07, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=17, authorNames=朱自文, 宋晓鸥, 崔巍, journalName=计算机工程与应用, refType=null, unstructuredReference=朱自文,宋晓鸥,崔巍,.可见光-红外图像融合的目标检测综述[J/OL].计算机工程与应用(2025-03-21)[2025-04-07]. http://kns.cnki.net/kcms/detail/11.2127.TP.20250321.1453.006.html., articleTitle=可见光-红外图像融合的目标检测综述, refAbstract=null), Reference(id=1251895534303265545, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=2961, pageEnd=2969, url=null, language=null, rfNumber=[19], rfOrder=18, authorNames=HE K, GKIOXARI G, DOLLÁR P, journalName=null, refType=null, unstructuredReference=HE K, GKIOXARI G, DOLLÁR P, et al. Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision. Venice:IEEE,2017:2961-2969., articleTitle=Mask R-CNN, refAbstract=null), Reference(id=1251895534391345933, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=770, pageEnd=778, url=null, language=null, rfNumber=[20], rfOrder=19, authorNames=HE K M, ZHANG X Y, REN S Q, journalName=null, refType=null, unstructuredReference=HE K M, ZHANG X Y, REN S Q,et al. Deep Residual Learning for Image Recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas:IEEE,2016:770-778., articleTitle=Deep Residual Learning for Image Recognition, refAbstract=null), Reference(id=1251895534462649106, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=2117, pageEnd=2125, url=null, language=null, rfNumber=[21], rfOrder=20, authorNames=LIN T Y, DOLLÁR P, GIRSHICK R, journalName=null, refType=null, unstructuredReference=LIN T Y,DOLLÁR P,GIRSHICK R,et al. Feature Pyramid Networks for Object Detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu:IEEE,2017:2117-2125., articleTitle=Feature Pyramid Networks for Object Detection, refAbstract=null), Reference(id=1251895534554923800, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2016, volume=39, issue=6, pageStart=1137, pageEnd=1149, url=null, language=null, rfNumber=[22], rfOrder=21, authorNames=REN S Q, HE K M, GIRSHICK R, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=REN S Q,HE K M,GIRSHICK R,et al. Faster R-CNN:Towards Real-time Object Detection with Region Proposal Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,39(6):1137-1149., articleTitle=Faster R-CNN:Towards Real-time Object Detection with Region Proposal Networks, refAbstract=null), Reference(id=1251895534663975707, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=10012, pageEnd=10022, url=null, language=null, rfNumber=[23], rfOrder=22, authorNames=LIU Z, LIN Y T, CAO Y, journalName=null, refType=null, unstructuredReference=LIU Z,LIN Y T,CAO Y,et al. Swin Transformer:Hierarchical Vision Transformer Using Shifted Windows[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Montreal:IEEE,2021:10012-10022., articleTitle=Swin Transformer:Hierarchical Vision Transformer Using Shifted Windows, refAbstract=null), Reference(id=1251895534752056096, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2023, volume=49, issue=2, pageStart=216, pageEnd=230, url=null, language=null, rfNumber=[24], rfOrder=23, authorNames=马文轩, 蔡卓燃, 徐从安, journalName=无线电通信技术, refType=null, unstructuredReference=马文轩,蔡卓燃,徐从安,.基于深度学习的认知无线电调制参数估计[J].无线电通信技术,2023,49(2):216-230., articleTitle=基于深度学习的认知无线电调制参数估计, refAbstract=null), Reference(id=1251895534840136487, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=7132, pageEnd=7141, url=null, language=null, rfNumber=[25], rfOrder=24, authorNames=HU J, SHEN L, SUN G, journalName=null, refType=null, unstructuredReference=HU J,SHEN L,SUN G. Squeeze-and-excitation Networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018:7132-7141., articleTitle=Squeeze-and-excitation Networks, refAbstract=null), Reference(id=1251895534928216874, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=5998, pageEnd=6008, url=null, language=null, rfNumber=[26], rfOrder=25, authorNames=VASWANI A, SHAZEER N, PARMAR N, journalName=null, refType=null, unstructuredReference=VASWANI A,SHAZEER N,PARMAR N,et al. Attention Is All You Need[C]//Advances in Neural Information Processing Systems. Long Beach:Curran Associates,Inc, 2017:5998-6008., articleTitle=Attention Is All You Need, refAbstract=null), Reference(id=1251895535016297263, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=4, pageStart=82, pageEnd=93, url=null, language=null, rfNumber=[27], rfOrder=26, authorNames=陈池瑶, 苗世洪, 殷浩然, journalName=电力建设, refType=null, unstructuredReference=陈池瑶,苗世洪,殷浩然,.基于注意力机制-卷积神经网络的配电网单相接地故障选线方法[J].电力建设,2023,44(4):82-93., articleTitle=基于注意力机制-卷积神经网络的配电网单相接地故障选线方法, refAbstract=null), Reference(id=1251895535121154871, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2021, volume=47, issue=4, pageStart=513, pageEnd=518, url=null, language=null, rfNumber=[28], rfOrder=27, authorNames=张学军, 周云, 杜丹, journalName=无线电通信技术, refType=null, unstructuredReference=张学军,周云,杜丹,.基于多尺度注意力特征的识别算法研究[J].无线电通信技术,2021,47(4):513-518., articleTitle=基于多尺度注意力特征的识别算法研究, refAbstract=null), Reference(id=1251895535226012475, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2020, volume=146, issue=null, pageStart=760, pageEnd=768, url=null, language=null, rfNumber=[29], rfOrder=28, authorNames=KONG Z Q, TANG B P, DENG L, journalName=Renewable Energy, refType=null, unstructuredReference=KONG Z Q,TANG B P,DENG L,et al. Condition Monitoring of Wind Turbines Based on Spatio-temporal Fusion of SCADA Data by Convolutional Neural Networks and Gated Recurrent Units[J]. Renewable Energy,2020,146:760-768., articleTitle=Condition Monitoring of Wind Turbines Based on Spatio-temporal Fusion of SCADA Data by Convolutional Neural Networks and Gated Recurrent Units, refAbstract=null), Reference(id=1251895535318287169, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=增刊2, pageStart=140, pageEnd=144, url=null, language=null, rfNumber=[30], rfOrder=29, authorNames=朱林川, 黄声享, 张赛, journalName=测绘通报, refType=null, unstructuredReference=朱林川,黄声享,张赛,,一种基于点云的隧道渗漏检测方法[J].