Article(id=1195402180481037223, tenantId=1146029695717560320, journalId=1189621681917173762, issueId=1195402179973526439, articleNumber=null, orderNo=null, doi=10.19620/j.cnki.1000-3703.20240036, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=null, receivedDateStr=null, revisedDate=1706803200000, revisedDateStr=2024-02-02, acceptedDate=null, acceptedDateStr=null, onlineDate=1762935689325, onlineDateStr=2025-11-12, pubDate=1750694400000, pubDateStr=2025-06-24, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1762935689325, onlineIssueDateStr=2025-11-12, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1762935689325, creator=13701087609, updateTime=1762935689325, updator=13701087609, issue=Issue{id=1195402179973526439, tenantId=1146029695717560320, journalId=1189621681917173762, year='2025', volume='', issue='6', pageStart='1', pageEnd='62', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1762935689204, creator=13701087609, updateTime=1762938972759, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1195415952272699544, tenantId=1146029695717560320, journalId=1189621681917173762, issueId=1195402179973526439, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1195415952272699545, tenantId=1146029695717560320, journalId=1189621681917173762, issueId=1195402179973526439, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1, endPage=7, ext={EN=ArticleExt(id=1195402180724306857, articleId=1195402180481037223, tenantId=1146029695717560320, journalId=1189621681917173762, language=EN, title=Improved YOLOv8n Object Detection Algorithm in Dust and Fog Environment, columnId=null, journalTitle=Automobile Technology, columnName=null, runingTitle=null, highlight=null, articleAbstract=

To address the issues of missed detections, false detections and low accuracy in detecting small and distant objects under adverse conditions such as dust and haze, this paper proposes the EPM-YOLOv8 object detection algorithm. The Efficient Channel Attention (ECA) module is integrated into the C2f module of the YOLOv8n algorithm, enabling the backbone network to focus more effectively on shallow and smaller object features. By adding an additional detection layer and designing a multi-dimension feature fusion architecture, the model’s ability to extract target features and its detection accuracy are significantly improved. Furthermore, a loss function based on the Minimum Point Distance Intersection over Union (MPDIoU) is employed to enhance the precision of bounding box regression. Experimental results demonstrate that the EPM-YOLOv8 model achieves a precision ratio of 83.6% and a detection accuracy of 76.8%, exhibiting superior detection performance under challenging conditions such as haze and dust.

, 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=Ziyu Wang, Jiancheng Zhang, Yuansheng Liu), CN=ArticleExt(id=1195402487474729172, articleId=1195402180481037223, tenantId=1146029695717560320, journalId=1189621681917173762, language=CN, title=改进YOLOv8n的尘雾环境下目标检测算法*, columnId=0, journalTitle=汽车技术, columnName=, runingTitle=null, highlight=null, articleAbstract=

