首页 期刊 论文 学科刊群 资讯 加盟 关于
EN
image
Article(id=1322594927180104244, tenantId=1146029695717560320, journalId=1225396423026438145, issueId=1322594813749350688, 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=1719244800000, receivedDateStr=2024-06-25, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1793260803264, onlineDateStr=2026-10-29, pubDate=1740412800000, pubDateStr=2025-02-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793260803264, onlineIssueDateStr=2026-10-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793260803264, creator=13701087609, updateTime=1793260803264, updator=13701087609, issue=Issue{id=1322594813749350688, tenantId=1146029695717560320, journalId=1225396423026438145, year='2025', volume='45', issue='2', pageStart='1', pageEnd='288', issueExtLink='null', onlineDate='null', pubDate='1740412800000', pubDateStr='2025-02-25', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793260776220, creator='13701087609', updateTime=1793260776220, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=254, endPage=260, ext={EN=ArticleExt(id=1322594927540814389, articleId=1322594927180104244, tenantId=1146029695717560320, journalId=1225396423026438145, language=EN, title=Ore Identification System Developed Based on Orange Pi 5B, columnId=null, journalTitle=Mining Research and Development, columnName=null, runingTitle=null, highlight=null, articleAbstract=

In response to the current challenges of low accuracy, inefficiency, poor real-time performance, and weak environmental adaptability in ore detection technology, a ore identification system based on Orange Pi was proposed. This system utilized a high-definition camera to capture real-time images of ores and processed image data using the YOLOv4-tiny-tf2 model on the Orange Pi 5B development board to achieve efficient and accurate identification of ore types. The results show that the lightweight YOLOv4-tiny-tf2 model simplifies its structure without sacrificing the accuracy of the model, which is more suitable for deployment on lower-configured devices and has a higher portability. Compared with the traditional artificial visual inspection and chemical analysis methods, the ore identification system based on Orange Pi 5B can identify the ore in real time, and the identification accuracy rate reaches 93.75%, which has high reliability and stability.

, authors=Qin FUI, Qibing LINI, Zhoulin CHANGI, authorsList=Qin FU, Qibing LIN, Zhoulin CHANG, authorCompany=null, correspAuthors=Qibing LIN, 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=1322594930472632900, articleId=1322594927180104244, tenantId=1146029695717560320, journalId=1225396423026438145, language=CN, title=基于香橙派Orange Pi 5B开发的矿石识别系统, 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=

针对目前矿石检测技术准确性不高、效率低、实时性差以及环境适应性弱等问题，提出了一种基于香橙派的矿石识别系统。该系统利用高清摄像头实时捕获矿石图像，并通过香橙派Orange Pi 5B开发板搭载YOLOv4-tiny-tf2模型处理图像数据，实现矿石种类的高效准确识别。结果表明：轻量化的YOLOv4-tiny-tf2模型在不牺牲模型精度的情况下简化了其结构，更适合在配置较低的设备上部署，具备了较高的便携性；相较于传统的人工视觉检测和化学分析方法，基于香橙派Orange Pi 5B的矿石识别系统能够实时识别矿石，识别准确率达到93.75%，具有较高的可靠性和稳定性。

, authors=付琴I, 林奇兵I, 常周林I, authorsList=付琴, 林奇兵, 常周林, authorCompany=null, correspAuthors=林奇兵, authorNote=

付琴（1989—），女，湖北黄冈人，硕士，讲师，研究方向为电子系统设计。E-mail:

, correspAuthorsNote=
林奇兵（2000—），男，广东汕尾人，助理工程师，研究方向为电子系统设计。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=zttD/nibAG8G5/QjpTeHhg==, magXml=wq9ALx0w7AVHyHNgO05c0w==, pdfUrl=null, pdf=vCX6LaywAU/DhxvLA2gLpw==, pdfFileSize=2486185, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=HoS/Yg0J/r8C9y50t9BqUQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=LOkRrDB0Wd55YC/CGuzjCg==, mapNumber=null, fund=null)}, authors=[Author(id=1322594930967560777, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=fuqin_2023@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322594931059835467, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, authorId=1322594930967560777, language=EN, stringName=Qin FU, firstName=Qin, middleName=null, lastName=FU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=School of Mechanical and Electrical Engineering, Guangdong Mechanical & Electrical Polytechnic, Dongguan, Guangdong 523083, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322594931147915852, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, authorId=1322594930967560777, language=CN, stringName=付琴, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=广东科技学院 机电工程学院，广东　东莞市　523083, bio={"content":"

付琴（1989—），女，湖北黄冈人，硕士，讲师，研究方向为电子系统设计。E-mail:

