Article(id=1322162011094499663, tenantId=1146029695717560320, journalId=1225396423026438145, issueId=1322161751467078485, articleNumber=null, orderNo=null, doi=null, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1728489600000, receivedDateStr=2024-10-10, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1793157588027, onlineDateStr=2026-10-28, pubDate=1758729600000, pubDateStr=2025-09-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793157588027, onlineIssueDateStr=2026-10-28, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793157588027, creator=13701087609, updateTime=1793157588027, updator=13701087609, issue=Issue{id=1322161751467078485, tenantId=1146029695717560320, journalId=1225396423026438145, year='2025', volume='45', issue='9', pageStart='1', pageEnd='314', issueExtLink='null', onlineDate='null', pubDate='1758729600000', pubDateStr='2025-09-25', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793157526127, creator='13701087609', updateTime=1793158877659, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1322167420266074322, tenantId=1146029695717560320, journalId=1225396423026438145, issueId=1322161751467078485, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1322167420266074323, tenantId=1146029695717560320, journalId=1225396423026438145, issueId=1322161751467078485, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=200, endPage=207, ext={EN=ArticleExt(id=1322162011253883216, articleId=1322162011094499663, tenantId=1146029695717560320, journalId=1225396423026438145, language=EN, title=Mine Fire Smoke Target Detection Based on Improved YOLOv10s, columnId=null, journalTitle=Mining Research and Development, columnName=null, runingTitle=null, highlight=null, articleAbstract=

Mine fire smoke target detection is one of the important preventive measures to prevent fire accidents in mines. In order to improve the accuracy and speed of fire smoke target detection in mines, a mine fire smoke target detection scheme based on improved YOLOv10s was proposed. Firstly, the collected mine fire smoke image dataset was divided into a training set, validation set and test set according to 7:2:1 after annotation on the online annotation platform. Before training, the images were subjected to wavelet denoising and Auto-Msrcr algorithm enhancement processing, then the original YOLOv10 loss function was reconstructed using Focaler-IoU. The attention module CBAM that strengthened the performance of convolutional neural networks was added, and the third C2f module in Neck was replaced by the cross-stage partial network module VoV-GSCSP, thereby improving the representation ability and decision-making performance of the model. Finally, the feature weights of mine fire smoke recognition were improved. The experimental results show that the improved YOLOv10s model has a 3.5% higher accuracy than the original model, the average precision mAP@50 and mAP@50−95 are increased by 0.7% and 2.2% respectively, and the detection frame rate is increased by 11.9 frames/s. Compared with other mainstream YOLO models, the improved YOLOv10s model has higher detection accuracy and speed, as well as better comprehensive detection performance, which is suitable for high-precision and high real-time mine fire smoke detection scenarios.

, authors=Yeqiu WU1, Zelai SHI2, Huimin ZHU2, Yue LIU1, authorsList=Yeqiu WU, Zelai SHI, Huimin ZHU, Yue LIU, authorCompany=null, correspAuthors=Zelai SHI, 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, fund=null), CN=ArticleExt(id=1322162023488672670, articleId=1322162011094499663, tenantId=1146029695717560320, journalId=1225396423026438145, language=CN, title=基于改进YOLOv10s的矿井火灾烟雾目标检测, columnId=1226462295946085268, journalTitle=矿业研究与开发, columnName=矿山机电与矿业智能化, runingTitle=null, highlight=null, articleAbstract=

矿井火灾烟雾目标检测是防止矿井内发生火灾事故的重要预防措施之一。为了提高矿井内火灾烟雾检测的精度与速度,提出了一种基于改进YOLOv10s的矿井火灾烟雾检测方案。首先将收集的矿井火灾烟雾图像数据集通过在线平台完成标注,然后按7:2:1划分为训练集、验证集及测试集,在训练前对图片进行小波降噪及Auto-Msrcr算法增强处理;其次使用Focaler-IoU重构原始YOLOv10损失函数,以及添加强化卷积神经网络性能的注意力模块CBAM和使用跨阶段部分网络模块VoV-GSCSP替换颈部网络中的第三个C2f模块,从而提高模型的表征能力和决策性能,最终提高对矿井火灾烟雾识别的特征权重。试验结果表明,改进后的YOLOv10s模型与原模型相比准确率提升了3.5%,平均精度均值mAP@50和mAP@50-95分别提升了0.7%和2.2%,检测帧率提高了11.9 帧/s;相较其他主流YOLO模型,改进后的YOLOv10s模型检测精度和速度更高,具有更好的综合检测性能,适用于高精度和高实时性的矿井火灾烟雾检测场景。

, authors=武晔秋1, 石泽来2, 朱慧敏2, 刘玥1, authorsList=武晔秋, 石泽来, 朱慧敏, 刘玥, authorCompany=null, correspAuthors=石泽来, authorNote=

武晔秋(1986—),女,山西大同人,博士,教授,主要研究方向为矿井通风系统。E-mail:

, correspAuthorsNote=
石泽来(1996—),男,河南周口人,硕士研究生,主要研究方向为矿山安全工程。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=hSvz+pGXBs/Q4x/rWZ7VZQ==, magXml=/35UVdgj0V+ii1KP2YG43Q==, pdfUrl=null, pdf=fKexjbalgCCbvoGOYwD4/A==, pdfFileSize=5536759, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=pkjlYC2iUjqtvMpCcjrzog==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=LtDzG8LzUukZ/Y/mk7EVXQ==, mapNumber=null, fund=null)}, authors=[Author(id=1322162024176538534, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wuyeqiu@126.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322162024277201832, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, authorId=1322162024176538534, language=EN, stringName=Yeqiu WU, firstName=Yeqiu, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Architecture and Geomatics Engineering, Shanxi Datong University, Datong, Shanxi 037000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322162024352699305, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, authorId=1322162024176538534, language=CN, stringName=武晔秋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.山西大同大学 建筑与测绘工程学院,山西 大同市 037000, bio={"content":"

武晔秋(1986—),女,山西大同人,博士,教授,主要研究方向为矿井通风系统。E-mail:

"}, bioImg=null, bioContent=

武晔秋(1986—),女,山西大同人,博士,教授,主要研究方向为矿井通风系统。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322162023975211935, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, xref=1., ext=[AuthorCompanyExt(id=1322162023983600544, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, companyId=1322162023975211935, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Architecture and Geomatics Engineering, Shanxi Datong University, Datong, Shanxi 037000, China), AuthorCompanyExt(id=1322162023996183457, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, companyId=1322162023975211935, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.山西大同大学 建筑与测绘工程学院,山西 大同市 037000)])]), Author(id=1322162024428196779, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=s1931224921@outlook.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322162024503694253, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, authorId=1322162024428196779, language=EN, stringName=Zelai SHI, firstName=Zelai, middleName=null, lastName=SHI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.College of Coal Engineering, Shanxi Datong University, Datong, Shanxi 037000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322162024587580334, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, authorId=1322162024428196779, language=CN, stringName=石泽来, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.山西大同大学 煤炭工程学院,山西 大同市 037000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322162024071680930, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, xref=2., ext=[AuthorCompanyExt(id=1322162024080069539, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, companyId=1322162024071680930, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Coal Engineering, Shanxi Datong University, Datong, Shanxi 037000, China), AuthorCompanyExt(id=1322162024088458148, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, companyId=1322162024071680930, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.山西大同大学 煤炭工程学院,山西 大同市 037000)])]), Author(id=1322162024654689200, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, orderNo=2, 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=1322162024751158194, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, authorId=1322162024654689200, language=EN, stringName=Huimin ZHU, firstName=Huimin, middleName=null, lastName=ZHU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.College of Coal Engineering, Shanxi Datong University, Datong, Shanxi 037000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322162024822461363, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, authorId=1322162024654689200, language=CN, stringName=朱慧敏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.山西大同大学 煤炭工程学院,山西 大同市 037000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322162024071680930, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, xref=2., ext=[AuthorCompanyExt(id=1322162024080069539, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, companyId=1322162024071680930, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Coal Engineering, Shanxi Datong University, Datong, Shanxi 037000, China), AuthorCompanyExt(id=1322162024088458148, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, companyId=1322162024071680930, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.山西大同大学 煤炭工程学院,山西 大同市 037000)])]), Author(id=1322162024902153141, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, orderNo=3, 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=1322162024977650615, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, authorId=1322162024902153141, language=EN, stringName=Yue LIU, firstName=Yue, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Architecture and Geomatics Engineering, Shanxi Datong University, Datong, Shanxi 037000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322162025040565176, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, authorId=1322162024902153141, language=CN, stringName=刘玥, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.山西大同大学 建筑与测绘工程学院,山西 大同市 037000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322162023975211935, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, xref=1., ext=[AuthorCompanyExt(id=1322162023983600544, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, companyId=1322162023975211935, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Architecture and Geomatics Engineering, Shanxi Datong University, Datong, Shanxi 037000, China), AuthorCompanyExt(id=1322162023996183457, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, companyId=1322162023975211935, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.山西大同大学 建筑与测绘工程学院,山西 大同市 037000)])])], keywords=[Keyword(id=1322162025195754426, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=EN, orderNo=1, keyword=Mine fire), Keyword(id=1322162025296417723, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=EN, orderNo=2, keyword=Smoke detection), Keyword(id=1322162025371915196, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=EN, orderNo=3, keyword=Improved YOLOv10s), Keyword(id=1322162025455801277, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=EN, orderNo=4, keyword=Attention module), Keyword(id=1322162025531298750, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=EN, orderNo=5, keyword=Feature weight), Keyword(id=1322162025590019007, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=CN, orderNo=1, keyword=矿井火灾), Keyword(id=1322162025661322176, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=CN, orderNo=2, keyword=烟雾检测), Keyword(id=1322162025724236737, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=CN, orderNo=3, keyword=改进YOLOv10s), Keyword(id=1322162025778762690, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=CN, orderNo=4, keyword=注意力模块), Keyword(id=1322162025850065859, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=CN, orderNo=5, keyword=特征权重)], refs=[Reference(id=1322162028819633121, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2012, volume=32, issue=1, pageStart=47, pageEnd=58, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=REIMANN P, SCHUTZE A, journalName=Sensor Review, refType=null, unstructuredReference=REIMANN P, SCHUTZE A. Fire detection in coal mines based on semiconductor gas sensors[J]. Sensor Review, 2012, 32(1):47-58., articleTitle=Fire detection in coal mines based on semiconductor gas sensors, refAbstract=null), Reference(id=1322162028899324898, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2020, volume=95, issue=4, pageStart=350, pageEnd=358, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=KUMAR S, PAL K S, journalName=Journal of the Geological Society of India, refType=null, unstructuredReference=KUMAR S, PAL K S. Underground coal fire mapping using analysis of self-potential (SP) data collected from Akashkinaree Colliery, Jharia Coalfield, India[J]. Journal of the Geological Society of India, 2020, 95(4):350-358., articleTitle=Underground coal fire mapping using analysis of self-potential (SP) data collected from Akashkinaree Colliery, Jharia Coalfield, India, refAbstract=null), Reference(id=1322162028966433763, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2021, volume=47, issue=9, pageStart=53, pageEnd=57, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=王伟峰, 张宝宝, 王志强, journalName=工矿自动化, refType=null, unstructuredReference=王伟峰,张宝宝,王志强,等.基于YOLOv5的矿井火灾视频图像智能识别方法[J].工矿自动化,2021,47(9):53-57., articleTitle=基于YOLOv5的矿井火灾视频图像智能识别方法, refAbstract=null), Reference(id=1322162029033542628, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2021, volume=47, issue=9, pageStart=53, pageEnd=57, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=WANG Weifeng, ZHANG Baobao, WANG Zhiqiang, journalName=Journal of Mine Automation, refType=null, unstructuredReference=WANG Weifeng,ZHANG Baobao,WANG Zhiqiang,et al. Intelligent identification method of mine fire video images based onYOLOv5[J]. Journal of Mine Automation, 2021,47(9):53-57, articleTitle=Intelligent identification method of mine fire video images based onYOLOv5, refAbstract=null), Reference(id=1322162029100651493, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=20, pageEnd=46, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=白宝军, journalName=null, refType=null, unstructuredReference=白宝军.