Article(id=1197502601882284414, tenantId=1146029695717560320, journalId=1189621681917173762, issueId=1197502600254894452, articleNumber=null, orderNo=null, doi=10.19620/j.cnki.1000-3703.20231116, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=null, receivedDateStr=null, revisedDate=1703606400000, revisedDateStr=2023-12-27, acceptedDate=null, acceptedDateStr=null, onlineDate=1763436468810, onlineDateStr=2025-11-18, pubDate=1740326400000, pubDateStr=2025-02-24, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1763436468810, onlineIssueDateStr=2025-11-18, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1763436468810, creator=13701087609, updateTime=1763436468810, updator=13701087609, issue=Issue{id=1197502600254894452, tenantId=1146029695717560320, journalId=1189621681917173762, year='2025', volume='', issue='2', 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=1763436468423, creator=13701087609, updateTime=1763437713537, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1197507822717026735, tenantId=1146029695717560320, journalId=1189621681917173762, issueId=1197502600254894452, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1197507822717026736, tenantId=1146029695717560320, journalId=1189621681917173762, issueId=1197502600254894452, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=9, endPage=16, ext={EN=ArticleExt(id=1197502602108776831, articleId=1197502601882284414, tenantId=1146029695717560320, journalId=1189621681917173762, language=EN, title=An Improved Lightweight Road Target Detection Algorithm Based on YOLOv7-tiny, columnId=null, journalTitle=Automobile Technology, columnName=null, runingTitle=null, highlight=null, articleAbstract=
To address the high computational and storage demands of object detection algorithms that limit real-time performance of edge devices, this study proposes an improved lightweight road object detection algorithm based on YOLOv7-tiny. First, prior anchor boxes optimized for road object detection are generated using the K-means++ clustering algorithm. Secondly, the backbone network is streamlined by modifying the ELAN structure, while a Lightweight Multi-scale Feature (LMS) module is introduced to optimize the neck network. Finally, the Sigmoid Linear Unit (SiLU) activation function is adopted to accelerate model convergence, and the MPDIoU loss function is employed to further improve detection accuracy. Experimental results demonstrate that the improved model achieves an 18.3% reduction in parameters, a 15.0% decrease in computational complexity, and a 1.1% increase in mean average precision across all categories. When deployed on Jetson TX2 with TensorRT acceleration, the detection speed reaches 48 frames per second, essentially meeting real-time requirements for road object detection applications.
, 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=Zejiang He, Shuxia Jiang, Xia Liu), CN=ArticleExt(id=1197502786809147792, articleId=1197502601882284414, tenantId=1146029695717560320, journalId=1189621681917173762, language=CN, title=基于改进YOLOv7-tiny的轻量化道路目标检测算法
*, columnId=0, journalTitle=汽车技术, columnName=, runingTitle=null, highlight=null, articleAbstract=
针对目标检测算法对算力和存储空间的高要求限制其在边缘设备中检测功能实时性的问题,提出了一种基于YOLOv7-tiny改进的轻量化道路目标检测算法。首先,通过K-means++聚类算法生成适合道路目标检测的先验锚框;其次,改进ELAN结构轻量化主干网络,同时提出轻量型多尺度特征(LMS)模块优化颈部网络;最后,使用西格玛线性单元(SiLU)激活函数加速模型收敛,采用MPDIoU损失函数进一步提高检测精度。试验结果表明:改进后的模型参数量减少18.3%,计算量降低15.0%,且所有类别平均检测精度上升1.1%。在Jetson TX2中,使用TensorRT加速后的检测速度达到48帧/s,基本满足道路目标检测的实时性要求。
, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=Bb7QKoYarUn8Ip4SWWL9/w==, magXml=DqmyOkMifOymo89tJqpdDA==, pdfUrl=null, pdf=wjuMUSlaZcIMy6M2JqVAKQ==, pdfFileSize=4175525, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=cfB3HXpFtVd9tnbifW9VuA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=0fq6MGHLbwWMkXPYL/R8Ww==, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=何泽江, 蒋淑霞, 柳霞)}, authors=[Author(id=1197536507461415192, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, 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=1197536507541106971, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, authorId=1197536507461415192, language=EN, stringName=Zejiang He, firstName=Zejiang, middleName=null, lastName=He, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Mechanical and Intelligent Manufacturing, Central South University of Forestry and Technology, Changsha 410004, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1197536507612410140, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, authorId=1197536507461415192, language=CN, stringName=何泽江, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中南林业科技大学机械与智能制造学院,长沙 410004, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1197536507377529108, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, xref=null, ext=[AuthorCompanyExt(id=1197536507385917717, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, companyId=1197536507377529108, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Mechanical and Intelligent Manufacturing, Central South University of Forestry and Technology, Changsha 410004), AuthorCompanyExt(id=1197536507394306326, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, companyId=1197536507377529108, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中南林业科技大学机械与智能制造学院,长沙 410004)])]), Author(id=1197536507662741790, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1197536507738239264, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, authorId=1197536507662741790, language=EN, stringName=Shuxia Jiang, firstName=Shuxia, middleName=null, lastName=Jiang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Mechanical