Article(id=1297211800668369574, tenantId=1146029695717560320, journalId=1296125453100220459, issueId=1297211624738284246, articleNumber=null, orderNo=null, doi=10.11975/j.issn.1002-6819.202601133, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1768492800000, receivedDateStr=2026-01-16, revisedDate=1775059200000, revisedDateStr=2026-04-02, acceptedDate=null, acceptedDateStr=null, onlineDate=1787208994309, onlineDateStr=2026-08-20, pubDate=1782748800000, pubDateStr=2026-06-30, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1787208994309, onlineIssueDateStr=2026-08-20, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1787208994309, creator=13701087609, updateTime=1787208994309, updator=13701087609, issue=Issue{id=1297211624738284246, tenantId=1146029695717560320, journalId=1296125453100220459, year='2026', volume='42', issue='12', pageStart='1', pageEnd='396', issueExtLink='null', onlineDate='null', pubDate='1782748800000', pubDateStr='2026-06-30', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1787208952364, creator='13701087609', updateTime=1787212261177, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1297225503002357852, tenantId=1146029695717560320, journalId=1296125453100220459, issueId=1297211624738284246, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1297225503002357853, tenantId=1146029695717560320, journalId=1296125453100220459, issueId=1297211624738284246, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=204, endPage=215, ext={EN=ArticleExt(id=1297211800844530343, articleId=1297211800668369574, tenantId=1146029695717560320, journalId=1296125453100220459, language=EN, title=Effects of coppicing surface quality on sprouting regeneration of Caragana korshinskii, columnId=1297211683278189232, journalTitle=Transactions of the Chinese Society of Agricultural Engineering, columnName=Agricultural Information and Electrical Technologies, runingTitle=null, highlight=null, articleAbstract=

Quantitative evaluation standards are often required to accurately predict sprouting regeneration, particularly for cutting quality. However, the coppicing surface targets cannot be recognized in complex fields during Caragana korshinskii shrub coppicing in the arid regions of Northwest China. In this study, a quantitative evaluation was proposed for sprouting regeneration, according to the synergistic association between cutting morphologies and agronomic traits. Accurate recognition of coppicing surfaces was achieved in unstructured field environments. A segmentation network was constructed, named WoodGrainNet. Firstly, the global context modelling and target localization were enhanced via a semantic stream using a lightweight Transformer architecture. Secondly, a frequency-domain stream was incorporated with the Haar discrete wavelet transform to effectively suppress abiotic background interference for the texture representation of the targets. Simultaneously, a shape stream was combined with a differentiable Sobel operator. Explicit constraints were also applied to high-frequency gradient regions. Thereby, the adjacent cut boundaries were delineated to effectively alleviate the adhesion of dense targets. Three-stream features were synergistically simulated for the deep integration. The WoodGrainNet significantly improved the segmentation robustness and instance discrimination of the improved model in complex scenes, particularly at the level of underlying physical feature representation. Accurate segmentation was achieved to automatically extract a key geometric phenotypic indicator for coppicing quality—coppicing surface circularity (C). Accordingly, the coppicing quality grading and sprouting prediction were established after evaluation. The experimental results demonstrate that the better performance of WoodGrainNet was achieved to balance high accuracy and real-time processing, with a mean Intersection over Union (mIoU) of 86.99% and an inference speed of 51.78 frames/s. The performance was significantly superior to mainstream networks, such as DeepLabV3+, effectively recognizing tiny coppicing targets. In terms of agronomic analysis, statistical results revealed that there was a significant positive correlation between the morphological quality of the coppicing surface and the sprouting potential of lateral branches. Notably, the coefficient of determination (R²) between the coppicing surface circularity (C) and the number of lateral branch sprouts reached 0.764 at the 5th week (N). The circularity served as an important morphological indicator to evaluate coppicing quality and sprouting regeneration. Field tests were conducted to verify its feasibility for engineering applications. The improved model was deployed on a mobile intelligent system. A discrimination accuracy of 90.8% was achieved for coppicing quality grades under mobile working conditions. Sprouting prediction trend was highly consistent with the measured ones, indicating its potential to replace manual inspection and subjective empirical judgment. The pixel-level phenotypic analysis of the coppicing surface was effectively transformed to predict the single-plant regeneration. The finding can provide a theoretical basis and technical support for the quality evaluation, parameter monitoring, and precise detection of ecological shrub forests in arid regions.

, authors=Yaoyao GAO1, Hepeng ZHANG1, Lei YANG2, Aili QU1, Xuefei WEN3, Yutan WANG1, *, authorsList=Yaoyao GAO, Hepeng ZHANG, Lei YANG, Aili QU, Xuefei WEN, Yutan WANG, authorCompany=null, correspAuthors=Yutan WANG, authorNote=null, correspAuthorsNote=null, copyrightStatement=Copyright © 2026 Transactions of the Chinese Society of Agricultural Engineering., 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=1297211805105943240, articleId=1297211800668369574, tenantId=1146029695717560320, journalId=1296125453100220459, language=CN, title=柠条平茬面质量对其萌蘖再生能力的量化分析, columnId=1297211683441767090, journalTitle=农业工程学报, columnName=农业信息与电气技术, runingTitle=null, highlight=null, articleAbstract=

针对中国西北干旱区柠条灌木平茬作业中切割质量缺乏客观量化评价、萌蘖再生能力难以预测等问题,该研究提出了一种基于切割形态特征与农艺性状协同关联的柠条平茬萌蘖能力的量化方法,并构建了适用于野外非结构化环境的平茬面分割网络WoodGrainNet。该网络融合语义特征提取分支、频域感知分支和形状约束分支并配合特征融合策略,实现复杂背景及密集茬口条件下柠条平茬面的精准分割。结果表明,WoodGrainNet网络在兼顾实时性的同时,平均交并比达到86.99%,推理速度达到51.78帧/s。基于分割结果,自动提取反映平茬质量的关键农艺指标——平茬面圆度(C)。相关分析结果表明,平茬面圆度与第5周侧枝萌蘖数(N)的线性关系呈正相关性,表明圆度可作为评价柠条平茬质量及萌蘖再生能力的形态学指标。在此基础上,将轻量化模型部署于移动式智能评估系统,并通过田间试验验证了其实用性,系统对平茬质量等级的判别准确率达到90.8%。该研究实现了由平茬面像素级表型解析向单株再生能力预测的转化,为干旱区生态灌木林机械化抚育质量评价与精准管理提供了技术支撑。

, authors=高垚垚1, 张鹤篷1, 杨蕾2, 曲爱丽1, 温学飞3, 王昱潭1, *, authorsList=高垚垚, 张鹤篷, 杨蕾, 曲爱丽, 温学飞, 王昱潭, authorCompany=null, correspAuthors=王昱潭, authorNote=

高垚垚,博士,讲师,硕士生导师,研究方向为农业机械设计与智能农业装备。Email:

, correspAuthorsNote=
王昱潭,博士,博士生导师,研究方向为现代农业装备与智慧农业。Email:
, copyrightStatement=版权所有 © 2026 农业工程学报编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=WzjhjRP0X2UsAy25CtgBAA==, magXml=ziQwMssbFyk0dmzZuSSOaw==, pdfUrl=null, pdf=uAQfc5EvJTADhJNvC7swvw==, pdfFileSize=9140978, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=4GLqUUPkp6wGrlUXi+x4vA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=qqJBTx/6bQq/nXuW7rMfOA==, mapNumber=null, fund=null)}, authors=[Author(id=1299828221827113648, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=Gaoyy@nxu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1299828221915194034, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828221827113648, language=EN, stringName=Yaoyao GAO, firstName=Yaoyao, middleName=null, lastName=GAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Mechanical Engineering, Ningxia University, Yinchuan 750021, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828221994885811, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828221827113648, language=CN, stringName=高垚垚, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1宁夏大学机械工程学院,银川 750021, bio={"content":"

高垚垚,博士,讲师,硕士生导师,研究方向为农业机械设计与智能农业装备。Email:

