Article(id=1200070659066917574, tenantId=1146029695717560320, journalId=1189918454225211397, issueId=1200070646895051378, articleNumber=null, orderNo=null, doi=10.20104/j.cnki.1674-6546.20240149, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=null, receivedDateStr=null, revisedDate=1716912000000, revisedDateStr=2024-05-29, acceptedDate=null, acceptedDateStr=null, onlineDate=1764048741355, onlineDateStr=2025-11-25, pubDate=1723651200000, pubDateStr=2024-08-15, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1764048741355, onlineIssueDateStr=2025-11-25, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1764048741355, creator=13701087609, updateTime=1764048741355, updator=13701087609, issue=Issue{id=1200070646895051378, tenantId=1146029695717560320, journalId=1189918454225211397, year='2024', volume='', issue='8', pageStart='1', pageEnd='48', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1764048738454, creator=13701087609, updateTime=1764049350066, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1200073212257203051, tenantId=1146029695717560320, journalId=1189918454225211397, issueId=1200070646895051378, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1200073212257203052, tenantId=1146029695717560320, journalId=1189918454225211397, issueId=1200070646895051378, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=29, endPage=35, ext={EN=ArticleExt(id=1200070659691868900, articleId=1200070659066917574, tenantId=1146029695717560320, journalId=1189918454225211397, language=EN, title=Real-Time Lane Recognition Based on Feature Extraction and Edge Point Voting, columnId=1200070647679386243, journalTitle=Automotive Engineer, columnName=Special Issue on Intelligent Vehicle Environmental Perception and Target Detection Technology, runingTitle=null, highlight=null, articleAbstract=

To satisfy the requirement of low power consumption vehicle computing platform for lane detection, this paper proposes a low computing power dependent real-time lane recognition method. Considering the variation of illumination during vehicle driving, a color separation method based on adaptive illumination to extract lane characteristics is proposed. The effective edge point form is defined and the lane lines are determined by edge point voting based on the classical edge detection and Hough transform algorithm. The lane lines are used to filter and supplement the edge points and the lane curve equation is obtained by using the random sample consensus algorithm. The results show that the proposed method achieves a recognition accuracy of over 98% and computation speed of 38 frames per second on a low power processor. Furthermore, the method has proven to be stable and robust in a variety of scenarios.

, 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=Da Yang, Changhe Wei, Chengyu Jia, Siqin Ye), CN=ArticleExt(id=1200070664553066610, articleId=1200070659066917574, tenantId=1146029695717560320, journalId=1189918454225211397, language=CN, title=基于特征提取与边缘点投票的实时车道线识别*, columnId=1200070647847158411, journalTitle=汽车工程师, columnName=智能车辆环境感知与目标检测技术专刊, runingTitle=null, highlight=null, articleAbstract=

