首页 期刊 论文 学科刊群 资讯 加盟 关于
EN
image
Article(id=1226462297611224049, tenantId=1146029695717560320, journalId=1225396423026438145, issueId=1226462293408531329, 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=1730736000000, receivedDateStr=2024-11-05, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1770340998317, onlineDateStr=2026-02-06, pubDate=1761321600000, pubDateStr=2025-10-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1770340998317, onlineIssueDateStr=2026-02-06, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1770340998317, creator=13701087609, updateTime=1770340998317, updator=13701087609, issue=Issue{id=1226462293408531329, tenantId=1146029695717560320, journalId=1225396423026438145, year='2025', volume='45', issue='10', pageStart='1', pageEnd='288', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1770340997315, creator=13701087609, updateTime=1770341205851, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1226463168155792201, tenantId=1146029695717560320, journalId=1225396423026438145, issueId=1226462293408531329, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1226463168155792202, tenantId=1146029695717560320, journalId=1225396423026438145, issueId=1226462293408531329, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=199, endPage=206, ext={EN=ArticleExt(id=1226462297871269888, articleId=1226462297611224049, tenantId=1146029695717560320, journalId=1225396423026438145, language=EN, title=Research on the Extraction of Separation Point Positions for Shaking Table Concentrate Band Based on Lightweight Fusion Network, columnId=null, journalTitle=Mining Research and Development, columnName=null, runingTitle=null, highlight=null, articleAbstract=

The existing object detection algorithms for shaking table concentrate bands have problems such as inability to balance detection accuracy and speed, high computational costs, difficulty in compressing model size, and slow inference speed. To address these problems, a lightweight fusion network for shaking tables (YC-Lightweight Net) object detection algorithm was proposed. The YC-Lightweight Net model firstly used a repetitive visual transformation network to extract features from the images of shaking table sub-banding. Then, by introducing group space convolution, multi-scale efficient cross stage fusion modules, and using skip connections, an efficient and lightweight neck network was designed. Finally, a weight based layer adaptive pruning algorithm was used to compress the model size. The experimental results show that the accuracy, recall, mean average precision, and FPS indicators of the YC-Lightweight Net model are 98.4%, 97.9%, 98.8% and 333 frame/s, respectively. The detection accuracy and speed are significantly better than those of the compared models. The number of parameters, floating-point operations, and model size after pruning are 13.9%, 15.4% and 17.5% of the original model, respectively. The pruning operation greatly reduces the computational complexity and model size of the model. The YC-Lightweight Net model has good detection accuracy and real-time performance, meeting the requirements of industrial equipment for lightweight models in shaking table mineral processing plants. The study can provide a technical support for accurate identification of separation points in mineral bands and intelligent upgrading of the shaking table mineral processing plant equipment.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Huizhong LIU, Jianye LIU, Ao HUANG, Fulong DENG, Xixi LIU), CN=ArticleExt(id=1226462300677259467, articleId=1226462297611224049, tenantId=1146029695717560320, journalId=1225396423026438145, language=CN, title=基于轻量化融合网络的摇床精矿带分离点位置提取研究, 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=

针对现有摇床矿带目标检测算法存在检测精度和检测速度无法兼顾、计算成本高、模型大小难压缩和推理速度慢等问题，提出了一种摇床轻量化融合网络（YC-Lightweight Net）目标检测算法。YC-Lightweight Net模型首先采用重复视觉转换网络对摇床矿物分带图像进行特征提取，然后通过引入分组空间卷积、多尺度高效跨阶段融合模块并采用跳跃连接的方式设计了一种高效、轻量的颈部网络，最后采用基于权重的层自适应剪枝算法压缩模型大小。试验结果表明，YC-Lightweight Net模型精确度、召回率、平均精度均值和帧率指标分别为98.4%、97.9%、98.8%和333帧/s，检测精度和检测速度明显优于各对比模型；剪枝后参数量、浮点运算量和模型大小分别为原模型的13.9%、15.4%和17.5%，剪枝操作极大降低了模型的计算复杂度和模型大小。YC-Lightweight Net模型具有良好的检测精度和实时性能，满足摇床选矿厂的工业设备对模型轻量化的要求，可为摇床矿带分离点精准识别及选矿厂摇床设备智能化升级提供技术支持。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=R/D5i/6FJGbBIx5C/cAJig==, magXml=fbGazBFiFF0vl1qOBKPrlQ==, pdfUrl=null, pdf=Ek1qBUhrrca5VyBsYgRKwA==, pdfFileSize=10138753, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=B01ePrRCf6OuwhvLuZzpwQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=qMAHfV1lqy5ucpawz7zc1w==, mapNumber=null, authorCompany=null, fund=null, authors=

刘惠中（1969一），男，江西信丰人，博士，教授，博士生导师，主要从事选矿装备及智能化等方面的研究。E-mail:

, authorsList=刘惠中, 刘建业, 黄翱, 邓富龙, 刘茜茜)}, authors=[Author(id=1226462301126050036, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=huizhong6@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1226462301256073473, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, authorId=1226462301126050036, language=EN, stringName=Huizhong LIU, firstName=Huizhong, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi 341000, China
2.Jiangxi Province Engineering Research Center for Mechanical and Electrical of Mining and Metallurgy, Ganzhou, Jiangxi 341000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1226462301335765253, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, authorId=1226462301126050036, language=CN, stringName=刘惠中, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.江西理工大学机电工程学院，江西　赣州市　341000
2.江西省矿冶机电工程技术研究中心，江西　赣州市　341000, bio={"content":"

刘惠中（1969一），男，江西信丰人，博士，教授，博士生导师，主要从事选矿装备及智能化等方面的研究。E-mail:

"}, bioImg=null, bioContent=

刘惠中（1969一），男，江西信丰人，博士，教授，博士生导师，主要从事选矿装备及智能化等方面的研究。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1226462300899557599, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, xref=1., ext=[AuthorCompanyExt(id=1226462300907946208, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, companyId=1226462300899557599, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi 341000, China), AuthorCompanyExt(id=1226462300916334817, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, companyId=1226462300899557599, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.江西理工大学机电工程学院，江西　赣州市　341000)]), AuthorCompany(id=1226462301000220905, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, xref=2., ext=[AuthorCompanyExt(id=1226462301008609514, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, companyId=1226462301000220905, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Jiangxi Province Engineering Research Center for Mechanical and Electrical of Mining and Metallurgy, Ganzhou, Jiangxi 341000, China), AuthorCompanyExt(id=1226462301012803819, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, companyId=1226462301000220905, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.江西省矿冶机电工程技术研究中心，江西　赣州市　341000)])]), Author(id=1226462301428039948, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, 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=1226462301528703253, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, authorId=1226462301428039948, language=EN, stringName=Jianye LIU, firstName=Jianye, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi 341000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1226462301683892508, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, authorId=1226462301428039948, language=CN, stringName=刘建业, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.江西理工大学机电工程学院，江西　赣州市　341000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1226462300899557599, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, xref=1., ext=[AuthorCompanyExt(id=1226462300907946208, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, companyId=1226462300899557599, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi 341000, China), AuthorCompanyExt(id=1226462300916334817, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, companyId=1226462300899557599, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.江西理工大学机电工程学院，江西　赣州市　341000)])]), Author(id=1226462301822304554, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, 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=1226462302011048245, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, authorId=1226462301822304554, language=EN, stringName=Ao HUANG, firstName=Ao, middleName=null, lastName=HUANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi 341000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1226462302166237506, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, authorId=1226462301822304554, language=CN, stringName=黄翱, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.江西理工大学机电工程学院，江西　赣州市　341000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1226462300899557599, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, xref=1., ext=[AuthorCompanyExt(id=1226462300907946208, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, companyId=1226462300899557599, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi 341000, China), AuthorCompanyExt(id=1226462300916334817, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, companyId=1226462300899557599, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.江西理工大学机电工程学院，江西　赣州市　341000)])]), Author(id=1226462302296260943, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, 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=1226462302417895771, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, authorId=1226462302296260943, language=EN, stringName=Fulong DENG, firstName=Fulong, middleName=null, lastName=DENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi 341000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1226462302510170472, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, authorId=1226462302296260943, language=CN, stringName=邓富龙, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.江西理工大学机电工程学院，江西　赣州市　341000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1226462300899557599, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, xref=1., ext=[AuthorCompanyExt(id=1226462300907946208, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, companyId=1226462300899557599, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi 341000, China), AuthorCompanyExt(id=1226462300916334817, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, companyId=1226462300899557599, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.江西理工大学机电工程学院，江西　赣州市　341000)])]), Author(id=1226462302589862258, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, orderNo=4, 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=1226462302707302785, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, authorId=1226462302589862258, language=EN, stringName=Xixi LIU, firstName=Xixi, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi 341000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1226462302799577484, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, authorId=1226462302589862258, language=CN, stringName=刘茜茜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.江西理工大学机电工程学院，江西　赣州市　341000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1226462300899557599, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, xref=1., ext=[AuthorCompanyExt(id=1226462300907946208, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, companyId=1226462300899557599, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi 341000, China), AuthorCompanyExt(id=1226462300916334817, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, companyId=1226462300899557599, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.江西理工大学机电工程学院，江西　赣州市　341000)])])], keywords=[Keyword(id=1226462302925406620, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=EN, orderNo=1, keyword=Shaking table concentrate band), Keyword(id=1226462303038652843, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=EN, orderNo=2, keyword=Object detection), Keyword(id=1226462303156093368, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=EN, orderNo=3, keyword=Lightweight design), Keyword(id=1226462303256756675, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=EN, orderNo=4, keyword=LAMP algorithm), Keyword(id=1226462303374197203, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=EN, orderNo=5, keyword=Precise identification), Keyword(id=1226462303596495330, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=CN, orderNo=1, keyword=摇床精矿带), Keyword(id=1226462303743295981, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=CN, orderNo=2, keyword=目标检测), Keyword(id=1226462303843959290, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=CN, orderNo=3, keyword=轻量化设计), Keyword(id=1226462303961399814, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=CN, orderNo=4, keyword=LAMP算法), Keyword(id=1226462304083034647, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=CN, orderNo=5, keyword=精准识别)], refs=[Reference(id=1226462307027436300, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2024, volume=33, issue=6, pageStart=14, pageEnd=25, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=鞠建华, 韩见, 冯聪, journalName=中国矿业, refType=null, unstructuredReference=鞠建华，韩见，冯聪.我国矿产资源综合利用现状评估与发展路径[J].中国矿业，2024，33(6):14-25., articleTitle=我国矿产资源综合利用现状评估与发展路径, refAbstract=null), Reference(id=1226462307128099602, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2024, volume=33, issue=6, pageStart=14, pageEnd=25, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=JU Jianhua, HAN Jian, FENG Cong, journalName=China Mining Magazine, refType=null, unstructuredReference=JU Jianhua, HAN Jian, FENG Cong. Evaluation and development path of comprehensive utilization of mineral resources in China[J]. China Mining Magazine, 2024, 33(6):14-25., articleTitle=Evaluation and development path of comprehensive utilization of mineral resources in China, refAbstract=null), Reference(id=1226462307224568601, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2013, volume=40, issue=1, pageStart=248, pageEnd=272, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=张长青, 芮宗瑶, 陈毓川, journalName=中国地质, refType=null, unstructuredReference=张长青，芮宗瑶，陈毓川，等.中国铅锌矿资源潜力和主要战略接续区[J].中国地质，2013，40(1):248-272., articleTitle=中国铅锌矿资源潜力和主要战略接续区, refAbstract=null), Reference(id=1226462307354592032, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2013, volume=40, issue=1, pageStart=248, pageEnd=272, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=ZHANG Changqing, RUI Zongyao, CHEN Yuchuan, journalName=Geology in China, refType=null, unstructuredReference=ZHANG Changqing, RUI Zongyao, CHEN Yuchuan, et al. The main successive strategic bases of resources for Pb-Zn deposits in China[J]. Geology in China, 2013, 40(1):248-272., articleTitle=The main successive strategic bases of resources for Pb-Zn deposits in China, refAbstract=null), Reference(id=1226462307484615463, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2019, volume=42, issue=3, pageStart=453, pageEnd=482, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=张顺, 龚怡宏, 王进军, journalName=计算机学报, refType=null, unstructuredReference=张顺，龚怡宏，王进军.深度卷积神经网络的发展及其在计算机视觉领域的应用[J].计算机学报，2019，42(3):453-482., articleTitle=深度卷积神经网络的发展及其在计算机视觉领域的应用, refAbstract=null), Reference(id=1226462307572695853, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2019, volume=42, issue=3, pageStart=453, pageEnd=482, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=ZHANG Shun, GONG Yihong, WANG Jinjun, journalName=Chinese Journal of Computers, refType=null, unstructuredReference=ZHANG Shun, GONG Yihong, WANG Jinjun. The development of deep convolution neural network and its applications on computer vision [J]. Chinese Journal of Computers, 2019, 42(3):453-482., articleTitle=The development of deep convolution neural network and its applications on computer vision, refAbstract=null), Reference(id=1226462307690136371, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=9, pageStart=28, pageEnd=51, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=郑太雄, 江明哲, 冯明驰, journalName=仪器仪表学报, refType=null, unstructuredReference=郑太雄，江明哲，冯明驰.基于视觉的采摘机器人目标识别与定位方法研究综述[J].