"}, bioImg=null, bioContent=

高垚垚,博士,讲师,硕士生导师,研究方向为农业机械设计与智能农业装备。Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828221550289574, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, xref=1, ext=[AuthorCompanyExt(id=1299828221562872487, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221550289574, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Mechanical Engineering, Ningxia University, Yinchuan 750021, China), AuthorCompanyExt(id=1299828221571261096, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221550289574, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1宁夏大学机械工程学院,银川 750021)])]), Author(id=1299828222070383285, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, 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=1299828222137492151, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828222070383285, language=EN, stringName=Hepeng ZHANG, firstName=Hepeng, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Mechanical Engineering, Ningxia University, Yinchuan 750021, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828222200406712, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828222070383285, language=CN, stringName=张鹤篷, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1宁夏大学机械工程学院,银川 750021, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828221550289574, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, xref=1, ext=[AuthorCompanyExt(id=1299828221562872487, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221550289574, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Mechanical Engineering, Ningxia University, Yinchuan 750021, China), AuthorCompanyExt(id=1299828221571261096, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221550289574, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1宁夏大学机械工程学院,银川 750021)])]), Author(id=1299828222271709882, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, 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=1299828222338818748, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828222271709882, language=EN, stringName=Lei YANG, firstName=Lei, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2Ningxia Helan Mountain National Nature Reserve Administration, Yinchuan 750021 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828222426899133, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828222271709882, language=CN, stringName=杨蕾, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2宁夏贺兰山国家级自然保护区管理局,银川 750021, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828221655147177, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, xref=2, ext=[AuthorCompanyExt(id=1299828221659341482, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221655147177, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Ningxia Helan Mountain National Nature Reserve Administration, Yinchuan 750021 China), AuthorCompanyExt(id=1299828221667730091, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221655147177, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2宁夏贺兰山国家级自然保护区管理局,银川 750021)])]), Author(id=1299828222498202303, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, 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=1299828222556922561, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828222498202303, language=EN, stringName=Aili QU, firstName=Aili, middleName=null, lastName=QU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Mechanical Engineering, Ningxia University, Yinchuan 750021, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828222619837122, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828222498202303, language=CN, stringName=曲爱丽, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1宁夏大学机械工程学院,银川 750021, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828221550289574, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, xref=1, ext=[AuthorCompanyExt(id=1299828221562872487, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221550289574, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Mechanical Engineering, Ningxia University, Yinchuan 750021, China), AuthorCompanyExt(id=1299828221571261096, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221550289574, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1宁夏大学机械工程学院,银川 750021)])]), Author(id=1299828222686945988, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, 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=1299828222758249158, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828222686945988, language=EN, stringName=Xuefei WEN, firstName=Xuefei, middleName=null, lastName=WEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3Institute of Forestry and Grassland Ecology, Ningxia Academy of Agriculture and Forestry Sciences, Yinchuan 750002, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828222833746631, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828222686945988, language=CN, stringName=温学飞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3宁夏农林科学院林业与草业生态研究所,银川 750002, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828221751616172, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, xref=3, ext=[AuthorCompanyExt(id=1299828221755810477, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221751616172, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Institute of Forestry and Grassland Ecology, Ningxia Academy of Agriculture and Forestry Sciences, Yinchuan 750002, China), AuthorCompanyExt(id=1299828221764199086, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221751616172, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3宁夏农林科学院林业与草业生态研究所,银川 750002)])]), Author(id=1299828222913438409, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wang_yt1108@163.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1299828222984741579, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828222913438409, language=EN, stringName=Yutan WANG, firstName=Yutan, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1School of Mechanical Engineering, Ningxia University, Yinchuan 750021, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828223056044748, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828222913438409, language=CN, stringName=王昱潭, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1宁夏大学机械工程学院,银川 750021, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828221550289574, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, xref=1, ext=[AuthorCompanyExt(id=1299828221562872487, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221550289574, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Mechanical Engineering, Ningxia University, Yinchuan 750021, China), AuthorCompanyExt(id=1299828221571261096, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221550289574, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1宁夏大学机械工程学院,银川 750021)])])], keywords=[Keyword(id=1299828223198651085, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, orderNo=1, keyword=Caragana korshinskii.), Keyword(id=1299828223261565646, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, orderNo=2, keyword=coppice shoot), Keyword(id=1299828223332868815, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, orderNo=3, keyword=image segmentation), Keyword(id=1299828223395783376, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, orderNo=4, keyword=WoodGrainNet), Keyword(id=1299828223462892241, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, orderNo=5, keyword=stubble cutting quality evaluation), Keyword(id=1299828223530001106, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, orderNo=1, keyword=柠条), Keyword(id=1299828223580332755, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, orderNo=2, keyword=萌蘖), Keyword(id=1299828223655830228, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, orderNo=3, keyword=图像分割), Keyword(id=1299828223718744789, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, orderNo=4, keyword=WoodGrainNet), Keyword(id=1299828223777465046, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, orderNo=5, keyword=平茬质量评价)], refs=[Reference(id=1299828226960941825, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=GAO Y Y, WANG Y T, QU A L, et al. Study of sawing parameters for Caragana korshinskii (C. K. ) branches[J]. Forests, 2022, 13(2): 327-327., articleTitle=null, refAbstract=null), Reference(id=1299828227036439298, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=CHE C, ZHANG M, YANG W, et al. Dissimilarity in radial growth and response to drought of Korshinsk peashrub (Caragana korshinskii Kom.) under different management practices in the western Loess Plateau[J]. Frontiers in Plant Science, 2024, 15: 1-11., articleTitle=null, refAbstract=null), Reference(id=1299828227099353859, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=WANG X Q, HUANG X Y, ZHANG Z C, et al. Effect of Caragana korshinskii Kom. as a partial substitution for sheep forage on intake, digestibility, growth, carcass features, and the rumen bacterial community[J]. Tropical Animal Health and Production, 2022, 54(3): 190., articleTitle=null, refAbstract=null), Reference(id=1299828227162268420, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=GAO Y Y, WANG Y T, KANG F, et al. Multi-objective optimization of cross-section integrity rate and sawing power consumption in sawing Caragana korshinskii Kom. branches[J]. Industrial Crops and Products, 2023, 193: 116244., articleTitle=null, refAbstract=null), Reference(id=1299828227229377285, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=王昱潭, 张加欣, 高垚垚, 等. 液压剪式柠条平茬机的设计与试验[J]. 农业工程学报, 2025, 41(14): 71-81., articleTitle=null, refAbstract=null), Reference(id=1299828227288097542, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=WANG Yutan, ZHANG Jiaxin, GAO Yaoyao, et al. Design and test of the hydraulic shear-type Caragana korshinski Kom. coppicing machine[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(14): 71-81. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828227346817799, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=苏飞保, 王振华, 翟改霞, 等. 柠条机械化收获技术与装备研究现状及发展趋势[J]. 农业工程, 2021, 11(10): 20-27., articleTitle=null, refAbstract=null), Reference(id=1299828227405538056, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=SU Feibao, WANG Zhenhua, ZHAI Gaixia, et al. Research status and development trend of Caragana korshinski mechanized harvesting technology and equipment[J]. Agricultural Engineering 2021(11): 20-27 (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828227481035529, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=JI W, LI J, BI Q, et al. Correction to: segment anything Is not always perfect: an investigation of SAM on different real-world applications[J]. Machine Intelligence Research, 2024, 21(6): 1215., articleTitle=null, refAbstract=null), Reference(id=1299828227556533002, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=WANG Y, YANG L, LIU X, et al. An improved semantic segmentation algorithm for high-resolution remote sensing images based on DeepLabv3[J]. Scientific Reports, 2024, 14(1): 60375., articleTitle=null, refAbstract=null), Reference(id=1299828227619447563, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=张睿, 王骞, 张延军, 等. 基于多任务分割与自适应压缩的黄花菜采摘点三维定位[J]. 农业工程学报, 2026, 42(4): 66-77., articleTitle=null, refAbstract=null), Reference(id=1299828227694945036, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHANG Rui, WANG Qian, ZHANG Yanjun, et al. Three-dimensional positioning of the picking points for daylilies based onmulti-task segmentation and adaptive compression[J]. Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE), 2026, 42(4): 66-77. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828227757859597, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=王发明, 周洁, 莫昊一, 等. 基于改进DeepLabv3+的收获机视角下小麦倒伏区域在线检测[J]. 