"}, bioImg=null, bioContent=

付琴（1989—），女，湖北黄冈人，硕士，讲师，研究方向为电子系统设计。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322594930866897477, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, xref=null, ext=[AuthorCompanyExt(id=1322594930879480390, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, companyId=1322594930866897477, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mechanical and Electrical Engineering, Guangdong Mechanical & Electrical Polytechnic, Dongguan, Guangdong 523083, China), AuthorCompanyExt(id=1322594930887868999, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, companyId=1322594930866897477, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=广东科技学院 机电工程学院，广东　东莞市　523083)])]), Author(id=1322594931235996238, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=963476396@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322594931319882320, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, authorId=1322594931235996238, language=EN, stringName=Qibing LIN, firstName=Qibing, middleName=null, lastName=LIN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=School of Mechanical and Electrical Engineering, Guangdong Mechanical & Electrical Polytechnic, Dongguan, Guangdong 523083, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322594931403768401, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, authorId=1322594931235996238, language=CN, stringName=林奇兵, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=广东科技学院 机电工程学院，广东　东莞市　523083, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322594930866897477, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, xref=null, ext=[AuthorCompanyExt(id=1322594930879480390, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, companyId=1322594930866897477, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mechanical and Electrical Engineering, Guangdong Mechanical & Electrical Polytechnic, Dongguan, Guangdong 523083, China), AuthorCompanyExt(id=1322594930887868999, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, companyId=1322594930866897477, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=广东科技学院 机电工程学院，广东　东莞市　523083)])]), Author(id=1322594931491848787, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, 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=1322594931579929173, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, authorId=1322594931491848787, language=EN, stringName=Zhoulin CHANG, firstName=Zhoulin, middleName=null, lastName=CHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=School of Mechanical and Electrical Engineering, Guangdong Mechanical & Electrical Polytechnic, Dongguan, Guangdong 523083, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322594931655426646, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, authorId=1322594931491848787, language=CN, stringName=常周林, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=广东科技学院 机电工程学院，广东　东莞市　523083, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322594930866897477, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, xref=null, ext=[AuthorCompanyExt(id=1322594930879480390, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, companyId=1322594930866897477, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mechanical and Electrical Engineering, Guangdong Mechanical & Electrical Polytechnic, Dongguan, Guangdong 523083, China), AuthorCompanyExt(id=1322594930887868999, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, companyId=1322594930866897477, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=广东科技学院 机电工程学院，广东　东莞市　523083)])])], keywords=[Keyword(id=1322594931768672855, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=EN, orderNo=1, keyword=Ore identification system), Keyword(id=1322594931877724760, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=EN, orderNo=2, keyword=Orange Pi 5B), Keyword(id=1322594931974193753, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=EN, orderNo=3, keyword=YOLOv4-tiny-tf2), Keyword(id=1322594932066468442, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=EN, orderNo=4, keyword=Accuracy rate), Keyword(id=1322594932141965915, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=CN, orderNo=1, keyword=矿石识别系统), Keyword(id=1322594932234240604, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=CN, orderNo=2, keyword=香橙派Orange Pi 5B), Keyword(id=1322594932330709597, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=CN, orderNo=3, keyword=YOLOv4-tiny-tf2), Keyword(id=1322594932406207070, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=CN, orderNo=4, keyword=准确率)], refs=[Reference(id=1322594936441127541, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2021, volume=57, issue=21, pageStart=248, pageEnd=255, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=薄景文, 张春堂, 樊春玲, journalName=计算机工程与应用, refType=null, unstructuredReference=薄景文，张春堂，樊春玲，等.改进YOLOv3的矿石输送带杂物检测方法[J].计算机工程与应用，2021，57(21):248-255., articleTitle=改进YOLOv3的矿石输送带杂物检测方法, refAbstract=null), Reference(id=1322594936629871222, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2021, volume=57, issue=21, pageStart=248, pageEnd=255, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=BO Jingwen, ZHANG Chuntang, FAN Chunling, journalName=Computer Engineering and Applications, refType=null, unstructuredReference=BO Jingwen, ZHANG Chuntang, FAN Chunling，et al. Ore conveyor belt sundries detection based on improved YOLOv3[J]. Computer Engineering and Applications, 2021，57(21):248-255., articleTitle=Ore conveyor belt sundries detection based on improved YOLOv3, refAbstract=null), Reference(id=1322594936743117431, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2022, volume=45, issue=23, pageStart=99, pageEnd=106, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=马进, 王超, journalName=电子测量技术, refType=null, unstructuredReference=马进，王超.基于改进YOLOv4-tiny的印刷电路板缺陷检测研究[J].电子测量技术，2022，45(23):99-106., articleTitle=基于改进YOLOv4-tiny的印刷电路板缺陷检测研究, refAbstract=null), Reference(id=1322594936818614904, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2022, volume=45, issue=23, pageStart=99, pageEnd=106, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=MA Jin, WANG Chao, journalName=Electronic Measurement Technology, refType=null, unstructuredReference=MA Jin, WANG Chao. Research on printed circuit board defect detection based on improved YOLOv4-tiny algorithm[J]. Electronic Measurement Technology, 2022, 45(23):99-106., articleTitle=Research on printed circuit board defect detection based on improved YOLOv4-tiny algorithm, refAbstract=null), Reference(id=1322594936885723769, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2023, volume=53, issue=11, pageStart=2635, pageEnd=2644, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=杨志军, 昌新萌, 丁洪伟, journalName=无线电工程, refType=null, unstructuredReference=杨志军，昌新萌，丁洪伟.基于改进YOLOv4-Tiny的交通车辆实时目标检测[J].无线电工程，2023，53(11):2635-2644., articleTitle=基于改进YOLOv4-Tiny的交通车辆实时目标检测, refAbstract=null), Reference(id=1322594937032524410, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2023, volume=53, issue=11, pageStart=2635, pageEnd=2644, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=YANG Zhijun, CHANG Xinmeng, DING Hongwei, journalName=Radio Engineering, refType=null, unstructuredReference=YANG Zhijun, CHANG Xinmeng, DING Hongwei. Improved YOLOv4-Tiny real-time vehicle detection[J]. Radio Engineering, 2023, 53(11):2635-2644., articleTitle=Improved YOLOv4-Tiny real-time vehicle detection, refAbstract=null), Reference(id=1322594937108021883, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2023, volume=50, issue=增刊1, pageStart=484, pageEnd=490, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=窦智, 胡晨光, 梁竞一, journalName=计算机科学, refType=null, unstructuredReference=窦智，胡晨光，梁竞一，等.基于改进Yolov4-tiny的轻量型目标检测算法[J].计算机科学，2023，50(增刊1):484-490., articleTitle=基于改进Yolov4-tiny的轻量型目标检测算法, refAbstract=null), Reference(id=1322594937204490876, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2023, volume=50, issue=Suppl.1, pageStart=484, pageEnd=490, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=DOU Zhi, HU Chenguang, LIANG Jingyi, journalName=Computer Science, refType=null, unstructuredReference=DOU Zhi, HU Chenguang, LIANG Jingyi，et al. Lightweight target detection algorithm based on improved Yolov4-tiny[J]. Computer Science, 2023, 50(Suppl.1):484-490., articleTitle=Lightweight target detection algorithm based on improved Yolov4-tiny, refAbstract=null), Reference(id=1322594937305154173, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=11, pageStart=169, pageEnd=175, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=刘姣娣, 何捷, 许洪振, journalName=中国农机化学报, refType=null, unstructuredReference=刘姣娣，何捷，许洪振，等.