测绘通报,2021(增刊2):140-144., articleTitle=一种基于点云的隧道渗漏检测方法, refAbstract=null), Reference(id=1251895535389590341, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=13906, pageEnd=13915, url=null, language=null, rfNumber=[31], rfOrder=30, authorNames=LEE Y W, PARK J, journalName=null, refType=null, unstructuredReference=LEE Y W,PARK J. CenterMask:Real-time Anchor-free Instance Segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle:IEEE,2020:13906-13915., articleTitle=CenterMask:Real-time Anchor-free Instance Segmentation, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1251895523129639273, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, xref=null, ext=[AuthorCompanyExt(id=1251895523133833578, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, companyId=1251895523129639273, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Fujian Shuikou Power Generation Group Co , Ltd , Fuzhou 350004, China), AuthorCompanyExt(id=1251895523142222187, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, companyId=1251895523129639273, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=福建水口发电集团有限公司,福建 福州 350004)])], figs=[ArticleFig(id=1251895526371836360, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=EN, label=Fig. 1, caption=Data processing flowchart, figureFileSmall=1iNTj9OcN2wNwZsSGQJJog==, figureFileBig=0OIsrHDt9V/Vigy+k9MPPA==, tableContent=null), ArticleFig(id=1251895526493471182, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=CN, label=图1, caption=数据处理流程, figureFileSmall=1iNTj9OcN2wNwZsSGQJJog==, figureFileBig=0OIsrHDt9V/Vigy+k9MPPA==, tableContent=null), ArticleFig(id=1251895526594134484, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=EN, label=Fig. 2, caption=Mask R-CNN algorithm model structure, figureFileSmall=E8ksorBjXxC69j640Ia2kA==, figureFileBig=hjbtRheHkh5dbmsb2vXZEA==, tableContent=null), ArticleFig(id=1251895526686409179, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=CN, label=图2, caption=Mask R-CNN算法模型结构, figureFileSmall=E8ksorBjXxC69j640Ia2kA==, figureFileBig=hjbtRheHkh5dbmsb2vXZEA==, tableContent=null), ArticleFig(id=1251895526761906657, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=EN, label=Fig. 3, caption=Improved structure of Mask R-CNN algorithm, figureFileSmall=SyzLzWo8QYLEPUbU6Ko/6w==, figureFileBig=FPBuM/e1zyqA2Uc0O1IUvg==, tableContent=null), ArticleFig(id=1251895526858375655, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=CN, label=图3, caption=改进的Mask R-CNN算法结构, figureFileSmall=SyzLzWo8QYLEPUbU6Ko/6w==, figureFileBig=FPBuM/e1zyqA2Uc0O1IUvg==, tableContent=null), ArticleFig(id=1251895526942261741, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=EN, label=Fig. 4, caption=Swin Transformer algorithm model structure, figureFileSmall=PSlJVaCWuZXrwWeGTBWdJQ==, figureFileBig=vjb1d8Ax37Z1phl3FhHiWw==, tableContent=null), ArticleFig(id=1251895527059702261, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=CN, label=图4, caption=Swin Transformer算法模型结构, figureFileSmall=PSlJVaCWuZXrwWeGTBWdJQ==, figureFileBig=vjb1d8Ax37Z1phl3FhHiWw==, tableContent=null), ArticleFig(id=1251895527147782652, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=EN, label=Fig. 5, caption=Structure of two consecutive Swin Transformer Blocks, figureFileSmall=xa5RxmbAyOPxUJerN6ujPg==, figureFileBig=+ThM3vaah+QK9Morlo17DQ==, tableContent=null), ArticleFig(id=1251895527248445957, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=CN, label=图5, caption=2个连续的Swin Transformer Block结构, figureFileSmall=xa5RxmbAyOPxUJerN6ujPg==, figureFileBig=+ThM3vaah+QK9Morlo17DQ==, tableContent=null), ArticleFig(id=1251895527361692179, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=EN, label=Fig. 6, caption=FPN network structure, figureFileSmall=QNuempLjsXj44CflDU8u/w==, figureFileBig=yRntum8Kg+xOtRaXJ1aJCg==, tableContent=null), ArticleFig(id=1251895527470744088, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=CN, label=图6, caption=FPN网络结构, figureFileSmall=QNuempLjsXj44CflDU8u/w==, figureFileBig=yRntum8Kg+xOtRaXJ1aJCg==, tableContent=null), ArticleFig(id=1251895527575601693, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=EN, label=Fig. 7, caption=Architecture of SENet attention network, figureFileSmall=NJntpufzddQyRQw7BLW2YQ==, figureFileBig=BF9lp4FwzNGuZWPiOYZ1gg==, tableContent=null), ArticleFig(id=1251895527676264997, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=CN, label=图7, caption=SENet注意力机制网络结构, figureFileSmall=NJntpufzddQyRQw7BLW2YQ==, figureFileBig=BF9lp4FwzNGuZWPiOYZ1gg==, tableContent=null), ArticleFig(id=1251895527768539690, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=EN, label=Fig. 8, caption=Rapid estimation of seepage area based on binarized images, figureFileSmall=CdFHPo/lJgsfga3v6zoWBQ==, figureFileBig=CxupV4fwCVVX+2ppEz5EoQ==, tableContent=null), ArticleFig(id=1251895529349792308, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=CN, label=图8, caption=基于二值化图像的渗水面积快速统计, figureFileSmall=CdFHPo/lJgsfga3v6zoWBQ==, figureFileBig=CxupV4fwCVVX+2ppEz5EoQ==, tableContent=null), ArticleFig(id=1251895529492398654, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=EN, label=Fig. 9, caption=Overlay of seepage statistics for left and right dam sections, figureFileSmall=j0yNS+immEe74eJQYkN52w==, figureFileBig=mBvwCMqFeau0h4jVgB0QJQ==, tableContent=null), ArticleFig(id=1251895529622422089, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=CN, label=图9, caption=左、右岸坝段渗水统计叠加, figureFileSmall=j0yNS+immEe74eJQYkN52w==, figureFileBig=mBvwCMqFeau0h4jVgB0QJQ==, tableContent=null), ArticleFig(id=1251895529819554391, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=EN, label=Fig. 10, caption=Results of water seepage analyses, figureFileSmall=ZPayZXol13+sT3r+2ikwbA==, figureFileBig=G6V1DZ/p9+RoGwXOZtElYQ==, tableContent=null), ArticleFig(id=1251895529924411999, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=CN, label=图10, caption=渗漏水分析结果, figureFileSmall=ZPayZXol13+sT3r+2ikwbA==, figureFileBig=G6V1DZ/p9+RoGwXOZtElYQ==, tableContent=null), ArticleFig(id=1251895530037658215, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=EN, label=Tab. 1, caption=

