首页 期刊 论文 学科刊群 资讯 加盟 关于
EN
image
Article(id=1312006323466760701, tenantId=1146029695717560320, journalId=1311385739772133495, issueId=1311999647825101743, articleNumber=null, orderNo=null, doi=10.6041/j.issn.1000-1298.2025.12.060, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1747238400000, receivedDateStr=2025-05-15, revisedDate=1752076800000, revisedDateStr=2025-07-10, acceptedDate=null, acceptedDateStr=null, onlineDate=1790736283413, onlineDateStr=2026-09-30, pubDate=1766592000000, pubDateStr=2025-12-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1790736283413, onlineIssueDateStr=2026-09-30, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1790736283413, creator=13701087609, updateTime=1790736283413, updator=13701087609, issue=Issue{id=1311999647825101743, tenantId=1146029695717560320, journalId=1311385739772133495, year='2025', volume='56', issue='12', pageStart='1', pageEnd='818', issueExtLink='null', onlineDate='null', pubDate='1766592000000', pubDateStr='2025-12-25', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1790734691815, creator='13701087609', updateTime=1790738411040, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1312015247465083866, tenantId=1146029695717560320, journalId=1311385739772133495, issueId=1311999647825101743, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1312015247465083867, tenantId=1146029695717560320, journalId=1311385739772133495, issueId=1311999647825101743, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=657, endPage=665, ext={EN=ArticleExt(id=1312006323655504382, articleId=1312006323466760701, tenantId=1146029695717560320, journalId=1311385739772133495, language=EN, title=Navigation Line Extractionin in Pear Orchard Based on MLKA and Temporal RANSAC Fusion, columnId=1311999800569066336, journalTitle=Transactions of the Chinese Society for Agricultural Machinery, columnName=Agricultural Informatization Engineering, runingTitle=null, highlight=null, articleAbstract=

Traditional visual navigation methods struggle to handle interference from varying lighting conditions and weed occlusion in complex pear orchard environments. An improved navigation line extraction method was proposed based on YOLO v8 to address this challenge. The process integrated a multi-scale large kernel attention (MLKA) module into the YOLO v8 model to enhance the perception of trunk features. A multi-frame feature point fusion mechanism was designed. By recording and utilizing feature points detected in five consecutive frames, this mechanism effectively compensated for the problem of insufficient feature points in single-frame detection. Additionally, the random sample consensus (RANSAC) algorithm was introduced to denoise the feature points of the left and right tree rows, respectively, and the least squares method was used for the two side tree rows' line fitting. The navigation line was ultimately generated by calculating the angle bisector of the fitted lines from both sides of the tree rows. Experimental results showed that the improved model achieved a precision of 89.8%, a recall of 79.9%, and a mean average precision (mAP50-95) of 55.1% in tree trunk detection tasks under various lighting conditions and weed occlusion scenarios. The navigation line generated by combining multi-frame feature point fusion with RANSAC denoising exhibited an average angular deviation of only 1.17° from the manually annotated reference navigation line, an average position deviation of 20.40 pixels, and an average root mean square deviation of 0.27. The research result can provide a low-cost and highly adaptable technical solution for visual navigation in pear orchard environments.

, authors=Jianjun ZHOU1, Quanle LIU1, Lei CAO1, Lin FAN1, Quan QIU2, authorsList=Jianjun ZHOU, Quanle LIU, Lei CAO, Lin FAN, Quan QIU, authorCompany=null, 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, fund=null), CN=ArticleExt(id=1312006328143409717, articleId=1312006323466760701, tenantId=1146029695717560320, journalId=1311385739772133495, language=CN, title=基于MLKA与时序RANSAC融合的梨园导航线提取方法, columnId=1311999800749421410, journalTitle=农业机械学报, columnName=农业信息化工程, runingTitle=null, highlight=null, articleAbstract=

在复杂梨园环境中，传统视觉导航方法容易受到光照变化、杂草遮挡等因素的干扰。针对此问题，本文提出了一种基于改进YOLO v8模型的梨园导航线提取方法。该方法在YOLO v8模型中集成了多尺度大核注意力（Multi-scale large kernel attention，MLKA）模块以增强对树干特征的感知。设计了多帧特征点融合机制，通过记录并利用连续5帧图像中检测到的特征点，有效弥补了单帧图像特征点不足的问题。此外，引入随机抽样一致性（Random sample consensus，RANSAC）算法，分别对左右两侧树行的特征点进行降噪处理，并使用最小二乘法进行树行线拟合。通过计算左右两侧树行线的角平分线生成果园导航线。实验结果表明：改进模型在复杂的果园环境中，树干检测的精确率（Precision）达到89.8%，召回率（Recall）达到79.9%，平均精度均值（mean average precision，mAP50-95）达到了55.1%。结合多帧特征点融合与RANSAC降噪生成的导航线与手动标注的参考导航线之间的角度偏差均值为1.17°，位置偏差均值为20.40像素，均方根偏差均值为0.27。本文方法为梨园环境中的视觉导航提供了一种低成本、高适应性的技术方案。

, authors=周建军1, 刘泉乐1, 曹磊1, 樊林1, 邱权2, authorsList=周建军, 刘泉乐, 曹磊, 樊林, 邱权, authorCompany=null, correspAuthors=null, authorNote=

周建军（1977—），男，副教授，博士，主要从事农业智能装备研究，E-mail：

, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=j3URGfwYr21tvar9j+//ZA==, magXml=QPhjYWlLK43qY5fkri/f4w==, pdfUrl=null, pdf=nTWlRoo1pBY9D3Y/HAdgog==, pdfFileSize=9038519, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=HNQ5lG3PkLrRI5ifmFlxWw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=MgieQbITfj66/KQfg4oAnA==, mapNumber=null, fund=null)}, authors=[Author(id=1312006328533479997, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhoujianjun@bipt.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1312006328621560383, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, authorId=1312006328533479997, language=EN, stringName=Jianjun ZHOU, firstName=Jianjun, middleName=null, lastName=ZHOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1312006328688669248, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, authorId=1312006328533479997, language=CN, stringName=周建军, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.北京石油化工学院信息工程学院，北京　102617, bio={"content":"