and Intelligent Manufacturing, Central South University of Forestry and Technology, Changsha 410004, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1197536507796959521, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, authorId=1197536507662741790, language=CN, stringName=蒋淑霞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中南林业科技大学机械与智能制造学院,长沙 410004, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1197536507377529108, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, xref=null, ext=[AuthorCompanyExt(id=1197536507385917717, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, companyId=1197536507377529108, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Mechanical and Intelligent Manufacturing, Central South University of Forestry and Technology, Changsha 410004), AuthorCompanyExt(id=1197536507394306326, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, companyId=1197536507377529108, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中南林业科技大学机械与智能制造学院,长沙 410004)])]), Author(id=1197536507855679779, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, 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=1197536507922788645, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, authorId=1197536507855679779, language=EN, stringName=Xia Liu, firstName=Xia, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Mechanical and Intelligent Manufacturing, Central South University of Forestry and Technology, Changsha 410004, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1197536507985703206, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, authorId=1197536507855679779, language=CN, stringName=柳霞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中南林业科技大学机械与智能制造学院,长沙 410004, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1197536507377529108, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, xref=null, ext=[AuthorCompanyExt(id=1197536507385917717, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, companyId=1197536507377529108, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Mechanical and Intelligent Manufacturing, Central South University of Forestry and Technology, Changsha 410004), AuthorCompanyExt(id=1197536507394306326, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, companyId=1197536507377529108, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中南林业科技大学机械与智能制造学院,长沙 410004)])])], keywords=[Keyword(id=1197536508128309543, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=EN, orderNo=1, keyword=Autonomous driving), Keyword(id=1197536508191224104, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=EN, orderNo=2, keyword=YOLOv7-tiny), Keyword(id=1197536508325441833, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=EN, orderNo=3, keyword=Road target detection), Keyword(id=1197536508379967786, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=EN, orderNo=4, keyword=Lightweight), Keyword(id=1197536508434493739, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=EN, orderNo=5, keyword=Jetson TX2), Keyword(id=1197536508522574124, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=CN, orderNo=1, keyword=自动驾驶), Keyword(id=1197536508593877293, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=CN, orderNo=2, keyword=YOLOv7-tiny), Keyword(id=1197536508652597550, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=CN, orderNo=3, keyword=道路目标检测), Keyword(id=1197536508715512111, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=CN, orderNo=4, keyword=轻量化), Keyword(id=1197536508774232368, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=CN, orderNo=5, keyword=Jetson TX2)], refs=[Reference(id=1197536511840268618, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=7, pageStart=19, pageEnd=23, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=胡超超, 刘军, 张凯, journalName=汽车技术, refType=null, unstructuredReference=胡超超, 刘军, 张凯, 等. 基于深度学习的行人和骑行者目标检测及跟踪算法研究[J].
汽车技术,
2019(7): 19-23., articleTitle=基于深度学习的行人和骑行者目标检测及跟踪算法研究, refAbstract=null), Reference(id=1197536511894794571, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=7, pageStart=19, pageEnd=23, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=HU C C, LIU J, ZHANG K, journalName=Automobile Technology, refType=null, unstructuredReference=
HU C C,
LIU J,
ZHANG K, et al. Research on Target Detection and Tracking of Pedestrian and Cyclist Based on Deep Learning[J].
Automobile Technology,
2019(7): 19-23., articleTitle=Research on Target Detection and Tracking of Pedestrian and Cyclist Based on Deep Learning, refAbstract=null), Reference(id=1197536511966097740, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=JIN Z Z, ZHENG Y F, journalName=The 2020 International Conference on Mechatronics Technology and Intelligent Manufacturing (ICMTIM), refType=null, unstructuredReference=
JIN Z Z,
ZHENG Y F. Research on Application of Improved YOLO V3 Algorithm in Road Target Detection[C]//
The 2020 International Conference on Mechatronics Technology and Intelligent Manufacturing (ICMTIM). Xi’an, China: Jouranl of Physics: Conference Series, 2020., articleTitle=Research on Application of Improved YOLO V3 Algorithm in Road Target Detection, refAbstract=null), Reference(id=1197536512029012301, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=113, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=DONG X D, YAN S, DUAN C, journalName=Engineering Applications of Artificial Intelligence, refType=null, unstructuredReference=
DONG X D,
YAN S,
DUAN C. A Lightweight Vehicles Detection Network Model Based on YOLOv5[J].