基于改进YOLOv4-Tiny的蔗芽识别方法[J].中国农机化学报，2023，44(11):169-175., articleTitle=基于改进YOLOv4-Tiny的蔗芽识别方法, refAbstract=null), Reference(id=1322594937401623166, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=11, pageStart=169, pageEnd=175, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=LIU Jiaodi, HE Jie, XU Hongzhen, journalName=Journal of Chinese Agricultural Mechanization, refType=null, unstructuredReference=LIU Jiaodi, HE Jie, XU Hongzhen，et al. Identification method of cane sprout based on improved YOLOv4-Tiny[J]. Journal of Chinese Agricultural Mechanization，2023，44 (11):169-175., articleTitle=Identification method of cane sprout based on improved YOLOv4-Tiny, refAbstract=null), Reference(id=1322594937523257983, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2021, volume=40, issue=1, pageStart=98, pageEnd=100+103, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=江美玲, 章杰, journalName=传感器与微系统, refType=null, unstructuredReference=江美玲，章杰.基于树莓派的服装识别系统设计[J].传感器与微系统，2021，40(1):98-100+103., articleTitle=基于树莓派的服装识别系统设计, refAbstract=null), Reference(id=1322594937611338368, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2021, volume=40, issue=1, pageStart=98, pageEnd=100+103, url=null, language=null, rfNumber=[6], rfOrder=11, authorNames=JIANG Meiling, ZHANG Jie, journalName=Transducer and Microsystem Technologies, refType=null, unstructuredReference=JIANG Meiling, ZHANG Jie. Design of clothing recognition system based on Raspberry Pi[J]. Transducer and Microsystem Technologies, 2021, 40(1):98-100+103., articleTitle=Design of clothing recognition system based on Raspberry Pi, refAbstract=null), Reference(id=1322594937703613057, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=9, pageStart=131, pageEnd=136, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=陈品岚, 张小花, 朱立学, journalName=中国农机化学报, refType=null, unstructuredReference=陈品岚，张小花，朱立学，等.基于树莓派及深度学习的柑橘识别系统设计[J].中国农机化学报，2022，43(9):131-136., articleTitle=基于树莓派及深度学习的柑橘识别系统设计, refAbstract=null), Reference(id=1322594937783304834, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=9, pageStart=131, pageEnd=136, url=null, language=null, rfNumber=[7], rfOrder=13, authorNames=CHEN Pinlan, ZHANG Xiaohua, ZHU Lixue, journalName=Journal of Chinese Agricultural Mechanization, refType=null, unstructuredReference=CHEN Pinlan, ZHANG Xiaohua, ZHU Lixue，et al. Citrus recognition system based on Raspberry Pi and deep learning[J]. Journal of Chinese Agricultural Mechanization, 2022, 43(9):131-136., articleTitle=Citrus recognition system based on Raspberry Pi and deep learning, refAbstract=null), Reference(id=1322594937871385219, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=8, pageStart=192, pageEnd=201, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=杨环宇, 黄文静, 李义华, journalName=中南林业科技大学学报, refType=null, unstructuredReference=杨环宇，黄文静，李义华，等.基于树莓派平台的柑橘智能识别与采摘[J].中南林业科技大学学报，2023，43(8):192-201., articleTitle=基于树莓派平台的柑橘智能识别与采摘, refAbstract=null), Reference(id=1322594937942688388, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=8, pageStart=192, pageEnd=201, url=null, language=null, rfNumber=[8], rfOrder=15, authorNames=YANG Huanyu, HUANG Wenjing, LI Yihua, journalName=Journal of Central South University of Forestry & Technology, refType=null, unstructuredReference=YANG Huanyu, HUANG Wenjing, LI Yihua，et al. Design of citrus identification and picking based on the Raspberry Pi platform[J]. Journal of Central South University of Forestry & Technology, 2023, 43(8):192-201., articleTitle=Design of citrus identification and picking based on the Raspberry Pi platform, refAbstract=null), Reference(id=1322594939658158726, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=9, pageStart=34, pageEnd=41, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=张硕, 陆宇峰, 王丹翔, journalName=兵器装备工程学报, refType=null, unstructuredReference=张硕，陆宇峰，王丹翔，等.基于YOLOv4-tiny的无人机全自动跟踪方法[J].兵器装备工程学报，2023，44(9):34-41., articleTitle=基于YOLOv4-tiny的无人机全自动跟踪方法, refAbstract=null), Reference(id=1322594939758822023, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=9, pageStart=34, pageEnd=41, url=null, language=null, rfNumber=[9], rfOrder=17, authorNames=ZHANG Shuo, LU Yufeng, WANG Danxiang, journalName=Journal of Ordnance Equipment Engineering, refType=null, unstructuredReference=ZHANG Shuo, LU Yufeng, WANG Danxiang，et al. Fully automatic tracking method for UAVs based on YOLOv4-tiny[J]. Journal of Ordnance Equipment Engineering, 2023, 44(9):34-41., articleTitle=Fully automatic tracking method for UAVs based on YOLOv4-tiny, refAbstract=null), Reference(id=1322594939842708104, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=1, pageStart=174, pageEnd=181, url=null, language=null, rfNumber=[10], rfOrder=18, authorNames=宛鹤, 张金艳, 屈娟萍, journalName=金属矿山, refType=null, unstructuredReference=宛鹤，张金艳，屈娟萍，等.基于改进MobileNet V3的矿物智能识别模型[J].金属矿山，2024(1):174-181., articleTitle=基于改进MobileNet V3的矿物智能识别模型, refAbstract=null), Reference(id=1322594939926594185, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=1, pageStart=174, pageEnd=181, url=null, language=null, rfNumber=[10], rfOrder=19, authorNames=WAN He, ZHANG Jinyan, QU Juanping, journalName=Metal Mine, refType=null, unstructuredReference=WAN He, ZHANG Jinyan, QU Juanping，et al. Intelligent recognition model of mineral based on improved MobileNet V3[J]. Metal Mine, 2024(1):174-181., articleTitle=Intelligent recognition model of mineral based on improved MobileNet V3, refAbstract=null), Reference(id=1322594940023063178, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2023, volume=49, issue=8, pageStart=127, pageEnd=133, url=null, language=null, rfNumber=[11], rfOrder=20, authorNames=陈海舰, 王唯一, 范锦鸽, journalName=工矿自动化, refType=null, unstructuredReference=陈海舰，王唯一，范锦鸽，等.基于树莓派的井下水仓水位智能测控系统[J].工矿自动化，2023，49(8):127-133., articleTitle=基于树莓派的井下水仓水位智能测控系统, refAbstract=null), Reference(id=1322594940098560651, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2023, volume=49, issue=8, pageStart=127, pageEnd=133, url=null, language=null, rfNumber=[11], rfOrder=21, authorNames=CHEN Haijian, WANG Weiyi, FAN Jin'ge, journalName=Jounal and Mine Automation, refType=null, unstructuredReference=CHEN Haijian, WANG Weiyi, FAN Jin'ge，et al. Intelligent measurement and control system of mine water level based on Raspberry Pi[J]. Jounal and Mine Automation, 2023, 49(8):127-133., articleTitle=Intelligent measurement and control system of mine water level based on Raspberry Pi, refAbstract=null), Reference(id=1322594940207612556, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2023, volume=45, issue=11, pageStart=111, pageEnd=116, url=null, language=null, rfNumber=[12], rfOrder=22, authorNames=周国宏, 陆宏, journalName=制造业自动化, refType=null, unstructuredReference=周国宏，陆宏.基于树莓派的低成本教学机器人设计与实现[J].制造业自动化，2023，45(11):111-116., articleTitle=基于树莓派的低成本教学机器人设计与实现, refAbstract=null), Reference(id=1322594940287304333, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2023, volume=45, issue=11, pageStart=111, pageEnd=116, url=null, language=null, rfNumber=[12], rfOrder=23, authorNames=ZHOU Guohong, LU Hong, journalName=Manufacturing Automation, refType=null, unstructuredReference=ZHOU Guohong, LU Hong. Design and implementation of a low-cost teaching robot based on Raspberry Pi[J]. Manufacturing Automation, 2023, 45(11):111-116., articleTitle=Design and implementation of a low-cost teaching robot based on Raspberry Pi, refAbstract=null), Reference(id=1322594940375384718, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=9, pageStart=103, pageEnd=107, url=null, language=null, rfNumber=[13], rfOrder=24, authorNames=张开飞, 尚增强, 马清俊, journalName=农机化研究, refType=null, unstructuredReference=张开飞，尚增强，马清俊，等.基于树莓派的喷雾质量检测系统设计[J].农机化研究，2022，44(9):103-107., articleTitle=基于树莓派的喷雾质量检测系统设计, refAbstract=null), Reference(id=1322594940450882191, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=9, pageStart=103, pageEnd=107, url=null, language=null, rfNumber=[13], rfOrder=25, authorNames=ZHANG Kaifei, SHANG Zengqiang, MA Qingjun, journalName=Journal of Agricultural Mechanization Research, refType=null, unstructuredReference=ZHANG Kaifei, SHANG Zengqiang, MA Qingjun，et al. Design of spray quality inspection system based on Raspberry Pi[J]. Journal of Agricultural Mechanization Research, 2022, 44(9):103-107., articleTitle=Design of spray quality inspection system based on Raspberry Pi, refAbstract=null), Reference(id=1322594940547351184, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2019, volume=42, issue=19, pageStart=36, pageEnd=40, url=null, language=null, rfNumber=[14], rfOrder=26, authorNames=于镭, 林再腾, journalName=电子测量技术, refType=null, unstructuredReference=于镭，林再腾.