农业工程学报, 2026: 455-463., articleTitle=null, refAbstract=null), Reference(id=1299828227816579854, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=WANG Faming, ZHOU Jie, MO Haoyi, et al. Online detection of wheat lodging area from the perspective of harvester based on improved DeepLabv3+[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2026, 455-463. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828227871105807, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=边振兴, 姚舒译, 刘晓雨, 等. 基于边缘感知DeepLabV3+模型的耕地系统生境类型识别方法[J]. 农业工程学报, 2025, 41(18): 280-290., articleTitle=null, refAbstract=null), Reference(id=1299828227938214672, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=BIAN Zhenxing, YAO Shuyi, LIU Xiaoyu, et al. Habitat type recognition method for cultivated land system based on edge perception DeepLabV3+ model[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(18): 280-290. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828228013712145, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=LEI L, YANG Q, YANG L, et al. Deep learning implementation of image segmentation in agricultural applications: a comprehensive review[J]. Artificial Intelligence Review, 2024, 57(1): 149., articleTitle=null, refAbstract=null), Reference(id=1299828228101792530, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=张羽丰, 杨景, 邓寒冰, 等. 基于RGB和深度双模态的温室番茄图像语义分割模型[J]. 农业工程学报, 2024, 40(2): 295-306., articleTitle=null, refAbstract=null), Reference(id=1299828228160512787, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHANG Yufeng, YANG Jing, DENG Hanbing, et al. Semantic segmentation model for greenhouse tomato images using RGB and depth bimodal[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(2): 295-306. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828228223427348, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=高垚垚. 柠条切割工艺参数优化及平茬装备研发[D]. 北京: 北京林业大学, 2023., articleTitle=null, refAbstract=null), Reference(id=1299828228277953301, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=GAO Yaoyao. Optimization of Caragana korshinskii Cutting Process Parameters and Development of Stubble-flattening Equipment [D]. Beijing: Beijing Forestry University, 2023., articleTitle=null, refAbstract=null), Reference(id=1299828228353450774, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=农业部农业机械试验鉴定总站. GB/T 5262-2008 农业机械 试验条件测定方法的一般规定[S]. 北京: 中国标准出版社, 2008., articleTitle=null, refAbstract=null), Reference(id=1299828228412171031, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=CHE C, ZHANG M, YANG W, et al. Dissimilarity in radial growth and response to drought of Korshinsk peashrub (Caragana korshinskii Kom.) under different management practices in the western Loess Plateau[J]. Frontiers in Plant Science, 2024, 151357472-1357472., articleTitle=null, refAbstract=null), Reference(id=1299828228479279896, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=LUO Z, YANG W, YUAN Y, et al. Semantic segmentation of agricultural images: A survey[J]. Information Processing in Agriculture, 2024, 11(2): 172-186., articleTitle=null, refAbstract=null), Reference(id=1299828228538000153, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=ZONG Z, GUO S, PEI X, et al. Semantic segmentation of Caragana korshinskii stubble in complex environments based on an improved DeepLabV3+ network[J]. Agriculture, 2024, 14(2): 226., articleTitle=null, refAbstract=null), Reference(id=1299828228600914714, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHAO S, XIN G, LIU Y, et al. Semantic segmentation of remote sensing rooftops based on DAnet-SegFormer[C]// Proceedings of the 2024 4th International Conference on Artificial Intelligence, Automation and Algorithms, 2024: 200-205., articleTitle=null, refAbstract=null), Reference(id=1299828228680606491, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=刘茜, 易诗, 李立, 等. 基于轻量级CNN-Transformer混合网络的梯田图像语义分割[J]. 农业工程学报, 2023, 39(13): 171-181., articleTitle=null, refAbstract=null), Reference(id=1299828228751909660, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=LIU Xi, YI Shi, LI Li, et al. Semantic segmentation of terrace image regions based on lightweight CNN-Transformer hybrid networks[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2023, 39(13): 171-181. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828228839990045, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=GUI B, BHARDWAJ A, SAM L. Evaluating the efficacy of segment anything model for delineating agriculture and urban green spaces in multiresolution aerial and spaceborne remote sensing images[J]. Remote Sensing, 2024, 16(2): 414., articleTitle=null, refAbstract=null), Reference(id=1299828228911293214, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=祝诗平, 林曦, 冯川, 等. 基于改进DeepLabv3+的马铃薯幼苗与杂草识别方法[J]. 农业工程学报, 2025, 41(10): 147-156., articleTitle=null, refAbstract=null), Reference(id=1299828228986790687, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHU Shiping, LIN Xi, FENG Chuan, et al. Potato seeding and weed identification based on improved DeepLabv3+[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(10): 147-156. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828229045510944, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=蒲应俊, 张文州, 李金广, 等. 基于改进U-Net与RGB-D图像的青花椒枝条“下桩”剪切点定位[J]. 农业工程学报, 2026, 42(1): 160-170., articleTitle=null, refAbstract=null), Reference(id=1299828229121008417, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=PU Yingjun, ZHANG Wenzhou, Ll Jinguang, et al. Locating the pile picking points for green pepper branches using improved U-Net and R GB-D images[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2026, 42(1): 160-170. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828229213283106, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=LI Y, WANG D, YUAN C, et al Enhancing agricultural image segmentation with an agricultural segment anything model adapter[J]. Sensors, 2023, 23(18): 7884., articleTitle=null, refAbstract=null), Reference(id=1299828229292974883, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=HE Y, LU Z, HUAN H. SF3Net: Frequency-domain enhanced segmentation network for high-resolution remote sensing imagery[J]. Remote Sensing, 2025, 17(22): 3734., articleTitle=null, refAbstract=null), Reference(id=1299828229368472356, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=向玉云, 陈思远, 高爽, 等. 基于自适应BayesShrink和频-空特征融合的作物病害识别方法[J]. 农业工程学报, 2025, 41 (06): 204-215., articleTitle=null, refAbstract=null), Reference(id=1299828229464941349, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=XIANG Yuyun, CHEN Siyuan. GAO Shuang. et al. Crop disease identification method based on adaptive BayesShrink and firequency-spatial feature fusion[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE)2025, 41(6): 204-215. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828229544633126, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=QIN Z, ZHANG P, WU F, et al. FcaNet: Frequency channel attention networks[C]// 2021 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway: IEEE, 2021: 763-772., articleTitle=null, refAbstract=null), Reference(id=1299828229603353383, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=LI Z P, HU J, WU K Y, MIAO J W, ZHAO Z X, WU J S. Local feature acquisition and global context understanding network for very high-resolution land cover classification[J]. Scientific Reports, 2024, 14: 12597., articleTitle=null, refAbstract=null), Reference(id=1299828229666267944, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHANG X, CHENG B, CHEN J, et al. High-resolution boundary refined convolutional neural network for automatic agricultural greenhouses extraction from GaoFen-2 satellite imageries[J]. Remote Sensing, 2021, 13(21): 4237., articleTitle=null, refAbstract=null), Reference(id=1299828229750154025, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=ODUNTAN Y A, STUBBS C J, ROBERTSON D J. High throughput phenotyping of cross-sectional morphology to assess stalk lodging resistance[J]. Plant Methods, 2022, 18(1): 1-15., articleTitle=null, refAbstract=null), Reference(id=1299828229838234410, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=POLIVANOVA O B, BEDAREV V A. Hyperhydricity in plant tissue culture[J]. Plants, 2022, 11(23): 3313., articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1299828221550289574, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, xref=1, ext=[AuthorCompanyExt(id=1299828221562872487, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221550289574, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Mechanical Engineering, Ningxia University, Yinchuan 750021, China), AuthorCompanyExt(id=1299828221571261096, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221550289574, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1宁夏大学机械工程学院,银川 750021)]), AuthorCompany(id=1299828221655147177, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, xref=2, ext=[AuthorCompanyExt(id=1299828221659341482, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221655147177, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Ningxia Helan Mountain National Nature Reserve Administration, Yinchuan 750021 China), AuthorCompanyExt(id=1299828221667730091, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221655147177, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2宁夏贺兰山国家级自然保护区管理局,银川 750021)]), AuthorCompany(id=1299828221751616172, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, xref=3, ext=[AuthorCompanyExt(id=1299828221755810477, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221751616172, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Institute of Forestry and Grassland Ecology, Ningxia Academy of Agriculture and Forestry Sciences, Yinchuan 750002, China), AuthorCompanyExt(id=1299828221764199086, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221751616172, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3宁夏农林科学院林业与草业生态研究所,银川 750002)])], figs=[ArticleFig(id=1299828223945237207, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Fig.1, caption=Overall situation of Caragana korshinskii base, figureFileSmall=VU72d6XzW/e+txruqN6Ekg==, figureFileBig=0OmR7Tjz71DQJPaD2SmUzw==, tableContent=null), ArticleFig(id=1299828223995568856, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=图1, caption=柠条基地整体情况, figureFileSmall=VU72d6XzW/e+txruqN6Ekg==, figureFileBig=0OmR7Tjz71DQJPaD2SmUzw==, tableContent=null), ArticleFig(id=1299828224104620761, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Fig.2, caption=Weekly growth dynamics of Caragana korshinskii during the sprouting process, figureFileSmall=fiJMy6TMMfH/zCUE7Tzj0g==, figureFileBig=YRXz8wJDwB9bBGow8A31rA==, tableContent=null), ArticleFig(id=1299828224163341018, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=图2, caption=柠条萌蘖过程每周的长势变化, figureFileSmall=fiJMy6TMMfH/zCUE7Tzj0g==, figureFileBig=YRXz8wJDwB9bBGow8A31rA==, tableContent=null), ArticleFig(id=1299828224230449883, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Fig.3, caption=Shape of Caragana korshinskii flat coppicing surface, figureFileSmall=YMtEmEUNaeZN8oZY+2kY0g==, figureFileBig=pfUTNBy1rkO0Etkcza75RQ==, tableContent=null), ArticleFig(id=1299828224310141660, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=图3, caption=柠条平茬面的形态, figureFileSmall=YMtEmEUNaeZN8oZY+2kY0g==, figureFileBig=pfUTNBy1rkO0Etkcza75RQ==, tableContent=null), ArticleFig(id=1299828224364667613, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Fig.4, caption=WoodGrainNet model architecture diagram, figureFileSmall=jMNqn+WuiPIaTNNCtuYs+Q==, figureFileBig=6sqG0SDwOxyS8glqRPtybg==, tableContent=null), ArticleFig(id=1299828224427582174, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=图4, caption=WoodGrainNet模型结构图