Model training parameter settings

, figureFileSmall=null, figureFileBig=null, tableContent=
序号参数类型参数值
1权重衰减值0.005
2学习率0.000 1
3Epoch值100
4学习率调度流程策略Step
5预热起始学习率0.000 1
6预热策略Linear
7预热迭代次数100
8衰减学习率起回合数50
9衰减学习率止回合数100
), ArticleFig(id=1251895530155098734, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=CN, label=表1, caption=

模型训练参数设置

, figureFileSmall=null, figureFileBig=null, tableContent=
序号参数类型参数值
1权重衰减值0.005
2学习率0.000 1
3Epoch值100
4学习率调度流程策略Step
5预热起始学习率0.000 1
6预热策略Linear
7预热迭代次数100
8衰减学习率起回合数50
9衰减学习率止回合数100
), ArticleFig(id=1251895530259956338, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=EN, label=Tab. 2, caption=

Training results of different models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型准确率召回率APmAP
Mask R-CNN0.9420.856 00.916 00.916 0
CenterMask0.9630.887 00.952 00.959 0
改进后的Mask R-CNN0.9700.897 50.973 70.973 7
), ArticleFig(id=1251895530385785467, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=CN, label=表2, caption=

不同模型的训练结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模型准确率召回率APmAP
Mask R-CNN0.9420.856 00.916 00.916 0
CenterMask0.9630.887 00.952 00.959 0
改进后的Mask R-CNN0.9700.897 50.973 70.973 7
), ArticleFig(id=1251895530490643070, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=EN, label=Tab. 3, caption=

Comparison of complexities

, figureFileSmall=null, figureFileBig=null, tableContent=
模型参数量/M每秒帧率/(帧/秒)
Mask R-CNN(ResNet50)445~8
CenterMask3412~15
改进后的Mask R-CNN603~6
), ArticleFig(id=1251895530591306371, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893514771055168, language=CN, label=表3, caption=