基于香橙派的智能语音识别系统的设计[J].电子测量技术，2019，42(19):36-40., articleTitle=基于香橙派的智能语音识别系统的设计, refAbstract=null), Reference(id=1322594940618654353, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2019, volume=42, issue=19, pageStart=36, pageEnd=40, url=null, language=null, rfNumber=[14], rfOrder=27, authorNames=YU Lei, LIN Zaiteng, journalName=Electronic Measurement Technology, refType=null, unstructuredReference=YU Lei, LIN Zaiteng. Design of an intelligent speech recognition system based on Orange Pi[J]. Electronic Measurement Technology, 2019, 42(19):36-40., articleTitle=Design of an intelligent speech recognition system based on Orange Pi, refAbstract=null), Reference(id=1322594940685763218, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2024, volume=53, issue=5, pageStart=167, pageEnd=171, url=null, language=null, rfNumber=[15], rfOrder=28, authorNames=刘凡, 陈锐, journalName=机电工程技术, refType=null, unstructuredReference=刘凡，陈锐.基于改进ResNet50在高岭土矿石图像分类的应用[J].机电工程技术，2024，53(5):167-171., articleTitle=基于改进ResNet50在高岭土矿石图像分类的应用, refAbstract=null), Reference(id=1322594940782232211, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2024, volume=53, issue=5, pageStart=167, pageEnd=171, url=null, language=null, rfNumber=[15], rfOrder=29, authorNames=LIU Fan, CHEN Rui, journalName=Mechanical & Electrical Engineering Technology, refType=null, unstructuredReference=LIU Fan, CHEN Rui. Application of improved ResNet50 in image classification of Kaolin Ores[J]. Mechanical & Electrical Engineering Technology, 2024, 53(5):167-171., articleTitle=Application of improved ResNet50 in image classification of Kaolin Ores, refAbstract=null), Reference(id=1322594940853535380, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=4, pageStart=209, pageEnd=216, url=null, language=null, rfNumber=[16], rfOrder=30, authorNames=杨丽荣, 曹冲, 刘顺, journalName=矿业研究与开发, refType=null, unstructuredReference=杨丽荣，曹冲，刘顺.改进Mask RCNN算法对矿石分割定位的研究[J].矿业研究与开发，2023，43(4):209-216., articleTitle=改进Mask RCNN算法对矿石分割定位的研究, refAbstract=null), Reference(id=1322594940945810069, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=4, pageStart=209, pageEnd=216, url=null, language=null, rfNumber=[16], rfOrder=31, authorNames=YANG Lirong, CAO Chong, LIU Shun, journalName=Mining Reaearch and Development, refType=null, unstructuredReference=YANG Lirong, CAO Chong, LIU Shun. Study on improved Mask RCNN algorithm for ore segmentation and localization[J]. Mining Reaearch and Development，2023，43(4):209-216., articleTitle=Study on improved Mask RCNN algorithm for ore segmentation and localization, refAbstract=null), Reference(id=1322594941029696150, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=2, pageStart=178, pageEnd=182, url=null, language=null, rfNumber=[17], rfOrder=32, authorNames=邓田, 余翼, journalName=矿业研究与开发, refType=null, unstructuredReference=邓田，余翼.基于PSO-Faster R-CNN改进算法的矿石识别分类研究[J].矿业研究与开发，2021，41(2):178-182., articleTitle=基于PSO-Faster R-CNN改进算法的矿石识别分类研究, refAbstract=null), Reference(id=1322594941113582231, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=2, pageStart=178, pageEnd=182, url=null, language=null, rfNumber=[17], rfOrder=33, authorNames=DENG Tian, YU Yi, journalName=Mining Reaearch and Development, refType=null, unstructuredReference=DENG Tian, YU Yi. Research on ore identification and separation based on improved PSO-Faster R-CNN algorithm[J]. Mining Reaearch and Development，2021，41（2）：178-182., articleTitle=Research on ore identification and separation based on improved PSO-Faster R-CNN algorithm, refAbstract=null)], funds=[Fund(id=1322594936214635123, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, awardId=2021KQNCX119, language=CN, fundingSource=广东省教育厅青年创新人才项目(2021KQNCX119), fundOrder=null, country=null), Fund(id=1322594936285938292, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, awardId=GKZLGC2023156, language=CN, fundingSource=广东科技学院电子信息工程一流专业建设项目(GKZLGC2023156), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322594930866897477, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, xref=null, ext=[AuthorCompanyExt(id=1322594930879480390, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, companyId=1322594930866897477, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mechanical and Electrical Engineering, Guangdong Mechanical & Electrical Polytechnic, Dongguan, Guangdong 523083, China), AuthorCompanyExt(id=1322594930887868999, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, companyId=1322594930866897477, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=广东科技学院 机电工程学院，广东　东莞市　523083)])], figs=[ArticleFig(id=1322594932607533663, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=EN, label=Fig.1, caption=Framework of mineral identication system, figureFileSmall=EI2APkDt1g5yLRPLej++tg==, figureFileBig=HoS/Yg0J/r8C9y50t9BqUQ==, tableContent=null), ArticleFig(id=1322594932716585568, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=CN, label=图1, caption=矿石识别系统框架, figureFileSmall=EI2APkDt1g5yLRPLej++tg==, figureFileBig=HoS/Yg0J/r8C9y50t9BqUQ==, tableContent=null), ArticleFig(id=1322594932972438113, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=EN, label=Fig.2, caption=Feature structure of YOLOv4-tiny-tf2, figureFileSmall=QJ0xjGpOX35bNOdA64vl6g==, figureFileBig=Jrb9FNcLHxRD+0Wc22ns6w==, tableContent=null), ArticleFig(id=1322594933047935586, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=CN, label=图2, caption=YOLOv4-tiny-tf2特征结构, figureFileSmall=QJ0xjGpOX35bNOdA64vl6g==, figureFileBig=Jrb9FNcLHxRD+0Wc22ns6w==, tableContent=null), ArticleFig(id=1322594933115044451, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=EN, label=Fig.3, caption=Training process of model, figureFileSmall=zGJubE3P+WJBG7rjJ98a8Q==, figureFileBig=ErPQYmSyfdNQ7NlyI48mIA==, tableContent=null), ArticleFig(id=1322594933203124836, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=CN, label=图3, caption=模型训练流程, figureFileSmall=zGJubE3P+WJBG7rjJ98a8Q==, figureFileBig=ErPQYmSyfdNQ7NlyI48mIA==, tableContent=null), ArticleFig(id=1322594933295399525, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=EN, label=Fig.4, caption=Precision of various types of minerals, figureFileSmall=a6CnoFFaqiPyxn5S/HF2ZQ==, figureFileBig=E6w772ZBYApFU1it0Vnldw==, tableContent=null), ArticleFig(id=1322594933391868518, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=CN, label=图4, caption=各类别矿物的精准度, figureFileSmall=a6CnoFFaqiPyxn5S/HF2ZQ==, figureFileBig=E6w772ZBYApFU1it0Vnldw==, tableContent=null), ArticleFig(id=1322594933454783079, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=EN, label=Fig.5, caption=Area under P-R curve of apatite, figureFileSmall=RDKlRGtShMofsGsJ8ou1Cw==, figureFileBig=9N4iaX4H3uKr3Uo5HezlOg==, tableContent=null), ArticleFig(id=1322594935124116072, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=CN, label=图5, caption=磷灰石P-R曲线下的面积, figureFileSmall=RDKlRGtShMofsGsJ8ou1Cw==, figureFileBig=9N4iaX4H3uKr3Uo5HezlOg==, tableContent=null), ArticleFig(id=1322594935220585065, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=EN, label=Fig.6, caption=Precision, figureFileSmall=gx391CqXFzkBKWXgy+y2HA==, figureFileBig=+IODTJfJF/PfXhaC/Y3dnQ==, tableContent=null), ArticleFig(id=1322594935363191402, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=CN, label=图6, caption=查准率, figureFileSmall=gx391CqXFzkBKWXgy+y2HA==, figureFileBig=+IODTJfJF/PfXhaC/Y3dnQ==, tableContent=null), ArticleFig(id=1322594935451271787, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=EN, label=Fig.7, caption=Test flow of model, figureFileSmall=t2awL8+MvDvnBIMzW/ZilQ==, figureFileBig=NZ84K3UB2PuaRNQH7cEG8g==, tableContent=null), ArticleFig(id=1322594935560323692, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=CN, label=图7, caption=模型测试流程, figureFileSmall=t2awL8+MvDvnBIMzW/ZilQ==, figureFileBig=NZ84K3UB2PuaRNQH7cEG8g==, tableContent=null), ArticleFig(id=1322594935644209773, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=EN, label=Table 1, caption=