注:Transformer Blk为Transformer基本单元,$ H/4 $为将图片尺寸下采样为1/4,C1 Feat、C2 Feat为1/ 4、1/8尺寸的语义特征图;Haar DWT为Haar 离散小波变换,Physical Prior为模型引入的基于物理信号(如频谱、梯度)的预验知识,F Feat为频域特征图,Diff. Sobel Layer为可微分Sobel算子层,Grad Mag为梯度幅值,Stem Conv为根部卷积(用于几何分支起始阶段的空间降采样及初步特征转换),S2 Feat、S3 Feat为1/ 4、1/8尺寸的几何形状特征图,TMF Module为三模态融合单元,Main Seg 为主分割头,Boundary Aux Head为边界辅助监督头。下同。

, figureFileSmall=jMNqn+WuiPIaTNNCtuYs+Q==, figureFileBig=6sqG0SDwOxyS8glqRPtybg==, tableContent=null), ArticleFig(id=1299828224498885343, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Fig.5, caption=Comparison between the original image and high-frequency texture response image of Caragana korshinskii coppicing surface, figureFileSmall=usRsE0K9g6oNu6QERgsRLg==, figureFileBig=g4wUjTatmlYtE9UtDCXQhw==, tableContent=null), ArticleFig(id=1299828224591160032, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=图5, caption=柠条平茬面原图与高频纹理响应图对比, figureFileSmall=usRsE0K9g6oNu6QERgsRLg==, figureFileBig=g4wUjTatmlYtE9UtDCXQhw==, tableContent=null), ArticleFig(id=1299828224662463201, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Fig.6, caption=Technical route of frequency domain sensing branch, figureFileSmall=bth83W2hnq31fG53arH//g==, figureFileBig=xET5d2XwdxoVHibTnvjmFQ==, tableContent=null), ArticleFig(id=1299828224725377762, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=图6, caption=频域感知分支技术路线

注:DWT Coeffs为频域输出结果,$ H/2\times W/2\times {C}_{f1} $为尺寸为原图像1/2的频域特征图,MaxPool 2×2 (stride 2)为步长为2的最大池化层。下同。

, figureFileSmall=bth83W2hnq31fG53arH//g==, figureFileBig=xET5d2XwdxoVHibTnvjmFQ==, tableContent=null), ArticleFig(id=1299828224809263843, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Fig.7, caption=Technical route of geometric constraint module, figureFileSmall=ZQwFHSuX25WGr+sNwX2IMA==, figureFileBig=piWIxWLdPoTf8w2z+GG/4w==, tableContent=null), ArticleFig(id=1299828224880567012, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=图7, caption=形状约束分支技术路线

注:Conv2 d (Fixed Sobel-X/Y Kernel)为两个预设好的Sobel算子, Sobel-X/Y为专门检测图像中垂直/水平方向的边缘,Magnitude calculation为将两个方向的边缘信息合并,BatchNorm为批量归一化,Edge map为单通道边缘图,Stem为主干特征初始化层,$ H/2\times W/2\times {C}_{{\mathrm{s1}}} $为尺寸为原图像1/2的形状特征图,Conv 3×3 (stride 2)为步长为2的3×3卷积层。下同。

, figureFileSmall=ZQwFHSuX25WGr+sNwX2IMA==, figureFileBig=piWIxWLdPoTf8w2z+GG/4w==, tableContent=null), ArticleFig(id=1299828224947675877, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Fig.8, caption=TMF(three modes fusion) architecture, figureFileSmall=x+PRfOPrvPs1SHWkoxvzWA==, figureFileBig=YeDc9uDz9g6Zx7UqcZau8A==, tableContent=null), ArticleFig(id=1299828225006396134, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=图8, caption=三模态融合架构

注:Conv1×1为1×1卷积层, Concat (Auxiliary Context)为通道统一后的频域特征和形状特征在通道维度上拼接在一起,Element-wise multiplication为将融合辅助特征相乘,$\otimes $为特征重加权,$ \oplus $为信息融合,Sigmoid为将相乘的结果压缩到0到1之间生成一张注意力图,Attention Map为注意力图。下同。

, figureFileSmall=x+PRfOPrvPs1SHWkoxvzWA==, figureFileBig=YeDc9uDz9g6Zx7UqcZau8A==, tableContent=null), ArticleFig(id=1299828225065116391, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Fig.9, caption=Flow chart of individual automatic extraction and background decoupling of Caragana korshinskii coppicing surface, figureFileSmall=bKTiQgYybxRh5buOyOy4kA==, figureFileBig=onz3qk7XzQP/ohPsgWSOFg==, tableContent=null), ArticleFig(id=1299828225123836648, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=图9, caption=柠条平茬面个体自动化提取与背景解耦流程图, figureFileSmall=bKTiQgYybxRh5buOyOy4kA==, figureFileBig=onz3qk7XzQP/ohPsgWSOFg==, tableContent=null), ArticleFig(id=1299828225190945513, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Fig.10, caption=Comparison of mIoU curves across different models, figureFileSmall=lk+kue3JrJ2LkQHIk8V76A==, figureFileBig=lBPMfW9io4j4kX9SoCpuZg==, tableContent=null), ArticleFig(id=1299828225253860074, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=图10, caption=不同模型的平均交并比曲线, figureFileSmall=lk+kue3JrJ2LkQHIk8V76A==, figureFileBig=lBPMfW9io4j4kX9SoCpuZg==, tableContent=null), ArticleFig(id=1299828225329357547, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Fig.11, caption=Segmentation performance of different models in complex field environments, figureFileSmall=otfs9TX5nLO6r+gWN65HwA==, figureFileBig=ebMwowLhIIFby4lyLDuuUA==, tableContent=null), ArticleFig(id=1299828225396466412, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=图11, caption=不同模型在野外复杂环境下的分割能力, figureFileSmall=otfs9TX5nLO6r+gWN65HwA==, figureFileBig=ebMwowLhIIFby4lyLDuuUA==, tableContent=null), ArticleFig(id=1299828225459380973, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Fig.12, caption=Linear regression of sprout count (N) on stubble roundness (C) and its distribution across different quality grades, figureFileSmall=Nb4XaCRF3DKzexCKIWWZpA==, figureFileBig=AjgW4udMv2YNtFJDMLdJ6Q==, tableContent=null), ArticleFig(id=1299828225543267054, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=图12, caption=萌蘖发生数(N)与平茬面圆度(C)的线性回归及不同质量等级下的分布, figureFileSmall=Nb4XaCRF3DKzexCKIWWZpA==, figureFileBig=AjgW4udMv2YNtFJDMLdJ6Q==, tableContent=null), ArticleFig(id=1299828225610375919, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Fig.13, caption=Field test, figureFileSmall=3mREMX/59u7cVaBr9vWieA==, figureFileBig=hZxuAk7mXLuctvVK16t1nw==, tableContent=null), ArticleFig(id=1299828225685873392, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=图13, caption=田间试验, figureFileSmall=3mREMX/59u7cVaBr9vWieA==, figureFileBig=hZxuAk7mXLuctvVK16t1nw==, tableContent=null), ArticleFig(id=1299828225807508209, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Fig.14, caption=Visualization results of surface quality evaluation of Caragana korshinskii stubble in field environment, figureFileSmall=7XTp6LJVmTn1KqZbqz0Idg==, figureFileBig=JKJW6IQ+ldoWp/AxUZ3IlQ==, tableContent=null), ArticleFig(id=1299828225878811378, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=图14, caption=野外环境下柠条平茬面质量评价可视化结果, figureFileSmall=7XTp6LJVmTn1KqZbqz0Idg==, figureFileBig=JKJW6IQ+ldoWp/AxUZ3IlQ==, tableContent=null), ArticleFig(id=1299828225941725939, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Fig.15, caption=The linear regression relationship between the number of sprouting tillers and the observed true value was predicted by the system, figureFileSmall=G+mxeaFZM0q+EZbf4ElcMg==, figureFileBig=nWgA0VhHtroLy82mV2h8XQ==, tableContent=null), ArticleFig(id=1299828225996251892, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=图15, caption=系统预测萌蘖数与观测真值的线性回归关系, figureFileSmall=G+mxeaFZM0q+EZbf4ElcMg==, figureFileBig=nWgA0VhHtroLy82mV2h8XQ==, tableContent=null), ArticleFig(id=1299828226050777845, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Fig.16, caption=Stumping quality grading confusion matrix generated by field measured samples, figureFileSmall=sSDyELwgvzVmlsbq0WxcSA==, figureFileBig=G8hsWrLJuzyAtHCl9+fYnA==, tableContent=null), ArticleFig(id=1299828226126275318, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=图16, caption=野外实测样本生成的平茬质量分级混淆矩阵, figureFileSmall=sSDyELwgvzVmlsbq0WxcSA==, figureFileBig=G8hsWrLJuzyAtHCl9+fYnA==, tableContent=null), ArticleFig(id=1299828226197578487, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Tab.1, caption=