周建军（1977—），男，副教授，博士，主要从事农业智能装备研究，E-mail：

"}, bioImg=null, bioContent=

周建军（1977—），男，副教授，博士，主要从事农业智能装备研究，E-mail：

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1312006328365707830, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, xref=1., ext=[AuthorCompanyExt(id=1312006328378290743, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328365707830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China), AuthorCompanyExt(id=1312006328386679352, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328365707830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.北京石油化工学院信息工程学院，北京　102617)])]), Author(id=1312006328755778114, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, 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=1312006328839664196, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, authorId=1312006328755778114, language=EN, stringName=Quanle LIU, firstName=Quanle, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1312006328902578757, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, authorId=1312006328755778114, language=CN, stringName=刘泉乐, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.北京石油化工学院信息工程学院，北京　102617, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1312006328365707830, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, xref=1., ext=[AuthorCompanyExt(id=1312006328378290743, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328365707830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China), AuthorCompanyExt(id=1312006328386679352, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328365707830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.北京石油化工学院信息工程学院，北京　102617)])]), Author(id=1312006328973881927, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, 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=1312006329057768009, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, authorId=1312006328973881927, language=EN, stringName=Lei CAO, firstName=Lei, middleName=null, lastName=CAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1312006329120682570, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, authorId=1312006328973881927, language=CN, stringName=曹磊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.北京石油化工学院信息工程学院，北京　102617, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1312006328365707830, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, xref=1., ext=[AuthorCompanyExt(id=1312006328378290743, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328365707830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China), AuthorCompanyExt(id=1312006328386679352, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328365707830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.北京石油化工学院信息工程学院，北京　102617)])]), Author(id=1312006329196180044, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1312006329301037646, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, authorId=1312006329196180044, language=EN, stringName=Lin FAN, firstName=Lin, middleName=null, lastName=FAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1312006329363952207, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, authorId=1312006329196180044, language=CN, stringName=樊林, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.北京石油化工学院信息工程学院，北京　102617, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1312006328365707830, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, xref=1., ext=[AuthorCompanyExt(id=1312006328378290743, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328365707830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China), AuthorCompanyExt(id=1312006328386679352, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328365707830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.北京石油化工学院信息工程学院，北京　102617)])]), Author(id=1312006329435255377, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1312006329506558547, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, authorId=1312006329435255377, language=EN, stringName=Quan QIU, firstName=Quan, middleName=null, lastName=QIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.College of Intelligent Science and Engineering, Beijing University of Agriculture, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1312006329569473108, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, authorId=1312006329435255377, language=CN, stringName=邱权, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.北京农学院智能科学与工程学院，北京　102206, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1312006328453788217, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, xref=2., ext=[AuthorCompanyExt(id=1312006328462176826, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328453788217, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Intelligent Science and Engineering, Beijing University of Agriculture, Beijing 102206, China), AuthorCompanyExt(id=1312006328470565435, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328453788217, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.北京农学院智能科学与工程学院，北京　102206)])])], keywords=[Keyword(id=1312006329682719317, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, orderNo=1, keyword=pear orchard), Keyword(id=1312006329745633878, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, orderNo=2, keyword=automatic navigation), Keyword(id=1312006329816937047, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, orderNo=3, keyword=YOLO v8), Keyword(id=1312006329875657304, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, orderNo=4, keyword=MLKA), Keyword(id=1312006329951154777, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, orderNo=5, keyword=RANSAC algorithm), Keyword(id=1312006330009875034, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, orderNo=6, keyword=multi-frame feature point fusion), Keyword(id=1312006330068595291, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, orderNo=1, keyword=梨园), Keyword(id=1312006330135704156, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, orderNo=2, keyword=自动导航), Keyword(id=1312006330211201629, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, orderNo=3, keyword=YOLO v8), Keyword(id=1312006330316059230, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, orderNo=4, keyword=MLKA), Keyword(id=1312006330416722527, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, orderNo=5, keyword=RANSAC算法), Keyword(id=1312006330483831392, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, orderNo=6, keyword=多帧特征点融合)], refs=[Reference(id=1312006333424038531, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2022, volume=53, issue=7, pageStart=1, pageEnd=22, 55, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=刘成良, 贡亮, 苑进, journalName=农业机械学报, refType=null, unstructuredReference=刘成良, 贡亮, 苑进, 等. 农业机器人关键技术研究现状与发展趋势[J]. 农业机械学报, 2022, 53(7): 1-22, 55., articleTitle=农业机器人关键技术研究现状与发展趋势, refAbstract=null), Reference(id=1312006333503730308, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2022, volume=53, issue=7, pageStart=1, pageEnd=22, 55, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=LIU Chengliang, GONG Liang, YUAN Jin, journalName=Transactions of the Chinese Society for Agricultural Machinery, refType=null, unstructuredReference=LIU Chengliang, GONG Liang, YUAN Jin, et al. Current status and development trends of agricultural robots[J]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(7): 1-22, 55. (in Chinese), articleTitle=Current status and development trends of agricultural robots, refAbstract=null), Reference(id=1312006333579227781, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2024, volume=55, issue=4, pageStart=1, pageEnd=22, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=窦汉杰, 陈震宇, 翟长远, journalName=农业机械学报, refType=null, unstructuredReference=窦汉杰, 陈震宇, 翟长远, 等. 果园智能化作业装备自主导航技术研究进展[J]. 农业机械学报, 2024, 55(4): 1-22., articleTitle=果园智能化作业装备自主导航技术研究进展, refAbstract=null), Reference(id=1312006333625365126, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2024, volume=55, issue=4, pageStart=1, pageEnd=22, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=DOU Hanjie, CHEN Zhenyu, ZHAI Changyuan, journalName=Transactions of the Chinese Society for Agricultural Machinery, refType=null, unstructuredReference=DOU Hanjie, CHEN Zhenyu, ZHAI Changyuan, et al. Research progress on autonomous navigation technology for orchard intelligent equipment[J]. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55(4): 1-22. (in Chinese), articleTitle=Research progress on autonomous navigation technology for orchard intelligent equipment, refAbstract=null), Reference(id=1312006333700862599, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2022, volume=12, issue=10, pageStart=1650, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=ZHOU J, GENG S, QIU Q, journalName=Agriculture, refType=null, unstructuredReference=ZHOU J, GENG S, QIU Q, et al. A deep-learning extraction method for orchard visual navigation lines[J]. Agriculture, 2022, 12(10): 1650., articleTitle=A deep-learning extraction method for orchard visual navigation lines, refAbstract=null), Reference(id=1312006333767971464, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2023, volume=211, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=XIE B, JIN Y, FAHEEM M, journalName=Computers and Electronics in Agriculture, refType=null, unstructuredReference=XIE B, JIN Y, FAHEEM M, et al. Research progress of autonomous navigation technology for multi-agricultural scenes[J]. Computers and Electronics in Agriculture, 2023, 211: 107963., articleTitle=Research progress of autonomous navigation technology for multi-agricultural scenes, refAbstract=null), Reference(id=1312006333847663241, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2023, volume=54, issue=8, pageStart=97, pageEnd=109, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=朱立成, 韩振浩, 赵博, journalName=农业机械学报, refType=null, unstructuredReference=朱立成, 韩振浩, 赵博, 等. 基于VINS-MONO和改进YOLO v4-Tiny的果园自主寻筐方法[J]. 农业机械学报, 2023, 54(8): 97-109., articleTitle=基于VINS-MONO和改进YOLO v4-Tiny的果园自主寻筐方法, refAbstract=null), Reference(id=1312006333923160714, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2023, volume=54, issue=8, pageStart=97, pageEnd=109, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=ZHU Licheng, HAN Zhenhao, ZHAO Bo, journalName=Transactions of the Chinese Society for Agricultural Machinery, refType=null, unstructuredReference=ZHU Licheng, HAN Zhenhao, ZHAO Bo, et al. Autonomous basket searching method for orchards transporter based on VINS-MONO and improved YOLO v4-Tiny[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(8): 97-109. (in Chinese), articleTitle=Autonomous basket searching method for orchards transporter based on VINS-MONO and improved YOLO v4-Tiny, refAbstract=null), Reference(id=1312006334040601227, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2024, volume=55, issue=增刊1, pageStart=9, pageEnd=17, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=应仇凯, 程泓超, 马锃宏, journalName=农业机械学报, refType=null, unstructuredReference=应仇凯, 程泓超, 马锃宏, 等. 基于YOLO v8-Seg的地栽草莓采摘机器人垄面视觉导航控制方法[J]. 农业机械学报, 2024, 55(增刊1): 9-17., articleTitle=基于YOLO v8-Seg的地栽草莓采摘机器人垄面视觉导航控制方法, refAbstract=null), Reference(id=1312006334124487308, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2024, volume=55, issue=Supp. 1, pageStart=9, pageEnd=17, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=YING Qiukai, CHENG Hongchao, MA Zenghong, journalName=Transactions of the Chinese Society for Agricultural Machinery, refType=null, unstructuredReference=YING Qiukai, CHENG Hongchao, MA Zenghong, et al. Ridge visual navigation control method for ground-planted strawberry picking robots based on YOLO v8-Seg algorithm[J]. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55(Supp. 1): 9-17. (in Chinese), articleTitle=Ridge visual navigation control method for ground-planted strawberry picking robots based on YOLO v8-Seg algorithm, refAbstract=null), Reference(id=1312006334187401869, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=5, pageStart=530, pageEnd=539, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=吴城, 李晓娟, journalName=江苏大学学报(自然科学版), refType=null, unstructuredReference=吴城, 李晓娟. 基于单线激光的果园机器人自主导航方法[J]. 江苏大学学报(自然科学版), 2023, 44(5): 530-539., articleTitle=基于单线激光的果园机器人自主导航方法, refAbstract=null), Reference(id=1312006334250316430, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=5, pageStart=530, pageEnd=539, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=WU Cheng, LI Xiaojuan, journalName=Journal of Jiangsu University (Natural Science Edition), refType=null, unstructuredReference=WU Cheng, LI Xiaojuan. Autonomous navigation method of orchard robot based on single laser[J]. Journal of Jiangsu University (Natural Science Edition), 2023, 44(5): 530-539. (in Chinese), articleTitle=Autonomous navigation method of orchard robot based on single laser, refAbstract=null), Reference(id=1312006334317425295, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2024, volume=14, issue=2, pageStart=271, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=YUE B, ZHANG Z, ZHANG W, journalName=Agronomy, refType=null, unstructuredReference=YUE B, ZHANG Z, ZHANG W, et al. Design of an automatic navigation and operation system for a crawler-based orchard sprayer using GNSS positioning[J]. Agronomy, 2024, 14(2): 271., articleTitle=Design of an automatic navigation and operation system for a crawler-based orchard sprayer using GNSS positioning, refAbstract=null), Reference(id=1312006334380339856, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2023, volume=12, issue=4, pageStart=167, pageEnd=178, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=CHEN S, ZHANG M, LI X, journalName=IET Networks, refType=null, unstructuredReference=CHEN S, ZHANG M, LI X, et al. Precision agriculture intelligent connection network based on visual navigation[J]. IET Networks, 2023, 12(4): 167-178., articleTitle=Precision agriculture intelligent connection network based on visual navigation, refAbstract=null), Reference(id=1312006334455837329, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2024, volume=227, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=NAKAGUCHI V M, ABEYRATHNA R M R D, LIU Z, journalName=Computers and Electronics in Agriculture, refType=null, unstructuredReference=NAKAGUCHI V M, ABEYRATHNA R M R D, LIU Z, et al. Development of a machine stereo vision-based autonomous navigation system for orchard speed sprayers[J]. Computers and Electronics in Agriculture, 2024, 227: 109669., articleTitle=Development of a machine stereo vision-based autonomous navigation system for orchard speed sprayers, refAbstract=null), Reference(id=1312006334522946194, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2020, volume=10, issue=8, pageStart=2763, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=ZHANG S, GUO C, GAO Z, journalName=Applied Sciences, refType=null, unstructuredReference=ZHANG S, GUO C, GAO Z, et al. Research on 2D laser automatic navigation control for standardized orchard[J]. Applied Sciences, 2020, 10(8): 2763., articleTitle=Research on 2D laser automatic navigation control for standardized orchard, refAbstract=null), Reference(id=1312006334648775315, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2025, volume=46, issue=8, pageStart=1809, pageEnd=1817, url=null, language=null, rfNumber=[12], rfOrder=16, authorNames=毕盛, 杨礼铭, 董敏, journalName=小型微型计算机系统, refType=null, unstructuredReference=毕盛, 杨礼铭, 董敏, 等. 语言视觉激光多模态融合的机器人导航方法[J]. 小型微型计算机系统, 2025, 46(8): 1809-1817., articleTitle=语言视觉激光多模态融合的机器人导航方法, refAbstract=null), Reference(id=1312006334736855700, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2025, volume=46, issue=8, pageStart=1809, pageEnd=1817, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=BI Sheng, YANG Liming, DONG Min, journalName=Journal of Chinese Computer System, refType=null, unstructuredReference=BI Sheng, YANG Liming, DONG Min, et al. Robot navigation based on multi-modal fusion of language vision LiDAR[J]. Journal of Chinese Computer System, 2025, 46(8): 1809-1817. (in Chinese), articleTitle=Robot navigation based on multi-modal fusion of language vision LiDAR, refAbstract=null), Reference(id=1312006334837518997, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2022, volume=13, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=WANG S, SONG J, QI P, journalName=Frontiers in Plant Science, refType=null, unstructuredReference=WANG S, SONG J, QI P, et al. Design and development of orchard autonomous navigation spray system[J]. Frontiers in Plant Science, 2022, 13: 960686., articleTitle=Design and development of orchard autonomous navigation spray system, refAbstract=null), Reference(id=1312006334908822166, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2017, volume=33, issue=9, pageStart=45, pageEnd=52, url=null, language=null, rfNumber=[14], rfOrder=19, authorNames=彭顺正, 坎杂, 李景彬, journalName=农业工程学报, refType=null, unstructuredReference=彭顺正, 坎杂, 李景彬. 矮化密植枣园收获作业视觉导航路径提取[J]. 农业工程学报, 2017, 33(9): 45-52., articleTitle=矮化密植枣园收获作业视觉导航路径提取, refAbstract=null), Reference(id=1312006334980125335, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2017, volume=33, issue=9, pageStart=45, pageEnd=52, url=null, language=null, rfNumber=[14], rfOrder=20, authorNames=PENG Shunzheng, KAN Za, LI Jingbin, journalName=Transactions of the CSAE, refType=null, unstructuredReference=PENG Shunzheng, KAN Za, LI Jingbin. Extraction of visual navigation directrix for harvesting operation in short-stalked and close-planting jujube orchard[J]. Transactions of the CSAE, 2017, 33(9): 45-52. (in Chinese), articleTitle=Extraction of visual navigation directrix for harvesting operation in short-stalked and close-planting jujube orchard, refAbstract=null), Reference(id=1312006335047234200, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=10, pageStart=167, pageEnd=175, url=null, language=null, rfNumber=[15], rfOrder=21, authorNames=冯凯, 王茂励, 何晓宁, journalName=中国农机化学报, refType=null, unstructuredReference=冯凯, 王茂励, 何晓宁, 等. 