Statistics of ore identification results

, figureFileSmall=null, figureFileBig=null, tableContent=
矿石类别正确识别数量/个错误识别数量/个
赤铁矿282
黄铜矿255
萤石291
石墨282
白钨矿300
石英291
浮石264
磷灰石300
总计22515
), ArticleFig(id=1322594935740678766, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=CN, label=表1, caption=

矿石识别结果统计

, figureFileSmall=null, figureFileBig=null, tableContent=
矿石类别正确识别数量/个错误识别数量/个
赤铁矿282
黄铜矿255
萤石291
石墨282
白钨矿300
石英291
浮石264
磷灰石300
总计22515
), ArticleFig(id=1322594935820370543, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=EN, label=Table 2, caption=

Statistics of manual visual identification results

, figureFileSmall=null, figureFileBig=null, tableContent=
矿石类别正确识别数量/个错误识别数量/个
赤铁矿264
黄铜矿273
萤石282
石墨291
白钨矿273
石英282
浮石273
磷灰石255
总计21723
), ArticleFig(id=1322594935904256624, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=CN, label=表2, caption=

人工目视识别结果统计

, figureFileSmall=null, figureFileBig=null, tableContent=
矿石类别正确识别数量/个错误识别数量/个
赤铁矿264
黄铜矿273
萤石282
石墨291
白钨矿273
石英282
浮石273
磷灰石255
总计21723
), ArticleFig(id=1322594935992337009, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=EN, label=Table 3, caption=

Statistics of chemical tests identification results

, figureFileSmall=null, figureFileBig=null, tableContent=
矿石类别识别方法预计所需时间/h正确识别数量/个
赤铁矿酸洗、光谱分析0.530
黄铜矿X射线衍射分析1~230
萤石酸反应测试(与稀盐酸反应)1~230
石墨显微镜观察、化学成分分析0.530
白钨矿光谱分析、化学测试1~230
石英磁性测试、化学分析1~230
浮石硫酸测试、显微镜观察2~330
磷灰石X射线衍射、化学成分分析1~230
), ArticleFig(id=1322594936084611698, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, language=CN, label=表3, caption=

化学测试识别结果统计

, figureFileSmall=null, figureFileBig=null, tableContent=
矿石类别识别方法预计所需时间/h正确识别数量/个
赤铁矿酸洗、光谱分析0.530
黄铜矿X射线衍射分析1~230
萤石酸反应测试(与稀盐酸反应)1~230
石墨显微镜观察、化学成分分析0.530
白钨矿光谱分析、化学测试1~230
石英磁性测试、化学分析1~230
浮石硫酸测试、显微镜观察2~330
磷灰石X射线衍射、化学成分分析1~230
)], 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/I2/254, detailUrlEn=https://castjournals.cast.org.cn/joweb/kyyjykf/EN/Y2025/V45/I2/254, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kyyjykf/CN/PDF/Y2025/V45/I2/254, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kyyjykf/EN/PDF/Y2025/V45/I2/254, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1740412800000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于香橙派Orange Pi 5B开发的矿石识别系统
收藏切换
PDF下载
付琴 I , 林奇兵 I , 常周林 I
矿业研究与开发 | 矿山机电与矿业智能化 2025,45(2): 254-260
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 (2) : 254 -260
基于香橙派Orange Pi 5B开发的矿石识别系统
全屏
[Author(id=1322594930967560777, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=fuqin_2023@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322594931059835467, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, authorId=1322594930967560777, language=EN, stringName=Qin FU, firstName=Qin, middleName=null, lastName=FU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=School of Mechanical and Electrical Engineering, Guangdong Mechanical & Electrical Polytechnic, Dongguan, Guangdong 523083, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322594931147915852, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, authorId=1322594930967560777, language=CN, stringName=付琴, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=广东科技学院 机电工程学院，广东　东莞市　523083, bio={"content":"

付琴（1989—），女，湖北黄冈人，硕士，讲师，研究方向为电子系统设计。E-mail:

"}, bioImg=null, bioContent=

付琴（1989—），女，湖北黄冈人，硕士，讲师，研究方向为电子系统设计。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322594930866897477, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, xref=null, ext=[AuthorCompanyExt(id=1322594930879480390, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, companyId=1322594930866897477, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mechanical and Electrical Engineering, Guangdong Mechanical & Electrical Polytechnic, Dongguan, Guangdong 523083, China), AuthorCompanyExt(id=1322594930887868999, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, companyId=1322594930866897477, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=广东科技学院 机电工程学院，广东　东莞市　523083)])]), Author(id=1322594931235996238, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=963476396@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322594931319882320, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, authorId=1322594931235996238, language=EN, stringName=Qibing LIN, firstName=Qibing, middleName=null, lastName=LIN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=School of Mechanical and Electrical Engineering, Guangdong Mechanical & Electrical Polytechnic, Dongguan, Guangdong 523083, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322594931403768401, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, authorId=1322594931235996238, language=CN, stringName=林奇兵, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=广东科技学院 机电工程学院，广东　东莞市　523083, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322594930866897477, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, xref=null, ext=[AuthorCompanyExt(id=1322594930879480390, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, companyId=1322594930866897477, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mechanical and Electrical Engineering, Guangdong Mechanical & Electrical Polytechnic, Dongguan, Guangdong 523083, China), AuthorCompanyExt(id=1322594930887868999, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, companyId=1322594930866897477, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=广东科技学院 机电工程学院，广东　东莞市　523083)])]), Author(id=1322594931491848787, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, 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=1322594931579929173, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, authorId=1322594931491848787, language=EN, stringName=Zhoulin CHANG, firstName=Zhoulin, middleName=null, lastName=CHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=School of Mechanical and Electrical Engineering, Guangdong Mechanical & Electrical Polytechnic, Dongguan, Guangdong 523083, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322594931655426646, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, authorId=1322594931491848787, language=CN, stringName=常周林, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=广东科技学院 机电工程学院，广东　东莞市　523083, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322594930866897477, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, xref=null, ext=[AuthorCompanyExt(id=1322594930879480390, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, companyId=1322594930866897477, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mechanical and Electrical Engineering, Guangdong Mechanical & Electrical Polytechnic, Dongguan, Guangdong 523083, China), AuthorCompanyExt(id=1322594930887868999, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594927180104244, companyId=1322594930866897477, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=广东科技学院 机电工程学院，广东　东莞市　523083)])])]
付琴I , 林奇兵I , 常周林I
作者信息
  • 广东科技学院 机电工程学院，广东　东莞市　523083
通讯作者:
林奇兵（2000—），男，广东汕尾人，助理工程师，研究方向为电子系统设计。E-mail:
作者简介:

付琴（1989—），女，湖北黄冈人，硕士，讲师，研究方向为电子系统设计。E-mail:

Ore Identification System Developed Based on Orange Pi 5B
Qin FUI , Qibing LINI , Zhoulin CHANGI
Affiliations
  • School of Mechanical and Electrical Engineering, Guangdong Mechanical & Electrical Polytechnic, Dongguan, Guangdong 523083, China
出版时间: 2025-02-25
文章导航
收藏切换
摘要
收起

针对目前矿石检测技术准确性不高、效率低、实时性差以及环境适应性弱等问题，提出了一种基于香橙派的矿石识别系统。该系统利用高清摄像头实时捕获矿石图像，并通过香橙派Orange Pi 5B开发板搭载YOLOv4-tiny-tf2模型处理图像数据，实现矿石种类的高效准确识别。结果表明：轻量化的YOLOv4-tiny-tf2模型在不牺牲模型精度的情况下简化了其结构，更适合在配置较低的设备上部署，具备了较高的便携性；相较于传统的人工视觉检测和化学分析方法，基于香橙派Orange Pi 5B的矿石识别系统能够实时识别矿石，识别准确率达到93.75%，具有较高的可靠性和稳定性。

矿石识别系统  /  香橙派Orange Pi 5B  /  YOLOv4-tiny-tf2  /  准确率

In response to the current challenges of low accuracy, inefficiency, poor real-time performance, and weak environmental adaptability in ore detection technology, a ore identification system based on Orange Pi was proposed. This system utilized a high-definition camera to capture real-time images of ores and processed image data using the YOLOv4-tiny-tf2 model on the Orange Pi 5B development board to achieve efficient and accurate identification of ore types. The results show that the lightweight YOLOv4-tiny-tf2 model simplifies its structure without sacrificing the accuracy of the model, which is more suitable for deployment on lower-configured devices and has a higher portability. Compared with the traditional artificial visual inspection and chemical analysis methods, the ore identification system based on Orange Pi 5B can identify the ore in real time, and the identification accuracy rate reaches 93.75%, which has high reliability and stability.