针对扬尘、雾霾等恶劣环境下,车辆目标检测中漏检、误检及远小目标检测精度低等问题,提出了EPM-YOLOv8的目标检测算法。将高效通道注意力(ECA)模块集成到YOLOv8n算法的C2f模块,使骨干网络更加关注浅层较小的目标特征信息;通过增加目标检测层,并设计多尺度特征融合架构,提高模型目标特征提取能力与检测精度;使用基于最小点距离交并比(MPDIoU)损失作为损失函数,提高检测框回归精度。试验结果表明:EPM-YOLOv8模型检测框查准率达到83.6%,检测精度达到76.8%,对尘雾恶劣环境的检测性能具有一定优越性。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
张建成(1971—),教授,主要研究方向为智慧交通、无人驾驶感知定位技术,
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=VZQHvwGI9esCOUvDQWUBiw==, magXml=i/HmqSJNSdZFT00fHAsCxw==, pdfUrl=null, pdf=iAzlLFtmoWUfIx84weg3bw==, pdfFileSize=21706407, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=f2VeGEpbz+cZLtCJDADc9A==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=CQSsSWKguKVFkV7ydOABlQ==, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=王子钰, 张建成, 刘元盛)}, authors=[Author(id=1195414502884815834, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1195414502968701917, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, authorId=1195414502884815834, language=EN, stringName=Ziyu Wang, firstName=Ziyu, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Urban Rail Transit and Logistics, Beijing Union University, Beijing 100101, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1195414503035810782, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, authorId=1195414502884815834, language=CN, stringName=王子钰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 北京联合大学城市轨道交通与物流学院,北京 100101, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1195414502658323410, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, xref=1, ext=[AuthorCompanyExt(id=1195414502670906323, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, companyId=1195414502658323410, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Urban Rail Transit and Logistics, Beijing Union University, Beijing 100101), AuthorCompanyExt(id=1195414502683489236, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, companyId=1195414502658323410, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 北京联合大学城市轨道交通与物流学院,北京 100101)])]), Author(id=1195414503094531040, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=jdtjiancheng@buu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1195414503170028514, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, authorId=1195414503094531040, language=EN, stringName=Jiancheng Zhang, firstName=Jiancheng, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 School of Robotics,Beijing Union University, Beijing 100101, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1195414503228748771, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, authorId=1195414503094531040, language=CN, stringName=张建成, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 北京联合大学机器人学院,北京 100101, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1195414502775763925, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, xref=2, ext=[AuthorCompanyExt(id=1195414502796735446, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, companyId=1195414502775763925, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Robotics,Beijing Union University, Beijing 100101), AuthorCompanyExt(id=1195414502809318359, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, companyId=1195414502775763925, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 北京联合大学机器人学院,北京 100101)])]), Author(id=1195414503295857637, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, 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=1195414503371355111, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, authorId=1195414503295857637, language=EN, stringName=Yuansheng Liu, firstName=Yuansheng, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 School of Robotics,Beijing Union University, Beijing 100101, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1195414503438463976, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, authorId=1195414503295857637, language=CN, stringName=刘元盛, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 北京联合大学机器人学院,北京 100101, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1195414502775763925, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, xref=2, ext=[AuthorCompanyExt(id=1195414502796735446, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, companyId=1195414502775763925, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Robotics,Beijing Union University, Beijing 100101), AuthorCompanyExt(id=1195414502809318359, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, companyId=1195414502775763925, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 北京联合大学机器人学院,北京 100101)])])], keywords=[Keyword(id=1195414503568487401, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=EN, orderNo=1, keyword=Autonomous driving), Keyword(id=1195414503648179178, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=EN, orderNo=2, keyword=Object detection), Keyword(id=1195414503711093739, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=EN, orderNo=3, keyword=Attention mechanism), Keyword(id=1195414503794979820, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=EN, orderNo=4, keyword=Multi-scale feature fusion), Keyword(id=1195414503870477293, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=EN, orderNo=5, keyword=Dusty and foggy environment), Keyword(id=1195414503987917806, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=CN, orderNo=1, keyword=自动驾驶), Keyword(id=1195414504046638063, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=CN, orderNo=2, keyword=目标检测), Keyword(id=1195414504117941232, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=CN, orderNo=3, keyword=注意力机制), Keyword(id=1195414504222798833, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=CN, orderNo=4, keyword=多尺度特征融合), Keyword(id=1195414504327656434, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=CN, orderNo=5, keyword=尘雾环境)], refs=[Reference(id=1195414507473383436, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=LIU W Y, REN G F, YU R S, journalName=Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, California, refType=null, unstructuredReference=LIU W Y, REN G F, YU R S, et al. Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions[C/OL]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, California, USA: AAAI, 2022., articleTitle=Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions, refAbstract=null), Reference(id=1195414507536297997, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=3, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=QIU Y S, LU Y Y, WANG Y T, journalName=Sensors, refType=null, unstructuredReference=QIU Y S, LU Y Y, WANG Y T, et al. IDOD-YOLOV7: Image-Dehazing YOLOV7 for Object Detection in Low-Light Foggy Traffic Environments[J]. Sensors, 2023, 23(3)., articleTitle=IDOD-YOLOV7: Image-Dehazing YOLOV7 for Object Detection in Low-Light Foggy Traffic Environments, refAbstract=null), Reference(id=1195414507603406862, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, doi=null, pmid=null, pmcid=null, year=2023, volume=59, issue=16, pageStart=187, pageEnd=195, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=郭迎, 梁睿琳, 王润民, journalName=计算机工程与应用, refType=null, unstructuredReference=郭迎, 梁睿琳, 王润民. 基于CNN图像增强的雾天跨域自适应目标检测[J]. 计算机工程与应用, 2023, 59(16): 187-195., articleTitle=基于CNN图像增强的雾天跨域自适应目标检测, refAbstract=null), Reference(id=1195414507678904335, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, doi=null, pmid=null, pmcid=null, year=2023, volume=59, issue=16, pageStart=187, pageEnd=195, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=GUO Y, LIANG R L, WANG R M, journalName=Computer Engineering and Applications, refType=null, unstructuredReference=GUO Y, LIANG R L, WANG R M. Cross-Domain Adaptive Object Detection Based on CNN Image Enhancement in Foggy Conditions[J]. Computer Engineering and Applications, 2023, 59(16): 187-195., articleTitle=Cross-Domain Adaptive Object Detection Based on CNN Image Enhancement in Foggy Conditions, refAbstract=null), Reference(id=1195414507733430288, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=WANG Q L, WU B G, ZHU P F, journalName=null, refType=null, unstructuredReference=WANG Q L, WU B G, ZHU P F, et al. ECA-Net:Efficient Channel Attention for Deep Convolutional Neural Networks[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, WA, USA: IEEE, 2020., articleTitle=ECA-Net:Efficient Channel Attention for Deep Convolutional Neural Networks[C], refAbstract=null), Reference(id=1195414507842482193, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=TAN M X, PANG R M, LE Q V, journalName=2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), refType=null, unstructuredReference=TAN M X, PANG R M, LE Q V. EfficientDet:Scalable and Efficient Object Detection[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, WA, USA: IEEE, 2020., articleTitle=EfficientDet:Scalable and Efficient Object Detection[C], refAbstract=null), Reference(id=1195414507926368274, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=MA S L, XU Y, journalName=null, refType=null, unstructuredReference=MA S L, XU Y. MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression[EB/OL]. ( 2023-07-14) [2024-02-02]. https://doi.org/10.48550/arXiv.2307.07662., articleTitle=A Loss for Efficient and Accurate Bounding Box Regression, refAbstract=null), Reference(id=1195414507993477139, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, doi=null, pmid=null, pmcid=null, year=2018, volume=28, issue=1, pageStart=492, pageEnd=505, url=null, language=null, rfNumber=[7], rfOrder=7, authorNames=LI B Y, REN W Q, FU D P, journalName=IEEE Transactions on Image Processing, refType=null, unstructuredReference=LI B Y, REN W Q, FU D P, et al. Benchmarking Single-Image Dehazing and Beyond[J]. IEEE Transactions on Image Processing, 2018, 28(1): 492-505., articleTitle=Benchmarking Single-Image Dehazing and Beyond, refAbstract=null), Reference(id=1195414508056391700, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, doi=null, pmid=null, pmcid=null, year=2018, volume=126, issue=null, pageStart=973, pageEnd=992, url=null, language=null, rfNumber=[8], rfOrder=8, authorNames=SAKARIDIS C, DAI D X, VAN G L, journalName=International Journal of Computer Vision, refType=null, unstructuredReference=SAKARIDIS C, DAI D X, VAN G L. Semantic Foggy Scene Understanding with Synthetic Data[J]. International Journal of Computer Vision, 2018, 126: 973-992., articleTitle=Semantic Foggy Scene Understanding with Synthetic Data, refAbstract=null), Reference(id=1195414508136083477, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=9, authorNames=BUCKEL