基于辅助线的农机视觉导航路径提取算法研究[J]. 中国农机化学报, 2022, 43(10): 167-175., articleTitle=基于辅助线的农机视觉导航路径提取算法研究, refAbstract=null), Reference(id=1312006335118537369, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=10, pageStart=167, pageEnd=175, url=null, language=null, rfNumber=[15], rfOrder=22, authorNames=FENG Kai, WANG Maoli, HE Xiaoning, journalName=Journal of Chinese Agricultural Mechanization, refType=null, unstructuredReference=FENG Kai, WANG Maoli, HE Xiaoning, et al. Research on visual navigation path extraction algorithm for agricultural machinery based on auxiliary lines[J]. Journal of Chinese Agricultural Mechanization, 2022, 43(10): 167-175. (in Chinese), articleTitle=Research on visual navigation path extraction algorithm for agricultural machinery based on auxiliary lines, refAbstract=null), Reference(id=1312006335181451930, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2024, volume=14, issue=11, pageStart=1987, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=23, authorNames=ZHONG W, YANG W, ZHU J, journalName=Agriculture, refType=null, unstructuredReference=ZHONG W, YANG W, ZHU J, et al. An improved UNet-based path recognition method in low-light environments[J]. Agriculture, 2024, 14(11): 1987., articleTitle=An improved UNet-based path recognition method in low-light environments, refAbstract=null), Reference(id=1312006335261143707, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2024, volume=47, issue=6, pageStart=1241, pageEnd=1250, url=null, language=null, rfNumber=[17], rfOrder=24, authorNames=卢心缘, 赵华民, 任锐, journalName=南京农业大学学报, refType=null, unstructuredReference=卢心缘, 赵华民, 任锐, 等. 基于YOLO v5s-seg的非结构化枣园视觉导航路径提取[J]. 南京农业大学学报, 2024, 47(6): 1241-1250., articleTitle=基于YOLO v5s-seg的非结构化枣园视觉导航路径提取, refAbstract=null), Reference(id=1312006335328252572, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2024, volume=47, issue=6, pageStart=1241, pageEnd=1250, url=null, language=null, rfNumber=[17], rfOrder=25, authorNames=LU Xinyuan, ZHAO Huamin, REN Rui, journalName=Journal of Nanjing Agricultural University, refType=null, unstructuredReference=LU Xinyuan, ZHAO Huamin, REN Rui, et al. Unstructured jujube garden visual navigation path extraction based on YOLO v5s-seg[J]. Journal of Nanjing Agricultural University, 2024, 47(6): 1241-1250. (in Chinese), articleTitle=Unstructured jujube garden visual navigation path extraction based on YOLO v5s-seg, refAbstract=null), Reference(id=1312006335399555741, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2021, volume=52, issue=1, pageStart=30, pageEnd=39, url=null, language=null, rfNumber=[18], rfOrder=26, authorNames=韩振浩, 李佳, 苑严伟, journalName=农业机械学报, refType=null, unstructuredReference=韩振浩, 李佳, 苑严伟, 等. 基于U-Net网络的果园视觉导航路径识别方法[J]. 农业机械学报, 2021, 52(1): 30-39., articleTitle=基于U-Net网络的果园视觉导航路径识别方法, refAbstract=null), Reference(id=1312006335487636126, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2021, volume=52, issue=1, pageStart=30, pageEnd=39, url=null, language=null, rfNumber=[18], rfOrder=27, authorNames=HAN Zhenhao, LI Jia, YUAN Yanwei, journalName=Transactions of the Chinese Society for Agricultural Machinery, refType=null, unstructuredReference=HAN Zhenhao, LI Jia, YUAN Yanwei, et al. Path recognition of orchard visual navigation based on U-Net[J]. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(1): 30-39. (in Chinese), articleTitle=Path recognition of orchard visual navigation based on U-Net, refAbstract=null), Reference(id=1312006335546356383, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2024, volume=55, issue=7, pageStart=15, pageEnd=26, url=null, language=null, rfNumber=[19], rfOrder=28, authorNames=张伟荣, 陈学庚, 齐江涛, journalName=农业机械学报, refType=null, unstructuredReference=张伟荣, 陈学庚, 齐江涛, 等. 基于深度学习和高斯过程回归的玉米冠下视觉导航路径提取方法[J]. 农业机械学报, 2024, 55(7): 15-26., articleTitle=基于深度学习和高斯过程回归的玉米冠下视觉导航路径提取方法, refAbstract=null), Reference(id=1312006335621853856, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2024, volume=55, issue=7, pageStart=15, pageEnd=26, url=null, language=null, rfNumber=[19], rfOrder=29, authorNames=ZHANG Weirong, CHEN Xuegeng, QI Jiangtao, journalName=Transactions of the Chinese Society for Agricultural Machinery, refType=null, unstructuredReference=ZHANG Weirong, CHEN Xuegeng, QI Jiangtao, et al. Deep learning and gaussian process regression based path extraction for visual navigation under canopy[J]. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55(7): 15-26. (in Chinese), articleTitle=Deep learning and gaussian process regression based path extraction for visual navigation under canopy, refAbstract=null), Reference(id=1312006335705739937, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2023, volume=54, issue=6, pageStart=197, pageEnd=204, 252, url=null, language=null, rfNumber=[20], rfOrder=30, authorNames=肖珂, 夏伟光, 梁聪哲, journalName=农业机械学报, refType=null, unstructuredReference=肖珂, 夏伟光, 梁聪哲. 复杂背景下果园视觉导航路径提取算法[J]. 农业机械学报, 2023, 54(6): 197-204, 252., articleTitle=复杂背景下果园视觉导航路径提取算法, refAbstract=null), Reference(id=1312006335777043106, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2023, volume=54, issue=6, pageStart=197, pageEnd=204, 252, url=null, language=null, rfNumber=[20], rfOrder=31, authorNames=XIAO Ke, XIA Weiguang, LIANG Congzhe, journalName=Transactions of the Chinese Society for Agricultural Machinery, refType=null, unstructuredReference=XIAO Ke, XIA Weiguang, LIANG Congzhe. Visual navigation path extraction algorithm in orchard under complex background[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(6): 197-204, 252. (in Chinese), articleTitle=Visual navigation path extraction algorithm in orchard under complex background, refAbstract=null), Reference(id=1312006335839957667, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2022, volume=197, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=32, authorNames=YANG Z, OUYANG L, ZHANG Z, journalName=Computers and Electronics in Agriculture, refType=null, unstructuredReference=YANG Z, OUYANG L, ZHANG Z, et al. Visual navigation path extraction of orchard hard pavement based on scanning method and neural network[J]. Computers and Electronics in Agriculture, 2022, 197: 106964., articleTitle=Visual navigation path extraction of orchard hard pavement based on scanning method and neural network, refAbstract=null), Reference(id=1312006335923843748, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=8, pageStart=217, pageEnd=222, url=null, language=null, rfNumber=[22], rfOrder=33, authorNames=许贞辉, 李晓娟, journalName=中国农机化学报, refType=null, unstructuredReference=许贞辉, 李晓娟. 果园树干检测与导航线拟合算法研究[J]. 中国农机化学报, 2024, 45(8): 217-222., articleTitle=果园树干检测与导航线拟合算法研究, refAbstract=null), Reference(id=1312006335999341221, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=8, pageStart=217, pageEnd=222, url=null, language=null, rfNumber=[22], rfOrder=34, authorNames=XU Zhenhui, LI Xiaojuan, journalName=Journal of Chinese Agricultural Mechanization, refType=null, unstructuredReference=XU Zhenhui, LI Xiaojuan. Research on tree trunk detection and navigation line fitting algorithm in orchard[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(8): 217-222. (in Chinese), articleTitle=Research on tree trunk detection and navigation line fitting algorithm in orchard, refAbstract=null), Reference(id=1312006336062255782, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2023, volume=39, issue=16, pageStart=131, pageEnd=138, url=null, language=null, rfNumber=[23], rfOrder=35, authorNames=彭书博, 陈兵旗, 李景彬, journalName=农业工程学报, refType=null, unstructuredReference=彭书博, 陈兵旗, 李景彬, 等. 基于改进YOLOv7的果园行间导航线检测[J]. 农业工程学报, 2023, 39(16): 131-138., articleTitle=基于改进YOLOv7的果园行间导航线检测, refAbstract=null), Reference(id=1312006336133558951, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2023, volume=39, issue=16, pageStart=131, pageEnd=138, url=null, language=null, rfNumber=[23], rfOrder=36, authorNames=PENG Shubo, CHEN Bingqi, LI Jingbin, journalName=Transactions of the CSAE, refType=null, unstructuredReference=PENG Shubo, CHEN Bingqi, LI Jingbin, et al. Detection of the navigation line between lines in orchard using improved YOLOv7[J]. Transactions of the CSAE, 2023, 39(16): 131-138. (in Chinese), articleTitle=Detection of the navigation line between lines in orchard using improved YOLOv7, refAbstract=null), Reference(id=1312006336200667816, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2024, volume=12, issue=null, pageStart=104126, pageEnd=104137, url=null, language=null, rfNumber=[24], rfOrder=37, authorNames=CAO Z, GONG C, MENG J, journalName=IEEE Access, refType=null, unstructuredReference=CAO Z, GONG C, MENG J, et al. Orchard vision navigation line extraction based on YOLO v8-trunk detection[J]. IEEE Access, 2024, 12: 104126-104137., articleTitle=Orchard vision navigation line extraction based on YOLO v8-trunk detection, refAbstract=null), Reference(id=1312006336280359593, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=5950, pageEnd=5960, url=null, language=null, rfNumber=[25], rfOrder=38, authorNames=WANG Y, LI Y, WANG G, journalName=null, refType=null, unstructuredReference=WANG Y, LI Y, WANG G, et al. Multi-scale attention network for single image super-resolution[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024: 5950-5960., articleTitle=Multi-scale attention network for single image super-resolution, refAbstract=null)], funds=[Fund(id=1312006333268849281, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, awardId=61973040, language=CN, fundingSource=国家自然科学基金面上项目(61973040), fundOrder=null, country=null), Fund(id=1312006333335958146, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, awardId=2025J00250, language=CN, fundingSource=北京石油化工学院国家级大学生创新创业训练计划项目(2025J00250), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1312006328365707830, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, xref=1., ext=[AuthorCompanyExt(id=1312006328378290743, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328365707830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China), AuthorCompanyExt(id=1312006328386679352, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328365707830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.北京石油化工学院信息工程学院，北京　102617)]), AuthorCompany(id=1312006328453788217, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, xref=2., ext=[AuthorCompanyExt(id=1312006328462176826, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328453788217, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Intelligent Science and Engineering, Beijing University of Agriculture, Beijing 102206, China), AuthorCompanyExt(id=1312006328470565435, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328453788217, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.北京农学院智能科学与工程学院，北京　102206)])], figs=[ArticleFig(id=1312006330634826337, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, label=Fig. 1, caption=Structure of improved YOLO v8 model, figureFileSmall=dt2vRFgs1odV60ZAc6Yq9g==, figureFileBig=HNQ5lG3PkLrRI5ifmFlxWw==, tableContent=null), ArticleFig(id=1312006330697740898, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, label=图1, caption=改进的YOLO v8模型结构图, figureFileSmall=dt2vRFgs1odV60ZAc6Yq9g==, figureFileBig=HNQ5lG3PkLrRI5ifmFlxWw==, tableContent=null), ArticleFig(id=1312006330907456099, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, label=Fig. 2, caption=Comparison of trunk detection effects, figureFileSmall=+ThrB3yT77pXR5Qb4TifYQ==, figureFileBig=e/eP5quNtbPRMR9/roUlZw==, tableContent=null), ArticleFig(id=1312006330982953572, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, label=图2, caption=树干检测效果对比, figureFileSmall=+ThrB3yT77pXR5Qb4TifYQ==, figureFileBig=e/eP5quNtbPRMR9/roUlZw==, tableContent=null), ArticleFig(id=1312006331045868133, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, label=Fig. 3, caption=Comparison of detection effect under normal light, figureFileSmall=xJ1YBW190beHy94XDyS4sQ==, figureFileBig=FuYRBN2xx58ggiPADJJLZA==, tableContent=null), ArticleFig(id=1312006331104588390, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, label=图3, caption=正常光照下检测效果对比, figureFileSmall=xJ1YBW190beHy94XDyS4sQ==, figureFileBig=FuYRBN2xx58ggiPADJJLZA==, tableContent=null), ArticleFig(id=1312006331167502951, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, label=Fig. 4, caption=Comparison of detection effect under overcast conditions, figureFileSmall=PNmU4/Xm8o1XoJm3jm2uNg==, figureFileBig=C6xOrsHlG+wrouYSkPtwVw==, tableContent=null), ArticleFig(id=1312006331255583336, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, label=图4, caption=阴天下检测效果对比, figureFileSmall=PNmU4/Xm8o1XoJm3jm2uNg==, figureFileBig=C6xOrsHlG+wrouYSkPtwVw==, tableContent=null), ArticleFig(id=1312006331326886505, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, label=Fig. 5, caption=Comparison of detection effect under strong light, figureFileSmall=r7qV0ps0NJPucE1aFdBufQ==, figureFileBig=NSTfzGOW96X9qK2nmu0Pvw==, tableContent=null), ArticleFig(id=1312006331393995370, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, label=图5, caption=强光下检测效果对比, figureFileSmall=r7qV0ps0NJPucE1aFdBufQ==, figureFileBig=NSTfzGOW96X9qK2nmu0Pvw==, tableContent=null), ArticleFig(id=1312006331465298539, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, label=Fig. 6, caption=Comparison of detection effect under low light, figureFileSmall=TGpD2ZqJPWmS8jc1zbaufQ==, figureFileBig=z3/8RwqoaYIj20x0M89YXA==, tableContent=null), ArticleFig(id=1312006331557573228, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, label=图6, caption=弱光下检测效果对比, figureFileSmall=TGpD2ZqJPWmS8jc1zbaufQ==, figureFileBig=z3/8RwqoaYIj20x0M89YXA==, tableContent=null), ArticleFig(id=1312006331637265005, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, label=Fig. 7, caption=Comparison of detection effect under occlusion, figureFileSmall=Fcgauc8JSqaDvaw4635Bew==, figureFileBig=Jk5fp2nuVhjfpKXwz22ggw==, tableContent=null), ArticleFig(id=1312006331716956782, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, label=图7, caption=遮挡下检测效果对比, figureFileSmall=Fcgauc8JSqaDvaw4635Bew==, figureFileBig=Jk5fp2nuVhjfpKXwz22ggw==, tableContent=null), ArticleFig(id=1312006331784065647, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, label=Fig. 8, caption=Effects of temporal fusion mechanism, figureFileSmall=VWGVTVY02b2sVyJy23Eg0w==, figureFileBig=guCM1aHhTF4a+E2fHvjEJA==, tableContent=null), ArticleFig(id=1312006331888923248, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, label=图8, caption=多帧融合机制效果, figureFileSmall=VWGVTVY02b2sVyJy23Eg0w==, figureFileBig=guCM1aHhTF4a+E2fHvjEJA==, tableContent=null), ArticleFig(id=1312006331968615025, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, label=Fig. 9, caption=Denoising effect of RANSAC, figureFileSmall=WQGCe+je7XOWlwSzdnGnYA==, figureFileBig=fxIoe5J+bVhRBG7Cw+GiBA==, tableContent=null), ArticleFig(id=1312006332023140978, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, label=图9, caption=RANSAC降噪效果, figureFileSmall=WQGCe+je7XOWlwSzdnGnYA==, figureFileBig=fxIoe5J+bVhRBG7Cw+GiBA==, tableContent=null), ArticleFig(id=1312006332102832755, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, label=Fig. 10, caption=Combined effect of multi-frame fusion and RANSAC noise reduction, figureFileSmall=99RxpXkCKLSjF2xuByy4Jw==, figureFileBig=9DdUlJ3iL5LngH1Zx7fmGg==, tableContent=null), ArticleFig(id=1312006332174135924, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, label=图10, caption=多帧融合和RANSAC降噪结合效果, figureFileSmall=99RxpXkCKLSjF2xuByy4Jw==, figureFileBig=9DdUlJ3iL5LngH1Zx7fmGg==, tableContent=null), ArticleFig(id=1312006332245439093, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, label=Fig. 11, caption=Comparison of angle deviation, figureFileSmall=ql/rMt85c/Pld4pkrSxLpQ==, figureFileBig=5ZL1OHJn6ZLwnxxIHyCduw==, tableContent=null), ArticleFig(id=1312006332337713782, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, label=图11, caption=角度偏差对比, figureFileSmall=ql/rMt85c/Pld4pkrSxLpQ==, figureFileBig=5ZL1OHJn6ZLwnxxIHyCduw==, tableContent=null), ArticleFig(id=1312006332400628343, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, label=Fig. 12, caption=Comparison of position deviation, figureFileSmall=Uo+gzWBEuw0qe/T+pywNxw==, figureFileBig=N+xQj6x5GGLklnklv7yBfQ==, tableContent=null), ArticleFig(id=1312006332484514424, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, label=图12, caption=位置偏差对比, figureFileSmall=Uo+gzWBEuw0qe/T+pywNxw==, figureFileBig=N+xQj6x5GGLklnklv7yBfQ==, tableContent=null), ArticleFig(id=1312006332555817593, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, label=Fig. 13, caption=Root mean square error comparison, figureFileSmall=jBrGglco/GyK8UQ9EEF0uQ==, figureFileBig=Ym0OkWrLEjqEw+B31lzX1A==, tableContent=null), ArticleFig(id=1312006332627120762, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, label=图13, caption=均方根偏差对比, figureFileSmall=jBrGglco/GyK8UQ9EEF0uQ==, figureFileBig=Ym0OkWrLEjqEw+B31lzX1A==, tableContent=null), ArticleFig(id=1312006332757144187, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
输入：点集D={（xi，yi）}，迭代次数S，距离阈值τ，内点比例阈值d
输出：最佳直线参数（mbest，bbest）
1 初始化mbest←0；
2 初始化bbest←0；
3 初始化最大内点数←0；
4 for i=1 to S do
5      随机选择2个不同的点（x1，y1），（x2，y2）∈D；
6          计算直线参数；
7          计算直线参数b←y1-mx1；
8          初始化内点集合I←{}；
9          for j=1 to |D| do
10              计算点（xj，yj）到直线的垂直距离；
11              if Lj<τ then
12                  将（xj，yj）添加到内点集合I；
13              end
14          end
15          if |I|>d|D|且|I|大于最大内点数then
16            更新最大内点数←|I|；
17            使用内点集合I计算最小二乘法拟合参数mnew，bnew；
18            更新mbest←mnew；
19            更新bbest←bnew；
20        end
21 end
22 return（mbest，bbest）；
), ArticleFig(id=1312006332832641660, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, label=null, caption=

