首页 期刊 论文 学科刊群 资讯 加盟 关于
EN
image
Article(id=1322161679169859858, tenantId=1146029695717560320, journalId=1225396423026438145, issueId=1322161562689847927, 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=1724428800000, receivedDateStr=2024-08-24, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1793157508890, onlineDateStr=2026-10-28, pubDate=1756051200000, pubDateStr=2025-08-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793157508890, onlineIssueDateStr=2026-10-28, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793157508890, creator=13701087609, updateTime=1793157508890, updator=13701087609, issue=Issue{id=1322161562689847927, tenantId=1146029695717560320, journalId=1225396423026438145, year='2025', volume='45', issue='8', pageStart='1', pageEnd='278', issueExtLink='null', onlineDate='null', pubDate='1756051200000', pubDateStr='2025-08-25', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793157481119, creator='13701087609', updateTime=1793158854568, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1322167323411198934, tenantId=1146029695717560320, journalId=1225396423026438145, issueId=1322161562689847927, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1322167323411198935, tenantId=1146029695717560320, journalId=1225396423026438145, issueId=1322161562689847927, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=209, endPage=216, ext={EN=ArticleExt(id=1322161679488626963, articleId=1322161679169859858, tenantId=1146029695717560320, journalId=1225396423026438145, language=EN, title=A Fusion Improvement of YOLOv7-tiny and ByteTrack Tracking for Belt Conveyor Speed Measurement Method, columnId=null, journalTitle=Mining Research and Development, columnName=null, runingTitle=null, highlight=null, articleAbstract=

Aiming at the problems of deformation of object motion, trajectory drift, and tracking loss, which lead to large errors in belt conveyor speed measurement, a method based on fusion improvement of YOLOv7-tiny and ByteTrack tracking was proposed for belt conveyor speed measurement. Firstly, the improved YOLOv7-tiny object detection algorithm was used as a detector to achieve accurate positioning of objects in images. Secondly, a secondary data association strategy was applied to strengthen the association matching of low-score confidence, while a Kalman algorithm with introduced confidence was used to make the predicted trajectory tend to the detector results, so as to improve the stability of object tracking trajectory on the belt conveyor. Finally, the camera calibration method was simplified using the image coordinates between the belt conveyor's two support rods and the distance between the support rods, and the belt conveyor speed measurement model was established to realize the speed estimation of the belt conveyor. The test results show that the MAE and MSE indicators of the proposed method have been reduced by 0.037 m/s and 0.022 m/s, respectively, effectively reducing the speed measurement error of the belt conveyor.

, authors=Xu LIANG1, Huifeng ZHANG1, Kai GAO2, authorsList=Xu LIANG, Huifeng ZHANG, Kai GAO, authorCompany=null, 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, fund=null), CN=ArticleExt(id=1322161683984920884, articleId=1322161679169859858, tenantId=1146029695717560320, journalId=1225396423026438145, language=CN, title=融合改进YOLOv7-tiny与ByteTrack跟踪的胶带运输机速度测量方法, 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=

针对因胶带运输机上运动目标发生形变和轨迹漂移导致跟踪丢失，造成胶带运输机速度测量误差较大的问题，提出了一种融合改进YOLOv7-tiny与ByteTrack跟踪的胶带运输机速度测量方法。该方法首先采用改进的YOLOv7-tiny目标检测算法作为检测器，实现图像中运动目标的准确定位；其次，利用二次数据关联策略加强低分置信度的关联匹配，同时引入置信度的卡尔曼滤波算法，使卡尔曼滤波算法预测的轨迹倾向于检测器的结果，从而提高胶带运输机上运动目标跟踪轨迹的稳定性；最后，通过胶带运输机两个支撑杆间的图像坐标及支撑杆间的距离简化相机标定方法，建立胶带运输机速度测量模型，实现胶带运输机的速度估计。试验结果表明，所提出的新方法其计算结果的MAE和MSE指标分别降低了0.037 m/s和0.022 m/s，有效降低了胶带运输机的速度测量误差。

, authors=梁旭1, 张慧峰1, 高凯2, authorsList=梁旭, 张慧峰, 高凯, authorCompany=null, correspAuthors=null, authorNote=

梁旭（1985—），男，陕西富平人，硕士，高级工程师，主要从事智能矿山方面研究工作。E-mail:

, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=sq8qhHQtv38pdkxuOdm20Q==, magXml=oseaijZtY7x4TaZYSDVRWg==, pdfUrl=null, pdf=ZzIaGzHYtIcZFQHRTGDQ5w==, pdfFileSize=4375876, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=g+c8+gq/zBlFWPvBAE4EeA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=f8xm07/qQr8iP07QSxXWPQ==, mapNumber=null, fund=null)}, authors=[Author(id=1322161684827975996, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=56920905@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322161684932833598, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, authorId=1322161684827975996, language=EN, stringName=Xu LIANG, firstName=Xu, middleName=null, lastName=LIANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Shaanxi Xiaobaodang Mining Co., Ltd., Yulin, Shaanxi 719302, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322161685004136767, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, authorId=1322161684827975996, language=CN, stringName=梁旭, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.陕西小保当矿业有限公司，陕西　榆林市　719302, bio={"content":"

梁旭（1985—），男，陕西富平人，硕士，高级工程师，主要从事智能矿山方面研究工作。E-mail:

"}, bioImg=null, bioContent=

梁旭（1985—），男，陕西富平人，硕士，高级工程师，主要从事智能矿山方面研究工作。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322161684299493685, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, xref=1., ext=[AuthorCompanyExt(id=1322161684312076598, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, companyId=1322161684299493685, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Shaanxi Xiaobaodang Mining Co., Ltd., Yulin, Shaanxi 719302, China), AuthorCompanyExt(id=1322161684412739895, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, companyId=1322161684299493685, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.陕西小保当矿业有限公司，陕西　榆林市　719302)])]), Author(id=1322161685079634241, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, orderNo=1, 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=1322161685142548803, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, authorId=1322161685079634241, language=EN, stringName=Huifeng ZHANG, firstName=Huifeng, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Shaanxi Xiaobaodang Mining Co., Ltd., Yulin, Shaanxi 719302, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322161685209657668, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, authorId=1322161685079634241, language=CN, stringName=张慧峰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.陕西小保当矿业有限公司，陕西　榆林市　719302, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322161684299493685, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, xref=1., ext=[AuthorCompanyExt(id=1322161684312076598, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, companyId=1322161684299493685, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Shaanxi Xiaobaodang Mining Co., Ltd., Yulin, Shaanxi 719302, China), AuthorCompanyExt(id=1322161684412739895, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, companyId=1322161684299493685, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.陕西小保当矿业有限公司，陕西　榆林市　719302)])]), Author(id=1322161685285155142, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, 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=1322161685373235528, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, authorId=1322161685285155142, language=EN, stringName=Kai GAO, firstName=Kai, middleName=null, lastName=GAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.College of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an, Shaanxi 710699, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322161685461315913, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, authorId=1322161685285155142, language=CN, stringName=高凯, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.西安科技大学 计算机科学与技术学院，陕西　西安　710699, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322161684492431672, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, xref=2., ext=[AuthorCompanyExt(id=1322161684500820281, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, companyId=1322161684492431672, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an, Shaanxi 710699, China), AuthorCompanyExt(id=1322161684505014586, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, companyId=1322161684492431672, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.西安科技大学 计算机科学与技术学院，陕西　西安　710699)])])], keywords=[Keyword(id=1322161685561979210, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=EN, orderNo=1, keyword=Belt conveyor), Keyword(id=1322161685620699467, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=EN, orderNo=2, keyword=Operating speed), Keyword(id=1322161685700391244, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=EN, orderNo=3, keyword=Object detection), Keyword(id=1322161685763305805, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=EN, orderNo=4, keyword=Secondary data association strategy), Keyword(id=1322161685834608974, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=EN, orderNo=5, keyword=YOLOv7), Keyword(id=1322161685918495055, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=EN, orderNo=6, keyword=ByteTrack tracking algorithm), Keyword(id=1322161685985603920, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=CN, orderNo=1, keyword=胶带运输机), Keyword(id=1322161687625576785, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=CN, orderNo=2, keyword=运行速度), Keyword(id=1322161687747211602, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=CN, orderNo=3, keyword=目标检测), Keyword(id=1322161687826903379, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=CN, orderNo=4, keyword=二次数据关联策略), Keyword(id=1322161687906595156, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=CN, orderNo=5, keyword=YOLOv7), Keyword(id=1322161687986286933, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=CN, orderNo=6, keyword=ByteTrack跟踪算法)], refs=[Reference(id=1322161692553884020, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=580, pageEnd=587, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=GIRSHICK Ross, DONAHUE Jeff, DARRELL Trevor, journalName=null, refType=null, unstructuredReference=GIRSHICK Ross, DONAHUE Jeff, DARRELL Trevor, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]// 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE, 2014:580-587., articleTitle=Rich feature hierarchies for accurate object detection and semantic segmentation, refAbstract=null), Reference(id=1322161692650353013, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2015, volume=37, issue=9, pageStart=1904, pageEnd=1916, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=HE Kaiming, ZHANG Xiangyu, REN Shaoqing, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916., articleTitle=Spatial pyramid pooling in deep convolutional networks for visual recognition, refAbstract=null), Reference(id=1322161692742627702, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=1440, pageEnd=1448, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=GIRSHICK Ross, journalName=null, refType=null, unstructuredReference=GIRSHICK Ross. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision (ICCV). New York: IEEE, 2015: 1440-1448., articleTitle=Fast R-CNN, refAbstract=null), Reference(id=1322161692818125175, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2017, volume=39, issue=6, pageStart=1137, pageEnd=1149, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=REN Shaoqing, HE Kaiming, GIRSHICK Ross, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=REN Shaoqing, HE Kaiming, GIRSHICK Ross, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149., articleTitle=Faster R-CNN: towards real-time object detection with region proposal networks, refAbstract=null), Reference(id=1322161692906205560, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=379, pageEnd=387, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=DAI Jifeng, LI Yi, HE Kaiming, journalName=null, refType=null, unstructuredReference=DAI Jifeng, LI Yi, HE Kaiming, et al. R-FCN: object detection via region-based fully convolutional networks[C]//The 30th International Conference on Neural Information Processing Systems. New York: Curran Associates, 2016:379-387., articleTitle=R-FCN: object detection via region-based fully convolutional networks, refAbstract=null), Reference(id=1322161693032034681, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, 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 Zhaowei, VASCONCELOS Nuno, journalName=null, refType=null, unstructuredReference=CAI Zhaowei, VASCONCELOS Nuno. Cascade R-CNN: delving into high quality object detection[C]//2018 IEEE/ CVF Conference on Computer Vision and Pattern Recognition(CVPR). New York: IEEE, 2018:6154-6162., articleTitle=Cascade R-CNN: delving into high quality object detection, refAbstract=null), Reference(id=1322161693094949242, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=779, pageEnd=788, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=REDMON Joseph, DIVVALA Santosh, GIRSHICK Ross, journalName=null, refType=null, unstructuredReference=REDMON Joseph, DIVVALA Santosh, GIRSHICK Ross, et al. You only look once: Unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE, 2016:779-788., articleTitle=You only look once: Unified, real-time object detection, refAbstract=null), Reference(id=1322161693178835323, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=REDMON Joseph, FARHADI Ali, journalName=ArXiv, refType=null, unstructuredReference=REDMON Joseph, FARHADI Ali. YOLOv3: an incremental improvement[J]. ArXiv, 2018:4714433., articleTitle=YOLOv3: an incremental improvement, refAbstract=null), Reference(id=1322161693245944188, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=13029, pageEnd=13038, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=WANG Chenyao, BOCHKOVSKIY A, LIAO Hongyuan Mark, journalName=null, refType=null, unstructuredReference=WANG Chenyao, BOCHKOVSKIY A, LIAO Hongyuan Mark. Scaled-YOLOv4: scaling cross stage partial network[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE, 2021: 13029-13038., articleTitle=Scaled-YOLOv4: scaling cross stage partial network, refAbstract=null), Reference(id=1322161693317247357, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=13039, pageEnd=13048, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=CHEN Qiang, WANG Y M, YAN F T, journalName=null, refType=null, unstructuredReference=CHEN Qiang, WANG Y M, YAN F T, et al. You only look one-level feature[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2021:13039-13048., articleTitle=You only look one-level feature, refAbstract=null), Reference(id=1322161693417910654, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=13733, pageEnd=13742, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=DING Xiaohan, ZHANG Xiangyu, MA Ningning, journalName=null, refType=null, unstructuredReference=DING Xiaohan, ZHANG Xiangyu, MA Ningning, et al. Repvgg: making vgg-style convnets great again[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2021: 13733-13742., articleTitle=Repvgg: making vgg-style convnets great again, refAbstract=null), Reference(id=1322161693497602431, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2020, volume=46, issue=5, pageStart=63, pageEnd=68, url=null, language=null, rfNumber=[12], rfOrder=11, authorNames=杜京义, 郝乐, 王悦阳, journalName=工矿自动化, refType=null, unstructuredReference=杜京义，郝乐，王悦阳，等.一种煤矿井下输煤大块物检测方法[J].工矿自动化，2020，46(5):63-68., articleTitle=一种煤矿井下输煤大块物检测方法, refAbstract=null), Reference(id=1322161693564711296, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2020, volume=46, issue=5, pageStart=63, pageEnd=68, url=null, language=null, rfNumber=[12], rfOrder=12, authorNames=DU Jingyi, HAO Le, WANG Yueyang, journalName=Journal of Mine Automation, refType=null, unstructuredReference=DU Jingyi，HAO Le，WANG Yueyang，et al. A detection method for large blocks in underground coal transportation [J]. Journal of Mine Automation, 2020, 46(5):63-68., articleTitle=A detection method for large blocks in underground coal transportation, refAbstract=null), Reference(id=1322161693636014465, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2019, volume=50, issue=12, pageStart=127, pageEnd=130, url=null, language=null, rfNumber=[13], rfOrder=13, authorNames=吴守鹏, 丁恩杰, 俞啸, journalName=煤矿安全, refType=null, unstructuredReference=吴守鹏，丁恩杰，俞啸.