复杂度比较

, figureFileSmall=null, figureFileBig=null, tableContent=
模型参数量/M每秒帧率/(帧/秒)
Mask R-CNN(ResNet50)445~8
CenterMask3412~15
改进后的Mask R-CNN603~6
)], attaches=null, journal=Journal(id=1251231494887223395, delFlag=0, nameCn=无线电通信技术, nameEn=Radio Communications Technology, nameHistory1=null, nameHistory2=null, issn=1003-3114, eissn=, cn=13-1099/TN, coden=null, periodic=1, language=CN, oaType=1, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=, officePhone=, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=veWCdfK9mJVXm/uFgI4wQA==, journalPrice=null, startedYear=null, abbrevIsoEn=Radio Communications Technology, journalRemark=null, publicationField=null, createdTime=1776246435141, updatedTime=1776397604574, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=R, firstLetterEn=R, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=veWCdfK9mJVXm/uFgI4wQA==, picEn=OSQVHuARoHUd1TQ4ONLQrQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1251865545604285354, language=CN, name=无线电通信技术, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1776397604609, updatedTime=1776397604609, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://wxdt.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://wxdt.cbpt.cnki.net/index.aspx?t=3, submissionReviewUrl=https://wxdt.cbpt.cnki.net/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1251865545646228395, language=EN, name=Radio Communications Technology, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1776397604619, updatedTime=1776397604619, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://wxdt.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://wxdt.cbpt.cnki.net/index.aspx?t=3, submissionReviewUrl=https://wxdt.cbpt.cnki.net/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1251234473337991274, websiteList=[Website(id=1251257283515203650, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1251234473337991274, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/wxdtxjs/CN, language=CN, createTime=1776252583627, createBy=18614031015, updateTime=1776253691546, updateBy=18614031015, name=无线电通信技术-中文, tplId=1146099689490845704, title=无线电通信技术, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1251262047678313076, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283515203650, code=articleTextType, value=kx, createTime=1776253719491, updateTime=1776253719491, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262047653147249, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283515203650, code=banner, value=null, createTime=1776253719485, updateTime=1776253719485, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262047707673207, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283515203650, code=grayFlag, value=0, createTime=1776253719498, updateTime=1776253719498, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262047644758640, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283515203650, code=logo, value=https://castjournals.cast.org.cn/joweb/wxdtxjs/CN/file/pic?fileId=sk5LMh+QbAm+98l18HjovQ==, createTime=1776253719483, updateTime=1776253719483, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262047720256121, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283515203650, code=minRunFlag, value=0, createTime=1776253719501, updateTime=1776253719501, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262047669924467, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283515203650, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/wxdtxjs/CN/file/pic, createTime=1776253719489, updateTime=1776253719489, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262047716061816, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283515203650, code=silenceFlag, value=0, createTime=1776253719500, updateTime=1776253719500, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262047661535858, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283515203650, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1776253719487, updateTime=1776253719487, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262047682507381, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283515203650, code=themeColor, value=null, createTime=1776253719492, updateTime=1776253719492, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262047690895990, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283515203650, code=themeStyle, value=null, createTime=1776253719494, updateTime=1776253719494, creator=18614031015, updator=18614031015)]), Website(id=1251257283607478339, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1251234473337991274, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/wxdtxjs/EN, language=EN, createTime=1776252583648, createBy=18614031015, updateTime=1776253687916, updateBy=18614031015, name=无线电通信技术-英文, tplId=1146101810881728533, title=Radio Communications Technology, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1251262071707484468, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283607478339, code=articleTextType, value=kx, createTime=1776253725220, updateTime=1776253725220, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262071690707249, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283607478339, code=banner, value=null, createTime=1776253725216, updateTime=1776253725216, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262071724261687, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283607478339, code=grayFlag, value=0, createTime=1776253725224, updateTime=1776253725224, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262071682318640, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283607478339, code=logo, value=https://castjournals.cast.org.cn/joweb/wxdtxjs/EN/file/pic?fileId=sk5LMh+QbAm+98l18HjovQ==, createTime=1776253725214, updateTime=1776253725214, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262071732650297, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283607478339, code=minRunFlag, value=0, createTime=1776253725226, updateTime=1776253725226, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262071703290163, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283607478339, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/wxdtxjs/EN/file/pic, createTime=1776253725219, updateTime=1776253725219, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262071728455992, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283607478339, code=silenceFlag, value=0, createTime=1776253725225, updateTime=1776253725225, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262071694901554, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283607478339, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1776253725217, updateTime=1776253725217, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262071711678773, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283607478339, code=themeColor, value=null, createTime=1776253725221, updateTime=1776253725221, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262071720067382, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283607478339, code=themeStyle, value=null, createTime=1776253725223, updateTime=1776253725223, creator=18614031015, updator=18614031015)])], journalTitle=无线电通信技术, weixinUrl=null, journalUrl=https://wxdt.cbpt.cnki.net/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Radio Communications Technology, journalPhotoCn=veWCdfK9mJVXm/uFgI4wQA==, journalPhotoEn=OSQVHuARoHUd1TQ4ONLQrQ==, journalFirstLetter=R, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/wxdtxjs/CN/10.3969/j.issn.1003-3114.2025.05.013, detailUrlEn=https://castjournals.cast.org.cn/joweb/wxdtxjs/EN/10.3969/j.issn.1003-3114.2025.05.013, pdfUrlCn=https://castjournals.cast.org.cn/joweb/wxdtxjs/CN/PDF/10.3969/j.issn.1003-3114.2025.05.013, pdfUrlEn=https://castjournals.cast.org.cn/joweb/wxdtxjs/EN/PDF/10.3969/j.issn.1003-3114.2025.05.013, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于改进Mask R-CNN的红外图像坝体渗水区域检测研究
收藏切换
PDF下载
黄佳一
无线电通信技术 | 专题:智能通信、存储与信息处理技术前沿 2025,51(5): 1008-1015
收起
收藏切换
无线电通信技术 | 专题:智能通信、存储与信息处理技术前沿 2025, 51(5): 1008-1015
基于改进Mask R-CNN的红外图像坝体渗水区域检测研究
全屏
黄佳一
作者信息
  • 福建水口发电集团有限公司,福建 福州 350004
  • 黄佳一 女,(1996—),工程师。主要研究方向:水利工程水工建筑物观测。

Detection Research of Dam Seepage Areas in Infrared Images Based on the Improved Mask R-CNN
Jiayi HUANG
Affiliations
  • Fujian Shuikou Power Generation Group Co , Ltd , Fuzhou 350004, China
出版时间: 2025-09-18 doi: 10.3969/j.issn.1003-3114.2025.05.013
文章导航
收藏切换

渗水病害监测是大坝安全运行及运维的重点。针对传统大坝观测方法偶然误差大、汛期检测频次无法满足要求等缺点,提出以无人机搭载红外测温相机对坝体表面进行渗水检测。通过红外相机采集坝体表面影像,建立渗水病害区域影像集,将Swin Transformer架构整合到基于区域掩码的卷积神经网络(Mask Region-based Convolutional Neural Network,Mask R-CNN)中,提升该掩码区域检测网络的性能,据此提取渗水区域数据,实现坝体表面渗水区域的快速检测。通过对渗水区域数据二值化处理,统计坝体表面渗水区域面积。以某电站下游坝面为试验对象,结果表明,该方法相比传统大坝观测方法,检测周期缩短80%,渗水区域检测准确率达97%,满足大坝日常观测需求,有效实现大坝渗漏水定量分析。

大坝  /  渗水特征提取算法  /  无人机摄影测量  /  深度卷积神经网络  /  渗水识别

Seepage monitoring is crucial for the safe operation and maintenance of dams. Traditional dam observation methods suffer from significant random errors and insufficient inspection frequency during flood seasons. To address these limitations, this study proposes an infrared thermography-based unmanned aerial vehicle inspection system for detecting surface seepage on dam bodies. First, an image dataset of seepage-affected areas on the dam surface was collected and established using an infrared camera. Then, an improved Mask Region-based Convolutional Neural Network(Mask R-CNN) framework was employed to extract seepage region data, enabling rapid detection of surface seepage. Subsequently, binary processing was applied to quantify the seepage area. Finally, the proposed method was validated on the downstream face of a hydropower station. Experimental results demonstrate that the proposed approach reduces the inspection cycle by 80% compared to traditional methods while maintaining sufficient accuracy for routine dam monitoring. This study provides a novel technique for seepage detection and quantitative analysis, offering a new solution for dam leakage inspection and seepage-related damage assessment.