Engineering Applications of Artificial Intelligence,
2022, 113., articleTitle=A Lightweight Vehicles Detection Network Model Based on YOLOv5, refAbstract=null), Reference(id=1197536512083538254, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=21, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=YAO J L, FAN X S, LI B, journalName=Sensors, refType=null, unstructuredReference=
YAO J L,
FAN X S,
LI B, et al. Adverse Weather Target Detection Algorithm Based on Adaptive Color Levels and Improved YOLOv5[J].
Sensors,
2022,
22(21)., articleTitle=Adverse Weather Target Detection Algorithm Based on Adaptive Color Levels and Improved YOLOv5, refAbstract=null), Reference(id=1197536512150647119, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2023, volume=35, issue=10, pageStart=7853, pageEnd=7865, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=WANG J F, CHEN Y, DONG Z K, journalName=Neural Computing and Applications, refType=null, unstructuredReference=
WANG J F,
CHEN Y,
DONG Z K, et al. Improved YOLOv5 Network for Real-Time Multi-Scale Traffic Sign Detection[J].
Neural Computing and Applications,
2023,
35(10): 7853-7865., articleTitle=Improved YOLOv5 Network for Real-Time Multi-Scale Traffic Sign Detection, refAbstract=null), Reference(id=1197536512230338896, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2022, volume=13, issue=8, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=XUE Z Y, LIN H F, WANG F, journalName=Forests, refType=null, unstructuredReference=
XUE Z Y,
LIN H F,
WANG F. A Small Target Forest Fire Detection Model Based on YOLOv5 Improvement[J].
Forests,
2022,
13(8)., articleTitle=A Small Target Forest Fire Detection Model Based on YOLOv5 Improvement, refAbstract=null), Reference(id=1197536512289059153, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=7, authorNames=LIU H, LI D, PENG J Z, journalName=Proceedings of the Asian Conference on Computer Vision. Kyoto, refType=null, unstructuredReference=
LIU H,
LI D,
PENG J Z, et al. MTNAS: Search Multi-Task Networks for Autonomous Driving[C]//
Proceedings of the Asian Conference on Computer Vision. Kyoto, Japan: Springer,
2020., articleTitle=MTNAS: Search Multi-Task Networks for Autonomous Driving, refAbstract=null), Reference(id=1197536512347779410, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=275, pageEnd=283, url=null, language=null, rfNumber=[8], rfOrder=8, authorNames=WANG P F, FU S, CAO X J, journalName=Guangzhou, refType=null, unstructuredReference=
WANG P F,
FU S,
CAO X J. Improved Lightweight Target Detection Algorithm for Complex Roads with YOLOv5[C]// 2022 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE).
Guangzhou, China: IEEE,
2022: 275-283., articleTitle=Improved Lightweight Target Detection Algorithm for Complex Roads with YOLOv5[C]// 2022 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE), refAbstract=null), Reference(id=1197536512419082579, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, 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=JIANG W Y, WEN J Y, XIE G M, journalName=Third International Conference on Image Processing and Intelligent Control (IPIC). Kuala Lumpur, refType=null, unstructuredReference=
JIANG W Y,
WEN J Y,
XIE G M, et al. The Design of Lightweight Vehicle Detection Model Based on Improved YOLOv5[C]//
Third International Conference on Image Processing and Intelligent Control (IPIC). Kuala Lumpur, Malaysia: SPIE,
2023., articleTitle=The Design of Lightweight Vehicle Detection Model Based on Improved YOLOv5, refAbstract=null), Reference(id=1197536512481997140, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2023, volume=3, issue=1, pageStart=134, pageEnd=137, url=null, language=null, rfNumber=[10], rfOrder=10, authorNames=LIU C Y, HUANG D, WANG T, journalName=Frontiers in Computing and Intelligent Systems, refType=null, unstructuredReference=
LIU C Y,
HUANG D,
WANG T, et al. Road Traffic Small Target Detection Algorithm Based on Lightweight YOLOv5[J].
Frontiers in Computing and Intelligent Systems,
2023,
3(1): 134-137., articleTitle=Road Traffic Small Target Detection Algorithm Based on Lightweight YOLOv5, refAbstract=null), Reference(id=1197536512549106005, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/abs/2307.07662, language=null, rfNumber=[11], rfOrder=11, 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) [2023-12-27]. https://arxiv.org/abs/2307.07662., articleTitle=A Loss for Efficient and Accurate Bounding Box Regression, refAbstract=null), Reference(id=1197536512624603478, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=7464, pageEnd=7475, url=null, language=null, rfNumber=[12], rfOrder=12, authorNames=WANG C Y, BOCHKOVSKIY A, LIAO H Y M, journalName=Vancouver, BC, refType=null, unstructuredReference=
WANG C Y,
BOCHKOVSKIY A,
LIAO H Y M. 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), Reference(id=1197536512708489559, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=2636, pageEnd=2645, url=null, language=null, rfNumber=[13], rfOrder=13, authorNames=YU F, CHEN H F, WANG X, journalName=Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WA, refType=null, unstructuredReference=
YU F,
CHEN H F,
WANG X, et al. BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning[C]//
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WA, USA: IEEE,
2020: 2636-2645., articleTitle=BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning, refAbstract=null), Reference(id=1197536512775598424, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2019, volume=43, issue=2, pageStart=652, pageEnd=662, url=null, language=null, rfNumber=[14], rfOrder=14, authorNames=GAO S H, CHENG M M, ZHAO K, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=
GAO S H,
CHENG M M,
ZHAO K, et al. Res2net: A New Multi-Scale Backbone Architecture[J].