针对低算力车载计算平台的车道线检测需求,提出了一种低算力依赖的实时车道线识别方法。考虑车辆行驶过程中的光照变化,提出一种自适应光照的颜色分离方法实现车道特征提取;基于经典的边缘检测与霍夫变换算法,定义有效边缘点形式,通过边缘点投票确定车道直线;利用车道直线对边缘点进行筛选与补充,应用随机抽样一致性算法获取车道曲线方程。试验验证结果表明,所提出方法在低算力处理器上的识别精度高于98%,计算速度为38 帧/s,并在多种应用场景下具备稳定性与鲁棒性。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
叶思琴(1995—),女,讲师,博士,研究方向为汽车智能控制与机械振动分析,
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=FAxDJ1hvSVJoOc07dhAJBw==, magXml=HkHqUVzFEvFtm+gc3+Robg==, pdfUrl=null, pdf=Z2+L6XMFfiqxnlxWEvqY3A==, pdfFileSize=23773645, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=ZJ8DM1G/JL6FNgWgAylqyg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=WcxkCNxGcbKLC4jGZWwn+w==, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=杨达, 魏长河, 贾成禹, 叶思琴)}, authors=[Author(id=1200070665047994539, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, 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=1200070665215766713, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, authorId=1200070665047994539, language=EN, stringName=Da Yang, firstName=Da, middleName=null, lastName=Yang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Sany Heavy Industry Co., Ltd., Changsha 410199, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1200070665362567363, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, authorId=1200070665047994539, language=CN, stringName=杨达, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 三一重工股份有限公司, 长沙 410199, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1200070664813113488, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, xref=1, ext=[AuthorCompanyExt(id=1200070664821502097, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, companyId=1200070664813113488, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Sany Heavy Industry Co., Ltd., Changsha 410199), AuthorCompanyExt(id=1200070664829890706, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, companyId=1200070664813113488, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 三一重工股份有限公司, 长沙 410199)])]), Author(id=1200070665635197134, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, 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=1200070665761026272, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, authorId=1200070665635197134, language=EN, stringName=Changhe Wei, firstName=Changhe, middleName=null, lastName=Wei, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Sany Heavy Industry Co., Ltd., Changsha 410199, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1200070665891049708, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, authorId=1200070665635197134, language=CN, stringName=魏长河, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 三一重工股份有限公司, 长沙 410199, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1200070664813113488, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, xref=1, ext=[AuthorCompanyExt(id=1200070664821502097, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, companyId=1200070664813113488, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Sany Heavy Industry Co., Ltd., Changsha 410199), AuthorCompanyExt(id=1200070664829890706, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, companyId=1200070664813113488, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 三一重工股份有限公司, 长沙 410199)])]), Author(id=1200070666042044662, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, 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=1200070666209816839, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, authorId=1200070666042044662, language=EN, stringName=Chengyu Jia, firstName=Chengyu, middleName=null, lastName=Jia, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Sany Heavy Industry Co., Ltd., Changsha 410199, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1200070666310480144, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, authorId=1200070666042044662, language=CN, stringName=贾成禹, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 三一重工股份有限公司, 长沙 410199, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1200070664813113488, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, xref=1, ext=[AuthorCompanyExt(id=1200070664821502097, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, companyId=1200070664813113488, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Sany Heavy Industry Co., Ltd., Changsha 410199), AuthorCompanyExt(id=1200070664829890706, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, companyId=1200070664813113488, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 三一重工股份有限公司, 长沙 410199)])]), Author(id=1200070666427920666, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yesiqin@csust.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1200070666545361190, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, authorId=1200070666427920666, language=EN, stringName=Siqin Ye, firstName=Siqin, middleName=null, lastName=Ye, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 Changsha University of Science & Technology, Changsha 410114, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1200070666679578926, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, authorId=1200070666427920666, language=CN, stringName=叶思琴, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 长沙理工大学, 长沙 410114, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1200070664922165404, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, xref=2, ext=[AuthorCompanyExt(id=1200070664930554014, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, companyId=1200070664922165404, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Changsha University of Science & Technology, Changsha 410114), AuthorCompanyExt(id=1200070664934748319, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, companyId=1200070664922165404, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 长沙理工大学, 长沙 410114)])])], keywords=[Keyword(id=1200070666843156794, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, orderNo=1, keyword=Intelligent driving), Keyword(id=1200070666964791617, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, orderNo=2, keyword=Lane recognition), Keyword(id=1200070667082232135, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, orderNo=3, keyword=Edge detection), Keyword(id=1200070667216449871, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, orderNo=4, keyword=Random sample consensus), Keyword(id=1200070668441186655, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, orderNo=5, keyword=Adaptive illumination), Keyword(id=1200070668600570217, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, orderNo=1, keyword=智能驾驶), Keyword(id=1200070668768342392, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, orderNo=2, keyword=车道线识别), Keyword(id=1200070668919337350, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, orderNo=3, keyword=边缘检测), Keyword(id=1200070669049360782, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, orderNo=4, keyword=随机抽样一致性), Keyword(id=1200070669145829781, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, orderNo=5, keyword=自适应光照)], refs=[Reference(id=1200070675206599350, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2020, volume=2, issue=2, pageStart=151, pageEnd=153, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=PANDA L, MOHANTY B P, journalName=Ethics and Information Technology, refType=null, unstructuredReference=PANDA L, MOHANTY B P. Recent Developments in Departure Warning System: An Analysis[J]. Ethics and Information Technology, 2020, 2(2): 151-153., articleTitle=Recent Developments in Departure Warning System: An Analysis, refAbstract=null), Reference(id=1200070675303068348, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=286, pageEnd=291, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=NEVEN D, BRABANDERE B D, GEORGOULIS S, journalName=Proceedings of 2018 IEEE Intelligent Vehicles Symposium (IV), refType=null, unstructuredReference=NEVEN D, BRABANDERE B D, GEORGOULIS S, et al. Towards End-to-End Lane Detection:An Instance Segmentation Approach[C]// Proceedings of 2018 IEEE Intelligent Vehicles Symposium (IV). Changshu, China: IEEE, 2018: 286-291., articleTitle=Towards End-to-End Lane Detection:An Instance Segmentation Approach, refAbstract=null), Reference(id=1200070675420508862, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=294, pageEnd=302, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=TABELINI L, BERRIEL R, PAIXAO T M, journalName=Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, refType=null, unstructuredReference=TABELINI L, BERRIEL R, PAIXAO T M, et al. Keep Your Eyes on the Lane: Real-Time Attention-Guided Lane Detection[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, TN, USA: IEEE, 2021: 294-302., articleTitle=Keep Your Eyes on the Lane: Real-Time Attention-Guided Lane Detection, refAbstract=null), Reference(id=1200070675512783554, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2024, volume=46, issue=5, pageStart=2555, pageEnd=2568, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=QIN Z Q, ZHANG P Y, LI X, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=QIN Z Q, ZHANG P Y, LI X. Ultra Fast Deep Lane Detection with Hybrid Anchor Driven Ordinal Classification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(5): 2555-2568., articleTitle=Ultra Fast Deep Lane Detection with Hybrid Anchor Driven Ordinal Classification, refAbstract=null), Reference(id=1200070675617641158, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2023, volume=59, issue=13, pageStart=178, pageEnd=185, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=杜黎, 吕毅斌, 武德安, journalName=计算机工程与应用, refType=null, unstructuredReference=杜黎, 吕毅斌, 武德安, 等. 