Feature dimension changes of feature fusion strategies at different scales

, figureFileSmall=null, figureFileBig=null, tableContent=
模块层级
Module
hierarchy
RGB语义特征
分支
RGB semantic
频域分支
Frequency
形状分支
Shape
映射统一通道数输出
Projection for unified
channel number output
TMF-1H/4×W/4×32H/4×W/4×128H/4×W/4×64H/4×W/4×64
TMF-2H/8×W/8×64H/8×W/8×64H/8×W/8×64H/8×W/8×128
TMF-3H/8×W/8×160H/8×W/8×160H/8×W/8×160H/8×W/8×256
), ArticleFig(id=1299828226264687352, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=表1, caption=

特征融合策略在不同尺度下的特征维度变化

, figureFileSmall=null, figureFileBig=null, tableContent=
模块层级
Module
hierarchy
RGB语义特征
分支
RGB semantic
频域分支
Frequency
形状分支
Shape
映射统一通道数输出
Projection for unified
channel number output
TMF-1H/4×W/4×32H/4×W/4×128H/4×W/4×64H/4×W/4×64
TMF-2H/8×W/8×64H/8×W/8×64H/8×W/8×64H/8×W/8×128
TMF-3H/8×W/8×160H/8×W/8×160H/8×W/8×160H/8×W/8×256
), ArticleFig(id=1299828226331796217, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Tab.2, caption=

Performance comparison with different values of λ

, figureFileSmall=null, figureFileBig=null, tableContent=
边缘损失权重
Edge loss weight λ
平均交并比
mIoU/%
边界交并比
Boundary IoU/%
0(Baseline)84.7218.12
0.285.8220.45
0.486.9922.59
0.686.2122.10
0.885.0321.31
183.5019.88
), ArticleFig(id=1299828226394710778, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=表2, caption=

不同λ取值的性能对比

, figureFileSmall=null, figureFileBig=null, tableContent=
边缘损失权重
Edge loss weight λ
平均交并比
mIoU/%
边界交并比
Boundary IoU/%
0(Baseline)84.7218.12
0.285.8220.45
0.486.9922.59
0.686.2122.10
0.885.0321.31
183.5019.88
), ArticleFig(id=1299828226457625339, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Tab.3, caption=

Model running equipment and version number

, figureFileSmall=null, figureFileBig=null, tableContent=
项目
Item
版本
Version
运行系统Ubuntu 22.04
CUDA12.1
Pytorch2.4.1
GPUNVIDIA RTX4060 16GB
CPUi7-14650HX Intel(R)Core(TM)
), ArticleFig(id=1299828226541511420, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=表3, caption=

模型运行设备及版本号

, figureFileSmall=null, figureFileBig=null, tableContent=
项目
Item
版本
Version
运行系统Ubuntu 22.04
CUDA12.1
Pytorch2.4.1
GPUNVIDIA RTX4060 16GB
CPUi7-14650HX Intel(R)Core(TM)
), ArticleFig(id=1299828226612814589, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Tab.4, caption=

Comparative performance evaluation of various models on the test set

, figureFileSmall=null, figureFileBig=null, tableContent=
模型
Models
mIoU/
%
FPS/
(帧·s−1
参数量
Params/
M
F1分数
F1-Score/
%
召回率
Recall/
%
边界交并比
Boundary
IoU/%
DeepLabV3+84.3917.8340.5283.2282.4319.91
PSPNet80.2827.2529.8076.8975.4410.58
U-Net82.3128.847.7779.5478.8619.93
SegFormer-B182.9832.408.3982.7481.8018.29
WoodGrainNet86.9951.787.5986.5285.6422.59
), ArticleFig(id=1299828226679923454, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=表4, caption=

不同模型在测试集上的性能对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型
Models
mIoU/
%
FPS/
(帧·s−1
参数量
Params/
M
F1分数
F1-Score/
%
召回率
Recall/
%
边界交并比
Boundary
IoU/%
DeepLabV3+84.3917.8340.5283.2282.4319.91
PSPNet80.2827.2529.8076.8975.4410.58
U-Net82.3128.847.7779.5478.8619.93
SegFormer-B182.9832.408.3982.7481.8018.29
WoodGrainNet86.9951.787.5986.5285.6422.59
), ArticleFig(id=1299828226747032319, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=EN, label=Tab.5, caption=

Ablation test of modules

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 ModelsmIoU/%GFLOPsParams/MFPS/
(帧·s−1)
SegFormer-B0
(Baseline)
84.7020.114.81104.2
Baseline+Freq85.6723.585.5889.25
Baseline+Shape84.8634.816.8268.21
Baseline+Shape+Freq
(简单拼接)
85.2938.287.1660.32
Baseline+Shape+Freq
(特征融合)
86.9940.467.5951.78
), ArticleFig(id=1299828226805752576, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, language=CN, label=表5, caption=

模型各模块消融试验

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 ModelsmIoU/%GFLOPsParams/MFPS/
(帧·s−1)
SegFormer-B0
(Baseline)
84.7020.114.81104.2
Baseline+Freq85.6723.585.5889.25
Baseline+Shape84.8634.816.8268.21
Baseline+Shape+Freq
(简单拼接)
85.2938.287.1660.32
Baseline+Shape+Freq
(特征融合)
86.9940.467.5951.78
)], attaches=null, journal=Journal(id=1296123985890738214, delFlag=0, nameCn=农业工程学报, nameEn=Transactions of the Chinese Society of Agricultural Engineering, nameHistory1=null, nameHistory2=null, issn=1002-6819, eissn=null, cn=11-2047/S, coden=null, periodic=3, 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=+90GfMrDOo0sGnhM27IfIQ==, journalPrice=null, startedYear=null, abbrevIsoEn=Transactions of the Chinese Society of Agricultural Engineering, journalRemark=null, publicationField=null, createdTime=1786949639057, updatedTime=1788949514636, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=N, firstLetterEn=N, subjectCode=Agriculture, subjectName=null, subjectCodeEn=Agriculture, subjectNameEn=null, picCn=+90GfMrDOo0sGnhM27IfIQ==, picEn=+UrL7Qgb+cjoX8OpJtziCA==, jcr=null, cjcr=null, exts=[JournalExt(id=1304512072117678568, language=CN, name=农业工程学报, 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=1788949514655, updatedTime=1788949514655, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://tsg.tcsae.org/nygcxb/author/login, submissionEditorUrl=https://nygcxb.ijournals.cn/nygcxb/editor/login, submissionReviewUrl=http://tsg.tcsae.org/nygcxb/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1304512072168010217, language=EN, name=Transactions of the Chinese Society of Agricultural Engineering, 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=1788949514667, updatedTime=1788949514667, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://tsg.tcsae.org/nygcxb/author/login, submissionEditorUrl=https://nygcxb.ijournals.cn/nygcxb/editor/login, submissionReviewUrl=http://tsg.tcsae.org/nygcxb/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1296125453100220459, websiteList=[Website(id=1296128922534564555, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1296125453100220459, 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/nygcxb/CN, language=CN, createTime=1786950816043, createBy=18614031015, updateTime=1786950989293, updateBy=18614031015, name=农业工程学报-中文, tplId=1146099689490845704, title=农业工程学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1296129761215009609, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=articleTextType, value=kx, createTime=1786951016000, updateTime=1786951016000, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761194038086, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=banner, value=null, createTime=1786951015995, updateTime=1786951015995, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761231786828, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=grayFlag, value=0, createTime=1786951016004, updateTime=1786951016004, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761185649477, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=logo, value=https://castjournals.cast.org.cn/joweb/nygcxb/CN/file/pic?fileId=6wW+hIE4oBGmmFvGgEb5JQ==, createTime=1786951015993, updateTime=1786951015993, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761244369742, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=minRunFlag, value=0, createTime=1786951016007, updateTime=1786951016007, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761206621000, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/nygcxb/CN/file/pic, createTime=1786951015998, updateTime=1786951015998, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761240175437, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=silenceFlag, value=0, createTime=1786951016006, updateTime=1786951016006, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761202426695, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1786951015997, updateTime=1786951015997, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761219203914, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=themeColor, value=null, createTime=1786951016001, updateTime=1786951016001, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761227592523, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=themeStyle, value=null, createTime=1786951016003, updateTime=1786951016003, creator=18614031015, updator=18614031015)]), Website(id=1296128922677170905, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1296125453100220459, 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/nygcxb/EN, language=EN, createTime=1786950816077, createBy=18614031015, updateTime=1786950985772, updateBy=18614031015, name=农业工程学报-英文, tplId=1146101810881728533, title=Transactions of the Chinese Society of Agricultural Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1296129731049575225, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=articleTextType, value=kx, createTime=1786951008808, updateTime=1786951008808, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731028603702, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=banner, value=null, createTime=1786951008803, updateTime=1786951008803, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731070546748, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=grayFlag, value=0, createTime=1786951008813, updateTime=1786951008813, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731016020789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=logo, value=https://castjournals.cast.org.cn/joweb/nygcxb/EN/file/pic?fileId=6wW+hIE4oBGmmFvGgEb5JQ==, createTime=1786951008800, updateTime=1786951008800, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731087323966, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=minRunFlag, value=0, createTime=1786951008817, updateTime=1786951008817, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731041186616, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/nygcxb/EN/file/pic, createTime=1786951008806, updateTime=1786951008806, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731078935357, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=silenceFlag, value=0, createTime=1786951008815, updateTime=1786951008815, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731032798007, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1786951008804, updateTime=1786951008804, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731053769530, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=themeColor, value=null, createTime=1786951008809, updateTime=1786951008809, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731062158139, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=themeStyle, value=null, createTime=1786951008811, updateTime=1786951008811, creator=18614031015, updator=18614031015)])], journalTitle=农业工程学报, weixinUrl=null, journalUrl=http://www.tcsae.org/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Transactions of the Chinese Society of Agricultural Engineering, journalPhotoCn=+90GfMrDOo0sGnhM27IfIQ==, journalPhotoEn=+UrL7Qgb+cjoX8OpJtziCA==, 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/nygcxb/CN/10.11975/j.issn.1002-6819.202601133, detailUrlEn=https://castjournals.cast.org.cn/joweb/nygcxb/EN/10.11975/j.issn.1002-6819.202601133, pdfUrlCn=https://castjournals.cast.org.cn/joweb/nygcxb/CN/PDF/10.11975/j.issn.1002-6819.202601133, pdfUrlEn=https://castjournals.cast.org.cn/joweb/nygcxb/EN/PDF/10.11975/j.issn.1002-6819.202601133, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1782748800000, fullTextJson=null, articleText=null, reference=null)
收藏切换
柠条平茬面质量对其萌蘖再生能力的量化分析
收藏切换
PDF下载
高垚垚 1 , 张鹤篷 1 , 杨蕾 2 , 曲爱丽 1 , 温学飞 3 , 王昱潭 1, *
农业工程学报 | 农业信息与电气技术 2026,42(12): 204-215
收起
收藏切换
农业工程学报 |农业信息与电气技术 2026 , 42 (12) : 204 -215
柠条平茬面质量对其萌蘖再生能力的量化分析
全屏
[Author(id=1299828221827113648, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=Gaoyy@nxu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1299828221915194034, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828221827113648, language=EN, stringName=Yaoyao GAO, firstName=Yaoyao, middleName=null, lastName=GAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Mechanical Engineering, Ningxia University, Yinchuan 750021, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828221994885811, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828221827113648, language=CN, stringName=高垚垚, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1宁夏大学机械工程学院,银川 750021, bio={"content":"