仪器仪表学报，2021，42(9):28-51., articleTitle=基于视觉的采摘机器人目标识别与定位方法研究综述, refAbstract=null), Reference(id=1226462307807576890, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=9, pageStart=28, pageEnd=51, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=ZHENG Taixiong, JIANG Mingzhe, FENG Mingchi, journalName=Chinese Journal of Scientific Instrument, refType=null, unstructuredReference=ZHENG Taixiong, JIANG Mingzhe, FENG Mingchi. Vision based target recognition and location for picking robot: a review[J]. Chinese Journal of Scientific Instrument, 2021, 42(9):28-51., articleTitle=Vision based target recognition and location for picking robot: a review, refAbstract=null), Reference(id=1226462307908240192, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2021, volume=47, issue=5, pageStart=1017, pageEnd=1034, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=陶显, 侯伟, 徐德, journalName=自动化学报, refType=null, unstructuredReference=陶显，侯伟，徐德.基于深度学习的表面缺陷检测方法综述[J].自动化学报，2021，47(5):1017-1034., articleTitle=基于深度学习的表面缺陷检测方法综述, refAbstract=null), Reference(id=1226462308222812995, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2021, volume=47, issue=5, pageStart=1017, pageEnd=1034, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=TAO Xian, HOU Wei, XU De, journalName=Acta Automatica Sinica, refType=null, unstructuredReference=TAO Xian, HOU Wei, XU De. A survey of surface defect detection methods based on deep learning [J]. Acta Automatica Sinica, 2021, 47(5):1017-1034., articleTitle=A survey of surface defect detection methods based on deep learning, refAbstract=null), Reference(id=1226462308361225031, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=1, pageEnd=7, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=门定航, 谭钦红, journalName=激光杂志, refType=null, unstructuredReference=门定航，谭钦红.基于YOLOv8改进的航拍图像人员检测[J/OL].激光杂志：1-7[2024-07-15].http://kns.cnki.net/kcms/detail/50.1085.TN.20240710.2017.010.html., articleTitle=基于YOLOv8改进的航拍图像人员检测, refAbstract=null), Reference(id=1226462308466082638, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=1, pageEnd=7, url=null, language=null, rfNumber=[6], rfOrder=11, authorNames=MEN Dinghang, TAN Qinhong, journalName=Laser Journal, refType=null, unstructuredReference=MEN Dinghang, TAN Qinhong. Human detection for aerial photography based on improved YOLOv8 [J/OL]. Laser Journal:1-7[2024-07-15]. http://kns.cnki.net/kcms/detail/50.1085.TN.20240710.2017.010.html., articleTitle=Human detection for aerial photography based on improved YOLOv8, refAbstract=null), Reference(id=1226462308629660500, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2024, volume=40, issue=14, pageStart=118, pageEnd=125, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=董耿耿, 陈小康, 樊湘鹏, journalName=农业工程学报, refType=null, unstructuredReference=董耿耿，陈小康，樊湘鹏，等.基于改进YOLOv5s的复杂环境下新梅检测方法[J].农业工程学报，2024，40（14）：118-125., articleTitle=基于改进YOLOv5s的复杂环境下新梅检测方法, refAbstract=null), Reference(id=1226462308738712409, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2024, volume=40, issue=14, pageStart=118, pageEnd=125, url=null, language=null, rfNumber=[7], rfOrder=13, authorNames=DONG Genggeng, CHEN Xiaokang, FAN Xiangpeng, journalName=Transactions of the Chinese Society of Agricultural Engineering, refType=null, unstructuredReference=DONG Genggeng, CHEN Xiaokang, FAN Xiangpeng, et al. Detecting Xinmei fruit under complex environments using improved YOLOv5s[J]. Transactions of the Chinese Society of Agricultural Engineering, 2024, 40(14):118-125., articleTitle=Detecting Xinmei fruit under complex environments using improved YOLOv5s, refAbstract=null), Reference(id=1226462308843570016, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2024, volume=46, issue=9, pageStart=3739, pageEnd=3748, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=孟祥伟, journalName=电子与信息学报, refType=null, unstructuredReference=孟祥伟.SAR图像中舰船目标恒虚警率检测技术的研究[J].电子与信息学报，2024，46(9):3739-3748., articleTitle=SAR图像中舰船目标恒虚警率检测技术的研究, refAbstract=null), Reference(id=1226462308931650406, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2024, volume=46, issue=9, pageStart=3739, pageEnd=3748, url=null, language=null, rfNumber=[8], rfOrder=15, authorNames=MENG Xiangwei, journalName=Journal of Electronics & Information Technology, refType=null, unstructuredReference=MENG Xiangwei. Research on constant false alarm rate detection technique for ship in SAR image[J]. Journal of Electronics & Information Technology, 2024, 46(9):3739-3748., articleTitle=Research on constant false alarm rate detection technique for ship in SAR image, refAbstract=null), Reference(id=1226462309036508010, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2024, volume=50, issue=9, pageStart=4142, pageEnd=4151, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=杨栋, 朵文博, 李帅兵, journalName=高电压技术, refType=null, unstructuredReference=杨栋，朵文博，李帅兵，等.基于改进YOLOv8的电缆复合绝缘结构内部缺陷太赫兹成像识别方法[J].高电压技术，2024，50(9):4142-4151., articleTitle=基于改进YOLOv8的电缆复合绝缘结构内部缺陷太赫兹成像识别方法, refAbstract=null), Reference(id=1226462309195891568, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2024, volume=50, issue=9, pageStart=4142, pageEnd=4151, url=null, language=null, rfNumber=[9], rfOrder=17, authorNames=YANG Dong, DUO Wenbo, LI Shuaibing, journalName=High Voltage Engineering, refType=null, unstructuredReference=YANG Dong, DUO Wenbo, LI Shuaibing, et al. Terahertz imaging recognition method for internal defects in cable composite insulation structure based on improved YOLOv8 [J]. High Voltage Engineering, 2024, 50(9):4142-4151., articleTitle=Terahertz imaging recognition method for internal defects in cable composite insulation structure based on improved YOLOv8, refAbstract=null), Reference(id=1226462309296554874, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=4, pageStart=684, pageEnd=691, url=null, language=null, rfNumber=[10], rfOrder=18, authorNames=郭孟澳, 杨帮华, 耿亦婷, journalName=生物医学工程学杂志, refType=null, unstructuredReference=郭孟澳，杨帮华，耿亦婷，等.基于增强现实和稳态视觉诱发电位的视觉目标检测系统[J].生物医学工程学杂志，2024，41(4):684-691., articleTitle=基于增强现实和稳态视觉诱发电位的视觉目标检测系统, refAbstract=null), Reference(id=1226462309384635266, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=4, pageStart=684, pageEnd=691, url=null, language=null, rfNumber=[10], rfOrder=19, authorNames=GUO Meng'ao, Yang Banghua, GENG Yiting, journalName=Journal of Biomedical Engineering, refType=null, unstructuredReference=GUO Meng'ao, Yang Banghua, GENG Yiting, et al. Visual object detection system based on augmented reality and steady-state visual evoked potential [J]. Journal of Biomedical Engineering, 2024, 41(4):684-691., articleTitle=Visual object detection system based on augmented reality and steady-state visual evoked potential, refAbstract=null), Reference(id=1226462309434966919, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=8, pageStart=174, pageEnd=184, url=null, language=null, rfNumber=[11], rfOrder=20, authorNames=田心如, 褚洁, 蔡觉平, journalName=仪器仪表学报, refType=null, unstructuredReference=田心如，褚洁，蔡觉平，等.用于 Mini/Micro-LED芯片缺陷检测的全局特征压缩卷积神经网络[J].仪器仪表学报，2024，45(8):174-184., articleTitle=用于 Mini/Micro-LED芯片缺陷检测的全局特征压缩卷积神经网络, refAbstract=null), Reference(id=1226462309539824525, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=8, pageStart=174, pageEnd=184, url=null, language=null, rfNumber=[11], rfOrder=21, authorNames=TIAN Xinru, CHU Jie, CAI Jueping, journalName=Chinese Journal of Scientific Instrument, refType=null, unstructuredReference=TIAN Xinru, CHU Jie, CAI Jueping, et al. Global feature compression convolutional neural network for defect detection in Mini/Micro-LED chips[J]. Chinese Journal of Scientific Instrument, 2024, 45(8):174-184., articleTitle=Global feature compression convolutional neural network for defect detection in Mini/Micro-LED chips, refAbstract=null), Reference(id=1226462309648876433, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=10, pageStart=197, pageEnd=206, url=null, language=null, rfNumber=[12], rfOrder=22, authorNames=叶咏菁, 韩斌, 胡亚飞, journalName=矿业研究与开发, refType=null, unstructuredReference=叶咏菁，韩斌，胡亚飞，等.基于YOLOv7-CA-Faster的井下复杂环境下车牌定位算法研究[J].矿业研究与开发，2024，44(10):197-206., articleTitle=基于YOLOv7-CA-Faster的井下复杂环境下车牌定位算法研究, refAbstract=null), Reference(id=1226462309770511256, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=10, pageStart=197, pageEnd=206, url=null, language=null, rfNumber=[12], rfOrder=23, authorNames=YE Yongjing, HAN Bin, HU Yafei, journalName=Mining Research and Development, refType=null, unstructuredReference=YE Yongjing, HAN Bin, HU Yafei, et al. Research on license plate localization algorithm in underground complex environment based on YOLOv7-CA-Faster [J]. Mining Research and Development, 2024, 44(10):197-206., articleTitle=Research on license plate localization algorithm in underground complex environment based on YOLOv7-CA-Faster, refAbstract=null), Reference(id=1226462309913117597, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=9, pageStart=219, pageEnd=226, url=null, language=null, rfNumber=[13], rfOrder=24, authorNames=黄可, 樊玉萍, 董宪姝, journalName=矿业研究与开发, refType=null, unstructuredReference=黄可，樊玉萍，董宪姝，等.基于优化的VGG-16网络模型的煤矸识别研究[J].矿业研究与开发，2024，44(9):219-226., articleTitle=基于优化的VGG-16网络模型的煤矸识别研究, refAbstract=null), Reference(id=1226462310173164453, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=9, pageStart=219, pageEnd=226, url=null, language=null, rfNumber=[13], rfOrder=25, authorNames=HUANG Ke, FAN Yuping, DONG Xianshu, journalName=Mining Research and Development, refType=null, unstructuredReference=HUANG Ke, FAN Yuping, DONG Xianshu, et al. Coal gangue identification based on optimized VGG-16 network model[J]. Mining Research and Development, 2024, 44(9):219-226., articleTitle=Coal gangue identification based on optimized VGG-16 network model, refAbstract=null), Reference(id=1226462310290604970, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2024, volume=7, issue=11, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=26, authorNames=TANG Hao, XU Xixi, XU Haiyang, journalName=Advanced Theory and Simulations, refType=null, unstructuredReference=TANG Hao, XU Xixi, XU Haiyang, et al. Lightweight ViT with multiscale feature fusion for driving risk rating warning system [J]. Advanced Theory and Simulations, 2024, 7(11):2400586., articleTitle=Lightweight ViT with multiscale feature fusion for driving risk rating warning system, refAbstract=null), Reference(id=1226462310408045488, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2024, volume=21, issue=3, pageStart=62, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=27, authorNames=LI Hulin, LI Jun, WEI Hanbing, journalName=Journal of Real-Time Image Processing, refType=null, unstructuredReference=LI Hulin, LI Jun, WEI Hanbing, et al. Slim-neck by GSConv: a lightweight-design for real-time detector architectures [J]. Journal of Real-Time Image Processing, 2024, 21(3):62., articleTitle=Slim-neck by GSConv: a lightweight-design for real-time detector architectures, refAbstract=null), Reference(id=1226462310533874618, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2022, volume=56, issue=8, pageStart=994, pageEnd=1003, url=null, language=null, rfNumber=[16], rfOrder=28, authorNames=李登攀, 任晓明, 颜楠楠, journalName=上海交通大学学报, refType=null, unstructuredReference=李登攀，任晓明，颜楠楠.