基于改进 FPN 的输送带异物识别方法[J].煤矿安全，2019, 50(12): 127-130., articleTitle=基于改进 FPN 的输送带异物识别方法, refAbstract=null), Reference(id=1322161693715706242, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2019, volume=50, issue=12, pageStart=127, pageEnd=130, url=null, language=null, rfNumber=[13], rfOrder=14, authorNames=WU Shoupeng, DING Enjie, YU Xiao, journalName=Safety in Coal Mines, refType=null, unstructuredReference=WU Shoupeng, DING Enjie, YU Xiao. Foreign body identification of belt based on improved FPN[J]. Safety in Coal Mines, 2019, 50(12):127-130., articleTitle=Foreign body identification of belt based on improved FPN, refAbstract=null), Reference(id=1322161693799592323, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2021, volume=47, issue=12, pageStart=75, pageEnd=80, url=null, language=null, rfNumber=[14], rfOrder=15, authorNames=叶鸥, 窦晓熠, 付燕, journalName=工矿自动化, refType=null, unstructuredReference=叶鸥，窦晓熠，付燕，等.融合轻量级网络和双重注意力机制的煤块检测方法[J].工矿自动化，2021，47(12):75-80., articleTitle=融合轻量级网络和双重注意力机制的煤块检测方法, refAbstract=null), Reference(id=1322161693891867012, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2021, volume=47, issue=12, pageStart=75, pageEnd=80, url=null, language=null, rfNumber=[14], rfOrder=16, authorNames=YE Ou, DOU Xiaoyi, FU Yan, journalName=Journal of Mine Automation, refType=null, unstructuredReference=YE Ou, DOU Xiaoyi, FU Yan, et al. Coal block detection method integrating lightweight network and dual attention mechanism[J]. Journal of Mine Automation, 2021, 47(12):75-80., articleTitle=Coal block detection method integrating lightweight network and dual attention mechanism, refAbstract=null), Reference(id=1322161693954781573, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2012, volume=null, issue=null, pageStart=2716, pageEnd=2719, url=null, language=null, rfNumber=[15], rfOrder=17, authorNames=DU Kai, JU Yongfeng, JIN Yinli, journalName=null, refType=null, unstructuredReference=DU Kai, JU Yongfeng, JIN Yinli, et al. Object tracking based on improved meanshift and SIFT[C]//2012 2nd International Conference on Consumer Electronics: Communications and Networks (CECNet). New York: IEEE, 2012:2716-2719., articleTitle=Object tracking based on improved meanshift and SIFT, refAbstract=null), Reference(id=1322161694026084742, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2010, volume=null, issue=null, pageStart=9, pageEnd=16, url=null, language=null, rfNumber=[16], rfOrder=18, authorNames=EXNER David, BRUNS Erich, KURZ Daniel, journalName=null, refType=null, unstructuredReference=EXNER David, BRUNS Erich, KURZ Daniel, et al. Fast and robust camshift tracking[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Workshops. New York: IEEE, 2010:9-16., articleTitle=Fast and robust camshift tracking, refAbstract=null), Reference(id=1322161694101582215, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=3464, pageEnd=3468, url=null, language=null, rfNumber=[17], rfOrder=19, authorNames=BEWLEY Alex, GE Zongyuan, OTT Lionel, journalName=null, refType=null, unstructuredReference=BEWLEY Alex, GE Zongyuan, OTT Lionel, et al. Simple online and realtime tracking[C]//2016 IEEE International Conference on Image Processing (ICIP). New York: IEEE, 2016:3464-3468., articleTitle=Simple online and realtime tracking, refAbstract=null), Reference(id=1322161694177079688, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=3645, pageEnd=3649, url=null, language=null, rfNumber=[18], rfOrder=20, authorNames=NICOLAI Wojke, ALEX Bewley, PAULUS Dietrich, journalName=null, refType=null, unstructuredReference=NICOLAI Wojke, ALEX Bewley, PAULUS Dietrich. Simple online and realtime tracking with a deep association metric[C]//2017 IEEE International Conference on Image Processing (ICIP). New York: IEEE, 2017:3645-3649., articleTitle=Simple online and realtime tracking with a deep association metric, refAbstract=null), Reference(id=1322161694248382857, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=1, pageEnd=21, url=null, language=null, rfNumber=[19], rfOrder=21, authorNames=ZHANG Yifu, SUN Peize, JIANG Yi, journalName=null, refType=null, unstructuredReference=ZHANG Yifu, SUN Peize, JIANG Yi, et al. Bytetrack: multi-object tracking by associating every detection box [C]//European Conference on Computer Vision(ECCV). Chan: Springer, 2022:1-21., articleTitle=Bytetrack: multi-object tracking by associating every detection box, refAbstract=null), Reference(id=1322161694328074634, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=6, pageStart=183, pageEnd=190, url=null, language=null, rfNumber=[20], rfOrder=22, authorNames=高凯, 董立红, 邓凡, journalName=矿业研究与开发, refType=null, unstructuredReference=高凯，董立红，邓凡.基于递归门控卷积和上下文注意力的煤块检测算法[J].矿业研究与开发，2023，43(6):183-190., articleTitle=基于递归门控卷积和上下文注意力的煤块检测算法, refAbstract=null), Reference(id=1322161694395183499, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=6, pageStart=183, pageEnd=190, url=null, language=null, rfNumber=[20], rfOrder=23, authorNames=GAO Kai, DONG Lihong, DENG Fan, journalName=Mining Research and Development, refType=null, unstructuredReference=GAO Kai，DONG Lihong，DENG Fan. Coal block detection algorithm based on recursive gated convolution and contextual attention[J]. Mining Research and Development，2023, 43(6):183-190., articleTitle=Coal block detection algorithm based on recursive gated convolution and contextual attention, refAbstract=null)], funds=[Fund(id=1322161692390306162, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, awardId=62102309, language=CN, fundingSource=国家自然科学基金项目(62102309), fundOrder=null, country=null), Fund(id=1322161692453220723, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, awardId=8146119003, language=CN, fundingSource=陕西省教育厅科研计划专项项目(8146119003), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322161684299493685, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, xref=1., ext=[AuthorCompanyExt(id=1322161684312076598, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, companyId=1322161684299493685, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Shaanxi Xiaobaodang Mining Co., Ltd., Yulin, Shaanxi 719302, China), AuthorCompanyExt(id=1322161684412739895, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, companyId=1322161684299493685, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.陕西小保当矿业有限公司，陕西　榆林市　719302)]), AuthorCompany(id=1322161684492431672, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, xref=2., ext=[AuthorCompanyExt(id=1322161684500820281, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, companyId=1322161684492431672, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an, Shaanxi 710699, China), AuthorCompanyExt(id=1322161684505014586, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, companyId=1322161684492431672, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.西安科技大学 计算机科学与技术学院，陕西　西安　710699)])], figs=[ArticleFig(id=1322161688133087574, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=EN, label=Fig.1, caption=Network architecture of improved YOLOv7-tiny, figureFileSmall=uVXwylmV2I6E5tdVCx8PsQ==, figureFileBig=g+c8+gq/zBlFWPvBAE4EeA==, tableContent=null), ArticleFig(id=1322161688200196439, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=CN, label=图1, caption=改进的YOLOv7-tiny网络结构, figureFileSmall=uVXwylmV2I6E5tdVCx8PsQ==, figureFileBig=g+c8+gq/zBlFWPvBAE4EeA==, tableContent=null), ArticleFig(id=1322161688414105944, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=EN, label=Fig.2, caption=The idea of object tracking algorithm based on ByteTrack, figureFileSmall=WclWbpcnZ0d6PiEyMKi3Ag==, figureFileBig=i8BWEJ2ZzygqXAkJkM3zWg==, tableContent=null), ArticleFig(id=1322161688493797721, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=CN, label=图2, caption=基于ByteTrack的目标跟踪算法思路, figureFileSmall=WclWbpcnZ0d6PiEyMKi3Ag==, figureFileBig=i8BWEJ2ZzygqXAkJkM3zWg==, tableContent=null), ArticleFig(id=1322161688577683802, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=EN, label=Fig.3, caption=Scheme of speed measurement for tape conveyor, figureFileSmall=sOyLYm/EBnFHROL2xbYcWQ==, figureFileBig=uz9H+meAy37sSZt5l0BipA==, tableContent=null), ArticleFig(id=1322161688653181275, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=CN, label=图3, caption=胶带运输机速度测量方案, figureFileSmall=sOyLYm/EBnFHROL2xbYcWQ==, figureFileBig=uz9H+meAy37sSZt5l0BipA==, tableContent=null), ArticleFig(id=1322161688720290140, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=EN, label=Fig.4, caption=Pixel displacement at the center point, figureFileSmall=ivEr8ONMxUk6GS/PUIPdTA==, figureFileBig=zB/r59OXJbobUsV5tH4l8w==, tableContent=null), ArticleFig(id=1322161688791593309, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=CN, label=图4, caption=中心点像素位移, figureFileSmall=ivEr8ONMxUk6GS/PUIPdTA==, figureFileBig=zB/r59OXJbobUsV5tH4l8w==, tableContent=null), ArticleFig(id=1322161688854507870, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=EN, label=Fig.5, caption=ID identification switching, figureFileSmall=+kveGo6HF4R6HoA4PNpSFw==, figureFileBig=oNqQbGZdmrByX7bSX0ri/w==, tableContent=null), ArticleFig(id=1322161688938393951, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=CN, label=图5, caption=ID标识切换, figureFileSmall=+kveGo6HF4R6HoA4PNpSFw==, figureFileBig=oNqQbGZdmrByX7bSX0ri/w==, tableContent=null), ArticleFig(id=1322161689039057248, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=EN, label=Fig.6, caption=Tracking disappear, figureFileSmall=Tmh4eWMDBchKXRWh9/3auw==, figureFileBig=WzxTRe9yw7Y4ef1DRcm8jQ==, tableContent=null), ArticleFig(id=1322161689118749025, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=CN, label=图6, caption=跟踪丢失, figureFileSmall=Tmh4eWMDBchKXRWh9/3auw==, figureFileBig=WzxTRe9yw7Y4ef1DRcm8jQ==, tableContent=null), ArticleFig(id=1322161689190052194, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=EN, label=Fig.7, caption=Continuous tracking of multiple frames, figureFileSmall=PjRElwFjK/vFWj+IuGzs1w==, figureFileBig=nONVqXF2kCOt6IIgpwJ8kQ==, tableContent=null), ArticleFig(id=1322161689252966755, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=CN, label=图7, caption=多帧连续跟踪, figureFileSmall=PjRElwFjK/vFWj+IuGzs1w==, figureFileBig=nONVqXF2kCOt6IIgpwJ8kQ==, tableContent=null), ArticleFig(id=1322161689450099044, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=EN, label=Table 1, caption=