, figureFileSmall=null, figureFileBig=null, tableContent=
输入：点集D={（xi，yi）}，迭代次数S，距离阈值τ，内点比例阈值d
输出：最佳直线参数（mbest，bbest）
1 初始化mbest←0；
2 初始化bbest←0；
3 初始化最大内点数←0；
4 for i=1 to S do
5      随机选择2个不同的点（x1，y1），（x2，y2）∈D；
6          计算直线参数；
7          计算直线参数b←y1-mx1；
8          初始化内点集合I←{}；
9          for j=1 to |D| do
10              计算点（xj，yj）到直线的垂直距离；
11              if Lj<τ then
12                  将（xj，yj）添加到内点集合I；
13              end
14          end
15          if |I|>d|D|且|I|大于最大内点数then
16            更新最大内点数←|I|；
17            使用内点集合I计算最小二乘法拟合参数mnew，bnew；
18            更新mbest←mnew；
19            更新bbest←bnew；
20        end
21 end
22 return（mbest，bbest）；
), ArticleFig(id=1312006332933304957, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, label=Tab. 1, caption=

Model performance comparison

, figureFileSmall=null, figureFileBig=null, tableContent=
模型精确率召回率平均精度均值
YOLO v886.674.352.6
改进模型（MLKA-YOLO v8）89.879.955.1
), ArticleFig(id=1312006333025579646, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, label=表1, caption=

模型性能对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型精确率召回率平均精度均值
YOLO v886.674.352.6
改进模型（MLKA-YOLO v8）89.879.955.1
), ArticleFig(id=1312006333084299903, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=EN, label=Tab. 2, caption=

Comparison of navigation line generation accuracy

, figureFileSmall=null, figureFileBig=null, tableContent=
组合方式角度偏差均值/（°）位置偏差均值/像素均方根偏差均值
SFBD6.82226.380.80
MFBD5.03147.690.62
SFAD4.56163.050.52
MFAD1.1720.400.27
), ArticleFig(id=1312006333163991680, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, language=CN, label=表2, caption=