P, OKSANEN T, DIETMUELLER T, journalName=Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, BC, refType=null, unstructuredReference=BUCKEL P, OKSANEN T, DIETMUELLER T. RB-Dust-A Reference-Based Dataset for Vision-Based Dust Removal[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, BC, Canada: IEEE, 2023., articleTitle=RB-Dust-A Reference-Based Dataset for Vision-Based Dust Removal, refAbstract=null), Reference(id=1195414508198998038, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, doi=null, pmid=null, pmcid=null, year=1804, volume=null, issue=null, pageStart=1, pageEnd=6, url=null, language=null, rfNumber=[10], rfOrder=10, authorNames=REDMON J, FARHADI A, journalName=Computer Vision and Pattern Recognition. Berlin/Heidelberg, refType=null, unstructuredReference=REDMON J, FARHADI A. YOLOv3: An Incremental Improvement[C]// Computer Vision and Pattern Recognition. Berlin/Heidelberg, Germany: Springer, 2018, 1804: 1-6., articleTitle=YOLOv3: An Incremental Improvement, refAbstract=null), Reference(id=1195414508278689815, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=11, authorNames=LI C Y, LI L L, JIANG H L, journalName=null, refType=null, unstructuredReference=LI C Y, LI L L, JIANG H L, et al. YOLOv6:A Single-Stage Object Detection Framework for Industrial Applications[EB/OL]. (2022-09-07) [2024-02-02]. https://doi.org/10.48550/arXiv.2209.02976., articleTitle=YOLOv6:A Single-Stage Object Detection Framework for Industrial Applications, refAbstract=null), Reference(id=1195414508362575896, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, doi=null, pmid=null, pmcid=null, year=2016, volume=14, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=12, authorNames=LIU W, ANGUELOV D, ERHAN D, thEuropean Conference, Amsterdam, journalName=Computer Vision-ECCV 2016, refType=null, unstructuredReference=LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single Shot Multibox Detector[C]// Computer Vision-ECCV 2016: 14 thEuropean Conference. Amsterdam, The Netherlands: Springer International Publishing, 2016., articleTitle=SSD: Single Shot Multibox Detector, refAbstract=null), Reference(id=1195414508454850585, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=13, authorNames=LIN T Y, GOYAL P, GIRSHICK R, journalName=Proceedings of the IEEE International Conference on Computer Vision. Venice, refType=null, unstructuredReference=LIN T Y, GOYAL P, GIRSHICK R, et al. Focal Loss for Dense Object Detection[C]// Proceedings of the IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017., articleTitle=Focal Loss for Dense Object Detection, refAbstract=null), Reference(id=1195414508534542362, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, doi=null, pmid=null, pmcid=null, year=2016, volume=39, issue=6, pageStart=1137, pageEnd=1149, url=null, language=null, rfNumber=[14], rfOrder=14, authorNames=REN S Q, HE K M, GIRSHICK R, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 39(6): 1137-1149., articleTitle=Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, refAbstract=null), Reference(id=1195414508601651227, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=15, authorNames=CARION N, MASSA F, SYNNAEVE G, journalName=European Conference on Computer Vision. Glasgow, refType=null, unstructuredReference=CARION N, MASSA F, SYNNAEVE G, et al. End-to-End Object Detection with Transformers[C]// European Conference on Computer Vision. Glasgow, UK: Springer International Publishing, 2020., articleTitle=End-to-End Object Detection with Transformers, refAbstract=null), Reference(id=1195414508672954396, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=16, authorNames=ZHAO Y A, LV W Y, XU S L, journalName=Seattle, WA, refType=null, unstructuredReference=ZHAO Y A, LV W Y, XU S L, et al.DERTs Beat YOLOs on Real-Time Object Detection[C]// 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, WA, USA: IEEE, 2024., articleTitle=IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), refAbstract=null), Reference(id=1195414508752646173, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=7464, pageEnd=7475, url=null, language=null, rfNumber=[17], rfOrder=17, authorNames=WANG C Y, BOCHKOVSKIY A, LIAO H Y, journalName=Vancouver, BC, refType=null, unstructuredReference=WANG C Y, BOCHKOVSKIY A, LIAO H Y. YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors[C]// 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, BC, Canada: IEEE, 2023: 7464-7475., articleTitle=YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors[C]// 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), refAbstract=null)], funds=[Fund(id=1195414507129450504, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, awardId=62371013, language=CN, fundingSource=*国家自然科学基金项目(62371013), fundOrder=null, country=null), Fund(id=1195414507192365065, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, awardId=61931012, language=CN, fundingSource=国家自然科学基金项目(61931012), fundOrder=null, country=null), Fund(id=1195414507251085322, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, awardId=2021YFC3001300, language=CN, fundingSource=国家重点研发计划项目(2021YFC3001300), fundOrder=null, country=null), Fund(id=1195414507326582795, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, awardId=2022YFB4601100, language=CN, fundingSource=国家重点研发技术项目(2022YFB4601100), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1195414502658323410, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, xref=1, ext=[AuthorCompanyExt(id=1195414502670906323, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, companyId=1195414502658323410, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Urban Rail Transit and Logistics, Beijing Union University, Beijing 100101), AuthorCompanyExt(id=1195414502683489236, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, companyId=1195414502658323410, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 北京联合大学城市轨道交通与物流学院,北京 100101)]), AuthorCompany(id=1195414502775763925, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, xref=2, ext=[AuthorCompanyExt(id=1195414502796735446, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, companyId=1195414502775763925, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Robotics,Beijing Union University, Beijing 100101), AuthorCompanyExt(id=1195414502809318359, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, companyId=1195414502775763925, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 北京联合大学机器人学院,北京 100101)])], figs=[ArticleFig(id=1195414504482845683, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=EN, label=null, caption=null, figureFileSmall=bqczWXu1mScjR7Qud5EcRw==, figureFileBig=2U9HIBRkZy1cluzLhUU9YQ==, tableContent=null), ArticleFig(id=1195414504554148852, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=CN, label=图1, caption=模型整体网络架构, figureFileSmall=bqczWXu1mScjR7Qud5EcRw==, figureFileBig=2U9HIBRkZy1cluzLhUU9YQ==, tableContent=null), ArticleFig(id=1195414504700949493, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=EN, label=null, caption=null, figureFileSmall=Sefy0Av9wldmuI+4aY/1Kg==, figureFileBig=ccxKr6sCtLXHM0/K8/yJsA==, tableContent=null), ArticleFig(id=1195414504759669750, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=CN, label=图2, caption=C2f_ECA模块, figureFileSmall=Sefy0Av9wldmuI+4aY/1Kg==, figureFileBig=ccxKr6sCtLXHM0/K8/yJsA==, tableContent=null), ArticleFig(id=1195414505825022967, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=EN, label=null, caption=null, figureFileSmall=9g0aE1e79HR6zNSE/N6oog==, figureFileBig=Fh4b7DaC/1Z3Jl1lmoJjdA==, tableContent=null), ArticleFig(id=1195414505900520440, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=CN, label=图3, caption=特征融合层结构, figureFileSmall=9g0aE1e79HR6zNSE/N6oog==, figureFileBig=Fh4b7DaC/1Z3Jl1lmoJjdA==, tableContent=null), ArticleFig(id=1195414505980212217, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=EN, label=null, caption=null, figureFileSmall=Kb6ukGgwn02EXxkaV7+KFQ==, figureFileBig=fC5MArhCJl24FmmCnwjIEQ==, tableContent=null), ArticleFig(id=1195414506038932474, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=CN, label=图4, caption=改进后预测特征层, figureFileSmall=Kb6ukGgwn02EXxkaV7+KFQ==, figureFileBig=fC5MArhCJl24FmmCnwjIEQ==, tableContent=null), ArticleFig(id=1195414506114429947, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=EN, label=null, caption=null, figureFileSmall=5EEeAfsEM+o4v1G4/F6BXQ==, figureFileBig=bkqL8eXEBPefHWEZqQR5Zw==, tableContent=null), ArticleFig(id=1195414506219287548, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=CN, label=图5, caption=相同横纵比、不同宽度与高度示意图, figureFileSmall=5EEeAfsEM+o4v1G4/F6BXQ==, figureFileBig=bkqL8eXEBPefHWEZqQR5Zw==, tableContent=null), ArticleFig(id=1195414506278007805, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=EN, label=null, caption=null, figureFileSmall=wgTy2nbzNQpstHQ29FNsIA==, figureFileBig=mJTQj5sNXgoxwv5+qvkt0Q==, tableContent=null), ArticleFig(id=1195414506332533758, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=CN, label=图6, caption=损失函数原理, figureFileSmall=wgTy2nbzNQpstHQ29FNsIA==, figureFileBig=mJTQj5sNXgoxwv5+qvkt0Q==, tableContent=null), ArticleFig(id=1195414506387059711, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=EN, label=null, caption=null, figureFileSmall=7bBo8VJMkrou46PMu8omQw==, figureFileBig=b6xUqprJu8LENDMguUB17g==, tableContent=null), ArticleFig(id=1195414506449974272, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=CN, label=图7, caption=不同损失函数检测效果, figureFileSmall=7bBo8VJMkrou46PMu8omQw==, figureFileBig=b6xUqprJu8LENDMguUB17g==, tableContent=null), ArticleFig(id=1195414506504499200, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=EN, label=null, caption=null, figureFileSmall=YPTXJdOpYBD/JUoTdFRfWA==, figureFileBig=/MaigNAPVC4g0lbVeDQc9g==, tableContent=null), ArticleFig(id=1195414506588385281, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=CN, label=图8, caption=不同模型检测结果, figureFileSmall=YPTXJdOpYBD/JUoTdFRfWA==, figureFileBig=/MaigNAPVC4g0lbVeDQc9g==, tableContent=null), ArticleFig(id=1195414506642911234, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
C2f_ECA 新特征
检测层
MPDIoU P R mAP@50 参数量
/M
FLOPs
/×109
0.791 0.651 0.734 3.01 8.1
0.802 0.659 0.751 3.01 8.1
0.798 0.678 0.754 2.88 12.0
0.808 0.669 0.745 3.01 8.1
0.826 0.647 0.759 2.88 12.0
0.828 0.673 0.750 2.88 12.0
0.836 0.686 0.768 2.88 12.0
), ArticleFig(id=1195414506705825795, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=CN, label=表1, caption=