Test environment

, figureFileSmall=null, figureFileBig=null, tableContent=
操作系统CPUGPU内存编程软件
Windows 11AMD Ryzen 7 5800 HNVIDIA RTX 3 050 Ti16 GBPyCharm
), ArticleFig(id=1322161689513013605, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=CN, label=表1, caption=

试验环境

, figureFileSmall=null, figureFileBig=null, tableContent=
操作系统CPUGPU内存编程软件
Windows 11AMD Ryzen 7 5800 HNVIDIA RTX 3 050 Ti16 GBPyCharm
), ArticleFig(id=1322161689609482598, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=EN, label=Table 2, caption=

Performance verification test results of improved Kalman filter algorithm

, figureFileSmall=null, figureFileBig=null, tableContent=
算法MOTA/%HOTA/%IDF1/%
卡尔曼滤波88.579.690.0
改进的卡尔曼滤波91.283.592.4
), ArticleFig(id=1322161689676591463, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=CN, label=表2, caption=

改进卡尔曼滤波算法的性能验证试验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
算法MOTA/%HOTA/%IDF1/%
卡尔曼滤波88.579.690.0
改进的卡尔曼滤波91.283.592.4
), ArticleFig(id=1322161689877918056, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=EN, label=Table 3, caption=

Performance comparison results of different algorithms

, figureFileSmall=null, figureFileBig=null, tableContent=
算法MOTA/%HOTA/%IDF1/%
SORT81.372.484.6
OC-SORT85.178.688.7
本文的目标跟踪算法88.579.690.0
), ArticleFig(id=1322161689957609833, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=CN, label=表3, caption=

不同算法的性能对比结果

, figureFileSmall=null, figureFileBig=null, tableContent=
算法MOTA/%HOTA/%IDF1/%
SORT81.372.484.6
OC-SORT85.178.688.7
本文的目标跟踪算法88.579.690.0
), ArticleFig(id=1322161690041495914, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=EN, label=Table 4, caption=

Calculated speed based on the first video

, figureFileSmall=null, figureFileBig=null, tableContent=
视频帧数/帧真实速度/(m/s)帧间速度/(m/s)测量速度/(m/s)
363.60.211 23.80
723.60.180 43.24
1083.60.190 53.43
1443.60.220 93.97
1803.60.195 73.52
), ArticleFig(id=1322161690137964907, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=CN, label=表4, caption=

基于第 1 段视频计算的速度

, figureFileSmall=null, figureFileBig=null, tableContent=
视频帧数/帧真实速度/(m/s)帧间速度/(m/s)测量速度/(m/s)
363.60.211 23.80
723.60.180 43.24
1083.60.190 53.43
1443.60.220 93.97
1803.60.195 73.52
), ArticleFig(id=1322161690301542764, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=EN, label=Table 5, caption=

Calculated speed based on the second video

, figureFileSmall=null, figureFileBig=null, tableContent=
视频帧数/帧真实速度/(m/s)帧间速度/(m/s)测量速度/(m/s)
363.60.202 33.64
723.60.220 13.96
1083.60.187 43.37
1443.60.189 43.40
1803.60.198 93.58
), ArticleFig(id=1322161690364457325, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=CN, label=表5, caption=

基于第 2 段视频计算的速度

, figureFileSmall=null, figureFileBig=null, tableContent=
视频帧数/帧真实速度/(m/s)帧间速度/(m/s)测量速度/(m/s)
363.60.202 33.64
723.60.220 13.96
1083.60.187 43.37
1443.60.189 43.40
1803.60.198 93.58
), ArticleFig(id=1322161690431566190, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=EN, label=Table 6, caption=

Calculated speed based on the third video

, figureFileSmall=null, figureFileBig=null, tableContent=
视频帧数/帧真实速度/(m/s)帧间速度/(m/s)测量速度/(m/s)
363.60.211 23.80
723.60.180 33.24
1083.600
1443.600
1803.600
), ArticleFig(id=1322161692109287791, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=CN, label=表6, caption=

基于第 3 段视频计算的速度

, figureFileSmall=null, figureFileBig=null, tableContent=
视频帧数/帧真实速度/(m/s)帧间速度/(m/s)测量速度/(m/s)
363.60.211 23.80
723.60.180 33.24
1083.600
1443.600
1803.600
), ArticleFig(id=1322161692197368176, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=EN, label=Table 7, caption=

Error analysis of different speed measurement methods

, figureFileSmall=null, figureFileBig=null, tableContent=
方法MAE/(m/s)MSE/(m/s)FPS/(帧/s)
YOLOv5s+ByteTrack0.34240.359173
YOLOv7-tiny+ByteTrack0.32120.344572
本文方法0.30400.322172
), ArticleFig(id=1322161692264477041, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, language=CN, label=表7, caption=