IEEE Transactions on Pattern Analysis and Machine Intelligence,
2019,
43(2): 652-662., articleTitle=Res2net: A New Multi-Scale Backbone Architecture, refAbstract=null), Reference(id=1197536512842707289, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/abs/2308.05480, language=null, rfNumber=[15], rfOrder=15, authorNames=CHEN Y M, YUAN X B, WU R Q, journalName=null, refType=null, unstructuredReference=
CHEN Y M,
YUAN X B,
WU R Q, et al. YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-Time Object Detection[EB/OL]. ( 2023-08-10) [2023-12-27]. https://arxiv.org/abs/2308.05480., articleTitle=Rethinking Multi-Scale Representation Learning for Real-Time Object Detection, refAbstract=null), Reference(id=1197536512901427546, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2020, volume=34, issue=7, pageStart=12993, pageEnd=13000, url=null, language=null, rfNumber=[16], rfOrder=16, authorNames=ZHENG Z H, WANG P, LIU W, journalName=Proceedings of the AAAI Conference on Artificial Intelligence. Vancouver, refType=null, unstructuredReference=
ZHENG Z H,
WANG P,
LIU W, et al. Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression[C]//
Proceedings of the AAAI Conference on Artificial Intelligence. Vancouver, Canada: PKP,
2020,
34(7): 12993-13000., articleTitle=Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression, refAbstract=null), Reference(id=1197536512993702235, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/abs/2006.12085, language=null, rfNumber=[17], rfOrder=17, authorNames=ZHANG Q L, JIANG Z Q, LU Q S, journalName=null, refType=null, unstructuredReference=
ZHANG Q L,
JIANG Z Q,
LU Q S, et al. Split to Be Slim: An Overlooked Redundancy in Vanilla Convolution[EB/OL]. ( 2020-06-22) [2023-12-27]. https://arxiv.org/abs/2006.12085., articleTitle=An Overlooked Redundancy in Vanilla Convolution, refAbstract=null), Reference(id=1197536513060811100, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=680, pageEnd=697, url=null, language=null, rfNumber=[18], rfOrder=18, authorNames=ZHOU D Q, HOU Q B, CHEN Y P, journalName=European Conference on Computer Vision (ECCV). Glasgow, refType=null, unstructuredReference=
ZHOU D Q,
HOU Q B,
CHEN Y P, et al. Rethinking Bottleneck Structure for Efficient Mobile Network Design[C]//
European Conference on Computer Vision (ECCV). Glasgow, UK: Springer International Publishing,
2020: 680-697., articleTitle=Rethinking Bottleneck Structure for Efficient Mobile Network Design, refAbstract=null), Reference(id=1197536513111142749, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=19, authorNames=CHEN J R, KAO S H, HE H, Run, journalName=Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver, BC, refType=null, unstructuredReference=
CHEN J R,
KAO S H,
HE H, et al. Run, Don’t Walk: Chasing Higher FLOPS for Faster Neural Networks[C]//
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver, BC, Canada: IEEE,
2023., articleTitle=Don’t Walk: Chasing Higher FLOPS for Faster Neural Networks, refAbstract=null), Reference(id=1197536513174057310, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/abs/2206.02424, language=null, rfNumber=[20], rfOrder=20, authorNames=LI H L, LI J, WEI H B, journalName=null, refType=null, unstructuredReference=
LI H L,
LI J,
WEI H B, et al. Slim-Neck by Gsconv: A Better Design Paradigm of Detector Architectures for Autonomous Vehicles[EB/OL]. ( 2022-08-17) [2023-12-27]. https://arxiv.org/abs/2206.02424., articleTitle=A Better Design Paradigm of Detector Architectures for Autonomous Vehicles, refAbstract=null), Reference(id=1197536513245360479, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2023, volume=32, issue=null, pageStart=4341, pageEnd=4354, url=null, language=null, rfNumber=[21], rfOrder=21, authorNames=QUAN Y, ZHANG D, ZHANG L Y, journalName=IEEE Transactions on Image Processing, refType=null, unstructuredReference=
QUAN Y,
ZHANG D,
ZHANG L Y, et al. Centralized Feature Pyramid for Object Detection[J].