导航线生成精度对比

, figureFileSmall=null, figureFileBig=null, tableContent=
组合方式角度偏差均值/（°）位置偏差均值/像素均方根偏差均值
SFBD6.82226.380.80
MFBD5.03147.690.62
SFAD4.56163.050.52
MFAD1.1720.400.27
)], attaches=null, journal=Journal(id=1311384913490051186, delFlag=0, nameCn=农业机械学报, nameEn=Transactions of the Chinese Society for Agricultural Machinery, nameHistory1=null, nameHistory2=null, issn=1000-1298, eissn=null, cn=11-1964/S, coden=CODEN NUYCA3, 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=DpMljKbCTPO4JEohCaKm5A==, journalPrice=null, startedYear=null, abbrevIsoEn=Transactions of the Chinese Society for Agricultural Machinery, journalRemark=null, publicationField=null, createdTime=1790588127731, updatedTime=1790740716593, createdBy=18614031015, updatedBy=18614031015, firstLetterCn=N, firstLetterEn=N, subjectCode=Agriculture, subjectName=null, subjectCodeEn=Agriculture, subjectNameEn=null, picCn=DpMljKbCTPO4JEohCaKm5A==, picEn=klDuz9nOYH3sS2mMFZcDKQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1311386928897945885, language=CN, name=农业机械学报, 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=1790588608240, updatedTime=1790588608240, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://www.j-csam.org/jcsam/author/login, submissionEditorUrl=https://www.j-csam.org/jcsam/editor/login, submissionReviewUrl=https://www.j-csam.org/jcsam/user/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1311386928944083230, language=EN, name=Transactions of the Chinese Society of Agricultural Machinery, 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=1790588608251, updatedTime=1790588608251, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://www.j-csam.org/jcsam/author/login, submissionEditorUrl=https://www.j-csam.org/jcsam/editor/login, submissionReviewUrl=https://www.j-csam.org/jcsam/user/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1311385739772133495, websiteList=[Website(id=1311386135197221186, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1311385739772133495, 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/nyjxxb/CN, language=CN, createTime=1790588419007, createBy=18614031015, updateTime=1790588455647, updateBy=18614031015, name=农业机械学报-中文, tplId=1146099689490845704, title=农业机械学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1312024622120399707, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135197221186, code=articleTextType, value=kx, createTime=1790740646152, updateTime=1790740646152, creator=18614031015, updator=18614031015), WebsiteProps(id=1312024622091039576, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135197221186, code=banner, value=null, createTime=1790740646145, updateTime=1790740646145, creator=18614031015, updator=18614031015), WebsiteProps(id=1312024622149759838, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135197221186, code=grayFlag, value=0, createTime=1790740646159, updateTime=1790740646159, creator=18614031015, updator=18614031015), WebsiteProps(id=1312024622078456663, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135197221186, code=logo, value=https://castjournals.cast.org.cn/joweb/nyjxxb/CN/file/pic?fileId=oEf7LShi6rv3EG1pNx7PwQ==, createTime=1790740646142, updateTime=1790740646142, creator=18614031015, updator=18614031015), WebsiteProps(id=1312024622166537056, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135197221186, code=minRunFlag, value=0, createTime=1790740646163, updateTime=1790740646163, creator=18614031015, updator=18614031015), WebsiteProps(id=1312024622112011098, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135197221186, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/nyjxxb/CN/file/pic, createTime=1790740646150, updateTime=1790740646150, creator=18614031015, updator=18614031015), WebsiteProps(id=1312024622158148447, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135197221186, code=silenceFlag, value=0, createTime=1790740646161, updateTime=1790740646161, creator=18614031015, updator=18614031015), WebsiteProps(id=1312024622099428185, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135197221186, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1790740646147, updateTime=1790740646147, creator=18614031015, updator=18614031015), WebsiteProps(id=1312024622128788316, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135197221186, code=themeColor, value=null, createTime=1790740646154, updateTime=1790740646154, creator=18614031015, updator=18614031015), WebsiteProps(id=1312024622141371229, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135197221186, code=themeStyle, value=null, createTime=1790740646157, updateTime=1790740646157, creator=18614031015, updator=18614031015)]), Website(id=1311386135398547788, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1311385739772133495, 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/nyjxxb/EN, language=EN, createTime=1790588419055, createBy=18614031015, updateTime=1790740692575, updateBy=18614031015, name=农业机械学报-英文, tplId=1146101810881728533, title=Transactions of the Chinese Society for Agricultural Machinery, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1312024677325828967, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135398547788, code=articleTextType, value=kx, createTime=1790740659314, updateTime=1790740659314, creator=18614031015, updator=18614031015), WebsiteProps(id=1312024677300663140, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135398547788, code=banner, value=null, createTime=1790740659308, updateTime=1790740659308, creator=18614031015, updator=18614031015), WebsiteProps(id=1312024677350994794, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135398547788, code=grayFlag, value=0, createTime=1790740659320, updateTime=1790740659320, creator=18614031015, updator=18614031015), WebsiteProps(id=1312024677288080227, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135398547788, code=logo, value=https://castjournals.cast.org.cn/joweb/nyjxxb/EN/file/pic?fileId=oEf7LShi6rv3EG1pNx7PwQ==, createTime=1790740659305, updateTime=1790740659305, creator=18614031015, updator=18614031015), WebsiteProps(id=1312024677367772012, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135398547788, code=minRunFlag, value=0, createTime=1790740659324, updateTime=1790740659324, creator=18614031015, updator=18614031015), WebsiteProps(id=1312024677317440358, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135398547788, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/nyjxxb/EN/file/pic, createTime=1790740659312, updateTime=1790740659312, creator=18614031015, updator=18614031015), WebsiteProps(id=1312024677359383403, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135398547788, code=silenceFlag, value=0, createTime=1790740659322, updateTime=1790740659322, creator=18614031015, updator=18614031015), WebsiteProps(id=1312024677309051749, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135398547788, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1790740659310, updateTime=1790740659310, creator=18614031015, updator=18614031015), WebsiteProps(id=1312024677334217576, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135398547788, code=themeColor, value=null, createTime=1790740659316, updateTime=1790740659316, creator=18614031015, updator=18614031015), WebsiteProps(id=1312024677342606185, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1311386135398547788, code=themeStyle, value=null, createTime=1790740659318, updateTime=1790740659318, creator=18614031015, updator=18614031015)])], journalTitle=农业机械学报, weixinUrl=null, journalUrl=https://www.j-csam.org/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Transactions of the Chinese Society for Agricultural Machinery, journalPhotoCn=DpMljKbCTPO4JEohCaKm5A==, journalPhotoEn=klDuz9nOYH3sS2mMFZcDKQ==, journalFirstLetter=N, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/nyjxxb/CN/10.6041/j.issn.1000-1298.2025.12.060, detailUrlEn=https://castjournals.cast.org.cn/joweb/nyjxxb/EN/10.6041/j.issn.1000-1298.2025.12.060, pdfUrlCn=https://castjournals.cast.org.cn/joweb/nyjxxb/CN/PDF/10.6041/j.issn.1000-1298.2025.12.060, pdfUrlEn=https://castjournals.cast.org.cn/joweb/nyjxxb/EN/PDF/10.6041/j.issn.1000-1298.2025.12.060, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1766592000000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于MLKA与时序RANSAC融合的梨园导航线提取方法
收藏切换
PDF下载
周建军 1 , 刘泉乐 1 , 曹磊 1 , 樊林 1 , 邱权 2
农业机械学报 | 农业信息化工程 2025,56(12): 657-665
收起
收藏切换
农业机械学报 |农业信息化工程 2025 , 56 (12) : 657 -665
基于MLKA与时序RANSAC融合的梨园导航线提取方法
全屏
[Author(id=1312006328533479997, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhoujianjun@bipt.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1312006328621560383, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, authorId=1312006328533479997, language=EN, stringName=Jianjun ZHOU, firstName=Jianjun, middleName=null, lastName=ZHOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1312006328688669248, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, authorId=1312006328533479997, language=CN, stringName=周建军, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.北京石油化工学院信息工程学院，北京　102617, bio={"content":"

周建军（1977—），男，副教授，博士，主要从事农业智能装备研究，E-mail：

"}, bioImg=null, bioContent=

周建军（1977—），男，副教授，博士，主要从事农业智能装备研究，E-mail：

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1312006328365707830, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, xref=1., ext=[AuthorCompanyExt(id=1312006328378290743, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328365707830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China), AuthorCompanyExt(id=1312006328386679352, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328365707830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.北京石油化工学院信息工程学院，北京　102617)])]), Author(id=1312006328755778114, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, 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=1312006328839664196, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, authorId=1312006328755778114, language=EN, stringName=Quanle LIU, firstName=Quanle, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1312006328902578757, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, authorId=1312006328755778114, language=CN, stringName=刘泉乐, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.北京石油化工学院信息工程学院，北京　102617, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1312006328365707830, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, xref=1., ext=[AuthorCompanyExt(id=1312006328378290743, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328365707830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China), AuthorCompanyExt(id=1312006328386679352, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328365707830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.北京石油化工学院信息工程学院，北京　102617)])]), Author(id=1312006328973881927, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, 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=1312006329057768009, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, authorId=1312006328973881927, language=EN, stringName=Lei CAO, firstName=Lei, middleName=null, lastName=CAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1312006329120682570, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, authorId=1312006328973881927, language=CN, stringName=曹磊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.北京石油化工学院信息工程学院，北京　102617, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1312006328365707830, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, xref=1., ext=[AuthorCompanyExt(id=1312006328378290743, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328365707830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China), AuthorCompanyExt(id=1312006328386679352, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328365707830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.北京石油化工学院信息工程学院，北京　102617)])]), Author(id=1312006329196180044, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1312006329301037646, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, authorId=1312006329196180044, language=EN, stringName=Lin FAN, firstName=Lin, middleName=null, lastName=FAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1312006329363952207, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, authorId=1312006329196180044, language=CN, stringName=樊林, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.北京石油化工学院信息工程学院，北京　102617, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1312006328365707830, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, xref=1., ext=[AuthorCompanyExt(id=1312006328378290743, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328365707830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China), AuthorCompanyExt(id=1312006328386679352, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328365707830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.北京石油化工学院信息工程学院，北京　102617)])]), Author(id=1312006329435255377, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1312006329506558547, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, authorId=1312006329435255377, language=EN, stringName=Quan QIU, firstName=Quan, middleName=null, lastName=QIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.College of Intelligent Science and Engineering, Beijing University of Agriculture, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1312006329569473108, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, authorId=1312006329435255377, language=CN, stringName=邱权, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.北京农学院智能科学与工程学院，北京　102206, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1312006328453788217, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, xref=2., ext=[AuthorCompanyExt(id=1312006328462176826, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328453788217, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Intelligent Science and Engineering, Beijing University of Agriculture, Beijing 102206, China), AuthorCompanyExt(id=1312006328470565435, tenantId=1146029695717560320, journalId=1311385739772133495, articleId=1312006323466760701, companyId=1312006328453788217, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.北京农学院智能科学与工程学院，北京　102206)])])]
周建军1 , 刘泉乐1, 曹磊1, 樊林1, 邱权2
作者信息
  • 1.北京石油化工学院信息工程学院，北京　102617
  • 2.北京农学院智能科学与工程学院，北京　102206
作者简介:

周建军（1977—），男，副教授，博士，主要从事农业智能装备研究，E-mail：

Navigation Line Extractionin in Pear Orchard Based on MLKA and Temporal RANSAC Fusion
Jianjun ZHOU1 , Quanle LIU1, Lei CAO1, Lin FAN1, Quan QIU2
Affiliations
  • 1.College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China
  • 2.College of Intelligent Science and Engineering, Beijing University of Agriculture, Beijing 102206, China
出版时间: 2025-12-25 doi: 10.6041/j.issn.1000-1298.2025.12.060
文章导航
收藏切换
摘要
收起

在复杂梨园环境中，传统视觉导航方法容易受到光照变化、杂草遮挡等因素的干扰。针对此问题，本文提出了一种基于改进YOLO v8模型的梨园导航线提取方法。该方法在YOLO v8模型中集成了多尺度大核注意力（Multi-scale large kernel attention，MLKA）模块以增强对树干特征的感知。设计了多帧特征点融合机制，通过记录并利用连续5帧图像中检测到的特征点，有效弥补了单帧图像特征点不足的问题。此外，引入随机抽样一致性（Random sample consensus，RANSAC）算法，分别对左右两侧树行的特征点进行降噪处理，并使用最小二乘法进行树行线拟合。通过计算左右两侧树行线的角平分线生成果园导航线。实验结果表明：改进模型在复杂的果园环境中，树干检测的精确率（Precision）达到89.8%，召回率（Recall）达到79.9%，平均精度均值（mean average precision，mAP50-95）达到了55.1%。结合多帧特征点融合与RANSAC降噪生成的导航线与手动标注的参考导航线之间的角度偏差均值为1.17°，位置偏差均值为20.40像素，均方根偏差均值为0.27。本文方法为梨园环境中的视觉导航提供了一种低成本、高适应性的技术方案。

梨园  /  自动导航  /  YOLO v8  /  MLKA  /  RANSAC算法  /  多帧特征点融合

Traditional visual navigation methods struggle to handle interference from varying lighting conditions and weed occlusion in complex pear orchard environments. An improved navigation line extraction method was proposed based on YOLO v8 to address this challenge. The process integrated a multi-scale large kernel attention (MLKA) module into the YOLO v8 model to enhance the perception of trunk features. A multi-frame feature point fusion mechanism was designed. By recording and utilizing feature points detected in five consecutive frames, this mechanism effectively compensated for the problem of insufficient feature points in single-frame detection. Additionally, the random sample consensus (RANSAC) algorithm was introduced to denoise the feature points of the left and right tree rows, respectively, and the least squares method was used for the two side tree rows' line fitting. The navigation line was ultimately generated by calculating the angle bisector of the fitted lines from both sides of the tree rows. Experimental results showed that the improved model achieved a precision of 89.8%, a recall of 79.9%, and a mean average precision (mAP50-95) of 55.1% in tree trunk detection tasks under various lighting conditions and weed occlusion scenarios. The navigation line generated by combining multi-frame feature point fusion with RANSAC denoising exhibited an average angular deviation of only 1.17° from the manually annotated reference navigation line, an average position deviation of 20.40 pixels, and an average root mean square deviation of 0.27. The research result can provide a low-cost and highly adaptable technical solution for visual navigation in pear orchard environments.