本文模型的消融试验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
C2f_ECA 新特征
检测层
MPDIoU P R mAP@50 参数量
/M
FLOPs
/×109
0.791 0.651 0.734 3.01 8.1
0.802 0.659 0.751 3.01 8.1
0.798 0.678 0.754 2.88 12.0
0.808 0.669 0.745 3.01 8.1
0.826 0.647 0.759 2.88 12.0
0.828 0.673 0.750 2.88 12.0
0.836 0.686 0.768 2.88 12.0
), ArticleFig(id=1195414506772934660, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
模型 P R mAP@50 参数量/M FLOPs/×109 帧率/帧∙s-1
SSD 0.455 0.378 0.667 24.5 39.7
Faster R-CNN 0.526 0.455 0.706 28.5 65.2
Retinanet 0.663 0.489 0.684 19.8 31.2
DETR 0.779 0.645 0.697 36.8 114.2 70.5
RT-DETR 0.791 0.656 0.735 32.8 108.3 104.0
YOLOv3[10] 0.788 0.649 0.689 12.0 18.9 254.0
IA-YOLO 0.818 0.663 0.728 12.0 18.9 4.0
YOLOv5n 0.788 0.637 0.722 2.5 7.1 171.0
YOLOv6n[11] 0.798 0.646 0.725 4.2 11.8 168.0
YOLOv8n 0.791 0.651 0.734 3.01 8.1 166.0
YOLOv8s 0.844 0.683 0.768 11.1 28.4 143.0
本文 0.836 0.686 0.768 2.88 12.0 152.0
), ArticleFig(id=1195414506840043525, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=CN, label=表2, caption=