dam  /  seepage feature extraction algorithm  /  unmanned aerial vehicle photogrammetry  /  DCNN  /  seepage identification
黄佳一. 基于改进Mask R-CNN的红外图像坝体渗水区域检测研究. 无线电通信技术, 2025 , 51 (5) : 1008 -1015 . DOI: 10.3969/j.issn.1003-3114.2025.05.013
Jiayi HUANG. Detection Research of Dam Seepage Areas in Infrared Images Based on the Improved Mask R-CNN[J]. Radio Communications Technology, 2025 , 51 (5) : 1008 -1015 . DOI: 10.3969/j.issn.1003-3114.2025.05.013
大坝是调控水资源和防洪的关键工程,但其安全运行面临严峻挑战。我国2008年数据显示,大中型水库大坝安全达标率仅为64.1%,病险水库占比高达36%,其中小型水库问题尤为突出[1-2]。渗漏作为大坝主要病害之一,不仅影响工程效益,更可能引发溃坝风险[3-4]。为此,国家能源局提出建设智能化监测系统,加强人工智能在病害识别中的应用,以提升大坝安全水平。深入研究渗漏探测技术与评价方法对保障大坝安全具有重要意义。
传统的大坝渗水检测主要依赖人工目测法,这种方法虽然操作简单,但在实际应用中存在诸多局限性。一方面,该方法高度依赖监测人员的技术经验与操作熟练度,导致检测质量存在较大差异;另一方面,手动测量过程容易引入人为误差,显著影响监测数据的可靠性[5]
近年来,目标检测技术在工程病害识别领域得到广泛应用,主要分为2类典型方法:以R-CNN[6]、Fast R-CNN[7]和Faster R-CNN[8]为代表的双阶段神经网络,以及以单次检测多框探测器[9]和单次检测器系列[10-12]为代表的单阶段神经网络。在渗水检测方面,田有良等[13]开发了一种基于Mask R-CNN的移动扫描检测系统,结合深度学习与三维激光扫描技术,提升了识别精度和效率,但硬件成本较高。Mask R-CNN模型实现了渗水区域的快速定位,但检测精度仍有提升空间[14]。Li等[15]提出了一种融合EfficientNet深度学习模型与灰度阈值分割的水迹识别算法,提取了渗水特征,但传统图像预处理步骤增加了计算复杂度。针对复杂环境下渗漏检测的挑战,研究人员构建了一种多级Transformer编码器与自适应多任务解码器结合的渗水分割模型[16],解决了湿渍区域边缘模糊的难题,但较高的计算开销影响了实时性能。
针对上述问题,本文面向大坝日常观测的需求,创新性地提出一套基于无人机红外热成像坝体表面渗水检测的统计算法。利用无人机搭载红外测温相机构建坝体表面渗水病害影像数据库,采用改进的Mask R-CNN深度学习方法,实现渗水区域的智能识别与数据提取,再通过图像二值化处理定量计算渗水区域面积。以某电站下游坝面为试验对象进行实验,结果表明该方法较传统观测方式检测效率提升80%,同时达到97%的渗水区域检测准确率,满足大坝日常监测精度要求,为渗漏检测和病害定量分析提供了高效可靠的技术手段。
渗流区域的温度特征呈现显著的环境依赖性:在日照条件下,渗水部位因蒸发冷却效应形成明显的低温异常区;而在无光照环境中,由于水分的热容特性及蒸发减缓,该区域反而表现出相对高温特征。这种现象为红外热成像检测提供了物理依据[17]
本文采用DJI Mavic 3T无人机进行数据采集,其搭载的DFOV为61°,等效焦距40 mm,红外相机分辨率为640 pixel×512 pixel,搭配实时动态差分定位模块及额外惯导单元。红外图像采集覆盖整个研究区,且图像在左右岸方向及垂直高度方向的重叠度均大于90%,经过拼接、重采样后得到分辨率为640 pixel×1 024 pixel的坝体表面红外影像数据集。
首先,对坝体表面影像集基于温度值进行增强、去噪处理。突出温度异常区域,如渗水导致的低温区,并消除环境干扰,如日照反射等。
其次,通过摄影测量技术拼接生成红外图像点云。红外图像是通过捕捉物体自身辐射出的红外光波生成图像,受环境变化的影响较小,即使在恶劣条件下也能有效捕获目标的位置和轮廓信息,缺点是细节纹理信息丢失严重,空间分辨率低[18]。通过红外热像仪来采集目标物体的表面温度分布信息,并将其与三维空间坐标系统一融合,同时保留物体的几何形貌和热特征,实现温度场在三维空间中的精准定位及热异常区域的空间量化分析。
然后,经过控制测量、点云重投影、数字微分纠正、灰度赋值、锐化增强,将原始红外图像完整地投影至大坝工程平面坐标,得到高精度的大坝表面红外灰度图像。综合实验目的与硬件条件,采用1 024 pixel×1 024 pixel分割完整坝体表面影像得到大坝渗水病害数据集与镶嵌线,对数据集进行筛选和检查,再细分为训练集、验证集和测试集。
最后,由于坝体表面渗水病害的温度值与正常混凝土表面有区别,使用多边形图像标注工具对测试集的坝体表面渗水区域影像进行手动标注,制作语义分割数据集。数据处理流程如图1所示。
本文采用改进Mask R-CNN模型,旨在精准定位红外灰度图像中的渗水位置,实现坝体表面渗水病害的高效识别。作为语义分割领域的代表性算法,Mask R-CNN框架[19]实现了多任务协同处理能力,包括目标分类、边界框回归和像素级语义分割,其结构如图2所示。首先,待处理图像由残差网络(Residual Network,ResNet)[20]和特征金字塔网络(Feature Pyramid Network,FPN)[21]共同实现特征提取,由此生成若干特征图。然后,通过区域建议网络(Region Proposal Network,RPN)对输出的若干特征图进行处理,进而提取出目标候选框[22]。最后,目标候选框经过感兴趣区域对齐层(RoI Align)处理后,通过分支网络处理后得到渗水区域分类、边框及分割结果[19]