pear orchard  /  automatic navigation  /  YOLO v8  /  MLKA  /  RANSAC algorithm  /  multi-frame feature point fusion
周建军, 刘泉乐, 曹磊, 樊林, 邱权. 基于MLKA与时序RANSAC融合的梨园导航线提取方法. 农业机械学报, 2025 , 56 (12) : 657 -665 . DOI: 10.6041/j.issn.1000-1298.2025.12.060
Jianjun ZHOU, Quanle LIU, Lei CAO, Lin FAN, Quan QIU. Navigation Line Extractionin in Pear Orchard Based on MLKA and Temporal RANSAC Fusion[J]. Transactions of the Chinese Society for Agricultural Machinery, 2025 , 56 (12) : 657 -665 . DOI: 10.6041/j.issn.1000-1298.2025.12.060
正文
收起
0　引言
收起
随着现代农业向自动化和智能化的不断迈进，智慧农业已成为未来农业发展的趋势[1]。自动导航技术作为智能农机装备的关键技术之一，极大提高了果园机械作业的品质和效率[2-6]。近年来，激光雷达和计算机视觉技术在果园智能机械导航领域均有应用[7]。其中激光雷达因其硬件成本高昂、在复杂环境中特征提取困难以及数据信息冗余等因素，限制了其在小型果园中的应用推广。相较之下，视觉导航成本低廉、采集的信息丰富和检测精度高，逐渐成为果园智能导航研究的主流方向[8-13]。
早期的视觉导航主要依赖于传统的图像处理技术，例如颜色阈值分割、边缘检测或几何特征提取，再通过Hough变换或最小二乘法等数学方法拟合导航线[14-15]。随着深度学习技术的发展，部分学者使用该技术进行了导航路径的提取研究[16-24]。
但在光照变化、杂草遮挡的复杂果园环境中，视觉导航仍存在局限性。单帧图像中树干特征点不足或缺失会直接影响导航线的生成精度。现有方法在处理异常点（包括误检点、相邻行干扰点及各类噪声点）时缺乏有效的过滤机制，可能导致生成的导航线精度降低。
针对上述问题，本文提出一种基于改进YOLO v8模型的梨园行间导航线生成方法。该方法通过引入MLKA模块增强对树干特征的感知能力，设计多帧特征点融合机制，以弥补单帧图像检测时特征点缺失或不足的问题。采用RANSAC算法对特征点进行降噪处理，最终使用最小二乘法对两侧树行进行拟合，生成准确导航线。
1　模型与方法
收起
1.1　基于改进YOLO v8的树干检测
YOLO v8网络由主干网络（Backbone）、颈部（Neck）和头部（Head）3部分组成。主干网络负责提取图像的层次化特征，采用CSPDarknet结构，通过深层卷积网络和残差连接提取丰富的视觉特征；颈部负责融合不同尺度的特征图，增强网络对不同尺寸目标的检测能力；头部负责类别预测并生成最终的锚框。
在原始YOLO v8模型中，SPPF（Spatial pyramid pooling fast）模块作为主干网络中的关键组件，通过不同尺度的池化操作来获取多尺度的特征信息，增强了模型对各种尺寸目标的识别能力。梨树树干纵向延伸的细长几何结构通常呈现出明显的空间关联特性，各部位特征存在层次化依赖关系，因此需要采用全局感知机制进行特征提取。使用YOLO v8识别梨树树干时，SPPF模块通过简单的多尺度池化聚合方式，难以有效建立树干结构的长距离空间依赖关系，导致特征表达能力受限。本文使用MLKA模块替换原有的SPPF模块，以增强网络对树干特征的提取能力。改进的YOLO v8模型结构如图1所示。
MLKA模块的核心在于结合大核注意力机制（Large kernel attention，LKA）与分组多尺度策略来捕获图像中的长距离依赖关系[25]。LKA机制通过将计算成本高昂的大核卷积分解为深度卷积、深度空洞卷积和逐点卷积3个步骤，高效地构建了长距离像素间的关联。
为进一步增强模型的表达能力，MLKA模块引入了分组多尺度机制：首先将输入特征图沿通道维度划分为3组，随后对于每组特征，分别执行由特定参数Ki（核大小）和di（空洞率）定义的LKA操作，使网络能并行地关注到从局部纹理到全局结构的不同粒度特征。
考虑到不同尺度特征的重要性可能随输入图像内容动态变化，并且为了缓解空洞卷积可能带来的阻断效应，MLKA模块还整合了门控聚合单元。该单元利用一个小型深度卷积为每个LKA分支生成相应的空间门控图，并通过将门控图Gi与LKA输出LKAi进行逐元素相乘，实现对各尺度注意力图的自适应重新校准。这种机制允许网络根据输入内容动态调整各尺度特征的权重，例如利用大感受野分支关注长距离依赖，同时借助小感受野分支保留精细的局部细节。
1.2　多帧特征点融合
本文将改进YOLO v8模型检测到的树干锚框底边中心点作为特征点，利用单侧树行的树干特征点拟合出树行线。多帧特征点融合机制的核心是利用视频序列的时间连续性，累积多帧图像中检测到的特征点，避免单帧图像中特征点不足或缺失导致树行线拟合失败。维护一个固定长度的特征点集队列，该队列存储过去n帧图像内检测到的所有特征点坐标。每处理一帧新的图像，其检测到的特征点集被添加到队列中，同时最早一帧的所有特征点被移除，从而保持队列长度不变。多帧特征点队列的数学表示式为
式中
      Pt——当前帧t检测到的m个特征点坐标
      ——当前帧t检测到的第i个特征点坐标
      Phistory——保留的n帧历史特征点坐标集合
      n——保留的历史帧数
在特征点融合处理上，采用直接合并的方法，将队列中n帧图像检测到的所有特征点坐标整合为统一的特征点集合，并作为RANSAC树行线拟合算法的输入。
1.3　基于RANSAC的树行线拟合
本文采用RANSAC算法并结合最小二乘法拟合两侧树行线。RANSAC算法的核心原理是通过迭代采样，区分特征点中的内点（符合模型的数据）和外点（异常点），从而在噪声干扰下找到最优模型。首先根据输入图像将检测到的特征点划分为左右2个区域。对于每个区域的特征点，应用RANSAC算法滤除异常点。使用该算法时距离阈值设为10像素，迭代次数设置为100次。在每次迭代中，算法随机选取2个特征点构建一条候选直线，然后计算该区域所有特征点到这条直线的距离，将距离小于阈值的点标记为内点。经过S次迭代后，选取拥有最多内点支持的候选直线作为最优模型。最后，利用筛选出的所有内点，通过最小二乘法计算树行拟合线的参数。具体实现算法为
1.4　导航线生成
根据左右两侧拟合的树行线参数，通过计算这2条直线的角平分线可以生成导航线。为便于计算，将这2条直线的参数表示为归一化的方向向量和线上一点的形式，公式为
式中
      Lleft——左侧树行线
      vxl——左侧树行线方向向量的水平分量
      vyl——左侧树行线方向向量的垂直分量
      x0l——左侧树行线上一点的x坐标
      y0l——左侧树行线上一点的y坐标
      Lright——右侧树行线
      vxr——右侧树行线方向向量的水平分量
      vyr——右侧树行线方向向量的垂直分量
      x0r——右侧树行线上一点的x坐标
      y0r——右侧树行线上一点的y坐标
式中的方向向量均已满足归一化条件。
首先计算左右2条树行线的交点，作为导航线的参考点。交点计算时需要考虑两侧树行线位置关系的多种情形，当2条线都是斜线时，将它们转换为斜率-截距形式，计算公式为
式中
      kl——左侧树行线的斜率
      bl——左侧树行线的截距
      kr——右侧树行线的斜率
      br——右侧树行线的截距
通过解方程组可得交点坐标
式中
      xintersection——左右树行线交点的x坐标
      yintersection——左右树行线交点的y坐标
当左右两侧树行线方向向量的点积绝对值大于0.99时，两树行线近似平行，判定此时不存在交点，取2条树行线的中心线作为导航线。在图像坐标系中随机选取一个参考点yref，计算该y坐标下左右树行线上的对应点xl和xr，然后取其中点（xmid，yref）作为导航线上的参考点，表达式为
式中
      yref——选取的参考点y坐标
      xmid——参考点的x坐标
对于一条垂直线与一条斜线相交的情况，直接使用垂直线的x坐标，代入斜线方程求得y坐标。确定交点后，通过计算角平分线生成导航线。角平分线向量通过左右树行线方向向量相加并归一化获得，计算式为
式中
      vnav——导航线的方向向量
      vl——左侧树行线的方向向量
      vr——右侧树行线的方向向量
      vxnav——导航线方向向量的水平分量
      vynav——导航线方向向量的垂直分量
最终导航线使用斜率-截距式方程表示为
式中
      knav——导航线的斜率
      bnav——导航线的截距
当水平分量的绝对值小于10-5时，则使用垂直线形式x=xintersection表示。
针对特殊情况，如当前帧仅检测到单侧树行的特征点时，利用多帧特征点融合机制，通过队列中前几帧的历史特征点数据，按照1.3节的拟合流程，对缺失的树行进行线性拟合，最终通过计算左右两侧拟合线的角平分线生成导航线。
2　实验与结果分析
收起
2.1　图像采集与数据集制作
于2024年9—11月在北京市大兴区庞各庄镇赵村的梨园内采集数据，分为静态图像采集和动态视频采集2个阶段。为增强模型的泛化能力，选择在晴朗、多云、阴天等多种天气条件下，使用分辨率为1 920像素×1 080像素的摄像设备进行图像和视频数据采集。并设计了覆盖全天不同光照条件的采集方案，分别在早晨、中午和傍晚3个时间段获取顺光、逆光、强光、弱光等数据样本。同时，采集范围涵盖了多种复杂场景，包括树干被地面杂草或自身枝叶部分遮挡、强烈阳光直射在树干上形成高光区域、树干与背景颜色或纹理相近等场景。
静态图像采集阶段手持摄像设备进行相对静止的图像采集工作，采集过程中，摄像设备保持在距离地面约0.8 m的高度。在获取原始图像后，对样本进行了筛选，剔除了模糊、过度曝光等不合格图像，最终保留了742幅高质量的图像用于模型训练。为保持数据真实性，所有图像均保持原始分辨率，未进行额外的尺寸调整或数据增强处理。使用标注工具JieLabel 6.2.0对梨树树干进行了边界框标注。按照比例7∶2∶1将数据集随机划分为训练集、验证集和测试集。
动态视频采集阶段将摄像设备安装于作业机械上，在树行间以正常作业速度移动并录制连续的视频数据。从视频中按一定间隔提取关键帧，获得包含因相机位移影响导致的视角连续变化、光照快速波动的图像样本，用于后续验证模型在实际农机作业环境中检测的准确性以及导航线生成的稳定性。
2.2　模型训练
本文的模型训练在台式计算机上完成，运行环境为Windows 11（64位）操作系统，硬件配置为NVIDIA RTX 4060 GPU（8 GB显存），Intel i5-12600KF CPU（16 GB运行内存）。软件环境采用PyTorch 2.5.1的深度学习框架，搭配CUDA 12.6实现GPU加速。
模型训练的总周期（epochs）设置为400，批处理大小为56，初始学习率为0.01。为提高训练初期的稳定性，引入了学习率预热策略。优化算法选用带动量的随机梯度下降（SGD）方法，其中动量因子设置为0.937，以加快模型收敛，权重衰减系数设置为0.000 5，以抑制过拟合现象。
2.3　模型的评估指标
为了评估改进后模型在梨树树干检测任务中的性能表现，本文将精确率、召回率和平均精度均值作为核心评估指标，并分别赋予0.3、0.2和0.5的权重以筛选出最佳模型。
表1对比了原始YOLO v8模型与改进的YOLO v8模型在梨树树干数据集上的检测性能。分析结果显示，改进模型的检测性能在各项性能指标上均有显著提升。精确率提升3.2个百分点，表明模型的误检率降低，能够更准确地识别树干；召回率提升5.6个百分点，表明模型能够检测到更多真正的树干；平均精度均值提升2.5个百分点，综合反映了改进模型在不同IoU阈值下的整体检测性能得到提升。
图2展示了原始模型与改进模型在同一测试样本上的检测结果对比。从图2可看出改进模型在树干检测任务中生成的置信度分数整体高于原始模型。
为进一步验证改进模型在不同环境中的泛化能力，在测试集之外的其他梨园环境中进行了对比验证实验。如图3所示，在正常光照条件下，原始模型与改进模型均能有效识别出大部分树干。但改进模型在树干检测过程中性能更好，生成的类别置信度分数普遍高于原始模型。
如图4所示，在阴天环境中，自然光线相对暗淡且分布均匀，树干与背景之间的对比度有所下降。在此条件下，原始模型有树干检测类别置信度偏低和漏检的问题，而改进模型在阴天环境中不仅保持了较高的检测能力，类别置信度也明显高于原始模型。
如图5所示，在强光照射条件下，光线过强可能导致树干与背景的对比度降低。在此场景下，原始模型不仅存在明显的类别置信度偏低问题且有误检情况。相比之下，改进模型表现出更强的光照适应能力，维持了较高的检测准确率且抑制了误检现象。
如图6所示，在弱光环境中，原始模型特征提取能力上表现出明显的局限性，部分树干的检测类别置信度普遍较低且存在漏检现象。相比之下，改进模型能够准确地识别出树干，且类别置信度显著提高。
如图7所示，在存在地面杂草、树干被藤蔓缠绕或被自身叶片遮挡的复杂梨园环境中，虽然2种模型均能识别出树干，但原始模型在相同目标上的检测类别置信度显著低于改进模型。
综上，在光照不均、部分树干被遮挡以及树干与背景颜色相近的复杂场景下，改进模型均表现出更好的检测性能。
2.4　多帧特征点融合与RANSAC算法效果分析
本文对是否采用多帧特征点融合机制和RANSAC降噪算法的效果进行了比较分析。对以下4种组合方式进行了比较：①降噪前单帧（Single frame before denoising，SFBD），该组合方式根据当前帧图像检测到的特征点进行树行线拟合，不使用RANSAC算法进行降噪处理。②降噪前多帧（Multi-frame before denoising，MFBD），该组合方式融合并利用连续多帧图像检测到的特征点，不使用RANSAC算法进行降噪处理。③降噪后单帧（Single frame after denoising，SFAD），该组合方式基于当前帧图像检测到的特征点，使用RANSAC算法降噪处理后再进行树行线的拟合。④降噪后多帧（Multi-frame after denoising，MFAD），该组合方式同时采用多帧特征点融合机制和RANSAC算法对特征点进行树行线的拟合。
图8对比了SFBD组合方式与MFBD组合方式处理后的特征点分布及生成的导航线。在SFBD组合方式下，左侧树行特征点的数量不足，无法有效拟合出树行线，导致导航线生成失败。采用多帧特征点融合机制后，通过累积连续5帧的检测结果，显著增加了两侧树行的特征点数，即使单帧检测存在漏检，也有足够的特征点进行树行线的拟合。
图9比较了是否采用RANSAC降噪算法在树行线拟合中的效果。在降噪前（图9a），特征点中包含来自目标树行的特征点（蓝点）以及其他树行的干扰特征点（红点），这些噪点严重干扰了树行线的拟合过程，导致生成的导航线（红线）明显偏离实际的树行中心。经过RANSAC降噪处理后（图9b），有效滤除了非目标树行的干扰点，保留了属于两侧树行的内点，两侧树行线的拟合更加准确。
图10展示了在极端条件下，同时应用多帧特征点融合与RANSAC降噪的效果。在SFBD组合方式（图10a）下，左侧树行因无法检测到有效特征点，导致无法生成树行线；同时右侧树行受其他行特征点影响，树行线拟合精度不足，最终无法生成导航线。应用多帧特征点融合机制和RANSAC降噪算法后（图10b），左侧区域累积了足够的特征点进行树行线的拟合，同时有效剔除了右侧区域的干扰点，最终导航线（黄色线）精确地生成于树行中心位置。
为了评估4种组合方式生成导航线的精度，随机选取了35个测试样本，手动标注参考导航线，并对每种组合方式生成的导航线与参考导航线之间的偏差进行分析。手动标注参考导航线的具体方法为：在每个测试样本图像上，选择清晰可见的树干底部中点作为特征点，并通过最小二乘法分别拟合出左右树行线，然后计算两侧树行线的角平分线作为参考导航线。
基于手动标注的参考导航线，采用角度偏差、位置偏差和均方根偏差（RMSE）作为导航线生成精度的评估指标。
角度偏差反映了生成导航线与参考导航线在方向上的差异，其计算公式为
式中
      θdev——角度偏差，（°）
      vref——参考导航线的单位方向向量
位置偏差用于衡量生成导航线与参考导航线之间的距离差异，通过计算2条导航线在图像中间高度处的水平距离来实现，其计算公式为
式中
      dpos——位置偏差，像素
      xnavmid——生成导航线在图像中间高度处的x坐标，像素
      xrefmid——参考导航线在图像中间高度处的x坐标，像素
均方根偏差综合考虑了角度偏差和位置偏差，能够更全面地评估导航线的整体质量。考虑到角度偏差和位置偏差具有不同的量纲和数值尺度，对两类偏差进行归一化处理。为在不同方法间建立公平的对比基准，本文采用动态归一化策略，针对每一个测试样本动态选取4种方法在该样本上的最大偏差作为归一化基准，将其映射到相同的数值区间，然后再计算均方根偏差，计算公式为
式中
      θmax——同一测试样本在不同方法下观测到的最大角度偏差，（°）
      dmax——同一测试样本在不同方法下观测到的最大位置偏差，像素
      θnorm——归一化后的角度偏差
      dnorm——归一化后的位置偏差
      RMSE——均方根偏差
图11展示了4种组合方式生成的导航线与参考导航线在35个样本中的角度偏差比较。从图11可以看出，MFAD组合方式的角度偏差在所有样本中始终保持在较低水平，且波动最小，稳定性更好；相比之下，SFBD和SFAD组合方式的角度偏差较大且波动剧烈；MFBD组合方式则介于两者之间，表明多帧特征点融合机制能在一定程度上减轻角度波动，但缺乏有效的异常点过滤机制，其稳定性提升仍然有限。