IEEE Transactions on Image Processing,
2023,
32: 4341-4354., articleTitle=Centralized Feature Pyramid for Object Detection, refAbstract=null), Reference(id=1197536513346023776, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=10781, pageEnd=10790, url=null, language=null, rfNumber=[22], rfOrder=22, authorNames=TAN M X, PANG R M, LE Q V, journalName=Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WA, refType=null, unstructuredReference=
TAN M X,
PANG R M,
LE Q V. EfficientDet: Scalable and Efficient Object Detection[C]//
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WA, USA: IEEE,
2020: 10781-10790., articleTitle=EfficientDet: Scalable and Efficient Object Detection, refAbstract=null), Reference(id=1197536513438298465, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2023, volume=15, issue=19, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=23, authorNames=ZHANG Y L, FANG X P, GUO J, journalName=Remote Sensing, refType=null, unstructuredReference=
ZHANG Y L,
FANG X P,
GUO J, et al. CURI-YOLOv7: A Lightweight YOLOv7tiny Target Detector for Citrus Trees from UAV Remote Sensing Imagery Based on Embedded Device[J].
Remote Sensing,
2023,
15(19)., articleTitle=CURI-YOLOv7: A Lightweight YOLOv7tiny Target Detector for Citrus Trees from UAV Remote Sensing Imagery Based on Embedded Device, refAbstract=null), Reference(id=1197536513530573154, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2023, volume=13, issue=7, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=24, authorNames=JIA L Q, WANG T, CHEN Y, journalName=Agriculture, refType=null, unstructuredReference=
JIA L Q,
WANG T,
CHEN Y, et al. MobileNet-CA-YOLO: An Improved YOLOv7 Based on the MobileNetV3 and Attention Mechanism for Rice Pests and Diseases Detection[J].
Agriculture,
2023,
13(7)., articleTitle=MobileNet-CA-YOLO: An Improved YOLOv7 Based on the MobileNetV3 and Attention Mechanism for Rice Pests and Diseases Detection, refAbstract=null), Reference(id=1197536513597682019, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=17302, pageEnd=17313, url=null, language=null, rfNumber=[25], rfOrder=25, authorNames=CAI H, LI J Y, HU M Y, journalName=null, refType=null, unstructuredReference=
CAI H,
LI J Y,
HU M Y, et al. EfficientViT:Lightweight Multi-Scale Attention for High-Resolution Dense Prediction[C]// 2023 IEEE/CVF International Conference on Computer Vision (ICCV). Paris, France: IEEE,
2023: 17302-17313., articleTitle=EfficientViT:Lightweight Multi-Scale Attention for High-Resolution Dense Prediction[C], refAbstract=null), Reference(id=1197536513664790884, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=14420, pageEnd=14430, url=null, language=null, rfNumber=[26], rfOrder=26, authorNames=LIU X Y, PENG H W, ZHENG N X, journalName=null, refType=null, unstructuredReference=
LIU X Y,
PENG H W,
ZHENG N X, et al. EfficientViT:Memory Efficient Vision Transformer with Cascaded Group Attention[C]// 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, BC, Canada: IEEE,
2023: 14420-14430., articleTitle=EfficientViT:Memory Efficient Vision Transformer with Cascaded Group Attention[C], refAbstract=null)], funds=[Fund(id=1197536511584416071, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, awardId=230826311807159, language=CN, fundingSource=*教育部产学合作协同育人项目(230826311807159), fundOrder=null, country=null), Fund(id=1197536511647330632, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, awardId=2022JJ50012, language=CN, fundingSource=湖南省自然科学基金项目(2022JJ50012), fundOrder=null, country=null), Fund(id=1197536511710245193, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, awardId=CX20220735, language=CN, fundingSource=湖南省研究生科研创新项目(CX20220735), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1197536507377529108, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, xref=null, ext=[AuthorCompanyExt(id=1197536507385917717, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, companyId=1197536507377529108, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Mechanical