Ore identification system  /  Orange Pi 5B  /  YOLOv4-tiny-tf2  /  Accuracy rate
付琴, 林奇兵, 常周林. 基于香橙派Orange Pi 5B开发的矿石识别系统. 矿业研究与开发, 2025 , 45 (2) : 254 -260 .
Qin FU, Qibing LIN, Zhoulin CHANG. Ore Identification System Developed Based on Orange Pi 5B[J]. Mining Research and Development, 2025 , 45 (2) : 254 -260 .
正文
收起
0　引言
收起
矿石是地球上的重要自然资源之一，对矿石的开采和利用一直是人类重要的经济活动之一。因此，采取高效率的检测方式对于矿石的开采和利用至关重要。传统的矿石检测方法有人工目视、化学分析和光谱分析方法。人工目视的方法虽然直观，但受限于人的主观判断和经验，可能导致结果的准确性和稳定性不足[1]。化学分析和光谱分析方法精度较高，但通常需要进行样本采集、处理、分析等多个步骤，消耗的资源以及人力较多，且需要专业的设备和操作人员，对即时检测的精度与稳定缺乏研究。
本文提出一种基于香橙派的矿石识别系统[2-8]，通过使用嵌入式设备运行深度学习模型，实现矿石高精度、高稳定性识别。深度学习模型的搭载需要较高计算能力的硬件设备，而这些硬件设备通常需要占用一定的面积。此外，由于矿石开采现场环境复杂，设备的便携性尤为重要，这会对深度学习模型的运行产生影响。
YOLOv4-tiny算法是YOLOv4的精简版[9]。该算法对硬件要求较低，便于在小型设备上使用。YOLOv4-tiny使用CSPDarknet53-tiny主干网络代替YOLOv4的CSPDarknet53主干网络，整体网络结构仅有38层，使用3个残差单元，激活函数使用LeakyReLU。相较于YOLOv4, YOLOv4-tiny算法不仅大幅度优化了网络结构，而且保持了可接受的检测精度和速度[10-13]。
本文使用香橙派 Orange Pi 5B开发板[14]作为硬件基础设备，收集矿石图片，自制数据集并训练基于YOLOv4-tiny算法的YOLOv4-tiny-tf2模型，通过深度学习技术和嵌入式设备的结合，实现矿石检测的高效率、高准确性和设备便携性。这不仅有助于提升矿产资源行业的生产效率和经济效益，还有助于推动深度学习技术在工业领域的应用和发展。
1　矿石识别系统总体方案
收起
1.1　系统总体框架
矿石识别系统由香橙派Orange Pi 5B开发板平台、摄像头模块、显示器模块等硬件部分，Ubuntu 22.04操作系统、Anaconda 虚拟环境、TensorFlow 2.0、opencv-python等软件部分共同构成。香橙派 Orange Pi 5B 开发板的尺寸为100 mm×62 mm，质量为46 g，小尺寸与较轻的质量能满足便携性的要求。同时开发板使用 4 核心 Cortex-A76和 4 核心 Cortex-A55 大小核架构的 Rockchip RK3588S处理器，大核心频率最高能达到2.4 GHz，小核心频率最高能达到1.8 GHz，并且内置高达 6 Tops 算力的 AI 加速器NPU，在运行目标检测模型时能提高摄像头捕捉帧率。开发板搭载的 8 GB LPDDR4X RAM 与 64 GB eMMC ROM在满足模型容量的同时又具备高速的读写与运行能力，保证设备在运行过程中不卡顿。系统框架如图1 所示。
1.2　系统运行流程
本系统运行流程主要包括数据预处理、模型训练、模型部署和矿石识别4个步骤。首先，收集矿石图片并标注，构建矿石数据集。然后，使用TensorFlow 深度学习框架训练YOLOv4-tiny-tf2模型，使其能够识别图像中的矿石。在模型训练过程中，通过调整模型参数和超参数，优化模型的识别精度和速度。训练完成后，将模型部署到香橙派Orange Pi 5B开发板平台上，通过摄像头模块实时捕捉矿石图像，将图像输入到模型中进行识别。最后，将识别结果显示在显示器模块上，实现矿石的高效率、高准确性识别。同时，为了保证模型的准确性和稳定性，还需要对模型进行定期更新和维护，以适应不同矿石类型和环境的变化。
1.3　系统硬件模块设计
（1）摄像头模块。摄像头模块是矿石识别系统的关键组成部分，负责实时捕捉矿石图像并进行检测识别。在矿井环境中对矿石进行识别，需要考虑便携性与清晰度，并且适合香橙派Orange Pi 5B开发板使用。因此，本系统选用的是RK3588S专用的一款MIPI摄像头，摄像头连接在转接板上，整体尺寸为59 mm×29 mm，传感器像素为1 300 万，满足系统要求。
（2）显示器模块。香橙派Orange Pi 5B开发板支持HDMI2.1和DP1.4两种视频输出接口，最大可输出8 K 60 Hz的超高清画面。为了满足矿石识别系统的需求，本系统选用了HDMI接口显示屏，分辨率为1 024 px×600 px。显示屏通过HDMI线连接到香橙派Orange Pi 5B开发板的HDMI接口上，实现图像的实时显示和监控。
（3）外置供电模块。香橙派Orange Pi 5B开发板采用的是Type-C接口5V/4A的充电规格进行供电，过高的电流或电压会导致开发板过载损坏，过低会导致供电不足，无法同时驱动开发板与显示器，并且在矿井环境中，直接使用充电器为设备进行供电并不适宜。为解决这一难题，本系统采用了4节21 700锂电池并联为开发板进行供电，同时使用升压模块将电池原本的3.7 V电压输出提升到5 V电压，既满足了开发板的供电需求，又能保证充足的续航，也方便工作人员进行携带。
2　矿石识别模型的构建
收起
2.1　模型的选用
YOLOv4-tiny-tf2模型的特征结构如图2所示。YOLOv4-tiny-tf2是YOLO系列目标检测算法中的一个轻量级变体，是基于YOLOv4模型改进而来，主要使用TensorFlow 2框架。
YOLO系列算法以其快速且准确的目标检测能力而闻名，而YOLOv4-tiny-tf2则用于在资源受限的环境中实现高效的实时目标检测。相比于完整的YOLOv4模型，YOLOv4-tiny-tf2在结构上进行了简化，减少了网络层数和参数数量，从而降低了模型的大小和计算复杂度。尽管在结构上有所简化，但YOLOv4-tiny-tf2仍然继承了YOLO系列的一些核心特性，如单次前向传递即可完成目标检测，无需进行复杂的后处理步骤。这使得YOLOv4-tiny-tf2能够在资源有限的硬件平台上运行，如嵌入式设备或移动设备，同时保持较高的检测速度和一定的检测精度，可以适应不同矿石类型和环境的变化。
2.2　矿石数据集制作
在构建矿石识别模型之前，首要任务是创建一个高质量的矿石数据集。目前利用深度学习进行矿石识别还处于初步探索阶段，缺乏开源数据集以供使用，因此需要自行制作数据集，数据集的质量对模型的训练效果起着至关重要的作用。
首先确定识别矿石的种类，本系统一共收集了8种矿石的样本，分别是磷灰石、黄铜矿、萤石、石墨、赤铁矿、浮石、石英、白钨矿。从不同光照条件、不同角度和不同背景环境中收集大量的图像，确保图像具有多样性，以涵盖实际应用中可能出现的各种情况[15-17]。
使用开源的标注工具 LabelImg 对采集到的 8 类矿石图像进行标注，标记出图像中矿石的位置和类别，手动绘制边界框并指定矿石类别。同时为了提高模型的泛化能力，对标注后的数据进行数据增强。数据增强包括旋转、平移、缩放、翻转、亮度调整等操作，以模拟不同的拍摄条件和视角变化，使其能够处理各种实际场景中的矿石图像。接着将标注并增强后的数据集划分为训练集、验证集和测试集。训练集用于训练模型，验证集用于调整模型参数和超参数，测试集用于评估模型的性能。训练集占比最大，验证集和测试集占比相对较小。
最后将划分好的数据集存储为模型训练所需的VOC格式。
2.3　模型训练
YOLOv4-tiny-tf2模型的网络结构主要包括4个部分：输入层、特征提取层、特征融合层、输出层。整个网络采用了深度可分离卷积和点卷积来减少计算量和参数数量，从而实现轻量级的目标检测。
输入层是网络的起始部分，负责接收待检测的图片数据。YOLOv4-tiny-tf2模型通常接受固定大小的图片输入，例如416×416或320×320。在输入层，图片会经过一些预处理操作，如缩放、归一化等，以便后续的特征提取。