不同测速方法的测量误差分析

, figureFileSmall=null, figureFileBig=null, tableContent=
方法MAE/(m/s)MSE/(m/s)FPS/(帧/s)
YOLOv5s+ByteTrack0.34240.359173
YOLOv7-tiny+ByteTrack0.32120.344572
本文方法0.30400.322172
)], 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/I8/209, detailUrlEn=https://castjournals.cast.org.cn/joweb/kyyjykf/EN/Y2025/V45/I8/209, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kyyjykf/CN/PDF/Y2025/V45/I8/209, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kyyjykf/EN/PDF/Y2025/V45/I8/209, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1756051200000, fullTextJson=null, articleText=null, reference=null)
收藏切换
融合改进YOLOv7-tiny与ByteTrack跟踪的胶带运输机速度测量方法
收藏切换
PDF下载
梁旭 1 , 张慧峰 1 , 高凯 2
矿业研究与开发 | 矿山机电与矿业智能化 2025,45(8): 209-216
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 (8) : 209 -216
融合改进YOLOv7-tiny与ByteTrack跟踪的胶带运输机速度测量方法
全屏
[Author(id=1322161684827975996, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=56920905@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322161684932833598, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, authorId=1322161684827975996, language=EN, stringName=Xu LIANG, firstName=Xu, middleName=null, lastName=LIANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Shaanxi Xiaobaodang Mining Co., Ltd., Yulin, Shaanxi 719302, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322161685004136767, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, authorId=1322161684827975996, language=CN, stringName=梁旭, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.陕西小保当矿业有限公司，陕西　榆林市　719302, bio={"content":"

梁旭（1985—），男，陕西富平人，硕士，高级工程师，主要从事智能矿山方面研究工作。E-mail:

"}, bioImg=null, bioContent=

梁旭（1985—），男，陕西富平人，硕士，高级工程师，主要从事智能矿山方面研究工作。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322161684299493685, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, xref=1., ext=[AuthorCompanyExt(id=1322161684312076598, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, companyId=1322161684299493685, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Shaanxi Xiaobaodang Mining Co., Ltd., Yulin, Shaanxi 719302, China), AuthorCompanyExt(id=1322161684412739895, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, companyId=1322161684299493685, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.陕西小保当矿业有限公司，陕西　榆林市　719302)])]), Author(id=1322161685079634241, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, orderNo=1, 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=1322161685142548803, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, authorId=1322161685079634241, language=EN, stringName=Huifeng ZHANG, firstName=Huifeng, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Shaanxi Xiaobaodang Mining Co., Ltd., Yulin, Shaanxi 719302, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322161685209657668, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, authorId=1322161685079634241, language=CN, stringName=张慧峰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.陕西小保当矿业有限公司，陕西　榆林市　719302, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322161684299493685, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, xref=1., ext=[AuthorCompanyExt(id=1322161684312076598, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, companyId=1322161684299493685, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Shaanxi Xiaobaodang Mining Co., Ltd., Yulin, Shaanxi 719302, China), AuthorCompanyExt(id=1322161684412739895, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, companyId=1322161684299493685, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.陕西小保当矿业有限公司，陕西　榆林市　719302)])]), Author(id=1322161685285155142, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, 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=1322161685373235528, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, authorId=1322161685285155142, language=EN, stringName=Kai GAO, firstName=Kai, middleName=null, lastName=GAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.College of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an, Shaanxi 710699, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322161685461315913, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, authorId=1322161685285155142, language=CN, stringName=高凯, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.西安科技大学 计算机科学与技术学院，陕西　西安　710699, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322161684492431672, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, xref=2., ext=[AuthorCompanyExt(id=1322161684500820281, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, companyId=1322161684492431672, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an, Shaanxi 710699, China), AuthorCompanyExt(id=1322161684505014586, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322161679169859858, companyId=1322161684492431672, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.西安科技大学 计算机科学与技术学院，陕西　西安　710699)])])]
梁旭1 , 张慧峰1, 高凯2
作者信息
  • 1.陕西小保当矿业有限公司，陕西　榆林市　719302
  • 2.西安科技大学 计算机科学与技术学院，陕西　西安　710699
作者简介:

梁旭（1985—），男，陕西富平人，硕士，高级工程师，主要从事智能矿山方面研究工作。E-mail:

A Fusion Improvement of YOLOv7-tiny and ByteTrack Tracking for Belt Conveyor Speed Measurement Method
Xu LIANG1 , Huifeng ZHANG1, Kai GAO2
Affiliations
  • 1.Shaanxi Xiaobaodang Mining Co., Ltd., Yulin, Shaanxi 719302, China
  • 2.College of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an, Shaanxi 710699, China
出版时间: 2025-08-25
文章导航
收藏切换
摘要
收起

针对因胶带运输机上运动目标发生形变和轨迹漂移导致跟踪丢失，造成胶带运输机速度测量误差较大的问题，提出了一种融合改进YOLOv7-tiny与ByteTrack跟踪的胶带运输机速度测量方法。该方法首先采用改进的YOLOv7-tiny目标检测算法作为检测器，实现图像中运动目标的准确定位；其次，利用二次数据关联策略加强低分置信度的关联匹配，同时引入置信度的卡尔曼滤波算法，使卡尔曼滤波算法预测的轨迹倾向于检测器的结果，从而提高胶带运输机上运动目标跟踪轨迹的稳定性；最后，通过胶带运输机两个支撑杆间的图像坐标及支撑杆间的距离简化相机标定方法，建立胶带运输机速度测量模型，实现胶带运输机的速度估计。试验结果表明，所提出的新方法其计算结果的MAE和MSE指标分别降低了0.037 m/s和0.022 m/s，有效降低了胶带运输机的速度测量误差。

胶带运输机  /  运行速度  /  目标检测  /  二次数据关联策略  /  YOLOv7  /  ByteTrack跟踪算法

Aiming at the problems of deformation of object motion, trajectory drift, and tracking loss, which lead to large errors in belt conveyor speed measurement, a method based on fusion improvement of YOLOv7-tiny and ByteTrack tracking was proposed for belt conveyor speed measurement. Firstly, the improved YOLOv7-tiny object detection algorithm was used as a detector to achieve accurate positioning of objects in images. Secondly, a secondary data association strategy was applied to strengthen the association matching of low-score confidence, while a Kalman algorithm with introduced confidence was used to make the predicted trajectory tend to the detector results, so as to improve the stability of object tracking trajectory on the belt conveyor. Finally, the camera calibration method was simplified using the image coordinates between the belt conveyor's two support rods and the distance between the support rods, and the belt conveyor speed measurement model was established to realize the speed estimation of the belt conveyor. The test results show that the MAE and MSE indicators of the proposed method have been reduced by 0.037 m/s and 0.022 m/s, respectively, effectively reducing the speed measurement error of the belt conveyor.