基于无人机航拍的绝缘子掉串实时检测研究[J].上海交通大学学报，2022，56(8):994-1003., articleTitle=基于无人机航拍的绝缘子掉串实时检测研究, refAbstract=null), Reference(id=1226462310642926528, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2022, volume=56, issue=8, pageStart=994, pageEnd=1003, url=null, language=null, rfNumber=[16], rfOrder=29, authorNames=LI Dengpan, REN Xiaoming, YAN Nannan, journalName=Journal of Shanghai Jiaotong University, refType=null, unstructuredReference=LI Dengpan, REN Xiaoming, YAN Nannan. Real-time detection of insulator drop string based on UAV aerial photography[J]. Journal of Shanghai Jiaotong University, 2022, 56(8):994-1003., articleTitle=Real-time detection of insulator drop string based on UAV aerial photography, refAbstract=null), Reference(id=1226462310768755652, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2022, volume=38, issue=23, pageStart=130, pageEnd=140, url=null, language=null, rfNumber=[17], rfOrder=30, authorNames=王政, 许兴时, 华志新, journalName=农业工程学报, refType=null, unstructuredReference=王政，许兴时，华志新，等.融合YOLOv5n与通道剪枝算法的轻量化奶牛发情行为识别[J].农业工程学报，2022，38(23):130-140., articleTitle=融合YOLOv5n与通道剪枝算法的轻量化奶牛发情行为识别, refAbstract=null), Reference(id=1226462310882001868, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2022, volume=38, issue=23, pageStart=130, pageEnd=140, url=null, language=null, rfNumber=[17], rfOrder=31, authorNames=WANG Zheng, XU Xingshi, HUA Zhixin, journalName=Transactions of the Chinese Society of Agricultural Engineering, refType=null, unstructuredReference=WANG Zheng, XU Xingshi, HUA Zhixin, et al. Lightweight recognition for the oestrus behavior of dairy cows combining YOLOv5n and channel pruning[J]. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(23):130-140., articleTitle=Lightweight recognition for the oestrus behavior of dairy cows combining YOLOv5n and channel pruning, refAbstract=null), Reference(id=1226462310995248078, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2020, volume=31, issue=9, pageStart=2654, pageEnd=2677, url=null, language=null, rfNumber=[18], rfOrder=32, authorNames=张政馗, 庞为光, 谢文静, journalName=软件学报, refType=null, unstructuredReference=张政馗，庞为光，谢文静，等.面向实时应用的深度学习研究综述[J].软件学报，2020，31(9):2654-2677., articleTitle=面向实时应用的深度学习研究综述, refAbstract=null), Reference(id=1226462311087522769, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2020, volume=31, issue=9, pageStart=2654, pageEnd=2677, url=null, language=null, rfNumber=[18], rfOrder=33, authorNames=ZHANG Zhengkui, PANG Weiguang, XIE Wenjing, journalName=Journal of Software, refType=null, unstructuredReference=ZHANG Zhengkui, PANG Weiguang, XIE Wenjing, et al. Deep learning for real-time applications: a survey[J]. Journal of Software, 2020, 31(9):2654-2677., articleTitle=Deep learning for real-time applications: a survey, refAbstract=null), Reference(id=1226462311188186070, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=11, pageStart=3647, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=34, authorNames=LIU Mingxin, LI Ruixin, HOU Mingxin, journalName=Sensors, refType=null, unstructuredReference=LIU Mingxin, LI Ruixin, HOU Mingxin, et al. SD-YOLOv8: an accurate seriola dumerili detection model based on improved YOLOv8[J]. Sensors, 2024, 24(11):3647., articleTitle=SD-YOLOv8: an accurate seriola dumerili detection model based on improved YOLOv8, refAbstract=null), Reference(id=1226462311284655063, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2023, volume=9, issue=8, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=35, authorNames=HUANG Jing, ZENG Keyao, ZHANG Zijun, journalName=Heliyon, refType=null, unstructuredReference=HUANG Jing, ZENG Keyao, ZHANG Zijun, et al. Solar panel defect detection design based on YOLOv5 algorithm [J]. Heliyon, 2023, 9(8):e18826., articleTitle=Solar panel defect detection design based on YOLOv5 algorithm, refAbstract=null), Reference(id=1226462311360152536, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2024, volume=21, issue=2, pageStart=33, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=36, authorNames=WANG Huilin, QIAN Huaming, FENG Shuai, journalName=Journal of Real-Time Image Processing, refType=null, unstructuredReference=WANG Huilin, QIAN Huaming, FENG Shuai, et al. L-SSD: lightweight SSD target detection based on depth-separable convolution [J]. Journal of Real-Time Image Processing, 2024, 21(2):33., articleTitle=L-SSD: lightweight SSD target detection based on depth-separable convolution, refAbstract=null), Reference(id=1226462311473398749, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, doi=null, pmid=null, pmcid=null, year=2017, volume=39, issue=6, pageStart=1137, pageEnd=1149, url=null, language=null, rfNumber=[22], rfOrder=37, 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)], funds=[Fund(id=1226462306717057781, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, awardId=20212BBE53026, language=CN, fundingSource=江西省重点研发计划项目(20212BBE53026), fundOrder=null, country=null), Fund(id=1226462306809332476, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, awardId=YC2023-S649; YC2023-S50, language=CN, fundingSource=江西省研究生创新专项资金项目(YC2023-S649; YC2023-S50), fundOrder=null, country=null), Fund(id=1226462306901607172, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, awardId=jxsq2018101046, language=CN, fundingSource=江西省“双千计划”引进高层次创新人才项目(jxsq2018101046), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1226462300899557599, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, xref=1., ext=[AuthorCompanyExt(id=1226462300907946208, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, companyId=1226462300899557599, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi 341000, China), AuthorCompanyExt(id=1226462300916334817, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, companyId=1226462300899557599, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.江西理工大学机电工程学院，江西　赣州市　341000)]), AuthorCompany(id=1226462301000220905, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, xref=2., ext=[AuthorCompanyExt(id=1226462301008609514, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, companyId=1226462301000220905, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Jiangxi Province Engineering Research Center for Mechanical and Electrical of Mining and Metallurgy, Ganzhou, Jiangxi 341000, China), AuthorCompanyExt(id=1226462301012803819, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, companyId=1226462301000220905, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.江西省矿冶机电工程技术研究中心，江西　赣州市　341000)])], figs=[ArticleFig(id=1226462304255001124, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=EN, label=Fig.1, caption=Schematic of YC-Lightweight Net architecture, figureFileSmall=hOXPUG6vek4f0Q1acgjPow==, figureFileBig=B01ePrRCf6OuwhvLuZzpwQ==, tableContent=null), ArticleFig(id=1226462304338887217, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=CN, label=图1, caption=摇床轻量化融合网络结构示意, figureFileSmall=hOXPUG6vek4f0Q1acgjPow==, figureFileBig=B01ePrRCf6OuwhvLuZzpwQ==, tableContent=null), ArticleFig(id=1226462304666042957, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=EN, label=Fig.2, caption=Architecture of RepViT, figureFileSmall=VKUtfce6N8H4IFQotan+Uw==, figureFileBig=o9I5VRqYGkqHBx4KhJ8okw==, tableContent=null), ArticleFig(id=1226462304758317655, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=CN, label=图2, caption=重复视觉转换网络结构, figureFileSmall=VKUtfce6N8H4IFQotan+Uw==, figureFileBig=o9I5VRqYGkqHBx4KhJ8okw==, tableContent=null), ArticleFig(id=1226462304846398050, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=EN, label=Fig.3, caption=Architecture of GSConv, figureFileSmall=BQ0auZDvNK1p+9GLDpKygQ==, figureFileBig=BdofVnzqCvYhUegX50k17Q==, tableContent=null), ArticleFig(id=1226462304934478439, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=CN, label=图3, caption=分组空间卷积结构, figureFileSmall=BQ0auZDvNK1p+9GLDpKygQ==, figureFileBig=BdofVnzqCvYhUegX50k17Q==, tableContent=null), ArticleFig(id=1226462305030947439, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=EN, label=Fig.4, caption=Architecture of VOVGSCSP module, figureFileSmall=ZCgdRwWUFwDh9JfrZk84bg==, figureFileBig=6DoHP7HMXRp7VbbX6XzlDA==, tableContent=null), ArticleFig(id=1226462305135805048, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=CN, label=图4, caption=多尺度高效跨阶段融合网络模块结构, figureFileSmall=ZCgdRwWUFwDh9JfrZk84bg==, figureFileBig=6DoHP7HMXRp7VbbX6XzlDA==, tableContent=null), ArticleFig(id=1226462305249051270, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=EN, label=Fig.5, caption=Architecture of lightweight detection head, figureFileSmall=YcoSpnR5F/d4zJHccPFBfA==, figureFileBig=wdw7OZ+AY397HzhuQW8KIg==, tableContent=null), ArticleFig(id=1226462305370686093, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=CN, label=图5, caption=轻量化检测头结构, figureFileSmall=YcoSpnR5F/d4zJHccPFBfA==, figureFileBig=wdw7OZ+AY397HzhuQW8KIg==, tableContent=null), ArticleFig(id=1226462305509098138, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=EN, label=Fig.6, caption=The image of shaking table surface sub-banding, figureFileSmall=9plnDHrRfavGD3Rq1+P72w==, figureFileBig=lDT3G8aMIrBNr+ZPucaQZg==, tableContent=null), ArticleFig(id=1226462305622344357, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=CN, label=图6, caption=摇床床面分带图像, figureFileSmall=9plnDHrRfavGD3Rq1+P72w==, figureFileBig=lDT3G8aMIrBNr+ZPucaQZg==, tableContent=null), ArticleFig(id=1226462305802699440, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=EN, label=Fig.7, caption=Detection performance of the YC-Lightweight-Net (after pruning) model, figureFileSmall=V81CJKqbgXeM/q2Kte2YVA==, figureFileBig=k/lN1b84vnPBpQphW3RHkg==, tableContent=null), ArticleFig(id=1226462305928528569, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=CN, label=图7, caption=剪枝后YC-LightweightNet模型检测效果, figureFileSmall=V81CJKqbgXeM/q2Kte2YVA==, figureFileBig=k/lN1b84vnPBpQphW3RHkg==, tableContent=null), ArticleFig(id=1226462306092106442, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=EN, label=Table 1, caption=