经过测试,坝体红外灰度图像经过FPN多层卷积以及池化后,出现少许细小的渗水特征被忽视,且一些其他部件被识别为渗水特征的情况。因此,本文将ResNet网络替换为Swin Transformer[23-24]主干网络,在最终特征层后引入挤压激励网络(Squeezeand-Excitation Network,SENet)模块,采用Transformer CNN替代原有结构,通过图像分割和特征划分弥补了Mask R-CNN的不足。该改进利用多头自注意力机制增强渗水区域像素权重,显著降低误检率,同时保持像素间关联性,完整保留渗水区域边缘特征,为后续渗水面积统计奠定基础。而最后一个特征层后面加入的SENet模块[25]本质上是提取通道特征,把注意力放在有效的通道信息上,不重要的特征就会被忽略掉,进一步提升了分割的准确性。具体改进算法结构如图3所示。
Swin Transformer算法模型结构如图4所示。首先,图像分块模块和线性嵌入层将输入的坝体表面图片进行分块处理,采用4 pixel×4 pixel块划分策略,沿深度方向展开以增加图像维度。然后,块合并层执行下采样操作,生成多尺度特征图。最后,Swin Trans former Block含有2个结构,如图5所示,分别使用基于窗口的多头自注意力(Window-based Multi-head Self-Attention,W-MSA)和基于滑动窗口的多头自注意力(Shifted Window-based Multi-head Self-Attention,SW-MSA),二者配对使用实现特征处理。
W-MSA和SW-MSA采用窗口划分策略处理输入图像,通过局部区域内的注意力计算增强特征提取能力。该方法利用多头注意力机制[26]突出渗水区域像素的显著性,抑制背景干扰信息,从而提升模型对关键特征的识别精度并降低误判率。
对于每个窗口Xw,通过线性变换生成Q/W/V矩阵,假设使用H个注意力头,每个头的维度是dh=d/H,计算为:
式中:为学习权重矩阵,用于生成查询、键、值;表示窗口内第h个头的W/K/V矩阵。通过式(1)能够将输入特征映射到不同语义空间(Q/K/V),捕捉不同角度的特征关系。
计算窗口内所有像素的注意力权重,并加权求和值特征,计算为:
式中:用于计算窗口中每个像素对其他像素的相似度;为缩放因子,防止点积过大导致梯度不稳定;softmax将相似度归一化为注意力权重;用注意力权重加权聚合值特征。
通过式(2)捕捉窗口内的局部上下文信息,例如渗水或物体局部结构。对多头注意力的输出采用拼接方式处理,并通过线性计算与变换融合:
式中:=Attention),表示第h个头的输出;Wo为可学习的输出投影矩阵;Concat用于拼接所有头的输出。通过融合不同注意力头学到的多样化特征,增强表达能力。
在注意力得分中加入相对位置偏置B,提升对空间位置关系的建模,计算为:
式中:B表示可学习的相对位置偏置矩阵,用于编码像素的相对位置。
以Swin Transformer充当主干网络,在4个阶段依次生成原图尺寸的1/4、1/8、1/16和1/32的特征图{C1C2C3C4},随后通过FPN对如上特征图进行特征融合得到新一轮的特征图{P1P2P3}。FPN具体网络结构如图6所示。
标准化处理由Bn()完成,激活函数采用ReLU(),上采样操作UpSample()将特征图放大2倍,而Conv()则实现3×3卷积运算。
通过卷积平滑和上采样处理后的特征图{P2P3C4},其尺寸最终与仅进行卷积平滑操作的P1特征图保持一致。随后通过通道{P1P2P3C4}拼接生成特征图F,最终输入至SENet模块,计算为:
注意力机制是一种受人类认知机制启发的关键信息筛选方法[27-28],其核心优势在于赋予模型自适应调整关注区域的能力,通过动态权重分配策略[29],引导模型聚焦于输入数据中的关键特征。
本文引入SENet注意力机制,其网络结构图如图7所示。SENet的创新点在于引入了一种由挤压和激励操作2个关键部分组成的轻量化注意力模块。
在挤压阶段,对输入的特征图进行全局平均池化,以压缩通道维度,即输入形状为(CHW)的特征图FHW分别是高度和宽度,C是通道数。该网络采用全局平均池化获得(C,1,1)维度的通道描述符,这些描述符编码了各通道的全局统计特性,使模型能够理解不同通道的重要性,降维特征向量可计算为:
式中:zcFsquc)为第c通道中的降维特征向量,uc为输入矩阵,ij为输入矩阵的行和列。
在激励过程中,系统先对特征张量进行全连接降维,再施加ReLU和Sigmoid函数变换,从而自动学习通道间的相关性权重:
式中:δ为ReLU激活函数,σ为Sigmoid激活函数,W1(·)、W2(·)为全连接层操作,z为所有通道zc拼成的向量,作为式(10)的输入。
本文模型在最后一个特征层后加入SENet模块,旨在提取通道特征,将注意力聚焦于有效的通道信息,同时忽略不重要的特征,进一步提升了分割的准确性。
本节使用改进的Mask R-CNN模型获取坝体渗水区域表面渗水病害的数据集作为研究基础,对渗水病害的面积进行详细的统计分析。对模型输出的掩码进行二值化处理,将其转化为高精度的二值图像数据集,作为渗水病害统计分析的基础。
通过设定合理的阈值T,将掩码中概率值大于T的像素判定为渗水区域(赋值为1),其余区域判定为正常(赋值为0)。这种基于模型置信度的二值化处理,显著提升了渗水边界的清晰度,消除了因温度渐变导致的模糊效应。在本数据集分析中,当阈值T设定为0.7时(基于验证集ROC曲线分析),模型在准确率与误检率之间达到最优平衡,具体效果如图8所示。
在实际的检测工作中,需要获取坝体表面中渗漏水的面积、数量、位置等信息。对灰度栅格图像,运用图像处理技术对渗水区域进行通道增强、图像腐蚀、图像膨胀、图像填充等步骤提取出若干个不相连的区域,对这些区域进行连通域标记并统计格网数量[30],记为n1n2,…,ni。图像上每个像素都代表大小相同的正方形,最终渗水面积可计算为:
式中:Step代表像素的边长,设定为0.2 cm。
为验证本文方法的可行性和精度,2022年9月—2023年9月在某大坝下游坝面进行了渗水面积统计的试验研究,某电站是一座以发电为主的引水式电站,在通过竣工验收投入使用后,由于坝体渗漏和析钙等问题曾被评为病坝,后期经补强加固处理后恢复正常,每周仍需对其进行表面渗水情况检查。
根据前文所述,将2022年9月—2023年8月拍摄的坝体图片作为数据集,其中训练集11 211张、验证集2 151张,共计13 362张大坝表面红外灰度图像用于模型的训练工作。
改进后的Mask R-CNN模型在初次训练时,先在ImageNet数据集上进行预训练。完成预训练后,采用相同的参数配置,选取10 240张坝体表面渗水区域的红外灰度图像作为训练集,进行模型的迭代训练,最后使用另外选取的2 048张验证集红外灰度图像进行准确度评价后完成模型训练。模型迭代选择的参数如表1所示,一般情况下,交并比(Intersection over Union,IoU)的值为0.5或以上时,表示检测成功。