图12展示了4种组合方式生成的导航线与参考导航线之间的位置偏差比较。从图12可知，MFAD组合方式生成的导航线在绝大多数的样本中的偏差显著低于其他3种组合方式。
图13展示了4种组合方式生成的导航线与参考导航线之间的均方根偏差对比。结果显示，MFAD组合方式生成的导航线几乎在所有样本中均方根偏差最小。
表2为35个测试样本使用4种组合方式的平均偏差比较。从表2可以看出，MFAD组合方式的3项指标均优于其他3种组合方式：角度偏差均值、位置偏差均值和均方根偏差均值分别比SFBD组合方式降低5.65°、205.98像素和0.53。
3　结论
收起
（1）本文提出了一种基于改进YOLO v8模型的梨园行间导航线生成方法，有效提升了模型在光照变化、杂草遮挡等复杂梨园环境中对树干特征的感知与检测能力。实验结果显示，改进模型的精确率、召回率和平均精度均值相较于原始模型分别提高3.2、5.6、2.5个百分点，减少了检测过程中出现的误检、漏检现象。
（2）设计了多帧特征点融合机制，并结合RANSAC算法对特征点进行降噪，应用最小二乘法对两侧树行进行拟合，最终根据两侧树行线的角平分线生成导航线。实验表明，本文提出的方法在所有评估指标上均取得了最佳效果，角度偏差均值为1.17°，位置偏差均值为20.40像素，均方根偏差均值为0.27。本文提出的方法能够有效提升梨园导航线生成的精度和稳定性。
（3）本文方法仍存在一定局限性。首先，RANSAC算法基于随机采样的特性可能无法保证全局最优，在特征点分布极不均匀时可能影响拟合精度，目前实验精度满足工程需求。此外，本文实验主要基于梨园环境进行实验研究，对于其他果树品种和种植模式的适应性有待进一步验证。
基金
收起
  • 国家自然科学基金面上项目(61973040)
  • 北京石油化工学院国家级大学生创新创业训练计划项目(2025J00250)
文献
收起
参考文献 引证文献
排序方式：
[1]
刘成良, 贡亮, 苑进, 等. 农业机器人关键技术研究现状与发展趋势[J]. 农业机械学报, 2022, 53(7): 1-22, 55.
LIU Chengliang, GONG Liang, YUAN Jin, et al. Current status and development trends of agricultural robots[J]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(7): 1-22, 55. (in Chinese)
[2]
窦汉杰, 陈震宇, 翟长远, 等. 果园智能化作业装备自主导航技术研究进展[J]. 农业机械学报, 2024, 55(4): 1-22.
DOU Hanjie, CHEN Zhenyu, ZHAI Changyuan, et al. Research progress on autonomous navigation technology for orchard intelligent equipment[J]. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55(4): 1-22. (in Chinese)
[3]
ZHOU J, GENG S, QIU Q, et al. A deep-learning extraction method for orchard visual navigation lines[J]. Agriculture, 2022, 12(10): 1650.
[4]
XIE B, JIN Y, FAHEEM M, et al. Research progress of autonomous navigation technology for multi-agricultural scenes[J]. Computers and Electronics in Agriculture, 2023, 211: 107963.
[5]
朱立成, 韩振浩, 赵博, 等. 基于VINS-MONO和改进YOLO v4-Tiny的果园自主寻筐方法[J]. 农业机械学报, 2023, 54(8): 97-109.
ZHU Licheng, HAN Zhenhao, ZHAO Bo, et al. Autonomous basket searching method for orchards transporter based on VINS-MONO and improved YOLO v4-Tiny[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(8): 97-109. (in Chinese)
[6]
应仇凯, 程泓超, 马锃宏, 等. 基于YOLO v8-Seg的地栽草莓采摘机器人垄面视觉导航控制方法[J]. 农业机械学报, 2024, 55(增刊1): 9-17.
YING Qiukai, CHENG Hongchao, MA Zenghong, et al. Ridge visual navigation control method for ground-planted strawberry picking robots based on YOLO v8-Seg algorithm[J]. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55(Supp. 1): 9-17. (in Chinese)
[7]
吴城, 李晓娟. 基于单线激光的果园机器人自主导航方法[J]. 江苏大学学报(自然科学版), 2023, 44(5): 530-539.
WU Cheng, LI Xiaojuan. Autonomous navigation method of orchard robot based on single laser[J]. Journal of Jiangsu University (Natural Science Edition), 2023, 44(5): 530-539. (in Chinese)
[8]
YUE B, ZHANG Z, ZHANG W, et al. Design of an automatic navigation and operation system for a crawler-based orchard sprayer using GNSS positioning[J]. Agronomy, 2024, 14(2): 271.
[9]
CHEN S, ZHANG M, LI X, et al. Precision agriculture intelligent connection network based on visual navigation[J]. IET Networks, 2023, 12(4): 167-178.
[10]
NAKAGUCHI V M, ABEYRATHNA R M R D, LIU Z, et al. Development of a machine stereo vision-based autonomous navigation system for orchard speed sprayers[J]. Computers and Electronics in Agriculture, 2024, 227: 109669.
[11]
ZHANG S, GUO C, GAO Z, et al. Research on 2D laser automatic navigation control for standardized orchard[J]. Applied Sciences, 2020, 10(8): 2763.
[12]
毕盛, 杨礼铭, 董敏, 等. 语言视觉激光多模态融合的机器人导航方法[J]. 小型微型计算机系统, 2025, 46(8): 1809-1817.
BI Sheng, YANG Liming, DONG Min, et al. Robot navigation based on multi-modal fusion of language vision LiDAR[J]. Journal of Chinese Computer System, 2025, 46(8): 1809-1817. (in Chinese)
[13]
WANG S, SONG J, QI P, et al. Design and development of orchard autonomous navigation spray system[J]. Frontiers in Plant Science, 2022, 13: 960686.
[14]
彭顺正, 坎杂, 李景彬. 矮化密植枣园收获作业视觉导航路径提取[J]. 农业工程学报, 2017, 33(9): 45-52.
PENG Shunzheng, KAN Za, LI Jingbin. Extraction of visual navigation directrix for harvesting operation in short-stalked and close-planting jujube orchard[J]. Transactions of the CSAE, 2017, 33(9): 45-52. (in Chinese)
[15]
冯凯, 王茂励, 何晓宁, 等. 基于辅助线的农机视觉导航路径提取算法研究[J]. 中国农机化学报, 2022, 43(10): 167-175.
FENG Kai, WANG Maoli, HE Xiaoning, et al. Research on visual navigation path extraction algorithm for agricultural machinery based on auxiliary lines[J]. Journal of Chinese Agricultural Mechanization, 2022, 43(10): 167-175. (in Chinese)
[16]
ZHONG W, YANG W, ZHU J, et al. An improved UNet-based path recognition method in low-light environments[J]. Agriculture, 2024, 14(11): 1987.
[17]
卢心缘, 赵华民, 任锐, 等. 基于YOLO v5s-seg的非结构化枣园视觉导航路径提取[J]. 南京农业大学学报, 2024, 47(6): 1241-1250.
LU Xinyuan, ZHAO Huamin, REN Rui, et al. Unstructured jujube garden visual navigation path extraction based on YOLO v5s-seg[J]. Journal of Nanjing Agricultural University, 2024, 47(6): 1241-1250. (in Chinese)
[18]
韩振浩, 李佳, 苑严伟, 等. 基于U-Net网络的果园视觉导航路径识别方法[J]. 农业机械学报, 2021, 52(1): 30-39.
HAN Zhenhao, LI Jia, YUAN Yanwei, et al. Path recognition of orchard visual navigation based on U-Net[J]. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(1): 30-39. (in Chinese)
[19]
张伟荣, 陈学庚, 齐江涛, 等. 基于深度学习和高斯过程回归的玉米冠下视觉导航路径提取方法[J]. 农业机械学报, 2024, 55(7): 15-26.
ZHANG Weirong, CHEN Xuegeng, QI Jiangtao, et al. Deep learning and gaussian process regression based path extraction for visual navigation under canopy[J]. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55(7): 15-26. (in Chinese)
[20]
肖珂, 夏伟光, 梁聪哲. 复杂背景下果园视觉导航路径提取算法[J]. 农业机械学报, 2023, 54(6): 197-204, 252.
XIAO Ke, XIA Weiguang, LIANG Congzhe. Visual navigation path extraction algorithm in orchard under complex background[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(6): 197-204, 252. (in Chinese)
[21]
YANG Z, OUYANG L, ZHANG Z, et al. Visual navigation path extraction of orchard hard pavement based on scanning method and neural network[J]. Computers and Electronics in Agriculture, 2022, 197: 106964.
[22]
许贞辉, 李晓娟. 果园树干检测与导航线拟合算法研究[J]. 中国农机化学报, 2024, 45(8): 217-222.
XU Zhenhui, LI Xiaojuan. Research on tree trunk detection and navigation line fitting algorithm in orchard[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(8): 217-222. (in Chinese)
[23]
彭书博, 陈兵旗, 李景彬, 等. 基于改进YOLOv7的果园行间导航线检测[J]. 农业工程学报, 2023, 39(16): 131-138.
PENG Shubo, CHEN Bingqi, LI Jingbin, et al. Detection of the navigation line between lines in orchard using improved YOLOv7[J]. Transactions of the CSAE, 2023, 39(16): 131-138. (in Chinese)
[24]
CAO Z, GONG C, MENG J, et al. Orchard vision navigation line extraction based on YOLO v8-trunk detection[J]. IEEE Access, 2024, 12: 104126-104137.
[25]
WANG Y, LI Y, WANG G, et al. Multi-scale attention network for single image super-resolution[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024: 5950-5960.
2025年第56卷第12期
PDF下载
203
96
引用本文
BibTeX
文章信息
doi: 10.6041/j.issn.1000-1298.2025.12.060
  • 接收时间：2025-05-15
  • 首发时间：2026-09-30
  • 出版时间：2025-12-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期：2025-05-15
  • 修回日期：2025-07-10
基金
国家自然科学基金面上项目(61973040)
北京石油化工学院国家级大学生创新创业训练计划项目(2025J00250)
作者信息
    1.北京石油化工学院信息工程学院，北京　102617
    2.北京农学院智能科学与工程学院，北京　102206
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/nyjxxb/CN/10.6041/j.issn.1000-1298.2025.12.060
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family		 属数
Number of
genus		 种数
Number of
species		 占总种数比例
Percentage of
total species (%)		 属
Genus		 种数
Number of
species		 占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
相关链接
论文
最新文章
热读文章
热点专题
内参
蓝皮书
产业发展报告
传播力报告
期刊分级目录
资讯
学术新闻
行业新闻
学术会议
行业会议
关于
关于我们
联系我们
北京市海淀区学院南路86号
100081
010-62662699（运营及技术支持）
qkjq@cast.org.cn

中国科学技术协会版权所有 京ICP 备10216604号-4 海淀分局备案 1101084647
科技导报社主办 中国科协信息中心技术支持