Parameter settings for model training

, figureFileSmall=null, figureFileBig=null, tableContent=
参数数值
图像大小640 px×640 px
学习率0.01
批量大小16
迭代次数200次
优化器SGD
梯度动量0.937
权重衰减系数0.000 5
), ArticleFig(id=1226462306167603917, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=CN, label=表1, caption=

模型训练参数设置

, figureFileSmall=null, figureFileBig=null, tableContent=
参数数值
图像大小640 px×640 px
学习率0.01
批量大小16
迭代次数200次
优化器SGD
梯度动量0.937
权重衰减系数0.000 5
), ArticleFig(id=1226462306297627351, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=EN, label=Table 2, caption=

Detection accuracy and speed indices of models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型精确率/%召回率/%平均精度均值/%帧率/(帧/s)
YOLOv8n89.081.091.0227
YOLOv5n84.077.083.0141
Faster R-CNN88.084.086.027
SSD86.081.081.041
YC-Lightweight Net98.497.998.8333
YC-Lightweight Net（剪枝）98.396.696.7357
), ArticleFig(id=1226462306398290657, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=CN, label=表2, caption=

模型检测精度、速度指标

, figureFileSmall=null, figureFileBig=null, tableContent=
模型精确率/%召回率/%平均精度均值/%帧率/(帧/s)
YOLOv8n89.081.091.0227
YOLOv5n84.077.083.0141
Faster R-CNN88.084.086.027
SSD86.081.081.041
YC-Lightweight Net98.497.998.8333
YC-Lightweight Net（剪枝）98.396.696.7357
), ArticleFig(id=1226462306515731174, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=EN, label=Table 3, caption=

Computational complexity indices of models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型参数量/ (×106)浮点运算量/ (×1010)模型大小/ MB
YOLOv8n3.208.76.30
YOLOv5n1.904.55.20
Faster R-CNN24.10193.6102.50
SSD12.1059.296.24
YC-Lightweight Net5.9816.912.60
YC-Lightweight Net（剪枝）0.832.62.20
), ArticleFig(id=1226462306620588781, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1226462297611224049, language=CN, label=表3, caption=

模型计算复杂度指标

, figureFileSmall=null, figureFileBig=null, tableContent=
模型参数量/ (×106)浮点运算量/ (×1010)模型大小/ MB
YOLOv8n3.208.76.30
YOLOv5n1.904.55.20
Faster R-CNN24.10193.6102.50
SSD12.1059.296.24
YC-Lightweight Net5.9816.912.60
YC-Lightweight Net（剪枝）0.832.62.20
)], 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=null, journalPrice=null, startedYear=null, abbrevIsoEn=Mining Research and Development, journalRemark=null, publicationField=null, createdTime=1770086852251, updatedTime=1770087111158, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=M, firstLetterEn=M, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=null, picEn=null, jcr=null, cjcr=null, exts=[JournalExt(id=1225397417764372753, 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=1770087111178, updatedTime=1770087111178, createdBy=13701087609, updatedBy=13701087609, 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=1225397417831481618, 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=1770087111194, updatedTime=1770087111194, createdBy=13701087609, updatedBy=13701087609, 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=1225410533512364352, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=articleTextType, value=kx, createTime=1770090238216, updateTime=1770090238216, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410533487198525, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=banner, value=null, createTime=1770090238210, updateTime=1770090238210, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410533533335875, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=grayFlag, value=0, createTime=1770090238221, updateTime=1770090238221, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410533470421308, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=logo, value=https://castjournals.cast.org.cn/joweb/kyyjykf/EN/file/pic?fileId=++etCLRiS7F8czudkkUdPA==, createTime=1770090238206, updateTime=1770090238206, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410533550113093, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=minRunFlag, value=0, createTime=1770090238225, updateTime=1770090238225, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410533508170047, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kyyjykf/CN/file/pic, createTime=1770090238215, updateTime=1770090238215, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410533541724484, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=silenceFlag, value=0, createTime=1770090238223, updateTime=1770090238223, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410533499781438, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1770090238213, updateTime=1770090238213, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410533520752961, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=themeColor, value=null, createTime=1770090238218, updateTime=1770090238218, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410533524947266, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=themeStyle, value=null, createTime=1770090238219, updateTime=1770090238219, 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=null, journalPhotoEn=null, journalFirstLetter=M, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kyyjykf/CN/Y2025/V45/I10/199, detailUrlEn=https://castjournals.cast.org.cn/joweb/kyyjykf/EN/Y2025/V45/I10/199, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kyyjykf/CN/PDF/Y2025/V45/I10/199, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kyyjykf/EN/PDF/Y2025/V45/I10/199, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于轻量化融合网络的摇床精矿带分离点位置提取研究
收藏切换
PDF下载
刘惠中 1, 2 , 刘建业 1 , 黄翱 1 , 邓富龙 1 , 刘茜茜 1
矿业研究与开发 | 矿山机电与矿业智能化 2025,45(10): 199-206
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(10): 199-206
基于轻量化融合网络的摇床精矿带分离点位置提取研究
全屏
刘惠中1, 2 , 刘建业1, 黄翱1, 邓富龙1, 刘茜茜1
作者信息
  • 1.江西理工大学机电工程学院，江西　赣州市　341000
  • 2.江西省矿冶机电工程技术研究中心，江西　赣州市　341000

    • 刘惠中（1969一），男，江西信丰人，博士，教授，博士生导师，主要从事选矿装备及智能化等方面的研究。E-mail:

Research on the Extraction of Separation Point Positions for Shaking Table Concentrate Band Based on Lightweight Fusion Network
Huizhong LIU1, 2 , Jianye LIU1, Ao HUANG1, Fulong DENG1, Xixi LIU1
Affiliations
  • 1.School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi 341000, China
  • 2.Jiangxi Province Engineering Research Center for Mechanical and Electrical of Mining and Metallurgy, Ganzhou, Jiangxi 341000, China
出版时间: 2025-10-25
文章导航
收藏切换
摘要
收起

针对现有摇床矿带目标检测算法存在检测精度和检测速度无法兼顾、计算成本高、模型大小难压缩和推理速度慢等问题，提出了一种摇床轻量化融合网络（YC-Lightweight Net）目标检测算法。YC-Lightweight Net模型首先采用重复视觉转换网络对摇床矿物分带图像进行特征提取，然后通过引入分组空间卷积、多尺度高效跨阶段融合模块并采用跳跃连接的方式设计了一种高效、轻量的颈部网络，最后采用基于权重的层自适应剪枝算法压缩模型大小。试验结果表明，YC-Lightweight Net模型精确度、召回率、平均精度均值和帧率指标分别为98.4%、97.9%、98.8%和333帧/s，检测精度和检测速度明显优于各对比模型；剪枝后参数量、浮点运算量和模型大小分别为原模型的13.9%、15.4%和17.5%，剪枝操作极大降低了模型的计算复杂度和模型大小。YC-Lightweight Net模型具有良好的检测精度和实时性能，满足摇床选矿厂的工业设备对模型轻量化的要求，可为摇床矿带分离点精准识别及选矿厂摇床设备智能化升级提供技术支持。

摇床精矿带  /  目标检测  /  轻量化设计  /  LAMP算法  /  精准识别

The existing object detection algorithms for shaking table concentrate bands have problems such as inability to balance detection accuracy and speed, high computational costs, difficulty in compressing model size, and slow inference speed. To address these problems, a lightweight fusion network for shaking tables (YC-Lightweight Net) object detection algorithm was proposed. The YC-Lightweight Net model firstly used a repetitive visual transformation network to extract features from the images of shaking table sub-banding. Then, by introducing group space convolution, multi-scale efficient cross stage fusion modules, and using skip connections, an efficient and lightweight neck network was designed. Finally, a weight based layer adaptive pruning algorithm was used to compress the model size. The experimental results show that the accuracy, recall, mean average precision, and FPS indicators of the YC-Lightweight Net model are 98.4%, 97.9%, 98.8% and 333 frame/s, respectively. The detection accuracy and speed are significantly better than those of the compared models. The number of parameters, floating-point operations, and model size after pruning are 13.9%, 15.4% and 17.5% of the original model, respectively. The pruning operation greatly reduces the computational complexity and model size of the model. The YC-Lightweight Net model has good detection accuracy and real-time performance, meeting the requirements of industrial equipment for lightweight models in shaking table mineral processing plants. The study can provide a technical support for accurate identification of separation points in mineral bands and intelligent upgrading of the shaking table mineral processing plant equipment.