本实验将IoU的阈值设为0.7,表2展示了多个经典分割模型的训练结果。相较之下,Center-Mask[31]相比原始Mask R-CNN在精度和召回率上略有提升。而改进后的模型对比其他2个方案,在准确率、召回率和整体性能上均有优势。
表3进一步给出比较模型的复杂度,可以看出改进后的Mask R-CNN引入Swin Transformer主干网络,在保持原有结构的基础上提升了分割精度,但也带来了参数量和计算量的增加,模型复杂度高于原始Mask R-CNN和CenterMask,推理速度略有下降。
将2023年9月12日的923幅样本数据集作为测试集输入训练完成的Mask R-CNN模型,输出641幅分割出渗水特征的红外灰度图像,其中坝左岸298幅,坝右岸343幅,将分割出的红外灰度图像进行二值化处理后采用式(10)进行面积统计,最终输出某电站下游坝面的总渗水面积S=105.342 m2,其中,坝左岸渗水面积S=23.684 m2,坝右岸渗水面积S=81.658 m2
同一时间段,投入8组人员采用传统方法观测,总耗时8 h,得到下游坝面总渗水面积=101.22 m2,坝左岸渗水面积=21.24 m2,坝右岸渗水面积=79.98 m2。左、右岸坝渗水统计叠加如图9所示。
以渗水区域分布为指标验证本文方法输出的面积精度,核心思路是将分割后的图像重新根据镶嵌线还原回一整张大图并叠加在传统观测方法得到的坝体表面渗水区域CAD图上。将分割后的渗水区域与传统方法得到的渗水区域的分布位置、渗水面积等指标对比,实现对方法精度的评价。
采用本文方法对2023年9月12日所采集的数据集中右岸桩号坝0+021~坝0+069、左岸桩号坝0+144~坝0+178的红外灰度数据集进行处理,共识别出渗漏水病害131处,集中在坝右岸桩号坝0+025~坝0+069、高程105~140 m以及坝左岸桩号坝0+147~坝0+151、坝0+157~坝0+167处。本文方法与传统人工目测法所得出的渗水面积分布基本一致,渗水结果分析如图10所示,分析得出以上所列渗漏水区域需要日常维护重点关注。
本文方法发现有95处面积小于0.5 m2渗水病害(即湿斑),而传统人眼观察仅记录其中7处,这表明本文方法在检测面积较小、目视特征不明显的渗水病害方面性能显著优于人眼观测,能够弥补人眼观测的不足。以人工测量的面积为基准,本文方法得出的坝体渗水面积准确率在90%以上,能够满足日常坝体渗水观测要求。
坝体表面渗水严重威胁大坝运行安全,本文基于改进的Mask R-CNN深度学习神经网络模型实现了对大坝表面渗水区域面积的快速检测、提取、统计。采用摄影测量技术,得到以无人机红外灰度图像为基础的大坝渗水病害数据集,基于此数据集进行神经网络训练与测试,对改进后的Mask R-CNN模型在坝体渗水病害快速检测中的准确性、有效性进行了评估。将本文方法所得出的渗水面积与传统方法统计的渗水面积对比,得出本文方法的渗水精度误差在3%~7%,能够满足大坝日常观测需求;而在检测面积较小、目视特征不明显的渗水病害区域上,该方法明显优于人眼观测性能。结果表明,基于改进的Mask R-CNN深度学习神经网络模型的图像处理技术在渗水病害中能够极大地提升渗漏水检测的效率与自动化程度,为其他工程场景渗漏水检测工作提供新的方法。
此外,本文所检测的大坝病害只包括渗水病害,病害种类单一,未来研究可考虑增加病害种类,扩大改进模型的应用范围。
参考文献 引证文献
排序方式:
[1]
方卫华.纵论大坝安全监测[J].水利水文自动化, 2001(3):9-12.
[2]
杨杰.大坝安全监控中若干不确定性问题的分析方法与应用研究[D].南京:河海大学,2006.
[3]
王周萼,王小波,杜国平.基于声呐技术的霍林河水库大坝渗漏区分析[J].长江技术经济,2023,7(2):58-62.
[4]
杭辉.地球物理计算在大坝渗漏检测中的应用[J].水利科技与经济,2025,31(7):145-149.
[5]
陈文燕,朱林,王文韬.大坝安全监测的现状与发展趋势[J].电力环境保护,2009,25(6):38-42.
[6]
CAI Z W,VASCONCELOS N. Cascade R-CNN:Delving into High Quality Object Detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City:IEEE,2018:6154-6162.
[7]
郭磊,王洋,靳正轩,.基于改进Faster RCNN的化纤丝缺陷检测[J].毛纺科技,2023,51(3):74-79.
[8]
CHERPANATH E D,NASREEN P R F,PRADEEP K, et al. Food Iage Rcognition and Calorie Prediction Using Faster R-CNN and Mask R-CNN[C]//2023 9th International Conference on Smart Computing and Communications (ICSCC). Kharagpur:IEEE,2023:83-89.
[9]
汪宋,费树岷. SSD(Single Shot MultiBox Detector)目标检测算法的研究与改进[J].工业控制计算机,2019, 32(4):103-105.
[10]
REDMON J, FARHADI A. YOLO9000: Better, Faster, Stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu:IEEE,2017:7263-7271.
[11]
REDMON J,DIVVALA S,GIRSHICK R,et al. You Only Look Once:Unified,Real-time Object Detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas:IEEE,2016:779-788.
[12]
ZHANG S S,YANG J,SCHIELE B. Occluded Pedestrian Detection Through Guided Attention in CNNs[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City:IEEE,2018:6995-7003.
[13]