and Intelligent Manufacturing, Central South University of Forestry and Technology, Changsha 410004), AuthorCompanyExt(id=1197536507394306326, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, companyId=1197536507377529108, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中南林业科技大学机械与智能制造学院,长沙 410004)])], figs=[ArticleFig(id=1197536508925227313, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=EN, label=null, caption=null, figureFileSmall=na0jTX/sdK2DaQPpTREIbw==, figureFileBig=lNkQAlWkTTFQIcrUnKxHjg==, tableContent=null), ArticleFig(id=1197536508979753266, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=CN, label=图1, caption=
改进的YOLOv7-tiny网络结构, figureFileSmall=na0jTX/sdK2DaQPpTREIbw==, figureFileBig=lNkQAlWkTTFQIcrUnKxHjg==, tableContent=null), ArticleFig(id=1197536509063639347, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=EN, label=null, caption=null, figureFileSmall=bp3Fej2V0vWmNtv8HyOPlQ==, figureFileBig=U99jig1tq2eHdo2yCYfovA==, tableContent=null), ArticleFig(id=1197536509122359604, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=CN, label=图2, caption=
B-ELAN结构, figureFileSmall=bp3Fej2V0vWmNtv8HyOPlQ==, figureFileBig=U99jig1tq2eHdo2yCYfovA==, tableContent=null), ArticleFig(id=1197536509264965941, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=EN, label=null, caption=null, figureFileSmall=1/MTPQ/DEuEZRrR600Cz7Q==, figureFileBig=/IEm0IlfdIXwiD1jqqCeeQ==, tableContent=null), ArticleFig(id=1197536509323686198, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=CN, label=图3, caption=
多尺度模块结构, figureFileSmall=1/MTPQ/DEuEZRrR600Cz7Q==, figureFileBig=/IEm0IlfdIXwiD1jqqCeeQ==, tableContent=null), ArticleFig(id=1197536509394989367, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=EN, label=null, caption=null, figureFileSmall=1G+A8FqlkMtNc3+amqYlhw==, figureFileBig=+EwWQYu5uuRJbnBDPVI3LQ==, tableContent=null), ArticleFig(id=1197536509453709624, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=CN, label=图4, caption=
夜间行车检测结果, figureFileSmall=1G+A8FqlkMtNc3+amqYlhw==, figureFileBig=+EwWQYu5uuRJbnBDPVI3LQ==, tableContent=null), ArticleFig(id=1197536509504041273, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=EN, label=null, caption=null, figureFileSmall=mWCCIr/bDBPGu7PMA1hieA==, figureFileBig=deFfhMv8IvWSNsLPwrzzyQ==, tableContent=null), ArticleFig(id=1197536509587927354, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=CN, label=图5, caption=
TensorRT加速推理行车视频, figureFileSmall=mWCCIr/bDBPGu7PMA1hieA==, figureFileBig=deFfhMv8IvWSNsLPwrzzyQ==, tableContent=null), ArticleFig(id=1197536510657474875, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=EN, label=null, caption=null, figureFileSmall=C457r1N4S5a3gbcCo1SKJQ==, figureFileBig=1bdPWg9zD0USYbf2YEi7RQ==, tableContent=null), ArticleFig(id=1197536510728778044, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=CN, label=图6, caption=
不同模型的视频推理速度, figureFileSmall=C457r1N4S5a3gbcCo1SKJQ==, figureFileBig=1bdPWg9zD0USYbf2YEi7RQ==, tableContent=null), ArticleFig(id=1197536510783303997, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 数据集 | 特征层 | 特征图尺寸 | 锚框 | P | R | mAP50 |