特征提取层是YOLOv4-tiny-tf2模型的核心部分，主要由一系列卷积层、批量归一化层和激活函数层组成。这些层共同构成了多个特征提取模块，用于从输入图片中提取出有用的特征信息。卷积层是特征提取的基础，通过对输入数据进行卷积操作来提取局部特征。在YOLOv4-tiny-tf2模型中，卷积层采用了深度可分离卷积和点卷积的组合，以减少计算量和参数数量；批量归一化层用于对卷积层的输出进行归一化处理，使得每一层的输出都具有适当的尺度，从而加速网络的训练过程并提高模型的泛化能力；激活函数层用于引入非线性因素，使得网络能够学习并逼近复杂的函数关系。在YOLOv4-tiny-tf2模型中，常用的激活函数包括ReLU和LeakyReLU等。
特征融合层是YOLOv4-tiny-tf2模型的另一个重要部分，负责将不同尺度的特征信息进行融合，以提高目标检测的精度。在YOLOv4-tiny-tf2模型中，特征融合主要通过上采样和拼接操作实现。上采样操作可以将低分辨率的特征图放大到高分辨率，以便与高分辨率的特征图进行拼接。拼接操作则将不同尺度的特征图在通道维度上进行拼接，形成更丰富的特征表示。
输出层是YOLOv4-tiny-tf2模型的最后一部分，负责生成目标检测的结果。在输出层，网络会输出一系列边界框以及对应的类别概率和置信度分数。这些边界框用于定位图片中的目标物体，而类别概率和置信度分数则用于判断目标的类别和检测的可靠性。
2.4　训练过程
准备好矿石数据集后，开始进行模型的训练。使用 TensorFlow深度学习框架，加载YOLOv4-tiny-tf2模型，并设置合适的训练参数和超参数。通过不断迭代训练集，调整模型权重，使得模型能够准确识别图像中的矿石。
在训练过程中，使用验证集来监控模型的性能，并根据验证集上的表现调整模型参数和超参数，如学习率、批大小、迭代次数等。通过不断调整和优化，使得模型在验证集上达到最佳性能。模型训练流程如图3所示。
2.5　训练结果
模型在预测中的表现可以用精准度（各类别矿物在测试集中的准确率表现，P）、召回率（模型对正样本预测正确的百分比，R）、F1分数、R2等数值体现，评估一个模型优劣最直接的表现为能否正确检测出正样本或者负样本。图4至图6分别为各类别矿物测试的精准度、召回率以及不同置信度下的精准度。P−R曲线下精准度代表识别图片中正样本的比例，而召回率则代表测试集中正确识别为正样本的比例，平均值越高则代表模型表现越好。置信度代表模型对识别出来的结果的自信程度，即便置信度非常高也不代表正确识别对象，而查准率则代表模型在实际预测中真正识别正确的比例。由图4可知，模型对磷灰石的识别效果表现最佳，精准度平均值可达到68%，浮石的表现最差，仅为9%，需要收集更多更好的数据样本继续进行训练，以提高预测准确率。由图5可知，磷灰石P−R曲线下的面积，即在各个召回率下的预测精准度平均值能达到68.41%。由图6可知，模型在置信度设置为0.3以及0.3以上时可以达到100%的精准度，对磷灰石的预测表现非常好。
在本次模型训练过程中，影响准确率的最关键因素是训练样本不足。为了提升模型的性能，需持续搜集更多高质量的样本，以便在未来的训练迭代中，将各类别的预测准确率提升至理想水平。同时，在构建更全面的矿石数据集时，需特别关注两方面：其一，应确保每类矿石的图片仅包含该类矿石的相关信息，避免其他类型矿石的干扰；其二，应从多角度收集每类矿石的图像数据，以便能够捕捉更多矿石特征，降低相似特征造成的干扰。
3　基于香橙派的矿石识别试验
收起
3.1　模型部署
为了在实际应用中部署训练好的矿石识别模型，需要将模型集成到香橙派的硬件平台上。这涉及到将模型文件、权重以及必要的依赖库移植到开发板上，并编写推理代码以实现实时矿石图像的处理和识别。
首先将YOLOv4-tiny-tf2模型转换为TensorFlowLite格式，这是一种轻量级的模型格式，适用于移动设备和嵌入式设备。转换过程中，利用TensorFlow Lite Converter工具对模型进行优化，以减少推理时间和内存占用。接下来，将转换后的模型文件、权重以及依赖库复制到香橙派Orange Pi 5B开发板的存储设备中。并编写一个基于TensorFlow Lite的推理程序，该程序能够读取输入的矿石图像，将其预处理为模型所需的格式，并通过模型进行推理。推理结果将输出为识别到的矿石种类及其置信度。
在部署过程中还需要考虑实时性能的要求。受香橙派 Orange Pi 5B开发板平台的处理器性能限制，需要对模型进行进一步的优化，使用量化技术减少模型大小，提高推理速度，并通过多线程或异步处理的方式，提高程序处理多个矿石图像的能力。模型预测流程如图7所示。
3.2　试验测试
为确保模型在香橙派平台的效能得到准确评估，本文引入了240个不同质量级别的矿石图像作为输入样本，其中每类矿石各取30个，以细致观察并记录模型在矿石识别任务中的表现情况。矿石识别结果见表1。
试验结果表明，经过优化后的YOLOv4-tiny-tf2模型在香橙派上能够实时识别矿石，识别准确率达到93.75%。对于高质量的矿石图像，模型能够准确识别出矿石的种类，并给出较高的置信度。对于质量较差或存在干扰的图像，模型的识别性能可能会有所下降，但仍然能够给出有意义的结果。
表2与表3的数据均基于同一样本，通过人工目视和X射线荧光分析等方法识别矿石。相较于本文所采用的模型识别成果，人工目视的识别准确率为90.42%，在识别准确度方面稍显不足，且其效率明显受操作者主观因素的影响，导致识别所需时间存在显著差异。尽管通过化学检测手段获得的测试结果准确率较高，但该方法受限于检测环境和设备条件，每次检测所需时间较长，在实际应用中易造成不便。
4　结论
收起
针对传统矿石检测技术在特定环境下的应用局限性，本文提出了一种部署于香橙派Orange Pi 5B开发板上基于YOLOv4-tiny-tf2的轻量级矿石识别模型，并开展了相关测试，获得了以下结论。
（1）该系统利用摄像头采集矿石图像，以CSPDarknet53-tiny作为网络骨干，并融合了BiFPN、SAM模块，以提升网络的特征提取能力，从而实现了高效的目标检测性能。
（2）本研究采用YOLOv4-tiny-tf2模型对8种矿石进行了识别试验，测试结果表明，该矿石检测模型的识别准确率达到了93.75%, 相较于人工目视检测提高了3.33个百分点。在检测速度方面，传统化学检测方法受限于特定设备，存在显著的速度瓶颈，而本模型仅需将待识别对象置于镜头范围内即可迅速完成识别。尽管在图像质量较差或存在较大干扰的情况下，模型的识别性能会有所下降，但总体而言，其准确率和识别速度相较于传统方法仍展现出显著的提升。
（3）相较于YOLOv4等模型系列，轻量化的YOLOv4-tiny-tf2模型在不牺牲模型精度的情况下简化了其结构，使得该模型更适合在配置较低的设备上部署，具备了较高的便携性，更好地满足了矿石开采行业的实际需求。
本系统成功解决了在井下这种特殊环境下进行矿石识别的难题。实现了对多种矿石种类及其成分的快速且精确辨识，显著提升了矿石检测的效率与精确度。
基金
收起
  • 广东省教育厅青年创新人才项目(2021KQNCX119)
  • 广东科技学院电子信息工程一流专业建设项目(GKZLGC2023156)
文献
收起
参考文献 引证文献
排序方式：
[1]
薄景文，张春堂，樊春玲，等.改进YOLOv3的矿石输送带杂物检测方法[J].计算机工程与应用，2021，57(21):248-255.
BO Jingwen, ZHANG Chuntang, FAN Chunling，et al. Ore conveyor belt sundries detection based on improved YOLOv3[J]. Computer Engineering and Applications, 2021，57(21):248-255.
[2]
马进，王超.基于改进YOLOv4-tiny的印刷电路板缺陷检测研究[J].电子测量技术，2022，45(23):99-106.
MA Jin, WANG Chao. Research on printed circuit board defect detection based on improved YOLOv4-tiny algorithm[J]. Electronic Measurement Technology, 2022, 45(23):99-106.
[3]
杨志军，昌新萌，丁洪伟.基于改进YOLOv4-Tiny的交通车辆实时目标检测[J].无线电工程，2023，53(11):2635-2644.
YANG Zhijun, CHANG Xinmeng, DING Hongwei. Improved YOLOv4-Tiny real-time vehicle detection[J]. Radio Engineering, 2023, 53(11):2635-2644.
[4]
窦智，胡晨光，梁竞一，等.基于改进Yolov4-tiny的轻量型目标检测算法[J].计算机科学，2023，50(增刊1):484-490.