不同模型性能对比结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 P R mAP@50 参数量/M FLOPs/×109 帧率/帧∙s-1
SSD 0.455 0.378 0.667 24.5 39.7
Faster R-CNN 0.526 0.455 0.706 28.5 65.2
Retinanet 0.663 0.489 0.684 19.8 31.2
DETR 0.779 0.645 0.697 36.8 114.2 70.5
RT-DETR 0.791 0.656 0.735 32.8 108.3 104.0
YOLOv3[10] 0.788 0.649 0.689 12.0 18.9 254.0
IA-YOLO 0.818 0.663 0.728 12.0 18.9 4.0
YOLOv5n 0.788 0.637 0.722 2.5 7.1 171.0
YOLOv6n[11] 0.798 0.646 0.725 4.2 11.8 168.0
YOLOv8n 0.791 0.651 0.734 3.01 8.1 166.0
YOLOv8s 0.844 0.683 0.768 11.1 28.4 143.0
本文 0.836 0.686 0.768 2.88 12.0 152.0
), ArticleFig(id=1195414506915540998, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
模型 行人 汽车 自行车 摩托车
YOLOv8n 0.794 0.849 0.622 0.67
本文 0.816 0.879 0.652 0.724
), ArticleFig(id=1195414506991038471, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1195402180481037223, language=CN, label=表3, caption=