基于图像增强与多特征的煤矿井下火灾烟雾检测方法研究[D]. 西安:西安建筑科技大学,2021,20-46., articleTitle=基于图像增强与多特征的煤矿井下火灾烟雾检测方法研究, refAbstract=null), Reference(id=1322162029184537574, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=20, pageEnd=46, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=BAI Baojun, journalName=null, refType=null, unstructuredReference=BAI Baojun. Research on smoke detection method of coal mine fire based on image enhancement and multiple features [D]. Xi'an: Xi'an University of Architecture and Technology, 2021, 20-46., articleTitle=Research on smoke detection method of coal mine fire based on image enhancement and multiple features, refAbstract=null), Reference(id=1322162029272617959, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2010, volume=null, issue=4, pageStart=94, pageEnd=97, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=吕宗宝, 董军, 汝洪芳, journalName=工业仪表与自动化装置, refType=null, unstructuredReference=吕宗宝,董军,汝洪芳.改进的多元数据融合算法在矿井火灾检测系统中的应用[J].工业仪表与自动化装置,2010(4):94-97., articleTitle=改进的多元数据融合算法在矿井火灾检测系统中的应用, refAbstract=null), Reference(id=1322162029335532520, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2010, volume=null, issue=4, pageStart=94, pageEnd=97, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=LYU Zongbao, DONG Jun, RU Hongfang, journalName=Industrial Instrumentation & Automation, refType=null, unstructuredReference=LYU Zongbao, DONG Jun, RU Hongfang. Application of mine fire detection system based on improved multi-data fusion algorithm[J]. Industrial Instrumentation & Automation, 2010(4):94-97., articleTitle=Application of mine fire detection system based on improved multi-data fusion algorithm, refAbstract=null), Reference(id=1322162029402641385, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2021, volume=47, issue=4, pageStart=1, pageEnd=5+38, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=孙继平, 崔佳伟, journalName=工矿自动化, refType=null, unstructuredReference=孙继平,崔佳伟.矿井外因火灾感知方法[J].工矿自动化,2021,47(4):1-5+38., articleTitle=矿井外因火灾感知方法, refAbstract=null), Reference(id=1322162029494916074, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2021, volume=47, issue=4, pageStart=1, pageEnd=5+38, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=SUN Jiping, CUI Jiawei, journalName=Journal of Mine Automation, refType=null, unstructuredReference=SUN Jiping, CUI Jiawei. Mine external fire sensing method[J]. Journal of Mine Automation, 2021, 47(4): 1-5+38., articleTitle=Mine external fire sensing method, refAbstract=null), Reference(id=1322162029578802155, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2024, volume=50, issue=3, pageStart=65, pageEnd=70+91, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=王树斌, 王旭, 闫世平, journalName=工矿自动化, refType=null, unstructuredReference=王树斌,王旭,闫世平,等.基于Transformer的矿井内因火灾时间序列预测方法[J].工矿自动化,2024,50(3):65-70+91., articleTitle=基于Transformer的矿井内因火灾时间序列预测方法, refAbstract=null), Reference(id=1322162029654299628, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2024, volume=50, issue=3, pageStart=65, pageEnd=70+91, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=WANG Shubin, WANG Xu, YAN Shiping, journalName=Journal of Mine Automation, refType=null, unstructuredReference=WANG Shubin, WANG Xu, YAN Shiping, et al. Transformer based time series prediction method for mine internal caused fire[J]. Journal of Mine Automation, 2024, 50(3):65-70+91., articleTitle=Transformer based time series prediction method for mine internal caused fire, refAbstract=null), Reference(id=1322162029742380013, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2023, volume=59, issue=17, pageStart=286, pageEnd=294, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=刘春霞, 李超, 潘理虎, journalName=计算机工程与应用, refType=null, unstructuredReference=刘春霞,李超,潘理虎,等.改进 YOLOv5s 的煤矿烟火检测算法[J].计算机工程与应用,2023,59(17): 286-294., articleTitle=改进 YOLOv5s 的煤矿烟火检测算法, refAbstract=null), Reference(id=1322162029809488878, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2019, volume=59, issue=17, pageStart=286, pageEnd=294, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=LIU Chunxia, LI Chao, PAN Lihu, journalName=Journal of Computer Engineering & Applications, refType=null, unstructuredReference=LIU Chunxia, LI Chao, PAN Lihu, et al. Improved coal mine smoke and fire detection algorithm of YOLOv5s[J]. Journal of Computer Engineering & Applications, 2019, 59(17):286-294., articleTitle=Improved coal mine smoke and fire detection algorithm of YOLOv5s, refAbstract=null), Reference(id=1322162029889180655, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=WANG A, CHEN H, LIU L H, journalName=arXiv, refType=null, unstructuredReference=WANG A, CHEN H, LIU L H, et al. Yolov10: Real-time end-to-end object detection[J]. arXiv preprint arXiv:2024., articleTitle=Yolov10: Real-time end-to-end object detection, refAbstract=null), Reference(id=1322162029973066736, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=390, pageEnd=391, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=WANG C Y, LIAO H Y M, WU Y H, journalName=null, refType=null, unstructuredReference=WANG C Y, LIAO H Y M, WU Y H, et al. CSPNet: a new backbone that can enhance learning capability of CNN: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops [C]. Seattle, USA: IEEE, 2020:390-391., articleTitle=CSPNet: a new backbone that can enhance learning capability of CNN, refAbstract=null), Reference(id=1322162030040175601, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=ZHANG H, ZHANG S, journalName=arXiv, refType=null, unstructuredReference=ZHANG H, ZHANG S. Focaler-IoU: more focused intersection over union loss[J]. arXiv preprint arXiv:2024., articleTitle=Focaler-IoU: more focused intersection over union loss, refAbstract=null), Reference(id=1322162030107284466, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=10.1007/978-3-030-01234-2_1, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=WOO S, PARK J, LEE J Y, journalName=Springer, Cham, refType=null, unstructuredReference=WOO S, PARK J, LEE J Y, et al. Cbam: Convolutional block attention module[J]. Springer, Cham, 2018., articleTitle=Cbam: Convolutional block attention module, refAbstract=null), Reference(id=1322162030182781939, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=LI H L, LI J, WEI H B, journalName=arXiv, refType=null, unstructuredReference=LI H L, LI J, WEI H B, et al. Slim-neck by GSConv: a better design paradigm of detector architectures for autonomous vehicles[J]. arXiv preprint arXiv:2022., articleTitle=Slim-neck by GSConv: a better design paradigm of detector architectures for autonomous vehicles, refAbstract=null), Reference(id=1322162030258279412, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=752, pageEnd=760, url=null, language=null, rfNumber=[14], rfOrder=19, authorNames=LEE Y, HWANG J, LEE S, journalName=null, refType=null, unstructuredReference=LEE Y, HWANG J, LEE S, et al. An energy and GPU-computation efficient backbone network for real-time object detection: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops [C]. Long Beach, USA: IEEE, 2019:752-760., articleTitle=An energy and GPU-computation efficient backbone network for real-time object detection, refAbstract=null), Reference(id=1322162030333776885, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2005, volume=12, issue=1, pageStart=99, pageEnd=107, url=null, language=null, rfNumber=[15], rfOrder=20, authorNames=CHEN G, BUI T, KRZYZAK A, journalName=Integrated Computer-Aided Engineering, refType=null, unstructuredReference=CHEN G, BUI T, KRZYZAK A. Image denoising using neighbouring wavelet coefficients[J]. Integrated Computer-Aided Engineering, 2005, 12(1):99-107., articleTitle=Image denoising using neighbouring wavelet coefficients, refAbstract=null), Reference(id=1322162030413468662, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, doi=null, pmid=null, pmcid=null, year=2012, volume=null, issue=null, pageStart=1, pageEnd=5, url=null, language=null, rfNumber=[16], rfOrder=21, authorNames=PARTHASARATHY