Shaking table concentrate band  /  Object detection  /  Lightweight design  /  LAMP algorithm  /  Precise identification
刘惠中, 刘建业, 黄翱, 邓富龙, 刘茜茜. 基于轻量化融合网络的摇床精矿带分离点位置提取研究. 矿业研究与开发, 2025 , 45 (10) : 199 -206 .
Huizhong LIU, Jianye LIU, Ao HUANG, Fulong DENG, Xixi LIU. Research on the Extraction of Separation Point Positions for Shaking Table Concentrate Band Based on Lightweight Fusion Network[J]. Mining Research and Development, 2025 , 45 (10) : 199 -206 .
正文
收起
0　引言
收起
随着经济的快速发展，矿产资源被大量开采，逐渐呈“贫、细、杂”的特点[1-2]。为了保证足够量的选矿精矿产出，选矿厂的生产规模逐渐扩大。为了提高生产效率以满足大规模选矿生产需求，选矿装备的自动化和智能化水平要求日益提高。选矿摇床作为工业生产中分选细粒矿石的常用设备，同时也是钨、锡、钽铌、钛和稀土等战略性矿产资源分离富集的关键设备，对选矿摇床进行自动化和智能化升级已成为重要的研究方向。现阶段摇床选矿生产依靠工人肉眼观察精矿带的位置，并通过手动调节精矿截取板至适当的位置以保证精矿品位，并根据观察到的精矿带分布特征和个人操作经验，对摇床的床面坡度、冲洗水、冲程和冲次等控制参数进行适当调整，保证摇床运行状态的正常。一般规模的选矿厂会配置几十或上百台套摇床同时运行，工人要对每台摇床逐一进行调节，导致调节滞后、调节精度低和劳动强度大等问题。因此，研究与开发选矿摇床矿带分离点位置检测技术，对于加快选矿摇床智能化发展、提高选矿厂经济效益具有重要且实际的科学意义。
近年来，深度学习目标检测技术发展迅速，已成为计算机视觉领域的核心技术之一。该技术凭借其高精度、高效率、低成本、实时性和适应性强等优点在工业生产的多种场景得到了广泛应用[3-5]。门定航等[6]基于YOLO算法提出了一种改进的YOLOv8算法，解决了无人机航拍图像人员漏检问题，其检测精度在应急救援场景下表现良好。董耿耿等[7]构建了新梅目标检测模型，解决了新梅在果林遮挡、果实重叠等复杂环境下难以检测的问题，满足了后续采摘机器人对新梅实时检测的需求。孟祥伟[8]提出了一种基于威尔科克森（Wilcoxon）非参数检测器，适用于检测新型合成孔径雷达(Synthetic Aperture Radar, SAR)图像中舰船目标，该检测方法在复杂的杂波背景下具有较好的检测性能，有效控制了虚警率并提高了对目标的检测能力。杨栋等[9]采用改进YOLOv8模型有效辨别了电缆复合绝缘结构内部缺陷的类型和位置，研究有助于将目标识别检测方法推广至对电缆复合绝缘结构乃至其他层状复合绝缘结构的内部缺陷无损可视化检测。郭孟澳等[10]结合目标检测技术和增强现实(Augmented Reality, AR)技术提出了一种新型人机交互系统，采用目标识别算法实时捕捉不同场景下的目标信息，并在AR中向每个目标施加不同程度的刺激效果以增强用户与目标物体的交互性，该系统结合YOLOv5目标检测算法成功实现了脑机接口医学应用转化。田心如等[11]设计了一种适应微型发光二极管(Mini/Micro-LED)芯片生产时尺寸小、密度大、需要快速检测缺陷等特点的压缩注意力细节-语义互补卷积神经网络，试验结果表明，该网络满足工业缺陷检测的要求。叶咏菁等[12]针对井下环境中传统车牌定位算法易受强光、反光、粉尘等不利条件影响，导致出现车牌与车身对比度降低、边缘弱化的问题，提出了一种基于改进YOLOv7的车牌高精度定位检测算法，为井下环境车辆编号的精准识别及车辆智能管控提供技术支持。黄可等[13]针对复杂工况下煤矸识别效率低、分选难度大的问题，采用视觉几何群（Visual Geometry Group, VGG)网络搭建煤矸识别模型，结果表明，优化后的VGG模型可以实现复杂情况下煤矸的高效精准识别。目标检测算法在上述场景应用成功的案例为实现选矿摇床矿带分离点检测提供了科学依据和技术支持。
目前，将目标检测技术应用于摇床选矿生产仍面临一些挑战和难题：检测床面矿带分离点属于小目标检测，对于目标检测算法的精度和速度均有较高要求；在提高算法精度保证矿带分离点的精准识别时，无法兼顾计算成本；在检测矿带分离点时缺少床面分带背景信息等纹理特征；目标检测算法模型大小难以进一步压缩，无法适应工业生产的轻量化需求等。为此，本文提出了摇床轻量化融合网络（YC-Lightweight Net），在保证检测精度和效率的同时对该算法进行轻量化剪枝，降低其计算成本，提高推理效率，并进一步对模型大小进行压缩，使其能够适应工业设备乃至嵌入式系统的轻量化要求。
1　摇床轻量化融合网络结构
收起
针对当前摇床矿带分离点检测任务中存在的模型大小难压缩、参数量大、检测速度和精度无法兼顾等问题，本文以重复视觉转换网络(RepViT)为主干网络，并设计了一种轻量高效的颈部网络和检测头结构，提出了摇床轻量化融合网络（YC-Lightweight Net)，其结构如图1所示。
1.1　重复视觉转换网络
重复视觉转换网络[14]是集成了转换器网络结构与卷积神经网络结构优势的高效视觉模型，其结构如图2所示。
重复视觉转换网络基于转换器网络结构(Transformer)，通过引入高效卷积模块、重参数化策略和多尺度特征提取机制，增强了原始视觉转换器网络(Vision Transformer)的特征表示能力。本文利用重复视觉转换网络的特殊结构，从不同尺度和层次提取摇床床面分带的低级边缘特征和高级语义特征，通过多尺度聚合过程整合图像的局部和全局的上下文信息，并以不同尺度捕捉矿带分离点这一重要特征。
重复视觉转换网络将局部卷积和全局卷积相结合，设计了适应性强的高效卷积块，该模块既可以精细提取局部区域特征，又能通过较大的感受野获取全局特征，能够在特征提取的过程中保证矿带分离点的细节特征，同时有效压缩信息，捕捉床面分带背景信息。重参数化结构使模型在训练时采用复杂多分支结构，在推理过程中将分支融合为更加简化、高效的独立结构。这种设计将整个网络简化为单一分支，不仅显著降低了计算成本，还能在保留训练中捕获的细节和全局信息的同时，提高检测速度和效率。重复视觉转换网络的轻量化和高表达能力为摇床矿带分离点检测任务提供了强大的前端支持。
1.2　颈部网络结构设计
为适应工业设备计算能力，本文设计了一种轻量化颈部网络，其网络结构见图1。为对模型大小进行压缩并降低模型计算复杂度，在颈部网络中引入分组空间卷积（GSConv）[15]减少计算复杂度，使得模型可以在有限的计算资源下高效运行，并提高了通道间的信息交互，增强特征多样性，其结构如图3所示。分组空间卷积模块可使模型在保持性能的同时大幅减少计算成本和参数量，保证了模型在摇床选矿厂工业设备及嵌入式设备的适用性。
采用多尺度高效跨阶段融合网络（VOVGSCSP）模块优化模型梯度流动，使模型减少参数量的同时仍能保持强大的特征表达能力，其结构如图4所示。多尺度高效跨阶段融合网络模块融合了分组空间卷积的高效特征提取能力、分组空间卷积颈部网络的深度特征提取能力，以及交叉阶段部分网络(CSPNet)的分层融合机制。该模块借鉴CSPNet结构思想，将输入特征图分流后并行处理，一部分跳过分组空间卷积颈部网络模块，以减少卷积操作并降低计算复杂度；另一部分经该模块处理提取深层特征。最终利用级联操作将两路输出进行特征融合，确保不同层次特征的传递。
改进了模型特征融合的方式，在第7号、11号和20号节点采用跳跃连接的方式，使各节点能够独立处理不同尺度的特征。该设计避免了将上一层的输出直接作为数据输入，专注当前层级的特征处理从而减少了特征冗余。此外，跳跃连接使网络不依赖数据的传递顺序，能够并行处理，有效降低了模型推理阶段的延迟，提高了实时性。跳跃连接使得梯度可以直接由更深层回传，保持较好的梯度流动，提高了模型训练的稳定性。
通过多层特征的缩放和拼接，将不同分辨率特征图融合，结合了低层次特征和高层次特征，使模型在处理多尺度目标时更加有效，增强了模型的检测性能和灵活性。
1.3　检测头结构设计
检测头是模型识别目标的关键，其计算复杂度对模型整体性能具有重要影响。传统基线模型检测头对每个尺度的特征层单独进行卷积操作，多次卷积加剧了模型的计算负担。而摇床选矿厂的工业设备及嵌入式设备计算资源有限，为此本文设计了一种轻量化检测头。首先通过1×1卷积操作对不同尺度的特征图进行通道压缩，减少其特征维度并保持特征空间信息不变，而后引入共享卷积层处理三个尺度的特征层。该设计可以使各尺度特征图实现特征交互并进行特征融合，而且实现了参数共享，大大减少了模型的参数和计算量，降低了模型计算复杂度并提高了模型的实时检测性能。轻量化检测头结构如图5所示。
2　基于权重的层自适应剪枝
收起
尽管在设计模型时采用了大量轻量化模块，但随着模型的深化，其规模和复杂度不断增加，计算和存储资源需求也随之增大。剪枝是使模型轻量化以适应资源有限设备的重要手段，通过剪枝可将神经网络各层中的冗余结构去除，释放模型计算资源[16-18]。为削减模型中的冗余参数，减少计算量和内存占用，并保持模型的准确性，本文采用基于权重的层自适应剪枝(Layer-Adaptive Magnitude-based Pruning, LAMP)算法，基于层间权重大小对模型进行自适应剪枝。为保证各层剪枝后稀疏性分布均匀，基于权重的层自适应剪枝算法引入，用于衡量各权重在全局的重要性及其在同一层内的相对位置和影响。LAMP评分计算见式(1)：
式中：W[u]为第u个权重值；S[u]表示该层中大于等于第u个权重值的权重的平方和。
式中：S(u;W)为权重中第u个索引的LAMP得分；W[u]2为索引u对应的权重值；为该层中大于等于第u个权重值的权重平方和。