各类别目标检测mAP@50对比结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 行人 汽车 自行车 摩托车
YOLOv8n 0.794 0.849 0.622 0.67
本文 0.816 0.879 0.652 0.724
)], attaches=null, journal=Journal(id=1149693407745847311, delFlag=0, nameCn=汽车技术, nameEn=Automobile Technology, nameHistory1=null, nameHistory2=null, issn=1000-3703, eissn=null, cn=22-1113/U, 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=rYFtDx/CU9+iX8QTM0ckbw==, journalPrice=null, startedYear=null, abbrevIsoEn=null, journalRemark=null, publicationField=null, createdTime=1752037868679, updatedTime=1761735668047, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=A, firstLetterEn=A, subjectCode=Engineering, subjectName=Engineering, subjectCodeEn=Engineering, subjectNameEn=null, picCn=rYFtDx/CU9+iX8QTM0ckbw==, picEn=oFT2NmUwKPUjZ27C1+d9pw==, jcr=null, cjcr=null, exts=[JournalExt(id=1190368926564450443, language=CN, name=汽车技术, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1761735668078, updatedTime=1761735668078, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://qcjs.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://qcjs.cbpt.cnki.net/index.aspx?t=3, submissionReviewUrl=https://qcjs.cbpt.cnki.net/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1190368926618976396, language=EN, name=Automobile Technology, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1761735668091, updatedTime=1761735668091, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://qcjs.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://qcjs.cbpt.cnki.net/index.aspx?t=3, submissionReviewUrl=https://qcjs.cbpt.cnki.net/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1189621681917173762, websiteList=[Website(id=1189624193747526544, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1189621681917173762, 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/qcjs/CN, language=CN, createTime=1761558109939, createBy=18614031015, updateTime=1761558140534, updateBy=18614031015, name=汽车技术-中, tplId=1146099689490845704, title=汽车技术, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1189625424704451180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193747526544, code=articleTextType, value=kx, createTime=1761558403421, updateTime=1761558403421, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625424675091049, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193747526544, code=banner, value=null, createTime=1761558403414, updateTime=1761558403414, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625424733811311, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193747526544, code=grayFlag, value=0, createTime=1761558403428, updateTime=1761558403428, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625424658313832, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193747526544, code=logo, value=https://castjournals.cast.org.cn/joweb/qcjs/CN/file/pic?fileId=7En9rzX2QCa/1J8NnKt/Fg==, createTime=1761558403410, updateTime=1761558403410, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625424746394225, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193747526544, code=minRunFlag, value=0, createTime=1761558403431, updateTime=1761558403431, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625424691868267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193747526544, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/qcjs/CN/file/pic, createTime=1761558403418, updateTime=1761558403418, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625424742199920, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193747526544, code=silenceFlag, value=0, createTime=1761558403430, updateTime=1761558403430, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625424683479658, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193747526544, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1761558403416, updateTime=1761558403416, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625424712839789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193747526544, code=themeColor, value=null, createTime=1761558403423, updateTime=1761558403423, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625424725422702, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193747526544, code=themeStyle, value=null, createTime=1761558403426, updateTime=1761558403426, creator=18614031015, updator=18614031015)]), Website(id=1189624193869161363, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1189621681917173762, 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/qcjs/EN, language=EN, createTime=1761558109967, createBy=18614031015, updateTime=1761558340679, updateBy=18614031015, name=汽车技术-英文, tplId=1146101810881728533, title=Automobile Technology, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1189625550722311064, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193869161363, code=articleTextType, value=kx, createTime=1761558433466, updateTime=1761558433466, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625550688756629, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193869161363, code=banner, value=null, createTime=1761558433458, updateTime=1761558433458, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625550739088283, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193869161363, code=grayFlag, value=0, createTime=1761558433470, updateTime=1761558433470, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625550676173716, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193869161363, code=logo, value=https://castjournals.cast.org.cn/joweb/qcjs/EN/file/pic?fileId=7En9rzX2QCa/1J8NnKt/Fg==, createTime=1761558433455, updateTime=1761558433455, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625550751671197, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193869161363, code=minRunFlag, value=0, createTime=1761558433473, updateTime=1761558433473, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625550713922455, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193869161363, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/qcjs/EN/file/pic, createTime=1761558433464, updateTime=1761558433464, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625550743282588, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193869161363, code=silenceFlag, value=0, createTime=1761558433471, updateTime=1761558433471, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625550705533846, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193869161363, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1761558433462, updateTime=1761558433462, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625550726505369, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193869161363, code=themeColor, value=null, createTime=1761558433467, updateTime=1761558433467, creator=18614031015, updator=18614031015), WebsiteProps(id=1189625550734893978, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189624193869161363, code=themeStyle, value=null, createTime=1761558433469, updateTime=1761558433469, creator=18614031015, updator=18614031015)])], journalTitle=汽车技术, weixinUrl=null, journalUrl=null, iacademicId=null, status=1, seqNo=null, journalTitleEn=Automobile Technology, journalPhotoCn=rYFtDx/CU9+iX8QTM0ckbw==, journalPhotoEn=oFT2NmUwKPUjZ27C1+d9pw==, journalFirstLetter=A, 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/qcjs/CN/10.19620/j.cnki.1000-3703.20240036, detailUrlEn=https://castjournals.cast.org.cn/joweb/qcjs/EN/10.19620/j.cnki.1000-3703.20240036, pdfUrlCn=https://castjournals.cast.org.cn/joweb/qcjs/CN/PDF/10.19620/j.cnki.1000-3703.20240036, pdfUrlEn=https://castjournals.cast.org.cn/joweb/qcjs/EN/PDF/10.19620/j.cnki.1000-3703.20240036, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
改进YOLOv8n的尘雾环境下目标检测算法*
收藏切换
PDF下载
王子钰 1 , 张建成 2 , 刘元盛 2
汽车技术 | 2025,(6): 1-7
收起
收藏切换
汽车技术 | 2025, (6): 1-7
改进YOLOv8n的尘雾环境下目标检测算法*
全屏
王子钰1, 张建成2 , 刘元盛2
作者信息
  • 1 北京联合大学城市轨道交通与物流学院,北京 100101
  • 2 北京联合大学机器人学院,北京 100101

通讯作者:

张建成(1971—),教授,主要研究方向为智慧交通、无人驾驶感知定位技术,
Improved YOLOv8n Object Detection Algorithm in Dust and Fog Environment
Ziyu Wang1, Jiancheng Zhang2 , Yuansheng Liu2
Affiliations
  • 1 School of Urban Rail Transit and Logistics, Beijing Union University, Beijing 100101
  • 2 School of Robotics,Beijing Union University, Beijing 100101
出版时间: 2025-06-24 doi: 10.19620/j.cnki.1000-3703.20240036
文章导航
收藏切换

针对扬尘、雾霾等恶劣环境下,车辆目标检测中漏检、误检及远小目标检测精度低等问题,提出了EPM-YOLOv8的目标检测算法。将高效通道注意力(ECA)模块集成到YOLOv8n算法的C2f模块,使骨干网络更加关注浅层较小的目标特征信息;通过增加目标检测层,并设计多尺度特征融合架构,提高模型目标特征提取能力与检测精度;使用基于最小点距离交并比(MPDIoU)损失作为损失函数,提高检测框回归精度。试验结果表明:EPM-YOLOv8模型检测框查准率达到83.6%,检测精度达到76.8%,对尘雾恶劣环境的检测性能具有一定优越性。