S, SANKARAN P, journalName=null, refType=null, unstructuredReference=PARTHASARATHY S, SANKARAN P. An automated multi scale retinex with color restoration for image enhancement: 2012 National Conference on Communications (NCC)[C]. Kharagpur, India: IEEE, 2012: 1-5., articleTitle=An automated multi scale retinex with color restoration for image enhancement, refAbstract=null)], funds=[Fund(id=1322162028500866014, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, awardId=51764044, language=CN, fundingSource=国家自然科学基金项目(51764044), fundOrder=null, country=null), Fund(id=1322162028576363487, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, awardId=2024SJ379, language=CN, fundingSource=山西省2024年度研究生教育创新计划实践创新项目(2024SJ379), fundOrder=null, country=null), Fund(id=1322162028639278048, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, awardId=2024SJCX06, language=CN, fundingSource=山西大同大学2024年研究生实践创新项目(2024SJCX06), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322162023975211935, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, xref=1., ext=[AuthorCompanyExt(id=1322162023983600544, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, companyId=1322162023975211935, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Architecture and Geomatics Engineering, Shanxi Datong University, Datong, Shanxi 037000, China), AuthorCompanyExt(id=1322162023996183457, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, companyId=1322162023975211935, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.山西大同大学 建筑与测绘工程学院,山西 大同市 037000)]), AuthorCompany(id=1322162024071680930, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, xref=2., ext=[AuthorCompanyExt(id=1322162024080069539, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, companyId=1322162024071680930, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Coal Engineering, Shanxi Datong University, Datong, Shanxi 037000, China), AuthorCompanyExt(id=1322162024088458148, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, companyId=1322162024071680930, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.山西大同大学 煤炭工程学院,山西 大同市 037000)])], figs=[ArticleFig(id=1322162026063975364, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=EN, label=Fig.1, caption=YOLOv10s network structure, figureFileSmall=FkRDV+dbQ55SZwomWHkt+A==, figureFileBig=pkjlYC2iUjqtvMpCcjrzog==, tableContent=null), ArticleFig(id=1322162026156250053, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=CN, label=图1, caption=YOLOv10s网络结构, figureFileSmall=FkRDV+dbQ55SZwomWHkt+A==, figureFileBig=pkjlYC2iUjqtvMpCcjrzog==, tableContent=null), ArticleFig(id=1322162026357576646, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=EN, label=Fig.2, caption=PSA network structure, figureFileSmall=ZeSqeyuohYh/tI5dj8K10Q==, figureFileBig=FLU71Br1G/T55wSTxrgBpA==, tableContent=null), ArticleFig(id=1322162026483405767, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=CN, label=图2, caption=PSA网络结构, figureFileSmall=ZeSqeyuohYh/tI5dj8K10Q==, figureFileBig=FLU71Br1G/T55wSTxrgBpA==, tableContent=null), ArticleFig(id=1322162026558903240, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=EN, label=Fig.3, caption=Comparison of ground truth boxes and predicted boxes, figureFileSmall=cI9xuG2YfZCJ27MxWCkpgQ==, figureFileBig=Imt6f2ZOdCcVDd+cXOKezg==, tableContent=null), ArticleFig(id=1322162026651177929, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=CN, label=图3, caption=真实框及预测框对比, figureFileSmall=cI9xuG2YfZCJ27MxWCkpgQ==, figureFileBig=Imt6f2ZOdCcVDd+cXOKezg==, tableContent=null), ArticleFig(id=1322162026726675402, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=EN, label=Fig.4, caption=Structure of the channel attention module, figureFileSmall=CWPR7m5pEuaVlgWr0kG1NA==, figureFileBig=whKrevO+X2ITISg4/b6JDQ==, tableContent=null), ArticleFig(id=1322162026818950091, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=CN, label=图4, caption=通道注意力模块结构, figureFileSmall=CWPR7m5pEuaVlgWr0kG1NA==, figureFileBig=whKrevO+X2ITISg4/b6JDQ==, tableContent=null), ArticleFig(id=1322162026890253260, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=EN, label=Fig.5, caption=Structure of the spatial attention module, figureFileSmall=qiHezvSejO7cCuBcPVd27Q==, figureFileBig=oMkcPTA0nc9RBGqboT1P1w==, tableContent=null), ArticleFig(id=1322162026982527949, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=CN, label=图5, caption=空间注意力模块结构, figureFileSmall=qiHezvSejO7cCuBcPVd27Q==, figureFileBig=oMkcPTA0nc9RBGqboT1P1w==, tableContent=null), ArticleFig(id=1322162027074802638, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=EN, label=Fig.6, caption=Structure of the VoV-GSCSP module, figureFileSmall=bImVAE8y5jNIIIWLaZPmYQ==, figureFileBig=wllGHCDr1OfJrD47H9KkAQ==, tableContent=null), ArticleFig(id=1322162027179660239, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=CN, label=图6, caption=VoV-GSCSP模块结构, figureFileSmall=bImVAE8y5jNIIIWLaZPmYQ==, figureFileBig=wllGHCDr1OfJrD47H9KkAQ==, tableContent=null), ArticleFig(id=1322162027276129232, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=EN, label=Fig.7, caption=Improved network structure of YOLOv10s model, figureFileSmall=eLiBaY1cC5dQSiiUxBXE8A==, figureFileBig=rmRqe7nqjO6ov1JrjLbzog==, tableContent=null), ArticleFig(id=1322162027355821009, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=CN, label=图7, caption=改进后的YOLOv10s模型网络结构, figureFileSmall=eLiBaY1cC5dQSiiUxBXE8A==, figureFileBig=rmRqe7nqjO6ov1JrjLbzog==, tableContent=null), ArticleFig(id=1322162027435512786, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=EN, label=Fig.8, caption=Some images before and after reducing noise and enhancement, figureFileSmall=zI9Bgax59tTvCPqkurxl8Q==, figureFileBig=UXf8IJEy3jFmmORw3j8/6w==, tableContent=null), ArticleFig(id=1322162027506815955, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=CN, label=图8, caption=部分图片降噪和增强前后对比, figureFileSmall=zI9Bgax59tTvCPqkurxl8Q==, figureFileBig=UXf8IJEy3jFmmORw3j8/6w==, tableContent=null), ArticleFig(id=1322162027586507732, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=EN, label=Fig.9, caption=Comparison of classification loss function curves, figureFileSmall=n4HQj59j6UfTBs6ZsqqfwQ==, figureFileBig=u+6lroglrYZ36A7SNV8heg==, tableContent=null), ArticleFig(id=1322162027674588117, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=CN, label=图9, caption=分类损失函数曲线对比, figureFileSmall=n4HQj59j6UfTBs6ZsqqfwQ==, figureFileBig=u+6lroglrYZ36A7SNV8heg==, tableContent=null), ArticleFig(id=1322162027750085590, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=EN, label=Fig.10, caption=Comparison of confidence loss function curves, figureFileSmall=JI3w/cAriLK33sKs7Fd2VA==, figureFileBig=iZPamanBVi6NpIAPJ4s7Uw==, tableContent=null), ArticleFig(id=1322162027825583063, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=CN, label=图10, caption=置信度损失函数曲线对比, figureFileSmall=JI3w/cAriLK33sKs7Fd2VA==, figureFileBig=iZPamanBVi6NpIAPJ4s7Uw==, tableContent=null), ArticleFig(id=1322162027901080536, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=EN, label=Fig.11, caption=Comparison of boundary frame loss function curves, figureFileSmall=COea+UI3wFSY2pCquxnQdw==, figureFileBig=aIlXG26P8Wevg9DZSHvR0Q==, tableContent=null), ArticleFig(id=1322162027989160921, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=CN, label=图11, caption=边界框损失函数曲线对比, figureFileSmall=COea+UI3wFSY2pCquxnQdw==, figureFileBig=aIlXG26P8Wevg9DZSHvR0Q==, tableContent=null), ArticleFig(id=1322162028064658394, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=EN, label=Fig.12, caption=Detection effects of different models, figureFileSmall=8EubKf+RrK7ynlWHrD+PMg==, figureFileBig=/hSo51hBQraOdWjbiaIYHQ==, tableContent=null), ArticleFig(id=1322162028161127387, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=CN, label=图12, caption=各模型检测效果图对比, figureFileSmall=8EubKf+RrK7ynlWHrD+PMg==, figureFileBig=/hSo51hBQraOdWjbiaIYHQ==, tableContent=null), ArticleFig(id=1322162028240819164, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=EN, label=Table 1, caption=