复杂场景中的快速车道线检测方法[J]. 计算机工程与应用, 2023, 59(13): 178-185., articleTitle=复杂场景中的快速车道线检测方法, refAbstract=null), Reference(id=1200070675743470282, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2023, volume=59, issue=13, pageStart=178, pageEnd=185, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=DU L, LÜ Y B, WU D A, journalName=Computer Engineering and Applications, refType=null, unstructuredReference=DU L, Y B, WU D A, et al. Fast Lane Detection Method in Complex Scenarios[J]. Computer Engineering and Applications, 2023, 59(13): 178-185., articleTitle=Fast Lane Detection Method in Complex Scenarios, refAbstract=null), Reference(id=1200070675818967758, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=8, pageStart=32, pageEnd=37, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=李守彪, 武志斐, journalName=汽车技术, refType=null, unstructuredReference=李守彪, 武志斐. 基于多尺寸分解卷积的车道线检测[J]. 汽车技术, 2022(8): 32-37., articleTitle=基于多尺寸分解卷积的车道线检测, refAbstract=null), Reference(id=1200070675919631057, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=8, pageStart=32, pageEnd=37, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=LI S B, WU Z F, journalName=Automobile Technology, refType=null, unstructuredReference=LI S B, WU Z F. Lane Detection Based on Multi-Size Factorized Convolution[J]. Automobile Technology, 2022(8): 32-37., articleTitle=Lane Detection Based on Multi-Size Factorized Convolution, refAbstract=null), Reference(id=1200070676007711445, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=4, pageStart=1, pageEnd=6, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=胡胜, 黄妙华, 陈毅, journalName=汽车技术, refType=null, unstructuredReference=胡胜, 黄妙华, 陈毅. 基于二次阈值分割和车道宽度匹配的车道线检测算法[J]. 汽车技术, 2019(4): 1-6., articleTitle=基于二次阈值分割和车道宽度匹配的车道线检测算法, refAbstract=null), Reference(id=1200070676171289301, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=4, pageStart=1, pageEnd=6, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=HU S, HUANG M H, CHEN Y, journalName=Automobile Technology, refType=null, unstructuredReference=HU S, HUANG M H, CHEN Y. Lane Marking Detection Algorithm Based on Double Threshold Segmentation and Lane Width[J]. Automobile Technology, 2019(4): 1-6., articleTitle=Lane Marking Detection Algorithm Based on Double Threshold Segmentation and Lane Width, refAbstract=null), Reference(id=1200070676259369689, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=32, pageStart=14298, pageEnd=14305, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=黄艳国, 钟勇, 夏金龙, journalName=科学技术与工程, refType=null, unstructuredReference=黄艳国, 钟勇, 夏金龙. 基于自适应透视变换与特征融合的车道线检测方法[J]. 科学技术与工程, 2022, 22(32): 14298-14305., articleTitle=基于自适应透视变换与特征融合的车道线检测方法, refAbstract=null), Reference(id=1200070677416997596, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=32, pageStart=14298, pageEnd=14305, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=HUANG Y G, ZHONG Y, XIA J L, journalName=Science Technology and Engineering, refType=null, unstructuredReference=HUANG Y G, ZHONG Y, XIA J L. Lane Detection Method Based on Adaptive Perspective Transformation and Feature Fusion[J]. Science Technology and Engineering, 2022, 22(32): 14298-14305., articleTitle=Lane Detection Method Based on Adaptive Perspective Transformation and Feature Fusion, refAbstract=null), Reference(id=1200070677500883679, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=53, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=NOMAN M A A, RAHAMAN M F, LI Z, journalName=A Computer Vision-Based Lane Detection Approach for an Autonomous Vehicle Using the Image Hough Transformation and the Edge Features, refType=null, unstructuredReference=NOMAN M A A, RAHAMAN M F, LI Z, et al. A Computer Vision-Based Lane Detection Approach for an Autonomous Vehicle Using the Image Hough Transformation and the Edge Features[M]// GOAR V, KURI M, KUMAR R, et al. Advances in Information Communication Technology and Computing. Singapore: Springer, 2023: 53-66., articleTitle=null, refAbstract=null), Reference(id=1200070677626712802, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2023, volume=11, issue=null, pageStart=67938, pageEnd=67955, url=null, language=null, rfNumber=[10], rfOrder=13, authorNames=SULTANA S, AHMED B, PAUL M, journalName=IEEE Access, refType=null, unstructuredReference=SULTANA S, AHMED B, PAUL M, et al. Vision-Based Robust Lane Detection and Tracking in Challenging Conditions[J]. IEEE Access, 2023, 11: 67938-67955., articleTitle=Vision-Based Robust Lane Detection and Tracking in Challenging Conditions, refAbstract=null), Reference(id=1200070677815456487, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=4, pageStart=386, pageEnd=391, url=null, language=null, rfNumber=[11], rfOrder=14, authorNames=蔡创新, 邹宇, 潘志庚, journalName=江苏大学学报(自然科学版), refType=null, unstructuredReference=蔡创新, 邹宇, 潘志庚, 等. 基于多特征融合和窗口搜索的新型车道线检测算法[J]. 江苏大学学报(自然科学版), 2023, 44(4): 386-391., articleTitle=基于多特征融合和窗口搜索的新型车道线检测算法, refAbstract=null), Reference(id=1200070677924508394, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=4, pageStart=386, pageEnd=391, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=CAI C X, ZOU Y, PAN Z G, journalName=Journal of Jiangsu University (Natural Science Edition), refType=null, unstructuredReference=CAI C X, ZOU Y, PAN Z G, et al. Novel Lane Detection Algorithm Based on Multi-Feature Fusion and Windows Searching[J]. Journal of Jiangsu University (Natural Science Edition), 2023, 44(4): 386-391., articleTitle=Novel Lane Detection Algorithm Based on Multi-Feature Fusion and Windows Searching, refAbstract=null), Reference(id=1200070678067114732, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=6, pageStart=9, pageEnd=16, url=null, language=null, rfNumber=[12], rfOrder=16, authorNames=黄艳国, 钟勇, 饶泽浩, journalName=汽车技术, refType=null, unstructuredReference=黄艳国, 钟勇, 饶泽浩. 基于优化最大类间方差法阈值分割与滑动窗口法的车道偏离预警[J]. 汽车技术, 2023(6): 9-16., articleTitle=基于优化最大类间方差法阈值分割与滑动窗口法的车道偏离预警, refAbstract=null), Reference(id=1200070678180360944, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=6, pageStart=9, pageEnd=16, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=HUANG Y G, ZHONG Y, RAO Z H, journalName=Automobile Technology, refType=null, unstructuredReference=HUANG Y G, ZHONG Y, RAO Z H. Lane Departure Warning Based on Optimized Threshold Segmentation of Maximum Inter-Class Variance and Sliding Window Method[J]. Automobile Technology, 2023(6): 9-16., articleTitle=Lane Departure Warning Based on Optimized Threshold Segmentation of Maximum Inter-Class Variance and Sliding Window Method, refAbstract=null), Reference(id=1200070678297801458, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=9, pageStart=15, pageEnd=20, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=王梓楠, 何东, 赵茂杰, journalName=汽车工程师, refType=null, unstructuredReference=王梓楠, 何东, 赵茂杰. 基于滑动窗口搜索的车道线检测与车道偏离预警算法[J]. 汽车工程师, 2023(9): 15-20+28., articleTitle=基于滑动窗口搜索的车道线检测与车道偏离预警算法, refAbstract=null), Reference(id=1200070678394270453, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=9, pageStart=15, pageEnd=20, url=null, language=null, rfNumber=[13], rfOrder=19, authorNames=WANG Z N, HE D, ZHAO M J, journalName=Automotive Engineer, refType=null, unstructuredReference=WANG Z N, HE D, ZHAO M J. Lane Line Detection and Lane Departure Warning Algorithm Based on Sliding Window Searching[J]. Automotive Engineer, 2023(9): 15-20+28., articleTitle=Lane Line Detection and Lane Departure Warning Algorithm Based on Sliding Window Searching, refAbstract=null), Reference(id=1200070678524293882, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2017, volume=39, issue=3, pageStart=357, pageEnd=363, url=null, language=null, rfNumber=[14], rfOrder=20, authorNames=陈无畏, 蒋玉亭, 谈东奎, journalName=汽车工程, refType=null, unstructuredReference=陈无畏, 蒋玉亭, 谈东奎. 一种基于边缘点投影的车道线快速识别算法[J]. 