自动驾驶  /  目标检测  /  注意力机制  /  多尺度特征融合  /  尘雾环境

To address the issues of missed detections, false detections and low accuracy in detecting small and distant objects under adverse conditions such as dust and haze, this paper proposes the EPM-YOLOv8 object detection algorithm. The Efficient Channel Attention (ECA) module is integrated into the C2f module of the YOLOv8n algorithm, enabling the backbone network to focus more effectively on shallow and smaller object features. By adding an additional detection layer and designing a multi-dimension feature fusion architecture, the model’s ability to extract target features and its detection accuracy are significantly improved. Furthermore, a loss function based on the Minimum Point Distance Intersection over Union (MPDIoU) is employed to enhance the precision of bounding box regression. Experimental results demonstrate that the EPM-YOLOv8 model achieves a precision ratio of 83.6% and a detection accuracy of 76.8%, exhibiting superior detection performance under challenging conditions such as haze and dust.

Autonomous driving  /  Object detection  /  Attention mechanism  /  Multi-scale feature fusion  /  Dusty and foggy environment
王子钰, 张建成, 刘元盛. 改进YOLOv8n的尘雾环境下目标检测算法*. 汽车技术, 2025 , (6) : 1 -7 . DOI: 10.19620/j.cnki.1000-3703.20240036
Ziyu Wang, Jiancheng Zhang, Yuansheng Liu. Improved YOLOv8n Object Detection Algorithm in Dust and Fog Environment[J]. Automobile Technology, 2025 , (6) : 1 -7 . DOI: 10.19620/j.cnki.1000-3703.20240036
在尘雾环境中,图像模糊、质量下降导致有效特征提取困难,目标检测任务易出现精度降低、错检和漏检等问题。因此,提高扬尘、雾霾等恶劣环境下的目标检测精度对于自动驾驶场景应用至关重要。
为了解决复杂恶劣环境下的目标检测问题,Liu等[1]提出图像自适应YOLO(Image-Adaptive YOLO,IA-YOLO),通过引入可微图像处理模块,并与YOLOv3联合实现检测。但该方法需要额外的图像增强和复杂的参数调整,增加了计算复杂度与实时性压力。Qiu等[2]基于图像去雾和图像增强提高了图像质量,但预处理阶段存在噪声,并且额外的处理步骤降低了实时检测性能。郭迎等[3]构建了一个结合卷积神经网络的图像增强与目标检测的端到端网络,在跨域检测中表现较好,但其计算复杂度较高,限制了应用场景。
目前,尘雾环境目标检测任务的检测精度有一定提升,但多依赖于去雾和图像增强方法,且该方法对图像背景要求较严苛,很难满足实时性需求。因此,本文提出了EPM-YOLOv8的目标检测算法,通过引入高效通道注意力[4](Efficient Channel Attention,ECA)机制,设计多尺度特征融合算法,增强模型对不同目标特征的表征能力。经过消融试验及对比试验,证明本文方法的有效性。
为了提升尘雾环境下模型的目标检测性能,本文基于YOLOv8n改进的网络结构如图1所示。其中,主干网络中浅层部分的C2f模块引入ECA注意力机制,形成C2f_ECA模块,增强骨干网络对浅层较小目标特征的关注能力;通过增加目标检测层,并设计多尺度特征融合架构,提高网络对不同尺度目标的特征提取能力;采用最小点距离交并比(Minimum Point Distance Intersection over Union,MPDIoU)损失函数优化目标框回归,提高检测精度。
YOLOv8模型主干网络能够获取信息丰富的高阶语义,但很难识别低分辨率尘雾图像中目标的位置信息。因此,通过将ECA注意力引入C2f模块中,增强特征提取能力,C2f_ECA模块结构如图2所示。
ECA为轻量注意力机制,不会增加模型复杂度。首先,对输入特征图 X R W × H × C进行平均池化:
g ( X ) = 1 W H i = 1 ,   j = 1 W ,   H X i j
式中:WH分别为特征图的宽度和高度,C为通道数, X i j为输入特征图在通道的第 ( i ,   j )个像素点的值。
卷积核k根据输入图像的通道数自适应决定,感受野随着通道数变化进行自适应调整。鉴于线性函数表征关系有限,网络通道数C通常为2的整次幂,所以kC间非线性映射关系为:
k = ψ C = l o g 2 C + b γ o d d γ = 1,2         b = 1,2
式中:| |odd为距点最近的奇数, γb分别为简单线性映射的比例系数和常量。
通过Sigmoid函数进行归一化处理,逐个通道特征加权求和,得到加权后特征图 X ˜ R W × H × C,完成跨通道的信息交互。
由于尘雾环境中,图像的特征信息所占像素点较少,所以在YOLOv8主干网络中,第一层和第二层的C2f模块的特征层加入ECA,提升获取特征浅层信息的能力,进一步提高模型对于尘雾干扰的低质量图像检测精度。C2f_ECA在非线性映射下,高维通道特征交互范围更大,低维通道特征的交互作用较小。
在连续下采样过程中,特征图的分辨率逐渐降低,模糊小目标的特征表征能力明显减弱,导致检测效果不佳。原始YOLOv8的路径聚合网络(Path Aggregation Network,PANet)采用自底向上和自顶向下路径聚合进行多尺度特征融合,见图3a,但自底向上特征融合阶段的输入特征缺少骨干中原始输出特征映射。根据双向特征金字塔网络[5](Bidirectional Feature Pyramid Network,BiFPN)的融合特点,见图3b,使用交叉融合可以有效去除对特征融合未产生贡献的节点,相同尺度下可融合更多特征,实现更高级别的特征融合。
由于检测模型难以有效学习尘雾环境的目标特征,仅在YOLOv8模型最后3个C2f模块中添加特征检测层,如图4所示。通过在较浅的特征图中添加一个额外的特征预测层,增强对浅层特征的利用,从而提升模型的特征提取能力和小目标检测性能。
对于受尘雾干扰的特征信息较少的目标检测问题,通过设计添加一个目标检测层来检测目标信息较浅的特征图,并融合到特征融合网络中。然而,仅在网络中保留额外的浅层语义信息会导致深层语义信息一定程度的丢失,所以本研究在增加额外的特征预测层的基础上,采用跨尺度连接的方法,在不增加计算成本的情况下融合更多的特征信息,进而提高网络模型的目标检测性能。
YOLOv8将完整的交并比(Complete Intersection over Union,CIoU)损失作为边界损失:
L C I o U = 1 - n I o U + ρ ( b , b g t ) c 2 + α ν ν = 4 π 2 ( a r c t a n ω g t h g t - a r c t a n ω h ) 2 α = ν ( 1 - n I o U ) + ν
式中:ρ(b,bgt)、nIoU分别为预测框和真实框间欧氏距离和交并比,c2为预测框和真实框间最小外联矩形框的对角线距离,v为正平衡参数,ωh分别为图像的宽度和高度。
CIoU损失虽然引入横纵比,但未考虑相同横纵比情况下,图像的宽度、高度不同的情况,如图5所示。因此,在密集物体检测任务中,极易出现检测框重复问题,从而影响检测精度。
已知检测框的左上角和右下角坐标,即可确定一个唯一的矩形。相较于CIoU损失函数,MPDIoU损失函数将检测框左上角、右下角坐标间的距离与全局图像对角线的比值作为相似性表示,如图6所示。通过最小化预测边界框与真实边界框间的距离,优化检测框回归问题,避免了忽略的相同横纵比而宽度、高度不同的情况[6]。MPDIoU损失函数可表示为:
L M P D I o U = 1 - n I o U + d 1 2 w 2 + h 2 + d 2 2 w 2 + h 2 d 1 2 = ( x 1 B - x 1 A ) 2 + ( y 1 B - y 1 A ) 2 d 2 2 = ( x 2 B - x 2 A ) 2 + ( y 2 B - y 2 A ) 2
式中: ( x 1 A , y 1 A ) ( x 2 A , y 2 A )分别为真值检测框A的左上点和右下点坐标, ( x 1 B , y 1 B ) ( x 2 B , y 2 B )分别为预测检测框B的左上点和右下点坐标,d1d2分别为检测框的左上角坐标间和右下角坐标间的欧氏距离。
在目标检测任务中,MPDIoU损失函数不仅考虑到损失函数中的所有因子,同时可以简化计算过程,保证了边界框回归的准确性,降低了预测的边界框的冗余性,解决了目标检测任务中,同一物体多个检测框和密集物体检测框重叠问题。
本文模型训练使用第13代英特尔酷睿i9-13900K处理器,图像处理器为英伟达GeForce RTX 3090,显存容量为48 GB。其中,模型的测试和推理统一使用单卡试验。使用PyTorch深度学习框架,以Python作为编程语言。
为了进一步验证本文提出模型的有效性及泛化性能,在扩充数据集的基础上,对模型进行消融试验及不同模型的对比试验。
由于传统数据集的环境多为清晰的白天或夜间图像,尘雾环境的数据较少,且传统的大气散射模型无法准确模拟真实的雾霾和扬尘环境。
为此,通过将公开的真实世界任务驱动数据集[7](Real-world Task-driven Testing Set,RTTS)中真实雾霾天气数据4417张、大雾城市景观(Foggy Cityscapes)数据集[8]的合成图像2 965张、公开RB-DUST数据集[9]的扬尘数据50张以及自采于鄂尔多斯东胜矿并经过数据标注的扬尘数据300张整合为试验使用数据集。通过数据增强,扩充后数据可分为行人、汽车、自行车和摩托车4类检测目标,共9 767张。将数据以7∶2∶1划分为训练集、测试集和验证集,其中,RB-DUST数据集和自采数据集均加入验证集。
将精确度(Precision)P、召回率(Recall)R、平均精度(mean Average Precision,mAP)作为模型性能评价指标。其中,精确度衡量模型预测的准确性,表示被预测为正样本的目标中,实际为正样本的比例;召回率评估模型对正样本的检出能力,表示实际正样本中,被正确检测出的比例;平均精度综合评估模型在所有类别和不同阈值下的整体性能,反映模型对所有类别目标的综合检测能力。各指标的计算公式为:
P = X T P X T P + X F P × 100 % R = X T P X T P + X F N × 100 % A A P = 0 1 P R d R A m A P = 1 c i = 1 c A A P , i × 100 %
式中:XTP为被网络模型正确检测出来的目标数,XFP为被网络模型错误检出的目标数,XFN为未被网络模型检测出来的目标数,c为分类数,AAP为单个目标类别的平均精度。
在试验平台中,使用外接英特尔RealSense D435i相机,结合机器人操作系统(Robot Operating System,ROS)Noetic版本测试模型实时性,将帧率作为评价指标。同时,将浮点运算次数(Floating-Point Operations,FLOPs)和参数量(Parameter)作为模型复杂度评价指标。为了更准确地评估模型的性能,经过多次测试取平均值作为最终结果。