高垚垚,博士,讲师,硕士生导师,研究方向为农业机械设计与智能农业装备。Email:

"}, bioImg=null, bioContent=

高垚垚,博士,讲师,硕士生导师,研究方向为农业机械设计与智能农业装备。Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828221550289574, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, xref=1, ext=[AuthorCompanyExt(id=1299828221562872487, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221550289574, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Mechanical Engineering, Ningxia University, Yinchuan 750021, China), AuthorCompanyExt(id=1299828221571261096, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221550289574, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1宁夏大学机械工程学院,银川 750021)])]), Author(id=1299828222070383285, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, 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=1299828222137492151, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828222070383285, language=EN, stringName=Hepeng ZHANG, firstName=Hepeng, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Mechanical Engineering, Ningxia University, Yinchuan 750021, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828222200406712, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828222070383285, language=CN, stringName=张鹤篷, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1宁夏大学机械工程学院,银川 750021, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828221550289574, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, xref=1, ext=[AuthorCompanyExt(id=1299828221562872487, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221550289574, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Mechanical Engineering, Ningxia University, Yinchuan 750021, China), AuthorCompanyExt(id=1299828221571261096, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221550289574, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1宁夏大学机械工程学院,银川 750021)])]), Author(id=1299828222271709882, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, 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=1299828222338818748, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828222271709882, language=EN, stringName=Lei YANG, firstName=Lei, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2Ningxia Helan Mountain National Nature Reserve Administration, Yinchuan 750021 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828222426899133, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828222271709882, language=CN, stringName=杨蕾, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2宁夏贺兰山国家级自然保护区管理局,银川 750021, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828221655147177, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, xref=2, ext=[AuthorCompanyExt(id=1299828221659341482, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221655147177, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Ningxia Helan Mountain National Nature Reserve Administration, Yinchuan 750021 China), AuthorCompanyExt(id=1299828221667730091, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221655147177, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2宁夏贺兰山国家级自然保护区管理局,银川 750021)])]), Author(id=1299828222498202303, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, 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=1299828222556922561, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828222498202303, language=EN, stringName=Aili QU, firstName=Aili, middleName=null, lastName=QU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Mechanical Engineering, Ningxia University, Yinchuan 750021, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828222619837122, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828222498202303, language=CN, stringName=曲爱丽, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1宁夏大学机械工程学院,银川 750021, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828221550289574, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, xref=1, ext=[AuthorCompanyExt(id=1299828221562872487, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221550289574, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Mechanical Engineering, Ningxia University, Yinchuan 750021, China), AuthorCompanyExt(id=1299828221571261096, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221550289574, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1宁夏大学机械工程学院,银川 750021)])]), Author(id=1299828222686945988, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, 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=1299828222758249158, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828222686945988, language=EN, stringName=Xuefei WEN, firstName=Xuefei, middleName=null, lastName=WEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3Institute of Forestry and Grassland Ecology, Ningxia Academy of Agriculture and Forestry Sciences, Yinchuan 750002, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828222833746631, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828222686945988, language=CN, stringName=温学飞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3宁夏农林科学院林业与草业生态研究所,银川 750002, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828221751616172, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, xref=3, ext=[AuthorCompanyExt(id=1299828221755810477, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221751616172, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Institute of Forestry and Grassland Ecology, Ningxia Academy of Agriculture and Forestry Sciences, Yinchuan 750002, China), AuthorCompanyExt(id=1299828221764199086, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221751616172, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3宁夏农林科学院林业与草业生态研究所,银川 750002)])]), Author(id=1299828222913438409, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wang_yt1108@163.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1299828222984741579, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828222913438409, language=EN, stringName=Yutan WANG, firstName=Yutan, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1School of Mechanical Engineering, Ningxia University, Yinchuan 750021, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828223056044748, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, authorId=1299828222913438409, language=CN, stringName=王昱潭, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1宁夏大学机械工程学院,银川 750021, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828221550289574, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, xref=1, ext=[AuthorCompanyExt(id=1299828221562872487, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221550289574, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Mechanical Engineering, Ningxia University, Yinchuan 750021, China), AuthorCompanyExt(id=1299828221571261096, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211800668369574, companyId=1299828221550289574, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1宁夏大学机械工程学院,银川 750021)])])]
高垚垚1 , 张鹤篷1, 杨蕾2, 曲爱丽1, 温学飞3, 王昱潭1, *
作者信息
  • 1宁夏大学机械工程学院,银川 750021
  • 2宁夏贺兰山国家级自然保护区管理局,银川 750021
  • 3宁夏农林科学院林业与草业生态研究所,银川 750002
通讯作者:
王昱潭,博士,博士生导师,研究方向为现代农业装备与智慧农业。Email:
作者简介:

高垚垚,博士,讲师,硕士生导师,研究方向为农业机械设计与智能农业装备。Email:

Effects of coppicing surface quality on sprouting regeneration of Caragana korshinskii
Yaoyao GAO1 , Hepeng ZHANG1, Lei YANG2, Aili QU1, Xuefei WEN3, Yutan WANG1, *
Affiliations
  • 1School of Mechanical Engineering, Ningxia University, Yinchuan 750021, China
  • 2Ningxia Helan Mountain National Nature Reserve Administration, Yinchuan 750021 China
  • 3Institute of Forestry and Grassland Ecology, Ningxia Academy of Agriculture and Forestry Sciences, Yinchuan 750002, China
出版时间: 2026-06-30 doi: 10.11975/j.issn.1002-6819.202601133
文章导航
收藏切换

针对中国西北干旱区柠条灌木平茬作业中切割质量缺乏客观量化评价、萌蘖再生能力难以预测等问题,该研究提出了一种基于切割形态特征与农艺性状协同关联的柠条平茬萌蘖能力的量化方法,并构建了适用于野外非结构化环境的平茬面分割网络WoodGrainNet。该网络融合语义特征提取分支、频域感知分支和形状约束分支并配合特征融合策略,实现复杂背景及密集茬口条件下柠条平茬面的精准分割。结果表明,WoodGrainNet网络在兼顾实时性的同时,平均交并比达到86.99%,推理速度达到51.78帧/s。基于分割结果,自动提取反映平茬质量的关键农艺指标——平茬面圆度(C)。相关分析结果表明,平茬面圆度与第5周侧枝萌蘖数(N)的线性关系呈正相关性,表明圆度可作为评价柠条平茬质量及萌蘖再生能力的形态学指标。在此基础上,将轻量化模型部署于移动式智能评估系统,并通过田间试验验证了其实用性,系统对平茬质量等级的判别准确率达到90.8%。该研究实现了由平茬面像素级表型解析向单株再生能力预测的转化,为干旱区生态灌木林机械化抚育质量评价与精准管理提供了技术支撑。