Performance data of each model

, figureFileSmall=null, figureFileBig=null, tableContent=
模型P/%R/%mAP@50/%mAP@50-95/%FPS/(帧·s-1)
YOLOv5s89.386.989.562.6285.7
YOLOv789.987.390.864.4238.1
YOLOv889.682.388.163.2243.9
YOLOv9s89.282.788.864.5322.5
YOLOv10s89.486.089.567.7324.6
本文方法92.584.790.169.2336.5
), ArticleFig(id=1322162028333093853, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, language=CN, label=表1, caption=

各模型性能数据

, figureFileSmall=null, figureFileBig=null, tableContent=
模型P/%R/%mAP@50/%mAP@50-95/%FPS/(帧·s-1)
YOLOv5s89.386.989.562.6285.7
YOLOv789.987.390.864.4238.1
YOLOv889.682.388.163.2243.9
YOLOv9s89.282.788.864.5322.5
YOLOv10s89.486.089.567.7324.6
本文方法92.584.790.169.2336.5
)], attaches=null, journal=Journal(id=1225396331729022976, delFlag=0, nameCn=矿业研究与开发, nameEn=Mining Research and Development, nameHistory1=null, nameHistory2=null, issn=1005-2763, eissn=null, cn=43-1215/TD, coden=null, periodic=0, language=CN, oaType=null, 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=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=BLic9JllTIKtYRYod5zIVQ==, journalPrice=null, startedYear=null, abbrevIsoEn=Mining Research and Development, journalRemark=null, publicationField=null, createdTime=1770086852251, updatedTime=1784018193958, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=K, firstLetterEn=K, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=BLic9JllTIKtYRYod5zIVQ==, picEn=Bqi6ei4JhI5hinJcqiOo2A==, jcr=null, cjcr=null, exts=[JournalExt(id=1283828614093321209, language=CN, name=矿业研究与开发, 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=1784018193982, updatedTime=1784018193982, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.chinamine.org.cn/kyyjykf/author/login, submissionEditorUrl=http://www.chinamine.org.cn/kyyjykf/editor/login, submissionReviewUrl=http://www.chinamine.org.cn/kyyjykf/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1283828614143652858, language=EN, name=Mining Research and Development, 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=1784018193994, updatedTime=1784018193994, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.chinamine.org.cn/kyyjykfen/author/login, submissionEditorUrl=http://www.chinamine.org.cn/kyyjykfen/editor/login, submissionReviewUrl=http://www.chinamine.org.cn/kyyjykfen/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1225396423026438145, websiteList=[Website(id=1225409554104627231, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1225396423026438145, 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/kyyjykf/CN, language=CN, createTime=1770090004708, createBy=18614031015, updateTime=1770090031995, updateBy=18614031015, name=矿业研究与开发-中文, tplId=1146099689490845704, title=矿业研究与开发, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1228001470277153440, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=articleTextType, value=kx, createTime=1770707965678, updateTime=1770707965678, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470256181917, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=banner, value=null, createTime=1770707965673, updateTime=1770707965673, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470293930659, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=grayFlag, value=0, createTime=1770707965682, updateTime=1770707965682, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470251987612, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=logo, value=https://castjournals.cast.org.cn/joweb/kyyjykf/CN/file/pic?fileId=++etCLRiS7F8czudkkUdPA==, createTime=1770707965672, updateTime=1770707965672, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470302319269, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=minRunFlag, value=0, createTime=1770707965684, updateTime=1770707965684, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470268764831, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kyyjykf/CN/file/pic, createTime=1770707965676, updateTime=1770707965676, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470298124964, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=silenceFlag, value=0, createTime=1770707965683, updateTime=1770707965683, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470264570526, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1770707965675, updateTime=1770707965675, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470281347745, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=themeColor, value=null, createTime=1770707965679, updateTime=1770707965679, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470285542050, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=themeStyle, value=null, createTime=1770707965680, updateTime=1770707965680, creator=18614031015, updator=18614031015)]), Website(id=1225409554180124705, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1225396423026438145, 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/kyyjykf/EN, language=EN, createTime=1770090004726, createBy=18614031015, updateTime=1770090069284, updateBy=18614031015, name=矿业研究与开发英文, tplId=1146101810881728533, title=Mining Research and Development, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1225410562574696778, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=articleTextType, value=kx, createTime=1770090245145, updateTime=1770090245145, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562553725255, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=banner, value=null, createTime=1770090245140, updateTime=1770090245140, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562612445517, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=grayFlag, value=0, createTime=1770090245154, updateTime=1770090245154, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562536948038, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=logo, value=https://castjournals.cast.org.cn/joweb/kyyjykf/EN/file/pic?fileId=++etCLRiS7F8czudkkUdPA==, createTime=1770090245136, updateTime=1770090245136, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562629222735, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=minRunFlag, value=0, createTime=1770090245158, updateTime=1770090245158, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562566308169, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kyyjykf/EN/file/pic, createTime=1770090245143, updateTime=1770090245143, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562620834126, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=silenceFlag, value=0, createTime=1770090245156, updateTime=1770090245156, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562562113864, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1770090245142, updateTime=1770090245142, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562583085387, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=themeColor, value=null, createTime=1770090245147, updateTime=1770090245147, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562604056908, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=themeStyle, value=null, createTime=1770090245152, updateTime=1770090245152, creator=18614031015, updator=18614031015)])], journalTitle=矿业研究与开发, weixinUrl=null, journalUrl=null, iacademicId=null, status=1, seqNo=null, journalTitleEn=Mining Research and Development, journalPhotoCn=BLic9JllTIKtYRYod5zIVQ==, journalPhotoEn=Bqi6ei4JhI5hinJcqiOo2A==, journalFirstLetter=K, 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, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/kyyjykf/CN/Y2025/V45/I9/200, detailUrlEn=https://castjournals.cast.org.cn/joweb/kyyjykf/EN/Y2025/V45/I9/200, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kyyjykf/CN/PDF/Y2025/V45/I9/200, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kyyjykf/EN/PDF/Y2025/V45/I9/200, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1758729600000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于改进YOLOv10s的矿井火灾烟雾目标检测
收藏切换
PDF下载
武晔秋 1 , 石泽来 2 , 朱慧敏 2 , 刘玥 1
矿业研究与开发 | 矿山机电与矿业智能化 2025,45(9): 200-207
收起
收藏切换
矿业研究与开发 |矿山机电与矿业智能化 2025 , 45 (9) : 200 -207
基于改进YOLOv10s的矿井火灾烟雾目标检测
全屏
[Author(id=1322162024176538534, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wuyeqiu@126.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322162024277201832, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, authorId=1322162024176538534, language=EN, stringName=Yeqiu WU, firstName=Yeqiu, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Architecture and Geomatics Engineering, Shanxi Datong University, Datong, Shanxi 037000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322162024352699305, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, authorId=1322162024176538534, language=CN, stringName=武晔秋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.山西大同大学 建筑与测绘工程学院,山西 大同市 037000, bio={"content":"

武晔秋(1986—),女,山西大同人,博士,教授,主要研究方向为矿井通风系统。E-mail:

"}, bioImg=null, bioContent=

武晔秋(1986—),女,山西大同人,博士,教授,主要研究方向为矿井通风系统。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322162023975211935, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, xref=1., ext=[AuthorCompanyExt(id=1322162023983600544, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, companyId=1322162023975211935, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Architecture and Geomatics Engineering, Shanxi Datong University, Datong, Shanxi 037000, China), AuthorCompanyExt(id=1322162023996183457, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, companyId=1322162023975211935, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.山西大同大学 建筑与测绘工程学院,山西 大同市 037000)])]), Author(id=1322162024428196779, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=s1931224921@outlook.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322162024503694253, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, authorId=1322162024428196779, language=EN, stringName=Zelai SHI, firstName=Zelai, middleName=null, lastName=SHI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.College of Coal Engineering, Shanxi Datong University, Datong, Shanxi 037000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322162024587580334, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, authorId=1322162024428196779, language=CN, stringName=石泽来, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.山西大同大学 煤炭工程学院,山西 大同市 037000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322162024071680930, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, xref=2., ext=[AuthorCompanyExt(id=1322162024080069539, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, companyId=1322162024071680930, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Coal Engineering, Shanxi Datong University, Datong, Shanxi 037000, China), AuthorCompanyExt(id=1322162024088458148, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, companyId=1322162024071680930, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.山西大同大学 煤炭工程学院,山西 大同市 037000)])]), Author(id=1322162024654689200, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, orderNo=2, 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=1322162024751158194, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, authorId=1322162024654689200, language=EN, stringName=Huimin ZHU, firstName=Huimin, middleName=null, lastName=ZHU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.College of Coal Engineering, Shanxi Datong University, Datong, Shanxi 037000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322162024822461363, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, authorId=1322162024654689200, language=CN, stringName=朱慧敏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.山西大同大学 煤炭工程学院,山西 大同市 037000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322162024071680930, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, xref=2., ext=[AuthorCompanyExt(id=1322162024080069539, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, companyId=1322162024071680930, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Coal Engineering, Shanxi Datong University, Datong, Shanxi 037000, China), AuthorCompanyExt(id=1322162024088458148, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, companyId=1322162024071680930, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.山西大同大学 煤炭工程学院,山西 大同市 037000)])]), Author(id=1322162024902153141, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, orderNo=3, 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=1322162024977650615, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, authorId=1322162024902153141, language=EN, stringName=Yue LIU, firstName=Yue, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Architecture and Geomatics Engineering, Shanxi Datong University, Datong, Shanxi 037000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322162025040565176, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, authorId=1322162024902153141, language=CN, stringName=刘玥, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.山西大同大学 建筑与测绘工程学院,山西 大同市 037000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322162023975211935, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, xref=1., ext=[AuthorCompanyExt(id=1322162023983600544, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, companyId=1322162023975211935, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Architecture and Geomatics Engineering, Shanxi Datong University, Datong, Shanxi 037000, China), AuthorCompanyExt(id=1322162023996183457, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322162011094499663, companyId=1322162023975211935, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.山西大同大学 建筑与测绘工程学院,山西 大同市 037000)])])]
武晔秋1 , 石泽来2 , 朱慧敏2, 刘玥1
作者信息
  • 1.山西大同大学 建筑与测绘工程学院,山西 大同市 037000
  • 2.山西大同大学 煤炭工程学院,山西 大同市 037000
通讯作者:
石泽来(1996—),男,河南周口人,硕士研究生,主要研究方向为矿山安全工程。E-mail:
作者简介:

武晔秋(1986—),女,山西大同人,博士,教授,主要研究方向为矿井通风系统。E-mail:

Mine Fire Smoke Target Detection Based on Improved YOLOv10s
Yeqiu WU1 , Zelai SHI2 , Huimin ZHU2, Yue LIU1
Affiliations
  • 1.College of Architecture and Geomatics Engineering, Shanxi Datong University, Datong, Shanxi 037000, China
  • 2.College of Coal Engineering, Shanxi Datong University, Datong, Shanxi 037000, China
出版时间: 2025-09-25
文章导航
收藏切换

矿井火灾烟雾目标检测是防止矿井内发生火灾事故的重要预防措施之一。为了提高矿井内火灾烟雾检测的精度与速度,提出了一种基于改进YOLOv10s的矿井火灾烟雾检测方案。首先将收集的矿井火灾烟雾图像数据集通过在线平台完成标注,然后按7:2:1划分为训练集、验证集及测试集,在训练前对图片进行小波降噪及Auto-Msrcr算法增强处理;其次使用Focaler-IoU重构原始YOLOv10损失函数,以及添加强化卷积神经网络性能的注意力模块CBAM和使用跨阶段部分网络模块VoV-GSCSP替换颈部网络中的第三个C2f模块,从而提高模型的表征能力和决策性能,最终提高对矿井火灾烟雾识别的特征权重。试验结果表明,改进后的YOLOv10s模型与原模型相比准确率提升了3.5%,平均精度均值mAP@50和mAP@50-95分别提升了0.7%和2.2%,检测帧率提高了11.9 帧/s;相较其他主流YOLO模型,改进后的YOLOv10s模型检测精度和速度更高,具有更好的综合检测性能,适用于高精度和高实时性的矿井火灾烟雾检测场景。

矿井火灾  /  烟雾检测  /  改进YOLOv10s  /  注意力模块  /  特征权重

Mine fire smoke target detection is one of the important preventive measures to prevent fire accidents in mines. In order to improve the accuracy and speed of fire smoke target detection in mines, a mine fire smoke target detection scheme based on improved YOLOv10s was proposed. Firstly, the collected mine fire smoke image dataset was divided into a training set, validation set and test set according to 7:2:1 after annotation on the online annotation platform. Before training, the images were subjected to wavelet denoising and Auto-Msrcr algorithm enhancement processing, then the original YOLOv10 loss function was reconstructed using Focaler-IoU. The attention module CBAM that strengthened the performance of convolutional neural networks was added, and the third C2f module in Neck was replaced by the cross-stage partial network module VoV-GSCSP, thereby improving the representation ability and decision-making performance of the model. Finally, the feature weights of mine fire smoke recognition were improved. The experimental results show that the improved YOLOv10s model has a 3.5% higher accuracy than the original model, the average precision mAP@50 and mAP@50−95 are increased by 0.7% and 2.2% respectively, and the detection frame rate is increased by 11.9 frames/s. Compared with other mainstream YOLO models, the improved YOLOv10s model has higher detection accuracy and speed, as well as better comprehensive detection performance, which is suitable for high-precision and high real-time mine fire smoke detection scenarios.