汽车工程, 2017, 39(3): 357-363., articleTitle=一种基于边缘点投影的车道线快速识别算法, refAbstract=null), Reference(id=1200070678645928703, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2017, volume=39, issue=3, pageStart=357, pageEnd=363, url=null, language=null, rfNumber=[14], rfOrder=21, authorNames=CHEN W W, JIANG Y T, TAN D K, journalName=Automotive Engineering, refType=null, unstructuredReference=CHEN W W, JIANG Y T, TAN D K. A Fast Lane Marking Recognition Algorithm Based on Edge Projection[J]. Automotive Engineering, 2017, 39(3): 357-363., articleTitle=A Fast Lane Marking Recognition Algorithm Based on Edge Projection, refAbstract=null), Reference(id=1200070678738203391, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=http://kns.cnki.net/kcms/detail/50.1085.TN.20230901.1047.008.html, language=null, rfNumber=[15], rfOrder=22, authorNames=刘悦, 杨桦, 王青正, journalName=激光杂志, refType=null, unstructuredReference=刘悦, 杨桦, 王青正. 面向复杂光照环境的车道线检测方法[J/OL]. 激光杂志 (2023-09-01) [2024-05-29]. http://kns.cnki.net/kcms/detail/50.1085.TN.20230901.1047.008.html, articleTitle=面向复杂光照环境的车道线检测方法, refAbstract=null), Reference(id=1200070678822089474, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=http://kns.cnki.net/kcms/detail/50.1085.TN.20230901.1047.008.html, language=null, rfNumber=[15], rfOrder=23, authorNames=LIU Y, YANG H, WANG Q Z, journalName=Laser Journal, refType=null, unstructuredReference=LIU Y, YANG H, WANG Q Z. Lane Detection Method for Complex Lighting Environment[J/OL]. Laser Journal (2023-09-01) [2024-05-29]. http://kns.cnki.net/kcms/detail/50.1085.TN.20230901.1047.008.html, articleTitle=Lane Detection Method for Complex Lighting Environment, refAbstract=null)], funds=[Fund(id=1200070675055604401, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, awardId=2023-2025, language=CN, fundingSource=*中国科协第九届青年人才托举工程项目(2023-2025), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1200070664813113488, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, xref=1, ext=[AuthorCompanyExt(id=1200070664821502097, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, companyId=1200070664813113488, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Sany Heavy Industry Co., Ltd., Changsha 410199), AuthorCompanyExt(id=1200070664829890706, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, companyId=1200070664813113488, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 三一重工股份有限公司, 长沙 410199)]), AuthorCompany(id=1200070664922165404, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, xref=2, ext=[AuthorCompanyExt(id=1200070664930554014, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, companyId=1200070664922165404, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Changsha University of Science & Technology, Changsha 410114), AuthorCompanyExt(id=1200070664934748319, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, companyId=1200070664922165404, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 长沙理工大学, 长沙 410114)])], figs=[ArticleFig(id=1200070669301019045, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, label=null, caption=null, figureFileSmall=eAuuHayIPOQ2NA4keydc0Q==, figureFileBig=ZJ8DM1G/JL6FNgWgAylqyg==, tableContent=null), ArticleFig(id=1200070669426848172, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, label=图1, caption=车道线识别算法流程, figureFileSmall=eAuuHayIPOQ2NA4keydc0Q==, figureFileBig=ZJ8DM1G/JL6FNgWgAylqyg==, tableContent=null), ArticleFig(id=1200070669682700738, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, label=null, caption=null, figureFileSmall=zIdC9LGKSW/Rf23MVlEQZQ==, figureFileBig=PcPueLMIpqfvOXaFfIrmhQ==, tableContent=null), ArticleFig(id=1200070669804335565, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, label=图2, caption=图像缩放与图像裁剪, figureFileSmall=zIdC9LGKSW/Rf23MVlEQZQ==, figureFileBig=PcPueLMIpqfvOXaFfIrmhQ==, tableContent=null), ArticleFig(id=1200070669917581781, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, label=null, caption=null, figureFileSmall=zjurhN46GvGLRcNw+bU/fQ==, figureFileBig=s5f4nparwbcW1I8K+f8rkQ==, tableContent=null), ArticleFig(id=1200070670035022302, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, label=图3, caption=亮度低阈值动态设置算法流程, figureFileSmall=zjurhN46GvGLRcNw+bU/fQ==, figureFileBig=s5f4nparwbcW1I8K+f8rkQ==, tableContent=null), ArticleFig(id=1200070670160851430, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, label=null, caption=null, figureFileSmall=AC8XM08HbmhKZc5OBQMyxg==, figureFileBig=8KC4KpmUeTAqaYi9RDEmtg==, tableContent=null), ArticleFig(id=1200070670441869811, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, label=图4, caption=车道特征提取, figureFileSmall=AC8XM08HbmhKZc5OBQMyxg==, figureFileBig=8KC4KpmUeTAqaYi9RDEmtg==, tableContent=null), ArticleFig(id=1200070670567698938, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, label=null, caption=null, figureFileSmall=xHbHM3QUwYzDxhDszRBxsw==, figureFileBig=6SyfHH9s9wEbue5tqL0gMQ==, tableContent=null), ArticleFig(id=1200070670672556546, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, label=图5, caption=不同场景下提取的车道特征, figureFileSmall=xHbHM3QUwYzDxhDszRBxsw==, figureFileBig=6SyfHH9s9wEbue5tqL0gMQ==, tableContent=null), ArticleFig(id=1200070670827745804, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, label=null, caption=null, figureFileSmall=DcTWoqdjG5S4z0x3lmsxTg==, figureFileBig=VDO4mICMZmy6De8c3NY+Jg==, tableContent=null), ArticleFig(id=1200070670953574933, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, label=图6, caption=候选直线提取, figureFileSmall=DcTWoqdjG5S4z0x3lmsxTg==, figureFileBig=VDO4mICMZmy6De8c3NY+Jg==, tableContent=null), ArticleFig(id=1200070671054238235, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, label=null, caption=null, figureFileSmall=rvEmM0o/a9KtWfAU8yaHWA==, figureFileBig=tAOJuC0egNrJibXVYrooFw==, tableContent=null), ArticleFig(id=1200070671171678755, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, label=图7, caption=有效边缘点选择示意, figureFileSmall=rvEmM0o/a9KtWfAU8yaHWA==, figureFileBig=tAOJuC0egNrJibXVYrooFw==, tableContent=null), ArticleFig(id=1200070671268147755, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, label=null, caption=null, figureFileSmall=FMUYPv83NsvR0S+q74uTFA==, figureFileBig=MexFPduUTdAclyZw2sHmoA==, tableContent=null), ArticleFig(id=1200070671381393973, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, label=图8, caption=3种场景下的有效边缘点分布及最终提取的车道线, figureFileSmall=FMUYPv83NsvR0S+q74uTFA==, figureFileBig=MexFPduUTdAclyZw2sHmoA==, tableContent=null), ArticleFig(id=1200070671490445880, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, label=null, caption=null, figureFileSmall=9gXl22BwsU9XGb5Z6jwDpQ==, figureFileBig=HCrawbL0FzMjDLBHXWYqAw==, tableContent=null), ArticleFig(id=1200070671624663618, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, label=图9, caption=边缘点补充, figureFileSmall=9gXl22BwsU9XGb5Z6jwDpQ==, figureFileBig=HCrawbL0FzMjDLBHXWYqAw==, tableContent=null), ArticleFig(id=1200070671746298446, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, label=null, caption=null, figureFileSmall=/zXx5gzxFd7v7Mpfphf0jw==, figureFileBig=A7om+O2NScalPZ1z8LKM4w==, tableContent=null), ArticleFig(id=1200070672878760529, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, label=图10, caption=车道直线与车道曲线, figureFileSmall=/zXx5gzxFd7v7Mpfphf0jw==, figureFileBig=A7om+O2NScalPZ1z8LKM4w==, tableContent=null), ArticleFig(id=1200070673059115609, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, label=null, caption=null, figureFileSmall=DIPpDOmqCdJNE/kIb8y4yg==, figureFileBig=iZ67hlS+NZmAYPRzH+I+eQ==, tableContent=null), ArticleFig(id=1200070673226887775, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, label=图11, caption=车载计算平台, figureFileSmall=DIPpDOmqCdJNE/kIb8y4yg==, figureFileBig=iZ67hlS+NZmAYPRzH+I+eQ==, tableContent=null), ArticleFig(id=1200070673365299814, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, label=null, caption=null, figureFileSmall=2U/Vpr3K0JH6+Hp/kYybkw==, figureFileBig=uv6L1rg2x7cTmxTxIkBQag==, tableContent=null), ArticleFig(id=1200070673499517548, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, label=图12, caption=高速公路测试集的3种路段, figureFileSmall=2U/Vpr3K0JH6+Hp/kYybkw==, figureFileBig=uv6L1rg2x7cTmxTxIkBQag==, tableContent=null), ArticleFig(id=1200070673629540977, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, label=null, caption=null, figureFileSmall=ge5zF7ozhef2LvcLh4gOcA==, figureFileBig=VN8RSHyYku8QWSuuvgsW/Q==, tableContent=null), ArticleFig(id=1200070673700844150, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, label=图13, caption=iROADS数据集的3种应用场景, figureFileSmall=ge5zF7ozhef2LvcLh4gOcA==, figureFileBig=VN8RSHyYku8QWSuuvgsW/Q==, tableContent=null), ArticleFig(id=1200070673776341626, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
颜色 (Hmin,Smin,Vmin) (Hmax,Smax,Vmax)
(0,0,100) (180,100,255)
(20,100,100) (34,255,255)
), ArticleFig(id=1200070673881199234, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, label=表1, caption=