Belt conveyor  /  Operating speed  /  Object detection  /  Secondary data association strategy  /  YOLOv7  /  ByteTrack tracking algorithm
梁旭, 张慧峰, 高凯. 融合改进YOLOv7-tiny与ByteTrack跟踪的胶带运输机速度测量方法. 矿业研究与开发, 2025 , 45 (8) : 209 -216 .
Xu LIANG, Huifeng ZHANG, Kai GAO. A Fusion Improvement of YOLOv7-tiny and ByteTrack Tracking for Belt Conveyor Speed Measurement Method[J]. Mining Research and Development, 2025 , 45 (8) : 209 -216 .
正文
收起
0　引言
收起
运行速度实时监测是胶带运输机的智能化发展方向，主要涉及目标检测、目标跟踪和视觉测速等技术，通过准确检测和跟踪胶带运输机上的运动目标，实现胶带运输机实时运行速度的视觉监测。其中，在目标检测研究方面，主要分为两阶段目标检测方法和单阶段目标检测方法。
两阶段目标检测包括生成候选框和分类位置回归两个部分。例如，R-CNN（Region-CNN）检测算法首先通过选择性搜索获取候选区域，再使用卷积神经网络提取特征，最后使用支持向量机和回归器对特征进行目标分类以及候选框坐标的获取，其检测性能远超传统方法[1]。SPP-Net(Spatial Pyramid Pooling Networks)算法通过金字塔池化层适应任何尺寸的图像输入，使得每个候选区域不需要经过CNN，可以直接获得感兴趣区域的特征[2]。Fast R-CNN算法结合SPP-Net网络，引入了多任务损失函数，提升了目标检测速度[3]。此后，改进的 Faster R-CNN算法通过RPN在生成候选区域的同时产生锚点，进一步提高了目标检测速度[4]。R-FCN算法通过引入全卷积网络，实现了参数共享，使得检测速度和检测精度得以权衡[5]。Cascade R-CNN算法引入了级联架构，减少了网络检测噪声[6]。
单阶段目标检测算法不需要预先生成候选区域，可以大幅提高目标检测效率。例如YOLO v1模型是首个基于回归分析的目标检测算法，省略了提取候选区域过程，大幅提高了检测效率[7]。YOLO v3算法使用了更大更深的Darknet-53网络，并引入残差网络的跨层加和操作，进一步提高了模型检测精度和速度[8]。Scaled-YOLO v4模型通过设计针对小模型的强大模型缩放方法，平衡了速度和准确性[9]。YOLOF模型采用分而治之的思想对FPN结构进行了改进，实现了检测速度的大幅提升[10]。YOLO v6检测算法基于RepVGG[11]结构，设计了EfficientRep的主干网络结构，增加了特征重用的效率。
在胶带运输机目标检测研究方面，传统方法需要人工设计特征，而目前基于深度学习的方法成为了主流。例如，杜京义等[12]提出融合Canny算子的HED神经网络，吴守鹏等[13]提出基于Faster-RCNN的输送带异物识别方法，叶鸥等[14]提出融合YOLO v4与MobileNet的轻量级网络模型。
此外，多目标跟踪也是计算机视觉领域备受关注的研究方向之一。传统方法有Meanshift[15]、粒子滤波和Camshift连续自适应均值滤波[16]等算法。基于深度学习的方法有经典SORT算法[17]和Deep SORT算法[18]。2022年，ZHANG等[19]提出了以BYTE数据关联的ByteTrack多目标跟踪算法。
根据目标检测和目标跟踪的相关研究发现，运动目标发生形变、轨迹漂移和跟踪丢失容易导致胶带运输机速度测量出现较大的误差，不利于胶带运输机运行速度的准确监测。为解决该问题，本文提出了一种融合改进YOLOv7-tiny与ByteTrack跟踪的胶带运输机速度测量方法。该方法首先采用改进的YOLOv7-tiny检测算法作为检测器，实现图像中运动目标的准确定位；然后，利用二次数据关联策略加强低分置信度的关联匹配，并引入置信度的卡尔曼滤波，使卡尔曼滤波预测轨迹倾向于检测器的结果，提高运动目标跟踪轨迹的稳定性；最后，通过胶带运输机两个支撑杆间的图像坐标及支撑杆间的距离简化相机标定的方法，建立胶带运输机速度测量模型，实现胶带运输机的速度估计。
1　改进的YOLOv7-tiny目标检测算法
收起
为减少光照不均和背景干扰等因素对运动目标检测的影响，本文采用文献[20]提出的改进YOLOv7-tiny目标检测算法进行运动目标的实时检测。该网络模型结构如图1所示。
该网络模型通过在YOLOv7-tiny的主干网络中引入递归门控卷积模块，并构建ELAN-GN模块，逐步捕获视频图像的高阶语义信息，增强运动目标特征提取的能力。在此基础上，嵌入无参数SimAM注意力模块，使得网络模型更加关注运动目标自身特征，弱化背景特征信息的干扰。其中，ELAN-GN模块由ELAN结构和GnBottleneck组成。首先，该模块通过卷积操作后，分别采用两个分支提取特征，一个分支采用1×1卷积操作，另一分支通过一个1×1卷积使通道数减半。然后，采用残差结构设计的GnBottleneck模块提取运动目标的语义特征。在此基础上，将多条分支的多个GnBottleneck模块提取出的特征进行合并，以便提升运动目标特征的复用能力。最后，再通过一个卷积层，实现特征图的输出。
为了更准确地表征运动目标特征，将上述输出的特征图注入至无参数SimAM注意力模块，通过式(1)所示的能量函数提高运动目标的显著性特征。在此基础上，利用Sigmoid激活函数，实现运动目标的检测。
式中：t和xi分别表示目标神经元和通道中的其他神经元；wt和bt表示t线性变换的权重和偏差；i表示空间维度的指数；λ为超参数；M=HW表示单个通道上的所有神经元数量。
2　基于 ByteTrack的目标跟踪算法
收起
目标跟踪过程中出现的目标跟踪丢失和轨迹漂移都会影响跟踪的准确性。为准确计算胶带运输机运行速度，以胶带运输机上的目标为主要参照物，在上述目标检测基础上，提出一种基于ByteTrack 的目标跟踪算法，总体思路如图2所示。
该方法通过引入低置信度分数目标的二次关联，保留低置信度轨迹，并利用先前的轨迹信息恢复真实目标。在数据关联匹配过程中重新考虑低置信度目标，从而提高置信度低的目标的数据匹配关联。为解决跟踪过程中的轨迹漂移问题，在卡尔曼滤波进行运动目标轨迹更新和预测时，将检测结果的置信度融入检测噪声的计算中，自适应调节每个目标的运动轨迹，提高跟踪目标的轨迹稳定性，减少因统一分配噪声尺度所导致的轨迹漂移。
2.1　二次数据关联策略
针对复杂环境下目标跟踪轨迹丢失问题，现有的数据关联方法主要是直接丢弃置信度小于一定阈值的低分框，但该方法会导致大量目标跟踪轨迹丢失，影响目标跟踪的效果。为解决该问题，本文构建了一种二次数据关联策略，实现对高分框的轨迹关联，同时保留低分跟踪框的二次关联，利用先前的移动轨迹的相似性恢复真实目标，提升目标跟踪的稳定性。具体的策略流程如下所述：
（1）将目标检测结果分为高分和低分检测框，若检测框的置信度大于高分检测框阈值，则将该检测框放入高分检测框集合，否则，放入低分检测框集合；
（2）使用匈牙利算法计算高分检测框集合与轨迹集合之间的IoU距离矩阵，将高分框集合与已有轨迹进行首次匹配，将未能成功匹配的高分检测框放入第一次关联未能匹配的检测框集合中；
（3）将低分检测框与第一次未能成功匹配关联的轨迹集合进行二次IoU关联匹配；
（4）对于没有匹配上检测框的跟踪轨迹，将其保留在最大跳帧阈值范围，并基于阈值范围进行轨迹的创建、删除和合并。
2.2　引入置信度的卡尔曼滤波
为解决目标跟踪过程中出现的跟踪轨迹预测不稳定的问题，首先将预测的状态向量a变为状态向量w，即将预测的宽高比用跟踪框的宽度替换，从而更好地描述目标的运动情况，再使用自适应计算噪声协方差的方法对卡尔曼滤波进行改进，如式(2)所示。
式中：Rk表示恒定的检测噪声协方差；表示新的噪声协方差；ck表示检测置信度得分。
为了融入检测置信度分数，需要自适应修正噪声协方差矩阵。本文首先计算预拟合残差，然后利用式(3)自适应更新检测噪声的协方差P′k。
式中：Ak为状态转移矩阵；Qk－1为噪声协方差矩阵。
然后，利用式（4）计算预拟合误差协方差计算Sk:
式中：Hk表示观测模型的矩阵。
最后，更新状态向量及误差协方差估计，如式(5)和式(6)所示。
式中：xk|k－1表示k状态下的预测估计值；最优卡尔曼增益;I表示单位矩阵；zk为k状态下的观测向量。
3　胶带运输机运行速度测量
收起
在上述目标跟踪的基础上，结合相机标定方法，建立一种目标速度测量模型，从而依据目标运行速度计算胶带运输机的运动速度，具体过程如图3所示。