DOU Zhi, HU Chenguang, LIANG Jingyi，et al. Lightweight target detection algorithm based on improved Yolov4-tiny[J]. Computer Science, 2023, 50(Suppl.1):484-490.
[5]
刘姣娣，何捷，许洪振，等.基于改进YOLOv4-Tiny的蔗芽识别方法[J].中国农机化学报，2023，44(11):169-175.
LIU Jiaodi, HE Jie, XU Hongzhen，et al. Identification method of cane sprout based on improved YOLOv4-Tiny[J]. Journal of Chinese Agricultural Mechanization，2023，44 (11):169-175.
[6]
江美玲，章杰.基于树莓派的服装识别系统设计[J].传感器与微系统，2021，40(1):98-100+103.
JIANG Meiling, ZHANG Jie. Design of clothing recognition system based on Raspberry Pi[J]. Transducer and Microsystem Technologies, 2021, 40(1):98-100+103.
[7]
陈品岚，张小花，朱立学，等.基于树莓派及深度学习的柑橘识别系统设计[J].中国农机化学报，2022，43(9):131-136.
CHEN Pinlan, ZHANG Xiaohua, ZHU Lixue，et al. Citrus recognition system based on Raspberry Pi and deep learning[J]. Journal of Chinese Agricultural Mechanization, 2022, 43(9):131-136.
[8]
杨环宇，黄文静，李义华，等.基于树莓派平台的柑橘智能识别与采摘[J].中南林业科技大学学报，2023，43(8):192-201.
YANG Huanyu, HUANG Wenjing, LI Yihua，et al. Design of citrus identification and picking based on the Raspberry Pi platform[J]. Journal of Central South University of Forestry & Technology, 2023, 43(8):192-201.
[9]
张硕，陆宇峰，王丹翔，等.基于YOLOv4-tiny的无人机全自动跟踪方法[J].兵器装备工程学报，2023，44(9):34-41.
ZHANG Shuo, LU Yufeng, WANG Danxiang，et al. Fully automatic tracking method for UAVs based on YOLOv4-tiny[J]. Journal of Ordnance Equipment Engineering, 2023, 44(9):34-41.
[10]
宛鹤，张金艳，屈娟萍，等.基于改进MobileNet V3的矿物智能识别模型[J].金属矿山，2024(1):174-181.
WAN He, ZHANG Jinyan, QU Juanping，et al. Intelligent recognition model of mineral based on improved MobileNet V3[J]. Metal Mine, 2024(1):174-181.
[11]
陈海舰，王唯一，范锦鸽，等.基于树莓派的井下水仓水位智能测控系统[J].工矿自动化，2023，49(8):127-133.
CHEN Haijian, WANG Weiyi, FAN Jin'ge，et al. Intelligent measurement and control system of mine water level based on Raspberry Pi[J]. Jounal and Mine Automation, 2023, 49(8):127-133.
[12]
周国宏，陆宏.基于树莓派的低成本教学机器人设计与实现[J].制造业自动化，2023，45(11):111-116.
ZHOU Guohong, LU Hong. Design and implementation of a low-cost teaching robot based on Raspberry Pi[J]. Manufacturing Automation, 2023, 45(11):111-116.
[13]
张开飞，尚增强，马清俊，等.基于树莓派的喷雾质量检测系统设计[J].农机化研究，2022，44(9):103-107.
ZHANG Kaifei, SHANG Zengqiang, MA Qingjun，et al. Design of spray quality inspection system based on Raspberry Pi[J]. Journal of Agricultural Mechanization Research, 2022, 44(9):103-107.
[14]
于镭，林再腾.基于香橙派的智能语音识别系统的设计[J].电子测量技术，2019，42(19):36-40.
YU Lei, LIN Zaiteng. Design of an intelligent speech recognition system based on Orange Pi[J]. Electronic Measurement Technology, 2019, 42(19):36-40.
[15]
刘凡，陈锐.基于改进ResNet50在高岭土矿石图像分类的应用[J].机电工程技术，2024，53(5):167-171.
LIU Fan, CHEN Rui. Application of improved ResNet50 in image classification of Kaolin Ores[J]. Mechanical & Electrical Engineering Technology, 2024, 53(5):167-171.
[16]
杨丽荣，曹冲，刘顺.改进Mask RCNN算法对矿石分割定位的研究[J].矿业研究与开发，2023，43(4):209-216.
YANG Lirong, CAO Chong, LIU Shun. Study on improved Mask RCNN algorithm for ore segmentation and localization[J]. Mining Reaearch and Development，2023，43(4):209-216.
[17]
邓田，余翼.基于PSO-Faster R-CNN改进算法的矿石识别分类研究[J].矿业研究与开发，2021，41(2):178-182.
DENG Tian, YU Yi. Research on ore identification and separation based on improved PSO-Faster R-CNN algorithm[J]. Mining Reaearch and Development，2021，41（2）：178-182.
2025年第45卷第2期
PDF下载
25
11
引用本文
BibTeX
文章信息
  • 接收时间：2024-06-25
  • 首发时间：2026-10-29
  • 出版时间：2025-02-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期：2024-06-25
基金
广东省教育厅青年创新人才项目(2021KQNCX119)
广东科技学院电子信息工程一流专业建设项目(GKZLGC2023156)
作者信息
    广东科技学院 机电工程学院，广东　东莞市　523083

通讯作者:

林奇兵（2000—），男，广东汕尾人，助理工程师，研究方向为电子系统设计。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kyyjykf/CN/1322594927180104244
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