柠条  /  萌蘖  /  图像分割  /  WoodGrainNet  /  平茬质量评价

Quantitative evaluation standards are often required to accurately predict sprouting regeneration, particularly for cutting quality. However, the coppicing surface targets cannot be recognized in complex fields during Caragana korshinskii shrub coppicing in the arid regions of Northwest China. In this study, a quantitative evaluation was proposed for sprouting regeneration, according to the synergistic association between cutting morphologies and agronomic traits. Accurate recognition of coppicing surfaces was achieved in unstructured field environments. A segmentation network was constructed, named WoodGrainNet. Firstly, the global context modelling and target localization were enhanced via a semantic stream using a lightweight Transformer architecture. Secondly, a frequency-domain stream was incorporated with the Haar discrete wavelet transform to effectively suppress abiotic background interference for the texture representation of the targets. Simultaneously, a shape stream was combined with a differentiable Sobel operator. Explicit constraints were also applied to high-frequency gradient regions. Thereby, the adjacent cut boundaries were delineated to effectively alleviate the adhesion of dense targets. Three-stream features were synergistically simulated for the deep integration. The WoodGrainNet significantly improved the segmentation robustness and instance discrimination of the improved model in complex scenes, particularly at the level of underlying physical feature representation. Accurate segmentation was achieved to automatically extract a key geometric phenotypic indicator for coppicing quality—coppicing surface circularity (C). Accordingly, the coppicing quality grading and sprouting prediction were established after evaluation. The experimental results demonstrate that the better performance of WoodGrainNet was achieved to balance high accuracy and real-time processing, with a mean Intersection over Union (mIoU) of 86.99% and an inference speed of 51.78 frames/s. The performance was significantly superior to mainstream networks, such as DeepLabV3+, effectively recognizing tiny coppicing targets. In terms of agronomic analysis, statistical results revealed that there was a significant positive correlation between the morphological quality of the coppicing surface and the sprouting potential of lateral branches. Notably, the coefficient of determination (R²) between the coppicing surface circularity (C) and the number of lateral branch sprouts reached 0.764 at the 5th week (N). The circularity served as an important morphological indicator to evaluate coppicing quality and sprouting regeneration. Field tests were conducted to verify its feasibility for engineering applications. The improved model was deployed on a mobile intelligent system. A discrimination accuracy of 90.8% was achieved for coppicing quality grades under mobile working conditions. Sprouting prediction trend was highly consistent with the measured ones, indicating its potential to replace manual inspection and subjective empirical judgment. The pixel-level phenotypic analysis of the coppicing surface was effectively transformed to predict the single-plant regeneration. The finding can provide a theoretical basis and technical support for the quality evaluation, parameter monitoring, and precise detection of ecological shrub forests in arid regions.