具体来说，首先通过利用改进的轻量级YOLOv7-tiny算法模型对运动目标进行检测。在检测到胶带运输机上的目标之后，利用基于ByteTrack的目标跟踪算法获得两帧间所有目标的中心点坐标，这样可以保证目标的移动速度接近胶带运输机的真实速度。假设运动目标在相邻两帧图像中能够匹配到目标的中心点坐标，就可以通过欧氏距离计算两帧之间目标的位移。然后，通过相机标定的方式计算像素位移Ks，进而可以将图像坐标位移映射至世界坐标系，用来表示前一帧到当前帧目标移动的真实位移距离S，则目标的速度计算式如下：
式中：V表示某个目标的瞬时速度；由于视频监控的帧速率为18帧/s，则T为1/18。
最终，通过计算两帧间所有目标的瞬时速度平均值，并以此作为胶带运输机的速度。
4　试验及结果分析
收起
4.1　试验数据集与评价指标
本文选择煤矿带式输送机上的煤块作为研究对象，试验数据集来源于真实的煤矿作业监控视频片段。图像采样间隔为1 s，共采集6 859张图像，其中训练集5 555个样本，验证集618个样本，测试集686个样本。整个数据集涵盖了不同大小的煤块，通过DarkLabel工具对图像中的煤块进行标注。在基于 ByteTrack 的目标跟踪算法中，设置跟踪置信度阈值为0.5，跟踪匹配阈值为 0.7，最小面积阈值为 10，最大帧跳过阈值为 30帧。试验环境见表1。
本文采用MOTA、HOTA以及IDF1性能评价指标验证方法的有效性。MOTA是多目标跟踪算法中常用的评价指标，用于度量算法的跟踪性能。该性能指标综合考虑了FP、FN和IDSW三种错误来源，可评估多目标跟踪算法的准确性，MOTA值越高，代表算法的多目标跟踪性能越好。HOTA引入高维度跟踪精度，能够更完整、均衡的评估跟踪算法的性能。IDF1是通过计算F1分数得出的性能指标。
4.2　改进卡尔曼滤波算法的有效性试验
改进卡尔曼滤波算法的性能，试验结果见表2。
从表2可以看出，改进后的卡尔曼滤波算法与改进前相比，在MOTA上提升了2.7个百分点，HOTA上提升了3.9个百分点，IDF1仅仅提升了2.4个百分点。由此说明，通过将检测的置信度引入卡尔曼滤波中进行状态估计，能够更好地估计边界框的位置，稳定地提升跟踪的精度和准确度。
此外，通过获取视频图像序列中多个目标跟踪轨迹的中心点像素位移，验证跟踪算法的稳定性，如图4所示。
从图4(a)可以看出，在视频图像序列的连续10帧中，目标中心点像素位移在使用原卡尔曼滤波算法预测的轨迹上出现飘逸现象，而改进的卡尔曼滤波算法较好地解决轨迹漂移的问题。从图4(b)可以看出，在连续的9帧图像中，在改进卡尔曼滤波算法预测的轨迹上，目标中心点像素位移坐标近似呈线性，说明跟踪的稳定性较好，没有出现较大的偏差。从图4(c)可以看出，在连续的8帧图像中，原始算法的目标中心点像素位移预测位置出现了较大的误差，而改进的卡尔曼滤波算法预测的中心点位移跟踪轨迹误差较小。从图4(d)也可以看出，改进后的算法能够较好地解决原算法不能稳定预测目标轨迹的问题。
4.3　不同算法的目标跟踪性能对比试验
本文将基于 ByteTrack的目标跟踪算法与其他经典的目标跟踪算法进行对比分析，试验结果见表3。
由表3可见，本文所提的基于ByteTrack的目标跟踪算法相较于SORT、OC-SORT两种算法，在MOTA性能指标上分别提高了7.2个百分点和3.4个百分点，HOTA分别提高了7.2个百分点和1.0个百分点，IDF1提高了5.4个百分点和1.3个百分点。表明本文的算法能够较好地适应于目标跟踪。
4.4　跟踪结果可视化
为了客观评估目标跟踪的连续性，本文分别从目标ID标识切换、跟踪丢失和多帧连续跟踪情况等方面分析，可视化煤块跟踪效果，分别如图5、图6和图7所示。
从图5(a)和图5(b)可以看出，黄色线条、绿色线条（颜色标识见电子版，下同）和其他煤块都能在多帧内连续稳定地跟踪，且ID标识唯一，没有出现ID切换的问题。
如图6(a)所示，利用原有跟踪算法，煤块在335帧到336帧出现了煤块跟踪丢失，在337帧依旧没有成功匹配跟踪。如图6(b)所示，改进的ByteTrack目标跟踪算法，煤块从第335帧到337帧都能成功匹配，说明使用改进的ByteTrack跟踪算法时出现煤块跟踪丢失的现象较少。
图像多帧跟踪时可以分为3种情况，第1种是连续的跟踪序列中始终都能跟踪到煤块，跟踪结果相对稳定。第2种是连续跟踪图像序列中煤块跟踪丢失，由于煤块发生形变或较小的煤块与其他煤块混在一起，无法实现跟踪，如图7中的橙色线条所示。第3种是在跟踪图像序列中，新跟踪到煤块加入实现连续跟踪，如图7中的黄色线条所示。由图7可见，本文所提方法能够有效解决ID切换和跟踪丢失的问题，实现煤块的准确匹配，为胶带运输机速度测量提供连续稳定的轨迹和尽可能多的煤块目标参与速度计算，降低速度测量过程中的误差。
4.5　速度测量结果与分析
为了验证本文方法的有效性，随机使用3种不同情况的视频数据进行测试。其中一段视频是前5 s有煤而后5 s无煤，其余两段采用10 s胶带运输机运行视频数据。试验视频数据均来自同一摄像头拍摄，每个视频帧速为18 帧/s，胶带运输机真实运行速度为3.6 m/s，试验结果分别见表4、表5和表6。
由表4可见，通过采用本文方法测量得到的速度在真实运行速度上下浮动，始终都能检测和跟踪到煤块，没有出现跟踪丢失的情况，说明本文的方法能够有效地计算胶带运输机的运行速度，测量的速度误差较为稳定，最大速度误差为0.37 m/s。
由表5中可以看出，测量的运行速度在真实运行速度上下波动。整个视频由于不断有煤块的跟踪，也有煤块的跟踪丢失，跟踪器也随之不断更新，造成大幅度波动，但整体上跟踪平稳，最大速度误差为0.36 m/s。
由表6可见，在后几秒无煤过程中，由于未检测到煤块的出现，导致胶带运输机的速度测量结果为0。因此，在没有速度返回的状态时，可以对其所监控的胶带运输机实现智能调速。
为了验证本文所提出的方法的性能，采用平均绝对误差（Mean Absolute Error, MAE）、均方误差（Mean Square Error, MSE）和 FPS评估胶带运输机运行速度测量的误差和实时性。分别以YOLOv5s、YOLOv7-tiny和改进的YOLOv7-tiny为检测器，结合ByteTrack和改进ByteTrack跟踪算法，利用前述的第1段视频进行胶带运输机的运行速度测量，并以胶带运输机真实运行速度3.6 m/s为参考标准，具体试验结果见表7。
由表7可见，本文所提出的方法相比于YOLOv5s + ByteTrack算法、YOLOv7-tiny+ByteTrack算法，胶带运输机运行速度在平均绝对误差上分别降低了0.038 4 m/s和0.021 2 m/s，在均方误差上分别降低了0.037 m/s和0.022 m/s。由此可见，本文所提的方法能够在保证实时性的条件下，有效提高胶带运输机运行速度测量的精度。融合改进YOLOv7-tiny与ByteTrack目标跟踪算法能够准确跟踪胶带运输机上的较大煤块。借助本文构建的胶带运输机速度测量模型计算出的实时测速为3.564 m/s，与真实速度3.6 m/s十分接近。
5　结论
收起
为提高胶带运输机运行速度测量的准确度，本文提出了一种融合改进YOLOv7-tiny与ByteTrack跟踪的胶带运输机速度测量方法。该方法在引入自适应噪声的卡尔曼滤波算法的基础上，融合了改进的YOLOv7-tiny与基于ByteTrack的目标跟踪算法，并构建了胶带运输机速度测量模型，从而计算视频帧间胶带运输机的实时速度。试验结果表明，本文所提的方法能够解决原卡尔曼滤波算法在状态估计方面的不稳定性问题，并可以准确刻画目标的运动轨迹。该方法在实时测速方面的MAE和MSE性能指标相较于其他方法分别降低了0.037 m/s和0.022 m/s，说明本文所提出的方法能够有效降低胶带运输机运行速度的测量误差。
在未来的工作中，将基于YOLO v10等新的目标检测模型对本文的方法进行优化，以便进一步提高胶带运输机实时运行速度的监测能力。
基金
收起
  • 国家自然科学基金项目(62102309)
  • 陕西省教育厅科研计划专项项目(8146119003)
文献
收起
参考文献 引证文献
排序方式：
[1]
GIRSHICK Ross, DONAHUE Jeff, DARRELL Trevor, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]// 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE, 2014:580-587.
[2]
HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916.
[3]
GIRSHICK Ross. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision (ICCV). New York: IEEE, 2015: 1440-1448.
[4]