| K-means | MS-COCO | P3 | 80×80 | [10,13,16,30,33,23] | 0.652 | 0.410 | 0.439 |
| P4 | 40×40 | [30,61,62,45,59,119] |
| P5 | 20×20 | [116,90,156,198,373,326] |
| K-means | BDD100K | P3 | 80×80 | [7,6,11,11,18,13] | 0.667 | 0.410 | 0.448 |
| P4 | 40×40 | [14,24,29,22,26,55] |
| P5 | 20×20 | [48,34,89,65,170,153] |
| K-means++ | BDD100K | P3 | 80×80 | [7,6,10,10,15,12] | 0.684 | 0.405 | 0.451 |
| P4 | 40×40 | [12,29,25,20,41,32] |
| P5 | 20×20 | [70,49,124,86,193,149] |
), ArticleFig(id=1197536510850412862, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=CN, label=表1, caption=
优化先验锚框结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 数据集 | 特征层 | 特征图尺寸 | 锚框 | P | R | mAP50 |
| K-means | MS-COCO | P3 | 80×80 | [10,13,16,30,33,23] | 0.652 | 0.410 | 0.439 |
| P4 | 40×40 | [30,61,62,45,59,119] |
| P5 | 20×20 | [116,90,156,198,373,326] |
| K-means | BDD100K | P3 | 80×80 | [7,6,11,11,18,13] | 0.667 | 0.410 | 0.448 |
| P4 | 40×40 | [14,24,29,22,26,55] |
| P5 | 20×20 | [48,34,89,65,170,153] |
| K-means++ | BDD100K | P3 | 80×80 | [7,6,10,10,15,12] | 0.684 | 0.405 | 0.451 |
| P4 | 40×40 | [12,29,25,20,41,32] |
| P5 | 20×20 | [70,49,124,86,193,149] |
), ArticleFig(id=1197536510921716031, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
| 模块 | P | R | mAP50 | 参数量/×106个 | FLOPs/×109次 | 帧率/帧∙s-1 | 模型大小/MB |
| B-ELAN | 0.692 | 0.391 | 0.440 | 5.3 | 11.6 | 105.5 | 10.4 |
| SP-ELAN | 0.667 | 0.393 | 0.429 | 5.0 | 10.9 | 73.5 | 9.8 |
| SG-ELAN | 0.669 | 0.386 | 0.429 | 4.7 | 10.1 | 96.2 | 9.2 |
| P-ELAN | 0.638 | 0.398 | 0.421 | 4.6 | 9.7 | 112.4 | 8.9 |
| GS-ELAN | 0.624 | 0.400 | 0.421 | 4.5 | 9.8 | 103.1 | 9.0 |
| DCk-ELAN | 0.660 | 0.383 | 0.418 | 4.5 | 9.6 | 107.5 | 8.8 |
| MSk-Block | 0.623 | 0.359 | 0.388 | 4.6 | 10.3 | 94.3 | 9.2 |
), ArticleFig(id=1197536510988824896, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=CN, label=表2, caption=
不同主干网络轻量化对比结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模块 | P | R | mAP50 | 参数量/×106个 | FLOPs/×109次 | 帧率/帧∙s-1 | 模型大小/MB |
| B-ELAN | 0.692 | 0.391 | 0.440 | 5.3 | 11.6 | 105.5 | 10.4 |
| SP-ELAN | 0.667 | 0.393 | 0.429 | 5.0 | 10.9 | 73.5 | 9.8 |
| SG-ELAN | 0.669 | 0.386 | 0.429 | 4.7 | 10.1 | 96.2 | 9.2 |
| P-ELAN | 0.638 | 0.398 | 0.421 | 4.6 | 9.7 | 112.4 | 8.9 |
| GS-ELAN | 0.624 | 0.400 | 0.421 | 4.5 | 9.8 | 103.1 | 9.0 |
| DCk-ELAN | 0.660 | 0.383 | 0.418 | 4.5 | 9.6 | 107.5 | 8.8 |
| MSk-Block | 0.623 | 0.359 | 0.388 | 4.6 | 10.3 | 94.3 | 9.2 |
), ArticleFig(id=1197536511055933761, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | P | R | mAP50 | 参数量/×106个 | FLOPs/×109次 | 帧率/帧∙s-1 | 模型大小/MB |
| YOLOv5n | 0.645 | 0.348 | 0.375 | 1.8 | 4.3 | 133.3 | 4.0 |
| YOLOv5s | 0.700 | 0.404 | 0.447 | 7.0 | 16 | 113.0 | 14.0 |
| YOLOv7-tiny | 0.656 | 0.393 | 0.426 | 6.0 | 13.3 | 105.0 | 11.7 |
| YOLOv8s | 0.720 | 0.424 | 0.477 | 11.2 | 28.6 | 118.6 | 21.0 |
| YOLOv7-tiny-VoVGSCSP[20] | 0.715 | 0.383 | 0.433 | 5.7 | 12.4 | 97.3 | 11.2 |
| YOLOv7-tiny-EVC[21] | 0.659 | 0.402 | 0.433 | 7.1 | 16.6 | 83.0 | 13.8 |
| YOLOv7-tiny-BiFPN[22] | 0.665 | 0.398 | 0.432 | 6.0 | 13.2 | 90.4 | 11.7 |
| YOLOv7-tiny-MobileOne[23] | 0.563 | 0.341 | 0.350 | 4.5 | 10.9 | 114.0 | 14.7 |
| YOLOv7-tiny-MobileNetV3[24] | 0.560 | 0.336 | 0.339 | 4.2 | 7.0 | 95.8 | 8.3 |
| YOLOv7-tiny-EfficientViT_B1[25] | 0.663 | 0.417 | 0.444 | 8.1 | 14.1 | 78.0 | 15.6 |
| YOLOv7-tiny-EfficientViT_M3[26] | 0.605 | 0.402 | 0.418 | 7.4 | 13.2 | 67.6 | 14.7 |
| 本文 | 0.685 | 0.393 | 0.437 | 4.9 | 11.3 | 120.2 | 9.6 |
), ArticleFig(id=1197536511135625538, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=CN, label=表3, caption=