为了验证各模块的合理性,以YOLOv8n为基线,对本文模型进行消融试验,结果如表1所示,其中,mAP@50为所有类别中,阈值IoU为0.5时的平均精度,反映了模型在较低IoU中的目标检测能力。
表1可知,由于ECA为轻量级的注意力机制,将C2f_ECA模块替换原始模型中主干网络的第1层、第2层的C2f模块,在降低模型参数量的同时,有效提高了目标检测精度。由于在原有模型中增加了一个目标检测层,且为多尺度特征融合架构,所以计算量有所增加。检测精度、检测框查准率分别提高了2.0和0.7百分点,表明改进后模型在精度和误检率控制方面取得了更优的平衡,检测性能得到了明显改善,进一步证明了本文模型的有效性。
使用MPDIoU作为模型的损失函数,在未增加模型参数量和计算量的基础上,检测性能与精度均有所提升,在验证集中可视化效果如图7所示。使用MPDIoU损失函数避免了多检测框漏检问题,进而提高了网络的检测效果。
通过消融试验可知,本文模型在保证实时性的情况下,检测框查准率从79.1%提升至83.6%,检测精度mAP@50从73.4%提升至76.8%,各模块均能够有效提高目标检测性能,为实际应用提供了一种兼顾实时性与可靠性的检测解决方案。
为了验证本文模型的有效性,对比YOLO系列算法及部分目标检测算法,结果如表2所示。同时,对检测结果进行可视化分析,如图8所示。
由检测结果可知,本文方法在检测性能上相对于其它算法的优越性。与经典单次多检测框(Single Shot MultiBox Detector,SSD)模型[12]、RetinaNet模型[13]和两阶段模型区域卷积神经网络[14](Fast Region-based Convolutional Neural Networks,Faster R-CNN)相比,YOLO系列模型在速度和精度之间达到了较好的平衡。
基于Transformer系列[15]最新模型RT-DETR(Real-Time Detection Transformer)[16]通过取消传统候选框生成和后处理步骤,简化了检测流程,但计算成本较高。虽然与本文模型的检测精度接近,但RT-DETR的参数量和计算复杂度明显高于本文模型,且实时性较差,在实际应用场景中局限性较大。
相较于基线模型YOLOv8n,YOLOv8继承了YOLOv5和YOLOv7的优点[17],提升了检测精度和速度,但对于小目标的检测,极易出现误识别和漏检问题。而本文模型对小目标和模糊目标的检测精度明显提升,帧率能够达到155帧/s,符合实时性检测要求;本文模型在参数量和计算浮点数显著降低的情况下,检测精度与YOLOv8s达到同等水平,同时具备更好的实时性优势。
综合分析表明,本文模型在复杂环境的目标检测任务中,充分考虑了图像模糊、小目标特征需求,实现了检测精度与运算效率的良好平衡;在同系列算法中,能够保持较低的参数量和较高的浮点运算次数,实现了检测性能与运算复杂度间的平衡,展现了实际工程中的应用潜力。
以YOLOv8n为基线,数据集中各类别目标检测结果如表3所示。本文模型对于行人检测精度提升了2.2%,表明改进算法在小目标和模糊目标检测方面更具优势;汽车检测精度提高了3%,进一步优化了对大目标的识别性能;自行车检测精度虽提升3%,但在复杂背景下表现更加稳定;摩托车检测精度提升幅度达到5.4%,改进算法对复杂目标的辨识能力显著增强。因此,本文模型通过改进特征提取和多尺度融合,增强了对复杂场景中多类别目标的检测能力,具有更高的实用价值。
本文针对尘雾环境下的目标检测需求,提出了EPM-YOLOv8算法,增强了模型对复杂环境中目标特征的学习能力,实现了更高效的自动检测性能,有效简化了检测流程,提升了实时性和场景适用性,具有一定潜力。
未来,将针对扬尘、雾霾环境继续扩充数据集,并探索远红外热成像仪、毫米波雷达等多传感器融合检测,以目标检测准确性和精确性,为自动驾驶车辆在尘雾恶劣环境下快速、准确的目标检测任务提供新思路。
  • *国家自然科学基金项目(62371013)
  • 国家自然科学基金项目(61931012)
  • 国家重点研发计划项目(2021YFC3001300)
  • 国家重点研发技术项目(2022YFB4601100)
参考文献 引证文献
排序方式:
[1]
LIU W Y, REN G F, YU R S, et al. Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions[C/OL]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, California, USA: AAAI, 2022.
[2]
QIU Y S, LU Y Y, WANG Y T, et al. IDOD-YOLOV7: Image-Dehazing YOLOV7 for Object Detection in Low-Light Foggy Traffic Environments[J]. Sensors, 2023, 23(3).
[3]
郭迎, 梁睿琳, 王润民. 基于CNN图像增强的雾天跨域自适应目标检测[J]. 计算机工程与应用, 2023, 59(16): 187-195.
GUO Y, LIANG R L, WANG R M. Cross-Domain Adaptive Object Detection Based on CNN Image Enhancement in Foggy Conditions[J]. Computer Engineering and Applications, 2023, 59(16): 187-195.
[4]
WANG Q L, WU B G, ZHU P F, et al. ECA-Net:Efficient Channel Attention for Deep Convolutional Neural Networks[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, WA, USA: IEEE, 2020.
[5]
TAN M X, PANG R M, LE Q V. EfficientDet:Scalable and Efficient Object Detection[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, WA, USA: IEEE, 2020.
[6]
MA S L, XU Y. MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression[EB/OL]. ( 2023-07-14) [2024-02-02]. https://doi.org/10.48550/arXiv.2307.07662.
[7]
LI B Y, REN W Q, FU D P, et al. Benchmarking Single-Image Dehazing and Beyond[J]. IEEE Transactions on Image Processing, 2018, 28(1): 492-505.
[8]
SAKARIDIS C, DAI D X, VAN G L. Semantic Foggy Scene Understanding with Synthetic Data[J]. International Journal of Computer Vision, 2018, 126: 973-992.
[9]
BUCKEL P, OKSANEN T, DIETMUELLER T. RB-Dust-A Reference-Based Dataset for Vision-Based Dust Removal[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, BC, Canada: IEEE, 2023.
[10]
REDMON J, FARHADI A. YOLOv3: An Incremental Improvement[C]// Computer Vision and Pattern Recognition. Berlin/Heidelberg, Germany: Springer, 2018, 1804: 1-6.
[11]
LI C Y, LI L L, JIANG H L, et al. YOLOv6:A Single-Stage Object Detection Framework for Industrial Applications[EB/OL]. (2022-09-07) [2024-02-02]. https://doi.org/10.48550/arXiv.2209.02976.
[12]
LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single Shot Multibox Detector[C]// Computer Vision-ECCV 2016: 14 thEuropean Conference. Amsterdam, The Netherlands: Springer International Publishing, 2016.
[13]
LIN T Y, GOYAL P, GIRSHICK R, et al. Focal Loss for Dense Object Detection[C]// Proceedings of the IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017.
[14]
REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 39(6): 1137-1149.
[15]
CARION N, MASSA F, SYNNAEVE G, et al. End-to-End Object Detection with Transformers[C]// European Conference on Computer Vision. Glasgow, UK: Springer International Publishing, 2020.
[16]
ZHAO Y A, LV W Y, XU S L, et al.DERTs Beat YOLOs on Real-Time Object Detection[C]// 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, WA, USA: IEEE, 2024.
[17]
WANG C Y, BOCHKOVSKIY A, LIAO H Y. YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors[C]// 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, BC, Canada: IEEE, 2023: 7464-7475.
2025年第卷第6期
PDF下载
342
136
引用本文
BibTeX
文章信息
doi: 10.19620/j.cnki.1000-3703.20240036
  • 首发时间:2025-11-12
  • 出版时间:2025-06-24
补充材料
相关文章
文章信息
作者
出版历史
  • 修回日期:2024-02-02
基金
*国家自然科学基金项目(62371013)
国家自然科学基金项目(61931012)
国家重点研发计划项目(2021YFC3001300)
国家重点研发技术项目(2022YFB4601100)
作者信息
    1 北京联合大学城市轨道交通与物流学院,北京 100101
    2 北京联合大学机器人学院,北京 100101

通讯作者:

张建成(1971—),教授,主要研究方向为智慧交通、无人驾驶感知定位技术,
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/qcjs/CN/10.19620/j.cnki.1000-3703.20240036
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

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

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