REN Shaoqing, HE Kaiming, GIRSHICK Ross, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[5]
DAI Jifeng, LI Yi, HE Kaiming, et al. R-FCN: object detection via region-based fully convolutional networks[C]//The 30th International Conference on Neural Information Processing Systems. New York: Curran Associates, 2016:379-387.
[6]
CAI Zhaowei, VASCONCELOS Nuno. Cascade R-CNN: delving into high quality object detection[C]//2018 IEEE/ CVF Conference on Computer Vision and Pattern Recognition(CVPR). New York: IEEE, 2018:6154-6162.
[7]
REDMON Joseph, DIVVALA Santosh, GIRSHICK Ross, et al. You only look once: Unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE, 2016:779-788.
[8]
REDMON Joseph, FARHADI Ali. YOLOv3: an incremental improvement[J]. ArXiv, 2018:4714433.
[9]
WANG Chenyao, BOCHKOVSKIY A, LIAO Hongyuan Mark. Scaled-YOLOv4: scaling cross stage partial network[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE, 2021: 13029-13038.
[10]
CHEN Qiang, WANG Y M, YAN F T, et al. You only look one-level feature[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2021:13039-13048.
[11]
DING Xiaohan, ZHANG Xiangyu, MA Ningning, et al. Repvgg: making vgg-style convnets great again[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2021: 13733-13742.
[12]
杜京义，郝乐，王悦阳，等.一种煤矿井下输煤大块物检测方法[J].工矿自动化，2020，46(5):63-68.
DU Jingyi，HAO Le，WANG Yueyang，et al. A detection method for large blocks in underground coal transportation [J]. Journal of Mine Automation, 2020, 46(5):63-68.
[13]
吴守鹏，丁恩杰，俞啸.基于改进 FPN 的输送带异物识别方法[J].煤矿安全，2019, 50(12): 127-130.
WU Shoupeng, DING Enjie, YU Xiao. Foreign body identification of belt based on improved FPN[J]. Safety in Coal Mines, 2019, 50(12):127-130.
[14]
叶鸥，窦晓熠，付燕，等.融合轻量级网络和双重注意力机制的煤块检测方法[J].工矿自动化，2021，47(12):75-80.
YE Ou, DOU Xiaoyi, FU Yan, et al. Coal block detection method integrating lightweight network and dual attention mechanism[J]. Journal of Mine Automation, 2021, 47(12):75-80.
[15]
DU Kai, JU Yongfeng, JIN Yinli, et al. Object tracking based on improved meanshift and SIFT[C]//2012 2nd International Conference on Consumer Electronics: Communications and Networks (CECNet). New York: IEEE, 2012:2716-2719.
[16]
EXNER David, BRUNS Erich, KURZ Daniel, et al. Fast and robust camshift tracking[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Workshops. New York: IEEE, 2010:9-16.
[17]
BEWLEY Alex, GE Zongyuan, OTT Lionel, et al. Simple online and realtime tracking[C]//2016 IEEE International Conference on Image Processing (ICIP). New York: IEEE, 2016:3464-3468.
[18]
NICOLAI Wojke, ALEX Bewley, PAULUS Dietrich. Simple online and realtime tracking with a deep association metric[C]//2017 IEEE International Conference on Image Processing (ICIP). New York: IEEE, 2017:3645-3649.
[19]
ZHANG Yifu, SUN Peize, JIANG Yi, et al. Bytetrack: multi-object tracking by associating every detection box [C]//European Conference on Computer Vision(ECCV). Chan: Springer, 2022:1-21.
[20]
高凯，董立红，邓凡.基于递归门控卷积和上下文注意力的煤块检测算法[J].矿业研究与开发，2023，43(6):183-190.
GAO Kai，DONG Lihong，DENG Fan. Coal block detection algorithm based on recursive gated convolution and contextual attention[J]. Mining Research and Development，2023, 43(6):183-190.
2025年第45卷第8期
PDF下载
49
24
引用本文
BibTeX
文章信息
  • 接收时间：2024-08-24
  • 首发时间：2026-10-28
  • 出版时间：2025-08-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期：2024-08-24
基金
国家自然科学基金项目(62102309)
陕西省教育厅科研计划专项项目(8146119003)
作者信息
    1.陕西小保当矿业有限公司，陕西　榆林市　719302
    2.西安科技大学 计算机科学与技术学院，陕西　西安　710699
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kyyjykf/CN/1322161679169859858
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
相关链接
论文
最新文章
热读文章
热点专题
内参
蓝皮书
产业发展报告
传播力报告
期刊分级目录
资讯
学术新闻
行业新闻
学术会议
行业会议
关于
关于我们
联系我们
北京市海淀区学院南路86号
100081
010-62662699（运营及技术支持）
qkjq@cast.org.cn

中国科学技术协会版权所有 京ICP 备10216604号-4 海淀分局备案 1101084647
科技导报社主办 中国科协信息中心技术支持