黄色与白色的HSV阈值

, figureFileSmall=null, figureFileBig=null, tableContent=
颜色 (Hmin,Smin,Vmin) (Hmax,Smax,Vmax)
(0,0,100) (180,100,255)
(20,100,100) (34,255,255)
), ArticleFig(id=1200070674019611272, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
参数 文献[9] 文献[10] 文献[13] 本文方法
精度/% 89.37 97.06 98.41 99.84
效率/帧·s-1 30 23 20 38
), ArticleFig(id=1200070674141246095, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, label=表2, caption=

精度与速度的试验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 文献[9] 文献[10] 文献[13] 本文方法
精度/% 89.37 97.06 98.41 99.84
效率/帧·s-1 30 23 20 38
), ArticleFig(id=1200070674267075222, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
阶段 运行时间
图像预处理 5.07
车道特征提取 3.37
车道直线提取 6.18
车道曲线拟合 11.68
总计 26.30
), ArticleFig(id=1200070674405487256, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, label=表3, caption=

本文方法各阶段的平均运行时间 ms

, figureFileSmall=null, figureFileBig=null, tableContent=
阶段 运行时间
图像预处理 5.07
车道特征提取 3.37
车道直线提取 6.18
车道曲线拟合 11.68
总计 26.30
), ArticleFig(id=1200070674543899295, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
应用场景 文献[9] 文献[10] 文献[13] 本文方法
晴天 96.40 97.34 98.23 98.78
雨天 99.38 96.85 99.05 99.81
夜间 94.19 98.00 98.76 99.90
), ArticleFig(id=1200070674657145508, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, label=表4, caption=

不同应用场景下的精度对比 %

, figureFileSmall=null, figureFileBig=null, tableContent=
应用场景 文献[9] 文献[10] 文献[13] 本文方法
晴天 96.40 97.34 98.23 98.78
雨天 99.38 96.85 99.05 99.81
夜间 94.19 98.00 98.76 99.90
), ArticleFig(id=1200070674787168935, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
应用场景 文献[9] 文献[10] 文献[13] 本文方法
晴天 33 28 25 42
雨天 32 26 21 40
夜间 30 23 20 39
), ArticleFig(id=1200070674908803755, tenantId=1146029695717560320, journalId=1189918454225211397, articleId=1200070659066917574, language=CN, label=表5, caption=

不同应用场景下的计算速度对比 帧/s

, figureFileSmall=null, figureFileBig=null, tableContent=
应用场景 文献[9] 文献[10] 文献[13] 本文方法
晴天 33 28 25 42
雨天 32 26 21 40
夜间 30 23 20 39
)], attaches=null, journal=Journal(id=1189918244568731652, delFlag=0, nameCn=汽车工程师, nameEn=Automotive Engineer, nameHistory1=null, nameHistory2=null, issn=1674-6546, eissn=null, cn=22-1432/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=+bJsKkKt/pjz9u6EwhnksQ==, journalPrice=null, startedYear=null, abbrevIsoEn=null, journalRemark=null, publicationField=null, createdTime=1761628217121, updatedTime=1761735708780, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=A, firstLetterEn=A, subjectCode=Engineering, subjectName=Engineering, subjectCodeEn=Engineering, subjectNameEn=null, picCn=+bJsKkKt/pjz9u6EwhnksQ==, picEn=O3Sn3tnYYrh/jm6emnnMWA==, jcr=null, cjcr=null, exts=[JournalExt(id=1190369097415233706, language=CN, name=汽车工程师, 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=1761735708812, updatedTime=1761735708812, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://tjqc.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://tjqc.cbpt.cnki.net/index.aspx?t=3, submissionReviewUrl=https://tjqc.cbpt.cnki.net/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1190369097553645739, language=EN, name=Automotive Engineer, 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=1761735708845, updatedTime=1761735708845, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://tjqc.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://tjqc.cbpt.cnki.net/index.aspx?t=3, submissionReviewUrl=https://tjqc.cbpt.cnki.net/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1189918454225211397, websiteList=[Website(id=1189918982430847716, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1189918454225211397, 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/qcgcs/CN, language=CN, createTime=1761628393037, createBy=18614031015, updateTime=1761628422913, updateBy=18614031015, name=汽车工程师-中文, tplId=1146099689490845704, title=汽车工程师, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1189919800185917791, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982430847716, code=articleTextType, value=kx, createTime=1761628588005, updateTime=1761628588005, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919800164946268, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982430847716, code=banner, value=null, createTime=1761628588000, updateTime=1761628588000, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919800211083618, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982430847716, code=grayFlag, value=0, createTime=1761628588011, updateTime=1761628588011, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919800156557659, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982430847716, code=logo, value=https://castjournals.cast.org.cn/joweb/qcgcs/CN/file/pic?fileId=yiZ96RYoYcnGnRMuWdmkWA==, createTime=1761628587998, updateTime=1761628587998, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919800223666532, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982430847716, code=minRunFlag, value=0, createTime=1761628588014, updateTime=1761628588014, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919800181723486, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982430847716, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/qcgcs/CN/file/pic, createTime=1761628588004, updateTime=1761628588004, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919800215277923, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982430847716, code=silenceFlag, value=0, createTime=1761628588012, updateTime=1761628588012, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919800173334877, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982430847716, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1761628588002, updateTime=1761628588002, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919800194306400, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982430847716, code=themeColor, value=null, createTime=1761628588007, updateTime=1761628588007, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919800202695009, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982430847716, code=themeStyle, value=null, createTime=1761628588009, updateTime=1761628588009, creator=18614031015, updator=18614031015)]), Website(id=1189918982527316711, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1189918454225211397, 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/qcgcs/EN, language=EN, createTime=1761628393061, createBy=18614031015, updateTime=1761628543075, updateBy=18614031015, name=汽车工程师-英文, tplId=1146101810881728533, title=Automotive Engineer, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1189919837561352952, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982527316711, code=articleTextType, value=kx, createTime=1761628596916, updateTime=1761628596916, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919837540381429, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982527316711, code=banner, value=null, createTime=1761628596911, updateTime=1761628596911, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919837582324475, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982527316711, code=grayFlag, value=0, createTime=1761628596921, updateTime=1761628596921, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919837527798516, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982527316711, code=logo, value=https://castjournals.cast.org.cn/joweb/qcgcs/EN/file/pic?fileId=yiZ96RYoYcnGnRMuWdmkWA==, createTime=1761628596908, updateTime=1761628596908, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919837594907389, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982527316711, code=minRunFlag, value=0, createTime=1761628596924, updateTime=1761628596924, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919837557158647, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982527316711, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/qcgcs/EN/file/pic, createTime=1761628596915, updateTime=1761628596915, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919837586518780, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982527316711, code=silenceFlag, value=0, createTime=1761628596922, updateTime=1761628596922, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919837548770038, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982527316711, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1761628596913, updateTime=1761628596913, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919837569741561, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982527316711, code=themeColor, value=null, createTime=1761628596918, updateTime=1761628596918, creator=18614031015, updator=18614031015), WebsiteProps(id=1189919837573935866, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189918982527316711, code=themeStyle, value=null, createTime=1761628596919, updateTime=1761628596919, creator=18614031015, updator=18614031015)])], journalTitle=汽车工程师, weixinUrl=null, journalUrl=https://tjqc.cbpt.cnki.net/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Automotive Engineer, journalPhotoCn=+bJsKkKt/pjz9u6EwhnksQ==, journalPhotoEn=O3Sn3tnYYrh/jm6emnnMWA==, 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/qcgcs/CN/10.20104/j.cnki.1674-6546.20240149, detailUrlEn=https://castjournals.cast.org.cn/joweb/qcgcs/EN/10.20104/j.cnki.1674-6546.20240149, pdfUrlCn=https://castjournals.cast.org.cn/joweb/qcgcs/CN/PDF/10.20104/j.cnki.1674-6546.20240149, pdfUrlEn=https://castjournals.cast.org.cn/joweb/qcgcs/EN/PDF/10.20104/j.cnki.1674-6546.20240149, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于特征提取与边缘点投票的实时车道线识别*
收藏切换
PDF下载
杨达 1 , 魏长河 1 , 贾成禹 1 , 叶思琴 2
汽车工程师 | 智能车辆环境感知与目标检测技术专刊 2024,(8): 29-35
收起
收藏切换
汽车工程师 | 智能车辆环境感知与目标检测技术专刊 2024, (8): 29-35
基于特征提取与边缘点投票的实时车道线识别*
全屏
杨达1, 魏长河1, 贾成禹1, 叶思琴2
作者信息
  • 1 三一重工股份有限公司, 长沙 410199
  • 2 长沙理工大学, 长沙 410114