Mine fire  /  Smoke detection  /  Improved YOLOv10s  /  Attention module  /  Feature weight
武晔秋, 石泽来, 朱慧敏, 刘玥. 基于改进YOLOv10s的矿井火灾烟雾目标检测. 矿业研究与开发, 2025 , 45 (9) : 200 -207 .
Yeqiu WU, Zelai SHI, Huimin ZHU, Yue LIU. Mine Fire Smoke Target Detection Based on Improved YOLOv10s[J]. Mining Research and Development, 2025 , 45 (9) : 200 -207 .
矿井火灾是矿井常见的五大灾害之一,若井下发生火灾事故,则会严重影响矿井的正常开采并威胁矿工的生命安全。如2021年山东省烟台招远市曹家洼金矿“2·17”较大火灾事故,2023年河南三门峡河南大有能源股份有限公司耿村煤矿“5·9”较大火灾事故等均造成了巨大的经济损失和人员伤亡。在火源出现时如果能及时、精准地监测和定位,可有效采取措施,从而预防火灾的发生。
国内外的研究者们对矿井火灾烟雾检测的相关研究主要集中在传感器检测、红外图像检测、图像增强目标检测等方面。REIMANN P等[1]研究开发了一个基于单个半导体气体传感器和相对湿度与温度传感器的系统,利用高动态范围的硬件控制和数据采集平台,实现了半导体气体传感器在矿井火灾中的应用。KUMAR S等[2]采用电位法(SP)对地下煤火进行了研究,通过利用卫星热红外数据进行煤火成图,从而识别地表煤火位置和煤火的横向传播。王伟峰等[3]通过改进YOLOv5算法并结合K-means算法进行图像增强,提高了矿井火灾识别准确率。白宝军[4]通过分析烟雾特征和融合判定,采用改进MSRCP算法进行矿井图像增强,最后结合SVM矿井烟雾检测模型设计出了适合矿井的火灾烟雾检测算法。吕宗宝等[5]针对矿井火灾检测系统提出了多元数据融合算法,利用数字滤波技术,实现了对火灾灾情和位置的探测。孙继平等[6]提出了基于近红外和可见光图像的矿井外因火灾感知方法,融合近红外图像和可见光图像,提高了矿井外因火灾的识别率。王树斌等[7]提出了一种基于Transformer的矿井火灾时间序列预测方法:先利用Hampel滤波和拉格朗日插值方法检测异常值,然后基于Transformer的自注意力机制从时间序列数据中提取特征并预测火灾趋势。刘春霞等[8]提出了一种改进的YOLOv5s矿井烟火探测算法,利用GhostNet对YOLOv5s的颈部进行重构,并在头部位置加入SA注意机制使其能够满足矿井烟火检测的要求。
基于深度学习的目标检测算法具有强大的特征表达能力和泛化性,在复杂场景下表现较好的性能,故在矿井火灾烟雾检测这种实时性需求较高的场景中更有优势。本文选用单阶段(One-Stage)目标检测算法YOLOv10s作为检测的基础模型。为了使模型能精准检测和定位井下火灾烟雾,首先对数据集图像进行小波降噪和Auto-Msrcr算法增强,然后对轻量级目标检测模型YOLOv10s进行改进:通过使用Focaler-IoU替换原损失函数(Loss),以及添加强化卷积神经网络性能的注意力模块CBAM和使用跨阶段部分网络模块VoV-GSCSP替换Neck中的第三个C2f模块,从而提高模型的性能,使改进模型可以满足矿井火灾烟雾的检测。
YOLOv10[9]是由清华大学研究团队开发,于2024年5月29日发布的全新SOTA模型。由于过往的YOLO版本对NMS(Non-Maximum Suppression)技术过度的依赖和架构方面的低效率影响了最佳性能的实现,YOLOv10通过引入双标签分配和以效率—准确性为导向的整体模型设计策略,其在训练阶段提供更多的正样本来丰富模型的训练,在推理阶段则通过梯度截断方式来切换一对一的检测头,使模型无需NMS后处理,同时在不损失性能的情况下减少了推理开销。本文选用YOLOv10s作为基础模型进行改进是因为其兼顾了速度和精度,对矿井火灾烟雾的检测具有显著的效果。
YOLOv10s网络主要由4部分组成:输入端、网络骨干、颈部网络和头部(输出端)。网络结构如图1所示。首先输入端输入640 px×640 px分辨率大小的图像,经过骨干网络卷积神经网络,逐步减小输入特征图的大小,并通过一系列的卷积和残差连接来学习提取图像的高级特征。颈部网络负责接收骨干网络卷积神经网络提取的特征,并继续通过一系列卷积和融合操作来学习图像特征。最终通过头部网络(输出端)进行目标检测。
在YOLOv10s的骨干网络部分C2f模块引入了增强版的CSPNet[10](Cross Stage Partial Network)结构,该结构提高了CNN 的学习能力,能在保持轻量化的同时保证准确性,以改善梯度流并减少计算冗余。SCDown模块将空间和通道解耦,先通过1×1的逐点卷积调节通道数,再通过3×3的深度卷积做空间下采样,在降低计算成本的同时最大限度保留信息。C2fCIB则是用CIB替换了原本C2f中的Bottleneck, CIB则是将Bottleneck中的标准卷积用深度卷积加逐点卷积进行替换。SPPF是空间金字塔池化,其作用是在不同尺度下对图像进行特征提取和编码,它可以将任意大小的输入图像重新缩放到固定大小,并生成固定长度的特征向量。PSA是一种高效的局部自注意力模块,它将卷积后的特征一部分输入到由多头自注意力模块MHSA和前馈网络FFN组成的模块中,然后将两部分连接起来并通过卷积进行融合,增强全局建模能力,降低计算复杂度,其网络结构如图2所示。
YOLOv10模型采用CIoU作为损失函数来评估检测中的边界框,其与IoU相比不仅考虑了重叠区域,还引入了中心点距离和长宽比,缓解了梯度消失问题,提升了检测的精度,公式如下:
式中:IoU为交并比;|A∩B|为边框交集面积;|A∪B|为边框并集面积;p2(b,bgt)为预测框b与真实框bgt的中心点之间距离的平方;c为最小外接框的对角线长度;α是一个权重参数,其公式为:
其中,v可衡量宽高比一致性,其公式为:
式中:w和h是预测框的宽和高;wgt和hgt是真实框的宽和高。由于CIoU需要计算框的中心距离和长宽比一致性,其计算复杂度增加,从而收敛缓慢。当预测框和真实框的重叠面积非常小时,无法有效处理低重叠或不重叠的框。
在实际应用中,对矿井火灾烟雾的精准定位要求极高,而目标检测定位精度很大程度上取决于边框回归损失函数,所以本文引用Focaler-IoU[11]方法,通过线性区间映射重构原始IoU损失函数,使边框回归效果提升。Focaler-IoU与本文所使用重构后的公式如下:
式中:IoU为原始IoU值,[d,u]∈[0,1],当IoU处于d和u之间时,损失函数是一个根据IoU值线性递增的函数。损失函数改进前后生成的真实框和预测框对比如图3所示。
为了增强对矿井火灾烟雾特征的提取,本文融合“即插即用”的卷积块注意模块[12](Convolutional Block Attention Module, CBAM),该模块是一种增强卷积神经网络性能的双重注意力机制,通过将通道注意力和空间注意力相结合,达到对火灾烟雾特征的双重精炼。CBAM的流程为: 输入特征先经过通道注意力(Channel Attention)模块进行加权处理,然后再经过空间注意力(Spatial Attention)模块进行最终加权处理,得到卷积输出的结果。
通道注意力模块结构如图4所示。其流程为:对输入特征图F(维度为c×h×w,c为通道数,h为高度,w为宽度)进行全局平均池化(AvgPool)和最大池化操作(MaxPool),随后生成两个不同的空间上下文描述符(平均池化后的特征)和(最大池化后的特征),然后这两个描述符被输入到一个共享的且包含隐藏层(多层感知器MLP (Multi-Layer Perceptron))的网络中,其中隐藏层的激活尺寸设为Rc/r×1×1,最终融合两个MLP的输出特征向量并相加,再通过激活函数σ(Sigmoid)映射后生成通道注意力图。通道注意力模块公式如下:
式中:Mc∈Rc×1×1为权重系数;σ为sigmoid函数;AP为AvgPool;MP为MaxPool;W0∈Rc/r×c,W1∈Rc×c/r,并且MLP权重W0和W1对于两个输入是共享的。
空间注意力模块结构如图5所示。其流程为:对输入的特征图F进行最大池化和平均池化操作,将其通道信息进行聚合,从而生成平均池化特征和最大池化特征这两个2D特征图,然后将生成的特征图拼接并进行7×7卷积运算,再通过激活函数σ(Sigmoid)映射后生成空间注意力图。空间注意力模块公式如下:
式中:Ms∈R1×h×w为权重系数;f7×7表示卷积核为7×7的运算。
YOLOv10s的颈部网络结构中第三个C2f模块负责处理中等尺寸的特征图,该层对模型检测不同大小的火灾烟雾场景至关重要。本次使用Slim-neck[13]轻量级框架中的跨阶段部分网络VoV-GSCSP模块来替换原C2f模块。该模块结合了VoVNet[14]的思想和CSPNet的特点,同时加入了全局上下文感知(Global Spatial Context, GSC)的机制。通过VoVNet的多层次特征聚合方式,VoV-GSCSP模块能够有效融合不同层次的特征;结合CSPNet能减少参数量和计算量;GSC机制可以增强模型对全局空间信息的感知。该模块非常适合在火灾烟雾检测这种复杂场景中使用,能够显著提升检测精度和效率。VoV-GSCSP模块结构如图6所示。其流程为:将输入的特征图通过残差连接(SC)进行初步特征提取,接着进入GS Bottleneck进行深层次特征压缩,然后将输出特征与初始特征拼接(Concat)后,再经过两个残差连接处理,最终生成输出结果。整体改进后的YOLOv10s模型网络结构如图7所示。
数据集的质量和规模直接影响研究和应用效果,因此,保证数据集的准确性和完整性是非常重要的。由于目前矿井火灾烟雾图像资料较少,且在井下试验具有很大的危险性,本文的图片数据来源于网络上与矿井下火灾烟雾场景相似的图片以及各种场景下的火灾烟雾图片,共计4 011张。为了减少图像中的干扰信息,对图像进行小波降噪[15]和Auto-Msrcr算法[16]图像增强处理。小波降噪技术通过对图像进行卷积操作,能够有效去除图像中的噪声,从而提升图像的质量;Auto-Msrcr算法能够有效地增强图像中的细节,改善在低照度条件下拍摄的图像清晰度。图片降噪和增强后的效果如图8所示。
本次试验采用的操作系统为ubuntu22.04,处理器为12 vCPU Intel (R) Xeon (R) Platinum 8352V CPU @ 2.10 GHz,内存为90 G,显卡为NVIDIA GeForce RTX 4090 Gpu,显存为24 G,编程语言为Python3. 12,深度学习框架版本为PyTorch2.3.0+Cuda12.1。具体操作步骤如下:
(1)数据集在Roboflow在线平台上完成标注及生成分辨率好640 px×640 px的图片,将生成的图片按7:2:1的比例分为训练集,验证集以及测试集;
(2)通过将训练集的图片进行小波降噪及Auto-Msrcr算法增强后使用改进的YOLOv10s模型进行训练,设置训练轮次为300,批处理尺寸为32,初始学习率为0.001,动量因子为0.9;
(3)与各个模型对比结果。
试验的结果采用深度学习传统的评价指标来评估,即P(Precision,准确率)、R(Recall,召回率)、AP(Average Precision,平均精度)、mAP(mean Average Precision,平均精度均值),计算公式如下:
式中:TP (True Positives)为真正例,即正确检验框数;FP (False Positives)为假正例,即错误检验框数;FN (False Negatives)为假负例,即漏检框数;P(r)为召回率r对应的精确率;APi为第i个类别的平均精度;n为总类别数(本次试验只检测火灾与烟雾,故取n=2)。