LAMP得分通过对计算和排序权重平方幅度与剩余权重累计平方和的比值，量化了每个权重在模型中相对其他权重的重要性，确保剪枝时保留对输出失真影响较大的权重。根据各权重的LAMP分数排序决定整体剪枝比例，保证了各层的稀疏性分布是全局最优化结果。同时在剪枝过程中避免了对关键权重的误剪，维持了模型的整体精度。
LAMP得分通过计算权重平方幅度与剩余权重累计平方和的比值，并对其进行排序，以量化每个权重在模型中的相对重要性。该方法能够在剪枝过程中保留对输出失真影响显著的权重，从而有效控制剪枝引起的性能损失。根据各权重的LAMP分数排序决定整体剪枝比例，可保证各层稀疏性分布达到全局最优。同时，该方法有效避免了对关键权重的误剪，有助于维持模型整体精度。
3　试验与分析
收起
3.1　数据集与试验设置
本文数据集来源于江西大余某摇床选矿厂生产车间，利用工业相机采集4台摇床选矿生产视频数据，并采用抽帧的方法制成图片数据集。数据集共1900张图片，包含不同尺寸和拍摄角度下的摇床床面分带图像数据，如图6所示。
利用开源标注工具 labelme对摇床矿带分离点进行人工标注，逐张框选出图片数据中的目标矿带分离点，生成包含图片名称、标签名称和目标框坐标位置的.xml文件，并采用随机缩放和 mosaic 拼接的方法丰富数据集。试验时，按照 8∶2的比例随机划分训练集和测试集。试验在 Windows 10 操作系统下运行，GPU配置为 NVIDIA GeForce GTX 3060 Laptop，试验环境为 Python 3.10 及CUDA11.0。模型训练参数设置见表1。
3.2　评价指标
综合考虑摇床轻量化融合网络矿带分离点特征提取算法的检测精度、检测速度及计算复杂度，选取精确度、召回率和平均精度均值三个指标衡量模型的检测精度，选取帧率指标衡量模型的检测速度，选取浮点运算量、模型大小和参数量为指标衡量模型的计算复杂度。
3.3　模型对比试验
模型性能是工业应用的先决条件，为验证本文模型对摇床床面矿带分离点目标检测的性能，分别与YOLOv8n[19]、YOLOv5n[20]、单发多框检测算法（Single Shot MultiBox Detector, SSD)[21]和更快速的区域卷积神经网络（Faster Region-Based Convolutional Neural Network, Faster R-CNN)[22]模型的性能进行对比，对比试验结果见表2、表3。
由试验结果可知，Faster R-CNN作为双阶段目标检测算法网络结构复杂，参数量和浮点运算量远高于其余算法，虽然具有较高的检测精度，但不适合在摇床选矿厂计算资源有限的工业设备上运行，且其帧率指标较低，不满足摇床选矿过程的实时检测要求。YOLO系列算法网络结构简单、检测速度快，但YOLOv5n算法的召回率较低，模型对正类样本的捕获能力较低，在应用时可能出现漏检问题。YOLOv8n算法在检测精度和检测速度上较YOLOv5n算法有明显提升，但其精确度、召回率仍较低，不满足工业应用要求。本文设计的 YC-Lightweight Net综合考虑摇床选矿过程中矿带分离点特征提取的检测精度和检测速度需求，采用重复视觉转换网络对矿带分离点特征信息进行提取，在保证模型高效特征提取能力和全局信息捕捉能力的前提下对模型进行轻量化设计，在颈部网络和检测头的设计上以模型轻量化为原则。YC-Lightweight Net 的精确度、召回率和平均精度均值分别为98.4%、97.9%和98.8%，帧率为 333 帧/s，检测精度指标（平均精度均值）比YOLOv8n、YOLOv5n、Faster R-CNN 和 SSD 模型分别提高了8.6%、19.0%、14.9%和22.0%，帧率较上述模型分别提高了46.7%、136.2%、1133.3%和712.2%，其检测精度和速度上的各项指标均明显优于其他模型。
尽管YC-Lightweight Net采用了轻量化设计，但由于Transformer机制的引入和多分支结构的训练需求，模型的参数量和浮点运算量仍有所增加，进而导致模型较大，其参数量、浮点运算量和模型大小相较于YOLO系列算法仍有差距。为优化模型计算复杂度和模型大小，本文对YC-Lightweight Net模型进行轻量化剪枝。经剪枝操作，多数层结构的通道数显著减少，从而降低了模型在推理时执行的浮点运算量，加快了推理速度。同时，通道数的减少直接降低了模型参数量和生成的中间特征图大小，有效减少GPU显存和RAM的占用，保障了模型部署在摇床选矿厂工业设备上的可行性。此外，基于权重的层自适应剪枝算法在剪枝过程中能够根据不同层结构的冗余程度进行自适应剪枝，对冗余度较高的层结构其通道数明显减少，而对于特征提取较为关键的层结构则保留了更多的通道数以维持模型的性能。
剪枝后YC-Lightweight Net模型（如图7所示)的浮点运算量参数量、浮点运算量和模型大小分别为0.83×106、2.6×106和2.2×106 MB，仅为原模型的13.9%、15.4%和17.5%，剪枝操作极大地降低了模型的计算复杂度和模型大小。相较于YOLOv8等模型，剪枝后的YC-LightweightNet模型浮点运算量、参数量和模型大小三项指标最低，模型计算复杂度最小，更适用于摇床选矿厂中计算资源有限的工业设备。剪枝后的YC-Lightweight-Net模型平均精度均值为96.7%，相较于剪枝前仅下降2.1个百分点，精度满足工业要求，其帧率达到357 帧/s，实时检测性能良好。
4　结论
收起
本文以摇床选矿厂自动化水平低、工人劳动强度大等实际问题出发，以重复视觉转换网络为主干网络，并设计了一种轻量高效的颈部网络结构和检测头结构，提出了摇床轻量化融合网络（YC-Lightweight Net)目标检测算法。对YC-Lightweight Net模型检测精度、检测速度和计算复杂度进行评价，并与其他算法进行对比，得到以下主要结论。
（1）YC-Lightweight Net模型能够平衡检测精度和检测速度间的需求，精确度、召回率、平均精度均值和帧率分别为98.4%、97.9%、98.8%和333帧/s。相较于YOLOv8n、YOLOv5n、Faster R-CNN和SSD模型，平均精度均值分别提高了8.6%、19.0%、14.9%和22.0%，帧率分别提高了46.7%、136.2%、1133.3%和712.2%，表明本文提出的YC-Lightweight Net模型具有优良的检测性能。
（2）运用基于权重的层自适应剪枝算法对YC-Lightweight Net进行轻量化剪枝，剪枝后模型参数量、浮点运算量和模型大小分别为原模型的13.9%、15.4%和17.5%，有效降低了模型的计算复杂度和模型大小，解决了现有模型参数量大、计算复杂度高和模型大小难压缩的问题，满足摇床选矿厂工业设备对模型轻量化的要求。
基金
收起
  • 江西省重点研发计划项目(20212BBE53026)
  • 江西省研究生创新专项资金项目(YC2023-S649; YC2023-S50)
  • 江西省“双千计划”引进高层次创新人才项目(jxsq2018101046)
文献
收起
参考文献 引证文献
排序方式：
[1]
鞠建华，韩见，冯聪.我国矿产资源综合利用现状评估与发展路径[J].中国矿业，2024，33(6):14-25.
JU Jianhua, HAN Jian, FENG Cong. Evaluation and development path of comprehensive utilization of mineral resources in China[J]. China Mining Magazine, 2024, 33(6):14-25.
[2]
张长青，芮宗瑶，陈毓川，等.中国铅锌矿资源潜力和主要战略接续区[J].中国地质，2013，40(1):248-272.
ZHANG Changqing, RUI Zongyao, CHEN Yuchuan, et al. The main successive strategic bases of resources for Pb-Zn deposits in China[J]. Geology in China, 2013, 40(1):248-272.
[3]
张顺，龚怡宏，王进军.深度卷积神经网络的发展及其在计算机视觉领域的应用[J].计算机学报，2019，42(3):453-482.
ZHANG Shun, GONG Yihong, WANG Jinjun. The development of deep convolution neural network and its applications on computer vision [J]. Chinese Journal of Computers, 2019, 42(3):453-482.
[4]
郑太雄，江明哲，冯明驰.基于视觉的采摘机器人目标识别与定位方法研究综述[J].仪器仪表学报，2021，42(9):28-51.
ZHENG Taixiong, JIANG Mingzhe, FENG Mingchi. Vision based target recognition and location for picking robot: a review[J]. Chinese Journal of Scientific Instrument, 2021, 42(9):28-51.
[5]
陶显，侯伟，徐德.基于深度学习的表面缺陷检测方法综述[J].自动化学报，2021，47(5):1017-1034.
TAO Xian, HOU Wei, XU De. A survey of surface defect detection methods based on deep learning [J]. Acta Automatica Sinica, 2021, 47(5):1017-1034.
[6]
门定航，谭钦红.基于YOLOv8改进的航拍图像人员检测[J/OL].激光杂志：1-7[2024-07-15].http://kns.cnki.net/kcms/detail/50.1085.TN.20240710.2017.010.html.