通讯作者:

叶思琴(1995—),女,讲师,博士,研究方向为汽车智能控制与机械振动分析,
Real-Time Lane Recognition Based on Feature Extraction and Edge Point Voting
Da Yang1, Changhe Wei1, Chengyu Jia1, Siqin Ye2
Affiliations
  • 1 Sany Heavy Industry Co., Ltd., Changsha 410199
  • 2 Changsha University of Science & Technology, Changsha 410114
出版时间: 2024-08-15 doi: 10.20104/j.cnki.1674-6546.20240149
文章导航
收藏切换

针对低算力车载计算平台的车道线检测需求,提出了一种低算力依赖的实时车道线识别方法。考虑车辆行驶过程中的光照变化,提出一种自适应光照的颜色分离方法实现车道特征提取;基于经典的边缘检测与霍夫变换算法,定义有效边缘点形式,通过边缘点投票确定车道直线;利用车道直线对边缘点进行筛选与补充,应用随机抽样一致性算法获取车道曲线方程。试验验证结果表明,所提出方法在低算力处理器上的识别精度高于98%,计算速度为38 帧/s,并在多种应用场景下具备稳定性与鲁棒性。

智能驾驶  /  车道线识别  /  边缘检测  /  随机抽样一致性  /  自适应光照

To satisfy the requirement of low power consumption vehicle computing platform for lane detection, this paper proposes a low computing power dependent real-time lane recognition method. Considering the variation of illumination during vehicle driving, a color separation method based on adaptive illumination to extract lane characteristics is proposed. The effective edge point form is defined and the lane lines are determined by edge point voting based on the classical edge detection and Hough transform algorithm. The lane lines are used to filter and supplement the edge points and the lane curve equation is obtained by using the random sample consensus algorithm. The results show that the proposed method achieves a recognition accuracy of over 98% and computation speed of 38 frames per second on a low power processor. Furthermore, the method has proven to be stable and robust in a variety of scenarios.