在目标检测任务中,损失函数一般由分类损失(cls_loss)、边界框损失(box_loss)和置信度损失(dfl_loss)组成,评价标准为越低越好。YOLOv10s采用双标签分配,在对齐时采用了oo(one2one)和om(one2 many)两种策略方式,在训练时两种损失函数策略同时计算,而推理时仅使用oo分支。本次试验在改进损失函数方面只针对边界框损失进行提升,所以分类损失和置信度损失结果曲线几乎完全重合,如图9和图10所示。而边界框损失有明显降低,如图11所示,较低的边界框损失可以使模型在矿井火灾烟雾检测任务中的定位精度较高,可以更准确地预测目标的位置和大小。
为了验证改进模型的有效性,与原模型及先前版本模型进行性能指标消融对比,试验结果见表1。
表1中mAP@50是在IoU=0.50的阈值下计算的所有类别的平均精度,该指标的衡量标准为:只要预测框与真实框的重叠超过50%就会算作正确的检测,容错率较高,可以更容易得到较高的精度值。mAP@50−95为IoU=0.50~0.95之间的阈值下计算得出的平均精度的平均值,该指标考虑了多种IoU阈值,能够更严格地全面反映模型的检测精度和鲁棒性。FPS(每秒帧数)为检测速度,该指标反映模型每秒处理图像的帧数,用来评估模型的实时性能。从表1的数据可以看出,本文改进模型召回率R对比YOLOv5s、YOLOv7、YOLOv10s有所下降,平均精度均值mAP@50对比YOLOv7有所下降,但其他数据均有提升,尤其是mAP@50−95这个重要指标,较YOLOv5s、YOLOv7、YOLOv8、YOLOv9s、YOLOv10s分别提升10.5%、7.5%、9.5%、7.3%、2.2%,对于检测矿井火灾烟雾这种需要高精度和高实时性的场景来说,改进后的YOLO10s模型可以满足。使用改进后的YOLOv10s模型对火灾烟雾场景进行检测和其他各模型的对比效果如图12所示。从图12中可以看出改进后的模型综合检测精度最好。
为了在矿井火灾发生的初期高效检测和精准定位火源,提出了使用改进的YOLOv10s模型作为检测工具,旨在预防矿井火灾发生。
(1)首先将收集的火灾烟雾图片在Roboflow在线平台上完成标注并按7:2:1划分成训练集、验证集以及测试集,在训练前对图片进行小波降噪及Auto-Msrcr算法增强处理;然后提出了使用Focaler-IoU方法重构YOLOv10原始损失函数,并融合强化卷积神经网络性能的注意力模块CBAM,以及使用跨阶段部分网络模块VoV-GSCSP替换颈部网络中的第三个C2f模块,通过这3种改进方法提高了YOLOv10s检测性能和精度。
(2)改进后的YOLOv10s模型与原模型相比,准确率提升了3.5%,召回率下降了1.5%、平均精度值mAP@50提升了0.7%,平均精度均值mAP@50-95提升了2.2%、FPS达到了336.5 帧/s,提高了11.9 帧/s。
(3)召回率微降1.5%,但精度显著提升,虽然对整体检测效果影响很小,但可以满足矿井火灾烟雾检测的实时性需求,未来可针对此问题加强试验研究,以期优化小目标漏检。
  • 国家自然科学基金项目(51764044)
  • 山西省2024年度研究生教育创新计划实践创新项目(2024SJ379)
  • 山西大同大学2024年研究生实践创新项目(2024SJCX06)
参考文献 引证文献
排序方式:
[1]
REIMANN P, SCHUTZE A. Fire detection in coal mines based on semiconductor gas sensors[J]. Sensor Review, 2012, 32(1):47-58.
[2]
KUMAR S, PAL K S. Underground coal fire mapping using analysis of self-potential (SP) data collected from Akashkinaree Colliery, Jharia Coalfield, India[J]. Journal of the Geological Society of India, 2020, 95(4):350-358.
[3]
王伟峰,张宝宝,王志强,等.基于YOLOv5的矿井火灾视频图像智能识别方法[J].工矿自动化,2021,47(9):53-57.
WANG Weifeng,ZHANG Baobao,WANG Zhiqiang,et al. Intelligent identification method of mine fire video images based onYOLOv5[J]. Journal of Mine Automation, 2021,47(9):53-57
[4]
白宝军.基于图像增强与多特征的煤矿井下火灾烟雾检测方法研究[D]. 西安:西安建筑科技大学,2021,20-46.
BAI Baojun. Research on smoke detection method of coal mine fire based on image enhancement and multiple features [D]. Xi'an: Xi'an University of Architecture and Technology, 2021, 20-46.
[5]
吕宗宝,董军,汝洪芳.改进的多元数据融合算法在矿井火灾检测系统中的应用[J].工业仪表与自动化装置,2010(4):94-97.
LYU Zongbao, DONG Jun, RU Hongfang. Application of mine fire detection system based on improved multi-data fusion algorithm[J]. Industrial Instrumentation & Automation, 2010(4):94-97.
[6]
孙继平,崔佳伟.矿井外因火灾感知方法[J].工矿自动化,2021,47(4):1-5+38.
SUN Jiping, CUI Jiawei. Mine external fire sensing method[J]. Journal of Mine Automation, 2021, 47(4): 1-5+38.
[7]
王树斌,王旭,闫世平,等.基于Transformer的矿井内因火灾时间序列预测方法[J].工矿自动化,2024,50(3):65-70+91.
WANG Shubin, WANG Xu, YAN Shiping, et al. Transformer based time series prediction method for mine internal caused fire[J]. Journal of Mine Automation, 2024, 50(3):65-70+91.
[8]
刘春霞,李超,潘理虎,等.改进 YOLOv5s 的煤矿烟火检测算法[J].计算机工程与应用,2023,59(17): 286-294.
LIU Chunxia, LI Chao, PAN Lihu, et al. Improved coal mine smoke and fire detection algorithm of YOLOv5s[J]. Journal of Computer Engineering & Applications, 2019, 59(17):286-294.
[9]
WANG A, CHEN H, LIU L H, et al. Yolov10: Real-time end-to-end object detection[J]. arXiv preprint arXiv:2024.
[10]
WANG C Y, LIAO H Y M, WU Y H, et al. CSPNet: a new backbone that can enhance learning capability of CNN: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops [C]. Seattle, USA: IEEE, 2020:390-391.
[11]
ZHANG H, ZHANG S. Focaler-IoU: more focused intersection over union loss[J]. arXiv preprint arXiv:2024.
[12]
WOO S, PARK J, LEE J Y, et al. Cbam: Convolutional block attention module[J]. Springer, Cham, 2018.
[13]
LI H L, LI J, WEI H B, et al. Slim-neck by GSConv: a better design paradigm of detector architectures for autonomous vehicles[J]. arXiv preprint arXiv:2022.
[14]
LEE Y, HWANG J, LEE S, et al. An energy and GPU-computation efficient backbone network for real-time object detection: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops [C]. Long Beach, USA: IEEE, 2019:752-760.
[15]
CHEN G, BUI T, KRZYZAK A. Image denoising using neighbouring wavelet coefficients[J]. Integrated Computer-Aided Engineering, 2005, 12(1):99-107.
[16]
PARTHASARATHY S, SANKARAN P. An automated multi scale retinex with color restoration for image enhancement: 2012 National Conference on Communications (NCC)[C]. Kharagpur, India: IEEE, 2012: 1-5.
2025年第45卷第9期
PDF下载
40
19
引用本文
BibTeX
文章信息
  • 接收时间:2024-10-10
  • 首发时间:2026-10-28
  • 出版时间:2025-09-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-10-10
基金
国家自然科学基金项目(51764044)
山西省2024年度研究生教育创新计划实践创新项目(2024SJ379)
山西大同大学2024年研究生实践创新项目(2024SJCX06)
作者信息
    1.山西大同大学 建筑与测绘工程学院,山西 大同市 037000
    2.山西大同大学 煤炭工程学院,山西 大同市 037000

通讯作者:

石泽来(1996—),男,河南周口人,硕士研究生,主要研究方向为矿山安全工程。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kyyjykf/CN/1322162011094499663
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
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
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