田有良,樊廷立,唐超.面向地铁隧道表面渗漏水的快速检测技术[J].测绘通报,2022(9):29-33.
[14]
周宝定,谢沛瑶,郭文浩,.基于激光点云灰度图像的隧道渗水病害检测[J].测绘通报,2023(8):34-39.
[15]
LI J Q,HE Z Y,LI D X,et al. Research on Water Seepage Detection Technology of Tunnel Asphalt Pavement Based on Deep Learning and Digital Image Processing[J]. Scientific Reports,2022,12(1):11519.
[16]
ZHAO L,WANG J W,LIU S P,et al. An Adaptive Multitask Network for Detecting the Region of Water Leakage in Tunnels[J]. Applied Sciences,2023,13(10):6231.
[17]
肖翠翠,远航.基于红外热成像技术的建筑外墙渗漏及空鼓检测研究[J].北方建筑,2025(1):70-73.
[18]
朱自文,宋晓鸥,崔巍,.可见光-红外图像融合的目标检测综述[J/OL].计算机工程与应用(2025-03-21)[2025-04-07]. http://kns.cnki.net/kcms/detail/11.2127.TP.20250321.1453.006.html.
[19]
HE K, GKIOXARI G, DOLLÁR P, et al. Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision. Venice:IEEE,2017:2961-2969.
[20]
HE K M, ZHANG X Y, REN S Q,et al. Deep Residual Learning for Image Recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas:IEEE,2016:770-778.
[21]
LIN T Y,DOLLÁR P,GIRSHICK R,et al. Feature Pyramid Networks for Object Detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu:IEEE,2017:2117-2125.
[22]
REN S Q,HE K M,GIRSHICK R,et al. Faster R-CNN:Towards Real-time Object Detection with Region Proposal Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,39(6):1137-1149.
[23]
LIU Z,LIN Y T,CAO Y,et al. Swin Transformer:Hierarchical Vision Transformer Using Shifted Windows[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Montreal:IEEE,2021:10012-10022.
[24]
马文轩,蔡卓燃,徐从安,.基于深度学习的认知无线电调制参数估计[J].无线电通信技术,2023,49(2):216-230.
[25]
HU J,SHEN L,SUN G. Squeeze-and-excitation Networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018:7132-7141.
[26]
VASWANI A,SHAZEER N,PARMAR N,et al. Attention Is All You Need[C]//Advances in Neural Information Processing Systems. Long Beach:Curran Associates,Inc, 2017:5998-6008.
[27]
陈池瑶,苗世洪,殷浩然,.基于注意力机制-卷积神经网络的配电网单相接地故障选线方法[J].电力建设,2023,44(4):82-93.
[28]
张学军,周云,杜丹,.基于多尺度注意力特征的识别算法研究[J].无线电通信技术,2021,47(4):513-518.
[29]
KONG Z Q,TANG B P,DENG L,et al. Condition Monitoring of Wind Turbines Based on Spatio-temporal Fusion of SCADA Data by Convolutional Neural Networks and Gated Recurrent Units[J]. Renewable Energy,2020,146:760-768.
[30]
朱林川,黄声享,张赛,,一种基于点云的隧道渗漏检测方法[J].测绘通报,2021(增刊2):140-144.
[31]
LEE Y W,PARK J. CenterMask:Real-time Anchor-free Instance Segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle:IEEE,2020:13906-13915.
2025年第51卷第5期
PDF下载
100
42
引用本文
BibTeX
文章信息
doi: 10.3969/j.issn.1003-3114.2025.05.013
  • 接收时间:2025-04-28
  • 首发时间:2026-04-17
  • 出版时间:2025-09-18
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-04-28
基金
作者信息
    福建水口发电集团有限公司,福建 福州 350004
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/wxdtxjs/CN/10.3969/j.issn.1003-3114.2025.05.013
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