Intelligent driving  /  Lane recognition  /  Edge detection  /  Random sample consensus  /  Adaptive illumination
杨达, 魏长河, 贾成禹, 叶思琴. 基于特征提取与边缘点投票的实时车道线识别*. 汽车工程师, 2024 , (8) : 29 -35 . DOI: 10.20104/j.cnki.1674-6546.20240149
Da Yang, Changhe Wei, Chengyu Jia, Siqin Ye. Real-Time Lane Recognition Based on Feature Extraction and Edge Point Voting[J]. Automotive Engineer, 2024 , (8) : 29 -35 . DOI: 10.20104/j.cnki.1674-6546.20240149
车道线识别是智能驾驶系统的关键技术之一,是实现车道偏离预警与车道居中保持等高级辅助驾驶功能的先决条件。在车辆行驶过程中,通过感知传感器准确且实时地识别车道线,对于提升车辆主动安全性与维护道路交通运输安全具有重要的研究意义与应用价值[1]。现有的车道线识别方法主要分为两类,即基于深度学习的方法和基于图像处理技术的方法。
基于深度学习的识别方法利用语义分割、参数回归以及行锚检测等方式提取图像中的车道线特征[2-6]。这类方法无需人工设置车道特征参数,经过大量数据集的训练与学习后,具有良好的识别鲁棒性。然而,由于存在多层神经网络,计算资源开销大,对硬件平台的算力依赖强。为了保证实时性,通常需要高算力的图形处理单元(Graphics Processing Unit,GPU)或专用的神经网络处理单元(Neural Processing Unit,NPU)进行模型的部署、训练与推理。
对于低算力、低功耗的嵌入式计算设备,如仅具有嵌入式中央处理器(Central Processing Unit,CPU)的嵌入式开发板,常采用基于图像处理技术的方法进行车道线检测。这种方法的首要目标是将潜在的车道线特征与道路背景分离,胡胜等[7]采用大津法和二次阈值分割算法提取道路图像的候选车道线特征。考虑到车道线一般为白色或黄色标线,黄艳国等[8]在亮、暗两种状态下分别采用HLS格式的S通道与RGB格式的R通道将原彩色图像进行灰度化。在提取车道线方面,存在霍夫变换与滑动窗口搜索两种主要形式。执行霍夫变换操作后,Noman等[9]直接选择左、右最近的两条直线作为车道线,Sultana等[10]限制候选车道线的角度范围,并选取最大长度的直线作为车道线。滑动窗口搜索法通过滑动一个固定大小的窗口,逐行扫描预处理后的二值图像,通过窗口内直方图的峰值位置确定车道线[11-12]。霍夫变换仅能获取车道直线,滑动窗口搜索法通过对搜索到的像素点作多项式拟合可获得车道线的曲线方程[13]。然而,滑动窗口搜索法的拟合精度易受二值图像中的非车道线像素的影响。陈无畏等[14]提出一种边缘点投影算法,将图像筛选的边缘投影到消失线上检测出消失点位置,并由消失点反向搜索检测出车道线。刘悦等[15]基于改进蚁群算法提高边缘点投影算法在复杂光照环境中的准确率。该类方法计算效率较高,但稳定性与抗干扰能力有待进一步加强。
鉴于上述原因,本文提出一种低算力依赖的实时车道线识别方法。首先,通过自适应光照算法提取车道颜色特征;然后,基于边缘点投票获得车道直线,并筛选与补充有效的车道边缘点;最后,利用随机抽样一致性(RANdom SAmple Consensus,RANSAC)算法拟合车道曲线,从而提高车道线识别的准确度与稳定性,适应不同工况场景,以满足低算力计算设备的车道线检测需求。
本文提出的车道线识别算法包含图像预处理、车道特征提取、车道直线提取、车道曲线拟合4个主要环节,流程如图1所示。
在图像预处理阶段,对车载摄像头采集到的原始图像依次进行图像缩放与图像裁剪等操作。图像缩放是为了缩小原始图像的尺寸。当前车载摄像头通常具有较高的分辨率,可以根据缩放比例,将图像缩小到原始分辨率的1/2、1/4或1/8等。原始图像中,车道线存在于图像的下半部分,因此将图像的上半部分裁去,仅保留下半部分用于后续操作。原始图像经过图像缩放与裁剪不会改变图像中的车道特征,但可以大幅提高后续特征提取等操作的计算效率。图像缩放与裁剪后的结果如图2所示。
车道线为道路上黄白两色的显著标志线,利用车道线本身的颜色与亮度特征可以将车道线与背景分离。相比于RGB颜色空间,由色相(Hue)、饱和度(Saturation)与亮度(Value)表示的HSV颜色空间更易于从图像中分离出黄色和白色[11]。通过对图像各像素的色相、饱和度与亮度分别设置高、低两个阈值,提取所需颜色的二值图像,低阈值为(Hmin,Smin,Vmin),高阈值为(Hmax,Smax,Vmax)。根据HSV空间内的颜色分布,黄色与白色的高、低阈值设置表如1所示。
需要注意的是,在不同光照条件下,色相与饱和度不会发生较大变化,而图像中各颜色的亮度会受到光照变化的强烈影响。在光照较强时,道路背景颜色与车道线颜色的亮度都会增大;反之,在光照较弱时,各颜色的亮度也会减小。因此,在晴天、阴天以及夜间等不同场景下,需要对亮度设置不同的低阈值。本文提出一种自适应光照的亮度低阈值动态设置算法,算法流程如图3所示。
首先将RGB图像转换为HSV图像,在HSV图像的居中位置确定一个61像素×61像素的区域,如图4所示的亮度统计区域,将该区域中每个像素的亮度存入数组中,并将数组中的亮度由高到低排序,计算前1/5亮度值的平均数,记作Vavg,亮度的低阈值确定为:
Vmin=[(Vavg-10)/90+1]·Vavg
为防止亮度低阈值过大,若Vmin>220,则将Vmin设置为220。
获取车道颜色特征的二值图像后,需要在二值图像中设置一个梯形感兴趣区域(Region of Interest,ROI),见图4。ROI是利用图像消失点信息构造的梯形掩模,使得图像中仅包含左、右车道线所在的前方道路。ROI的设置通过对车载摄像头的安装位置进行人工标定实现。根据车载摄像头获得的实际道路的图像,人工选择如图4的梯形区域,确定梯形区域4个顶点的图像坐标即可确定ROI参数。同一型号且具有同一安装位置的车辆可采用同一ROI参数,避免重复标定。图5显示了晴天、阴影覆盖以及夜间场景下的车道特征提取结果,表明本文方法具备光照变化适应性。
提取车道特征二值图像后,本文采用经典的坎尼(Canny)算法进行边缘检测,并以边缘检测结果作为输入,执行概率霍夫变换,从而提取到车道特征中的候选直线。
所有候选直线根据其中点位置分为左、右候选直线。根据文献[10]的角度与长度约束思想,可对左、右候选直线进行角度与长度范围限制。角度为候选直线与图像x轴的夹角大小。其中,左候选直线角度范围为π/4-c~π/4+c,右侧候选直线角度范围为3π/4-c~3π/4+c,其中c为根据摄像头的安装位置确定的常数项。直线长度为候选直线在图像中的像素长度,最小长度设置为20像素。不在设定角度与长度范围的直线将被滤除,可以排除一定干扰项,并缩短边缘点投票选择候选直线的时间。霍夫变换提取到的直线如图6a所示,左、右分类及利用长度与角度约束滤除后的直线如图6b所示。
边缘点投票的过程为,遍历边缘检测得到二值图像的每一行,提取有效边缘点,计算每个边缘点到每条候选直线的垂直距离,距离最小的直线获得该边缘点的一次投票,最终获得票数最多的候选直线即为所寻找的车道直线。对于左、右候选直线,由图像中轴位置,分别沿x轴向左与向右提取有效边缘点构成。有效边缘点是根据车道形状特征确定的。车道具有一定的宽度,其边缘特征如图7所示。以确定左车道线为例,在边缘二值图像中,每一行由中心位置向左搜索白点,若某个白点间隔若干黑点后,仍存在一个白点,表明该白点为有效边缘点。间隔范围可以设置为2~20像素,因为远端的车道线在图像中的宽度较小,近端的较大。保存所有的有效边缘点,对左侧候选直线进行距离投票。根据距离进行边缘点投票需要设置距离阈值,边缘点与候选直线的距离最小且小于该距离阈值时,方可对该候选直线投票。本文距离阈值设置为5像素。设置有效边缘点与最小距离,能够使投票结果更加稳定。3种应用场景下,有效边缘点的分布及最终投票提取的左、右车道直线如图8所示,可以看出,车道直线提取准确,均处于车道线的内部边缘。
在确定左、右车道直线时可采用并行计算提高整个算法的计算速度。
车道曲线拟合由边缘点筛选、边缘点补充与RANSAC算法3个部分组成,见图1。边缘点筛选是利用2.3节中提取的左、右车道线,对有效边缘点进行离群点删除。计算每个边缘点到车道直线的距离,若该点靠近车道直线,则认为该点为一个“好点”。为能拟合曲线,“好点”到直线的距离可以设置得比投票时的距离阈值稍大,本文设置为10像素。
对于虚线车道线,在靠近车头的区域可能不存在边缘点。为防止车道曲线欠拟合,对于这类情况,利用2.3节中提取的车道直线方程,在缺乏边缘点的车头区域进行边缘点补充。初始检测到的边缘点如图9a所示,补充后的边缘点如图9b所示。
经过筛选与补充后的边缘点仍可能存在噪声,应用RANSAC算法从边缘点的坐标数据中估计车道线曲线方程。车道线曲线方程采用Bezier三次曲线表达,其矩阵形式为:
$y=\left[\begin{array}{cccc}1& x& {x}^{2}& {x}^{3}\end{array}\right]\left[\begin{array}{cccc}1& 0& 0& 0\\ -3& 3& 0& 0\\ 3& -6& 3& 0\\ -1& 3& -3& 1\end{array}\right]\left[\begin{array}{c}{a}_{0}\\ {a}_{1}\\ {a}_{2}\\ {a}_{3}\end{array}\right]$
式中:a0a1a2a3为三次曲线方程的系数,(x,y)为边缘点在图像中的像素坐标。
RANSAC曲线拟合的流程为:将所有边缘点随机分为10组,每组包含20个边缘点;每组求解一次曲线方程,并计算所有边缘点到曲线的距离和;最小距离和对应的曲线方程即为所求曲线方程。
在每组拟合曲线方程时,采用最小二乘法求解三次曲线方程的4个系数。经过2.3节提取到的左、右车道直线与本节方法提取到的车道曲线如图10所示,显然,车道曲线更加贴合真实车道线。
试验设备采用本单位自研的低功耗车载计算平台,如图11所示,该计算平台搭载嵌入式CPU型号为ARM Cortex-A55,运行内存2 GB。本文提出的方法采用C++语言实现,程序全程运行在CPU上,不采用任何GPU或NPU进行加速计算。设计了2组验证试验,分别利用2个开源数据集验证所提出方法的精度与效率,以及在不同应用场景下的稳定性,同时与文献[9]、文献[10]和文献[13]提出的方法进行对比分析。车道线识别方法的精度采用正确识别帧数与图像总帧数之比进行量化,速度采用每秒可处理图像帧数作为评价指标。
试验采用的数据集为一段高速公路视频,共1 260帧图像,图像分辨率为1 280像素×720像素,晴天工况下,多数路段车道线清晰,部分路段道路有路边树木阴影遮挡与亮暗变化,如图12所示。测试结果如表2所示,本文方法在每个阶段的平均运行时间如表3所示。