MEN Dinghang, TAN Qinhong. Human detection for aerial photography based on improved YOLOv8 [J/OL]. Laser Journal:1-7[2024-07-15]. http://kns.cnki.net/kcms/detail/50.1085.TN.20240710.2017.010.html.
[7]
董耿耿，陈小康，樊湘鹏，等.基于改进YOLOv5s的复杂环境下新梅检测方法[J].农业工程学报，2024，40（14）：118-125.
DONG Genggeng, CHEN Xiaokang, FAN Xiangpeng, et al. Detecting Xinmei fruit under complex environments using improved YOLOv5s[J]. Transactions of the Chinese Society of Agricultural Engineering, 2024, 40(14):118-125.
[8]
孟祥伟.SAR图像中舰船目标恒虚警率检测技术的研究[J].电子与信息学报，2024，46(9):3739-3748.
MENG Xiangwei. Research on constant false alarm rate detection technique for ship in SAR image[J]. Journal of Electronics & Information Technology, 2024, 46(9):3739-3748.
[9]
杨栋，朵文博，李帅兵，等.基于改进YOLOv8的电缆复合绝缘结构内部缺陷太赫兹成像识别方法[J].高电压技术，2024，50(9):4142-4151.
YANG Dong, DUO Wenbo, LI Shuaibing, et al. Terahertz imaging recognition method for internal defects in cable composite insulation structure based on improved YOLOv8 [J]. High Voltage Engineering, 2024, 50(9):4142-4151.
[10]
郭孟澳，杨帮华，耿亦婷，等.基于增强现实和稳态视觉诱发电位的视觉目标检测系统[J].生物医学工程学杂志，2024，41(4):684-691.
GUO Meng'ao, Yang Banghua, GENG Yiting, et al. Visual object detection system based on augmented reality and steady-state visual evoked potential [J]. Journal of Biomedical Engineering, 2024, 41(4):684-691.
[11]
田心如，褚洁，蔡觉平，等.用于 Mini/Micro-LED芯片缺陷检测的全局特征压缩卷积神经网络[J].仪器仪表学报，2024，45(8):174-184.
TIAN Xinru, CHU Jie, CAI Jueping, et al. Global feature compression convolutional neural network for defect detection in Mini/Micro-LED chips[J]. Chinese Journal of Scientific Instrument, 2024, 45(8):174-184.
[12]
叶咏菁，韩斌，胡亚飞，等.基于YOLOv7-CA-Faster的井下复杂环境下车牌定位算法研究[J].矿业研究与开发，2024，44(10):197-206.
YE Yongjing, HAN Bin, HU Yafei, et al. Research on license plate localization algorithm in underground complex environment based on YOLOv7-CA-Faster [J]. Mining Research and Development, 2024, 44(10):197-206.
[13]
黄可，樊玉萍，董宪姝，等.基于优化的VGG-16网络模型的煤矸识别研究[J].矿业研究与开发，2024，44(9):219-226.
HUANG Ke, FAN Yuping, DONG Xianshu, et al. Coal gangue identification based on optimized VGG-16 network model[J]. Mining Research and Development, 2024, 44(9):219-226.
[14]
TANG Hao, XU Xixi, XU Haiyang, et al. Lightweight ViT with multiscale feature fusion for driving risk rating warning system [J]. Advanced Theory and Simulations, 2024, 7(11):2400586.
[15]
LI Hulin, LI Jun, WEI Hanbing, et al. Slim-neck by GSConv: a lightweight-design for real-time detector architectures [J]. Journal of Real-Time Image Processing, 2024, 21(3):62.
[16]
李登攀，任晓明，颜楠楠.基于无人机航拍的绝缘子掉串实时检测研究[J].上海交通大学学报，2022，56(8):994-1003.
LI Dengpan, REN Xiaoming, YAN Nannan. Real-time detection of insulator drop string based on UAV aerial photography[J]. Journal of Shanghai Jiaotong University, 2022, 56(8):994-1003.
[17]
王政，许兴时，华志新，等.融合YOLOv5n与通道剪枝算法的轻量化奶牛发情行为识别[J].农业工程学报，2022，38(23):130-140.
WANG Zheng, XU Xingshi, HUA Zhixin, et al. Lightweight recognition for the oestrus behavior of dairy cows combining YOLOv5n and channel pruning[J]. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(23):130-140.
[18]
张政馗，庞为光，谢文静，等.面向实时应用的深度学习研究综述[J].软件学报，2020，31(9):2654-2677.
ZHANG Zhengkui, PANG Weiguang, XIE Wenjing, et al. Deep learning for real-time applications: a survey[J]. Journal of Software, 2020, 31(9):2654-2677.
[19]
LIU Mingxin, LI Ruixin, HOU Mingxin, et al. SD-YOLOv8: an accurate seriola dumerili detection model based on improved YOLOv8[J]. Sensors, 2024, 24(11):3647.
[20]
HUANG Jing, ZENG Keyao, ZHANG Zijun, et al. Solar panel defect detection design based on YOLOv5 algorithm [J]. Heliyon, 2023, 9(8):e18826.
[21]
WANG Huilin, QIAN Huaming, FENG Shuai, et al. L-SSD: lightweight SSD target detection based on depth-separable convolution [J]. Journal of Real-Time Image Processing, 2024, 21(2):33.
[22]
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.
2025年第45卷第10期
PDF下载
96
45
引用本文
BibTeX
文章信息
  • 接收时间：2024-11-05
  • 首发时间：2026-02-06
  • 出版时间：2025-10-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期：2024-11-05
基金
江西省重点研发计划项目(20212BBE53026)
江西省研究生创新专项资金项目(YC2023-S649; YC2023-S50)
江西省“双千计划”引进高层次创新人才项目(jxsq2018101046)
作者信息
    1.江西理工大学机电工程学院，江西　赣州市　341000
    2.江西省矿冶机电工程技术研究中心，江西　赣州市　341000
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kyyjykf/CN/1226462297611224049
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
010-62199257
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