不同模型性能对比结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | P | R | mAP50 | 参数量/×106个 | FLOPs/×109次 | 帧率/帧∙s-1 | 模型大小/MB |
| YOLOv5n | 0.645 | 0.348 | 0.375 | 1.8 | 4.3 | 133.3 | 4.0 |
| YOLOv5s | 0.700 | 0.404 | 0.447 | 7.0 | 16 | 113.0 | 14.0 |
| YOLOv7-tiny | 0.656 | 0.393 | 0.426 | 6.0 | 13.3 | 105.0 | 11.7 |
| YOLOv8s | 0.720 | 0.424 | 0.477 | 11.2 | 28.6 | 118.6 | 21.0 |
| YOLOv7-tiny-VoVGSCSP[20] | 0.715 | 0.383 | 0.433 | 5.7 | 12.4 | 97.3 | 11.2 |
| YOLOv7-tiny-EVC[21] | 0.659 | 0.402 | 0.433 | 7.1 | 16.6 | 83.0 | 13.8 |
| YOLOv7-tiny-BiFPN[22] | 0.665 | 0.398 | 0.432 | 6.0 | 13.2 | 90.4 | 11.7 |
| YOLOv7-tiny-MobileOne[23] | 0.563 | 0.341 | 0.350 | 4.5 | 10.9 | 114.0 | 14.7 |
| YOLOv7-tiny-MobileNetV3[24] | 0.560 | 0.336 | 0.339 | 4.2 | 7.0 | 95.8 | 8.3 |
| YOLOv7-tiny-EfficientViT_B1[25] | 0.663 | 0.417 | 0.444 | 8.1 | 14.1 | 78.0 | 15.6 |
| YOLOv7-tiny-EfficientViT_M3[26] | 0.605 | 0.402 | 0.418 | 7.4 | 13.2 | 67.6 | 14.7 |
| 本文 | 0.685 | 0.393 | 0.437 | 4.9 | 11.3 | 120.2 | 9.6 |
), ArticleFig(id=1197536511211123011, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
| SiLU | K-means++ | B-ELAN | LMS模块 | MPDIoU | mAP50 | 参数量/×106个 | FLOPs/×109次 | 帧率/帧∙s-1 | 模型大小/MB |
| | | | | 0.426 | 6.0 | 13.3 | 105.0 | 11.7 |
| √ | | | | | 0.439 | 6.0 | 13.3 | 103.0 | 11.7 |
| √ | | | | 0.432 | 6.0 | 13.3 | 103.0 | 11.7 |
| | √ | | | 0.417 | 5.3 | 11.6 | 105.5 | 10.4 |
| | | √ | | 0.420 | 5.6 | 13.0 | 119.4 | 10.9 |
| | | | √ | 0.428 | 6.0 | 13.3 | 105.0 | 11.7 |
| √ | √ | | | | 0.451 | 6.0 | 13.3 | 103.0 | 11.7 |
| √ | √ | √ | | | 0.440 | 5.3 | 11.6 | 105.5 | 10.4 |
| √ | √ | √ | √ | | 0.434 | 4.9 | 11.3 | 120.2 | 9.6 |
| √ | √ | √ | √ | √ | 0.437 | 4.9 | 11.3 | 120.2 | 9.6 |
), ArticleFig(id=1197536511295009092, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=CN, label=表4, caption=
消融试验结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| SiLU | K-means++ | B-ELAN | LMS模块 | MPDIoU | mAP50 | 参数量/×106个 | FLOPs/×109次 | 帧率/帧∙s-1 | 模型大小/MB |
| | | | | 0.426 | 6.0 | 13.3 | 105.0 | 11.7 |
| √ | | | | | 0.439 | 6.0 | 13.3 | 103.0 | 11.7 |
| √ | | | | 0.432 | 6.0 | 13.3 | 103.0 | 11.7 |
| | √ | | | 0.417 | 5.3 | 11.6 | 105.5 | 10.4 |
| | | √ | | 0.420 | 5.6 | 13.0 | 119.4 | 10.9 |
| | | | √ | 0.428 | 6.0 | 13.3 | 105.0 | 11.7 |
| √ | √ | | | | 0.451 | 6.0 | 13.3 | 103.0 | 11.7 |
| √ | √ | √ | | | 0.440 | 5.3 | 11.6 | 105.5 | 10.4 |
| √ | √ | √ | √ | | 0.434 | 4.9 | 11.3 | 120.2 | 9.6 |
| √ | √ | √ | √ | √ | 0.437 | 4.9 | 11.3 | 120.2 | 9.6 |
), ArticleFig(id=1197536511362117957, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
| 类别 | AP50 |
| YOLOv7-tiny | 本文 |
| Car | 0.734 | 0.753 |
| Truck | 0.555 | 0.565 |
| Bus | 0.550 | 0.569 |
| Traffic Sign | 0.534 | 0.584 |
| Person | 0.492 | 0.506 |
), ArticleFig(id=1197536511425032518, tenantId=1146029695717560320, journalId=1189621681917173762, articleId=1197502601882284414, language=CN, label=表5, caption=
不同道路目标的检测精度对比结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类别 | AP50 |
| YOLOv7-tiny | 本文 |
| Car | 0.734 | 0.753 |
| Truck | 0.555 | 0.565 |
| Bus | 0.550 | 0.569 |
| Traffic Sign | 0.534 | 0.584 |
| Person | 0.492 | 0.506 |
)], 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.1000-3703.20231116, detailUrlEn=https://castjournals.cast.org.cn/joweb/qcjs/EN/10.19620/j.cnki.1000-3703.20231116, pdfUrlCn=https://castjournals.cast.org.cn/joweb/qcjs/CN/PDF/10.19620/j.cnki.1000-3703.20231116, pdfUrlEn=https://castjournals.cast.org.cn/joweb/qcjs/EN/PDF/10.19620/j.cnki.1000-3703.20231116, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)