表2可以看出,本文方法的识别精度显著优于文献[9]、文献[10]与文献[13]。文献[9]仅从霍夫变换结果中选择最靠近车侧的两条直线作为车道线,在阴影覆盖与亮暗变化路段误检较多。文献[10]采取的长度与角度约束一定程度上提高了算法在复杂路段的识别精度,但在车道线受磨损路段识别精度较低。文献[13]采用的滑动窗口搜索法同样具有较高的检测精度,但计算速度在本文计算平台上表现不佳。从计算速度来看,本文方法最优,在低算力车载计算平台上具有实时计算性能。由表3可知,本文方法的主要耗时操作为RANSAC曲线拟合,若实际应用中不需要曲线方程,如文献[9]与文献[10],则可以进一步优化车道线识别算法的计算速度。
采用iROADS数据集验证本文方法在不同应用场景下的稳定性与鲁棒性。应用场景分为晴天、雨天与夜间3种工况,晴天环境下的图像数据为903帧,雨天的图像数量为1 049帧,夜间包含1 050帧图像。图像分辨率均为640像素×360像素。各工况下的道路环境如图13所示。4种方法在上述场景中的测试精度与计算速度分别如表4表5所示。
表4可以看出,本文方法在晴天、雨天以及夜间3种应用场景中均具有最佳的识别精度。与3.1节试验结果相似,文献[9]、文献[10]与文献[13]提出的方法易受虚线车道线的影响,若图像中包含较短的车道线,容易出现误检的现象。本文基于边缘点投票的方法受虚线车道线干扰较小,只有虚线车道线非常模糊或消失等极端情况下会导致本文方法失效。从试验结果来看,本文方法更具备环境适应性。由表5可以看出,在3种应用场景中,本文方法均具有最高的计算效率,且表现出实时计算性能。
本文提出了一种适用于低算力车载计算平台的车道线识别方法。通过图像缩放、图像裁剪与左、右车道线的并行计算等技术手段提高算法效率,提出了一种自适应光照的车道特征提取方法,增强算法在光照变化条件下的稳定性,并设计了一种边缘点投票方法,有效提取车道直线,最后利用RANSAC算法与Bezier三次曲线拟合确定了车道曲线方程。
试验结果表明,本文方法在对比试验中具有最优的识别精度与计算效率,在低算力的车载计算平台上具有实时性能,且具备环境适应性,在晴天、雨天以及夜间场景下的识别精度均高于98%,计算速度不低于39 帧/s。
  • *中国科协第九届青年人才托举工程项目(2023-2025)
参考文献 引证文献
排序方式:
[1]
PANDA L, MOHANTY B P. Recent Developments in Departure Warning System: An Analysis[J]. Ethics and Information Technology, 2020, 2(2): 151-153.
[2]
NEVEN D, BRABANDERE B D, GEORGOULIS S, et al. Towards End-to-End Lane Detection:An Instance Segmentation Approach[C]// Proceedings of 2018 IEEE Intelligent Vehicles Symposium (IV). Changshu, China: IEEE, 2018: 286-291.
[3]
TABELINI L, BERRIEL R, PAIXAO T M, et al. Keep Your Eyes on the Lane: Real-Time Attention-Guided Lane Detection[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, TN, USA: IEEE, 2021: 294-302.
[4]
QIN Z Q, ZHANG P Y, LI X. Ultra Fast Deep Lane Detection with Hybrid Anchor Driven Ordinal Classification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(5): 2555-2568.
[5]
杜黎, 吕毅斌, 武德安, 等. 复杂场景中的快速车道线检测方法[J]. 计算机工程与应用, 2023, 59(13): 178-185.
DU L, Y B, WU D A, et al. Fast Lane Detection Method in Complex Scenarios[J]. Computer Engineering and Applications, 2023, 59(13): 178-185.
[6]
李守彪, 武志斐. 基于多尺寸分解卷积的车道线检测[J]. 汽车技术, 2022(8): 32-37.
LI S B, WU Z F. Lane Detection Based on Multi-Size Factorized Convolution[J]. Automobile Technology, 2022(8): 32-37.
[7]
胡胜, 黄妙华, 陈毅. 基于二次阈值分割和车道宽度匹配的车道线检测算法[J]. 汽车技术, 2019(4): 1-6.
HU S, HUANG M H, CHEN Y. Lane Marking Detection Algorithm Based on Double Threshold Segmentation and Lane Width[J]. Automobile Technology, 2019(4): 1-6.
[8]
黄艳国, 钟勇, 夏金龙. 基于自适应透视变换与特征融合的车道线检测方法[J]. 科学技术与工程, 2022, 22(32): 14298-14305.
HUANG Y G, ZHONG Y, XIA J L. Lane Detection Method Based on Adaptive Perspective Transformation and Feature Fusion[J]. Science Technology and Engineering, 2022, 22(32): 14298-14305.
[9]
NOMAN M A A, RAHAMAN M F, LI Z, et al. A Computer Vision-Based Lane Detection Approach for an Autonomous Vehicle Using the Image Hough Transformation and the Edge Features[M]// GOAR V, KURI M, KUMAR R, et al. Advances in Information Communication Technology and Computing. Singapore: Springer, 2023: 53-66.
[10]
SULTANA S, AHMED B, PAUL M, et al. Vision-Based Robust Lane Detection and Tracking in Challenging Conditions[J]. IEEE Access, 2023, 11: 67938-67955.
[11]
蔡创新, 邹宇, 潘志庚, 等. 基于多特征融合和窗口搜索的新型车道线检测算法[J]. 江苏大学学报(自然科学版), 2023, 44(4): 386-391.
CAI C X, ZOU Y, PAN Z G, et al. Novel Lane Detection Algorithm Based on Multi-Feature Fusion and Windows Searching[J]. Journal of Jiangsu University (Natural Science Edition), 2023, 44(4): 386-391.
[12]
黄艳国, 钟勇, 饶泽浩. 基于优化最大类间方差法阈值分割与滑动窗口法的车道偏离预警[J]. 汽车技术, 2023(6): 9-16.
HUANG Y G, ZHONG Y, RAO Z H. Lane Departure Warning Based on Optimized Threshold Segmentation of Maximum Inter-Class Variance and Sliding Window Method[J]. Automobile Technology, 2023(6): 9-16.
[13]
王梓楠, 何东, 赵茂杰. 基于滑动窗口搜索的车道线检测与车道偏离预警算法[J]. 汽车工程师, 2023(9): 15-20+28.
WANG Z N, HE D, ZHAO M J. Lane Line Detection and Lane Departure Warning Algorithm Based on Sliding Window Searching[J]. Automotive Engineer, 2023(9): 15-20+28.
[14]
陈无畏, 蒋玉亭, 谈东奎. 一种基于边缘点投影的车道线快速识别算法[J]. 汽车工程, 2017, 39(3): 357-363.
CHEN W W, JIANG Y T, TAN D K. A Fast Lane Marking Recognition Algorithm Based on Edge Projection[J]. Automotive Engineering, 2017, 39(3): 357-363.
[15]
刘悦, 杨桦, 王青正. 面向复杂光照环境的车道线检测方法[J/OL]. 激光杂志 (2023-09-01) [2024-05-29]. http://kns.cnki.net/kcms/detail/50.1085.TN.20230901.1047.008.html http://kns.cnki.net/kcms/detail/50.1085.TN.20230901.1047.008.html
LIU Y, YANG H, WANG Q Z. Lane Detection Method for Complex Lighting Environment[J/OL]. Laser Journal (2023-09-01) [2024-05-29]. http://kns.cnki.net/kcms/detail/50.1085.TN.20230901.1047.008.html http://kns.cnki.net/kcms/detail/50.1085.TN.20230901.1047.008.html
2024年第卷第8期
PDF下载
195
88
引用本文
BibTeX
文章信息
doi: 10.20104/j.cnki.1674-6546.20240149
  • 首发时间:2025-11-25
  • 出版时间:2024-08-15
补充材料
相关文章
文章信息
作者
出版历史
  • 修回日期:2024-05-29
基金
*中国科协第九届青年人才托举工程项目(2023-2025)
作者信息
    1 三一重工股份有限公司, 长沙 410199
    2 长沙理工大学, 长沙 410114

通讯作者:

叶思琴(1995—),女,讲师,博士,研究方向为汽车智能控制与机械振动分析,
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/qcgcs/CN/10.20104/j.cnki.1674-6546.20240149
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