Caragana korshinskii.  /  coppice shoot  /  image segmentation  /  WoodGrainNet  /  stubble cutting quality evaluation
高垚垚, 张鹤篷, 杨蕾, 曲爱丽, 温学飞, 王昱潭. 柠条平茬面质量对其萌蘖再生能力的量化分析. 农业工程学报, 2026 , 42 (12) : 204 -215 . DOI: 10.11975/j.issn.1002-6819.202601133
Yaoyao GAO, Hepeng ZHANG, Lei YANG, Aili QU, Xuefei WEN, Yutan WANG. Effects of coppicing surface quality on sprouting regeneration of Caragana korshinskii[J]. Transactions of the Chinese Society of Agricultural Engineering, 2026 , 42 (12) : 204 -215 . DOI: 10.11975/j.issn.1002-6819.202601133
柠条(Caragana korshinskii)根系发达,固土保水能力强,在防风固沙、水土保持等方面具有显著生态功能,已成为西北地区生态修复与植被建设的重要优势树种之一[1]。同时,柠条茎秆内含有丰富的粗蛋白、氨基酸等营养元素,又是当地畜牧产业发展的饲草料来源[2]。为了延缓植株衰老并维持其生长活力,定期开展平茬复壮是柠条抚育管理中的重要农艺措施之一[3]。现有研究表明,平茬面损伤程度直接制约着植株后续的侧枝萌蘖潜力[4]。平整光滑圆度较高的平茬面能够有效减少水分蒸发并抵御真菌感染,从而显著提高次年的萌蘖率与生物量[5];相反,撕裂、破碎等不规则的平茬面容易导致木质部腐烂,严重抑制再生能力。因此,将柠条的平茬面完整精确的分割出来,并对其质量进行快速、客观、准确的评价,对后续通过柠条的平茬面特征来进行试验以及保障生态的可持续性至关重要。
目前,柠条平茬质量评价主要依赖人工抽样方法,存在劳动强度大、评价效率低以及主观性较强等局限[6]。近年来计算机视觉技术在农业表型分析中取得显著进展,但在野外非结构化环境下实现高精度实例分割仍面临严峻挑战。在复杂背景下的农业目标识别领域,国内外学者开展了广泛研究。JI等[7]评估了SAM(segment anything model)在多种农业场景下的性能,探讨了大模型在零样本分割中的潜力;WANG等[8]通过改进语义分割网络,提升了农田遥感影像中作物的提取精度;张睿等[9]提出了一种集成密集信息估计与任务协同动态分割的多任务网络,旨在解决复杂田间环境下密集重叠目标的定位与分割难题。然而,将上述通用模型迁移至非结构化的柠条平茬场景时,其实例分割性能仍存在明显不足。以DeepLabV3+为代表的经典语义分割网络高度依赖空间下采样与池化操作,扩大了感受野,却损失了底层的微观纹理细节。在平茬面与沙壤土呈高度非结构化特性的野外环境下,单纯依赖空间语义特征难以捕获如年轮、平茬面木质纤维等关键的高频辨别信号,导致模型在复杂光照下极易产生背景误判[10-11]。SAM等大模型在缺乏显式几何边界约束的情况下,难以有效识别相邻桩头间微小的物理间隙,在面对密集簇生的平茬场景时常产生严重的拓扑粘连与欠分割现象[12-13]。尽管近期研究尝试通过引入物理先验或双域特征融合等方法提升分割性能,但现有改进策略大多侧重于全局频谱信息增强,缺乏对木质部定向周期性信号的针对性表征能力,同时也未能围绕密集个体间的物理拓扑分离构建有效约束机制。
针对上述挑战,本文提出一种基于物理先验引导的非对称三分支特征融合分割网络——WoodGrainNet,以提升复杂农业场景下柠条平茬目标的分割性能。该网络通过语义特征提取分支、频域感知分支和形状约束分支的协同建模,实现多模态特征的互补融合。其中,语义特征提取分支基于轻量化Transformer架构,用于增强全局上下文建模与目标定位能力;频域感知分支引入Haar离散小波变换(DWT),以抑制非生物背景干扰并增强目标纹理表征;形状约束分支结合可微分Sobel算子,对高频梯度区域进行显式约束,以强化相邻个体边界表征并缓解密集目标粘连。通过三分分支特征的深度集成,WoodGrainNet能够从底层物理特征表征层面提高模型在复杂场景中的分割鲁棒性与实例辨识能力。
数据集采集于宁夏盐池县宁夏大学野外柠条基地花马池镇(37°76'N,107°46'E)和冯记沟乡(38°2'N,107°22'E)。该地区属于典型的温带大陆性半干旱气候,该试验基地的选取具有极强的区域代表性。根据林业部门数据[14],宁夏全区柠条面积约33.3~40.0万hm2,而盐池县拥有约17.7万hm2,占据了全区近1/2的份额。且该地地处毛乌素沙地与黄土高原的交界地带,属于半干旱荒漠草原向荒漠过渡的典型区域,其生态环境涵盖了西北干旱区最普遍的沙壤地类型。年均降水量少且蒸发强烈,地形以缓坡丘陵和流动沙地为主(如图1a),是柠条为防风固沙先锋树种的重点分布区域。试验样地选取了生长年限为成熟期柠条林(如图1b),该林分种植密度均匀,且处于亟需平茬复壮的农艺管理周期内,具有极高的代表性。
踪数据集采集周期的科学性,开展了观测预试验,依据GB/T 5262-2008《农业机械试验条件——测试方法的一般规定》[15]选取300株柠条。构建了包含1016株样本的数据集(如图2),用于建立平茬质量与萌蘖再生能力的纵向追踪数据。
观测周期的设定具有充分的生物学依据:相关研究表明,柠条在区域尺度上的生长节律和对水分胁迫的生理防御机制具有高度一致性,且其发育节律遵循稳定的生物学演变规律[16]。通过前期对300株样本的预试验发现,95.7%的柠条在平茬后28 d进入生理稳定期,为消除萌蘖波动的偶然性,据此本研究将观测窗口设定为35 d,以确保采集的萌蘖数能反映植株发育成熟后的稳定状态。
具体“基线-终点”双时相对比预试验设计如下:
1)基线数据采集(第一周):在平茬作业后的第一周内,选取300个具有代表性的平茬后柠条树桩样本(涵盖平滑、粗糙、撕裂等不同平茬面形态),利用物理标签进行唯一身份标记,并采集其平茬面图像作为模型的输入变量。
2)终点表型评估(第五周):试验将观测窗口期设定为4周。在平茬后的第五周对同一批标记树桩进行复测。根据柠条的生长生理特性,此时萌蘖枝条已完成初期的爆发式生长并进入生理稳定期,侧枝发育完全且成活率趋于稳定,消除了早期环境胁迫导致的随机死亡风险。因此,统计5周的的柠条萌蘖的数据作为纵向追踪数据集具备有效性。
该数据集在自然光照条件下进行拍摄,为消除透视畸变并确保纹理特征的几何真实性,拍摄角度严格保持为垂直俯视,拍摄距离控制在平茬面上方30~50 cm范围内。这种近距离的采集策略确保能够清晰捕捉到年轮、木质部裂纹及韧皮部撕裂等微小的形态特征。此外,采集过程覆盖了晴天直射光、阴天漫反射光及杂草遮挡阴影等多种光照环境,以模拟真实的野外作业场景。分割数据集共拍摄1367张,通过对原始采集图像进行严格的人工清洗,剔除运动模糊与过曝样本,最终精选出957张高清原始图像作为分割基准集。为提升模型对野外非结构化环境的泛化能力,实施了“1+2”采样增强策略(即1张原图对应2张随机增强图)。在增强过程中,系统从几何变换、纹理增强、细节增强、光照调节及遮挡等模拟5类算子池中,通过独立概率决策随机组合2项算子进行处理。该策略旨在通过适度扰动增加特征多样性,同时保持目标的生物学保真度,避免因过度增强导致的年轮及纤维特征失真。理论生成影像2871张,经人工二次检查并剔除96张因极端扭曲或特征丢失的无效样本后,最终形成包含2775张样本的分割数据集。样本涵盖了从光滑平整到严重撕裂的全生命周期平茬面形态(如图3),并包含了黄土、碎石及枯枝等多种复杂的野外背景干扰,为模型提供了具有代表性的特征输入。
U-Net[17]、DeepLabV3+[18]及SegFormer[19]等通用语义分割网络在常规任务中表现优异,但在处理非结构化野外环境下的柠条平茬评价任务时面临显著瓶颈。DeepLabV3+等基于池化作的架构往往牺牲底层空间细节,导致高频纹理丢失;Transformer架构虽擅长全局建模,但在处理密集小目标时局部关注度不足,易导致边缘模糊[20-22]。且上述模型均忽视了频域特征的利用,难以在频谱层面有效区分木质部纹理与黄土背景的细微差异(即“背景视觉伪装”),且缺乏针对密集粘连平茬面的物理形状约束机制[23]。针对上述视觉伪装与密集粘连双重挑战,提出了一种非对称的三分支特征融合分割网络——WoodGrainNet(图4)。
语义特征提取分支旨在捕捉平茬面在复杂背景下的全局语义属性,采用轻量化Transformer架构SegFormer (MIT-B0)作为骨干。其核心在于利用重叠切片嵌入(overlapped patch embedding)和分层Transformer块提取多尺度特征,对输入$ I\in {R}^{3\times H\times W} $图像进行处理
$ F_{rgb}^{(i)}={TransformerLayer}_{i}\left({PatchEmbed}_{i}\left(F_{rgb}^{(i-1)}\right)\right) $
式中输入I是一个通道数为3、高度为H、宽度为W的图像,$ F_{rgb}^{(i-1)} $为上一阶段输出的特征图($ i $为1时为原始图像),$ {PatchEmbed}_{i} $为对特征图进行空间上的下采样(通常是降低分辨率,同时增加通道维度),$ F_{rgb}^{(i)} $为第$ i $阶段的最终特征图,$ i\in \{1{,}2,3{,}4\} $代表4个阶段。Transformer的自注意力机制确保了网络在处理大尺寸背景干扰时具备强大的长程建模能力。
非结构化的野外柠条平茬场景中,新鲜的柠条木质部平茬面(前景)与黄土、枯草(背景)在RGB颜色空间中具有极高的相似性[24]。然而,从信号处理的角度来看,两者在频域(frequency domain)表现出显著的差异:木质平茬面的年轮结构呈现出具有特定方向性的周期性高频信号,而土壤背景则表现为无序的低频漫反射或高频噪声(如图5)。
为了利用这种频谱差异性增强特征的可分性,设计了频域感知分支(如图6)。频域特征在辅助空间域捕获高频细节方面具有显著优势。借鉴SF3Net[25]中利用频域信息补偿空间特征以增强纹理边界处理的核心理念,本文构建了基于离散小波变换(DWT)的频域感知分支。与SF3Net侧重于遥感图像的选择性融合不同,WoodGrainNet旨在通过频域信号提取柠条平茬面的纤维撕裂特征,从而解决背景伪装下的目标粘连问题。
处理含有复杂背景(如枯草、人工标签)的柠条图像时,人工干扰物通常表现为平滑的低频特征,而平茬面因其独特的生物组织结构呈现出显著的高频响应[26-28]。通过DWT分解,模型能够在保留$ \text{LL} $分量辅助分割的同时,利用水平细节子带HL、垂直细节子带LH和对角线细节子带HH实现对非生物干扰的有效抑制,从而提升模型在非结构化环境下的识别鲁棒性。与傅里叶变换相比,DWT具有优异的时频局部化能力,能够同时保留图像的空间位置信息与频率分量。Haar DWT通过一组互补的低通滤波器和高通滤波器对图像进行分解。其分解过程可表示为对输入图像$ x $在行与列方向的卷积与下采样:
$ {x}_{\text{LL}}=(\mathrm{L}{\mathrm{L}}^{\mathrm{T}})*x\downarrow 2 $
$ x_{\text{LH}}=(\mathrm{LH}^{\mathrm{T}})*x\downarrow2 $
$ x_{\text{HL}}=(\mathrm{HL}^{\mathrm{T}})*x\downarrow2 $
$ {x}_{\text{HH}}=(\mathrm{H}{\mathrm{H}}^{\mathrm{T}})*x\downarrow 2 $
式中$ {x}_{\text{LL}} $对应图像的低频分量,反映了目标的宏观语义信息;LLT、HLT、LHT、HHT表示输入图像x进行二维 Haar小波变换的等效滤波器,T表示转置,使得一个滤波器作用于行,另一个作用于列;*表示卷积操作;$ \downarrow 2 $表示步长为2的下采样;$ {x}_{\text{LH}} $$ {x}_{\text{HL}} $$ {x}_{\text{HH}} $分别对应水平、垂直和对角线方向的高频分量,用于精确刻画平茬面的年轮纹理与木质纤维细节。
柠条具有典型的丛生生长特性,机械平茬后留下的树桩在物理空间上高度密集且相互粘连。通用的语义分割网络倾向于提取区域内部的平滑特征,往往模糊了物体间的精细边界,导致“欠分割”。为了满足萌蘖潜力预测对单株平茬面提取的精度要求,引入显式的几何约束(如图7)。
边缘梯度计算形状约束分支旨在强制网络关注图像中的高频梯度区域(即平茬面轮廓)。在图像进入编码器之前,利用Sobel算子计算图像的边缘梯度图。定义水平方向核$ {K}_{x} $和垂直方向核$ {K}_{y} $如下:
$ {K}_{x}=\left[\begin{array}{ccc}-1 & 0 & 1\\-2 & 0 & 2\\-1 & 0 & 1\end{array}\right],{K}_{y}=\left[\begin{array}{ccc}-1 & -2 & -1\\0 & 0 & 0\\1 & 2 & 1\end{array}\right] $
通过卷积操作计算水平梯度$ {G}_{x} $和垂直梯度$ {G}_{y} $
$ G_x=K_x\mathrm{*\mathit{I\ }},\ G_y=K_y\mathrm{*\mathit{I}} $
式中I为输入图像,$ {G}_{x} $$ {G}_{y} $分别为图像在水平方向和垂直方向的梯度幅值;$ {K}_{x} $$ {K}_{y} $分别为Sobel算子的水平与垂直卷积核。
最终的边缘梯度幅值$ {G}_{mag} $计算式为
$ {G}_{mag}=\sqrt{G_{x}^{2}+G_{y}^{2}} $
该梯度图$ {G}_{mag} $被归一化后输入到形状约束分支编码器中,形状分支专注于学习“在哪里(Where)”。在特征融合阶段,这些高响应的边缘特征充当了“语义剪刀”的角色,在特征空间上切断了相邻树桩之间的弱连接区域,从而确保了分割结果具有清晰、闭合的拓扑边界。
来自语义特征提取分支、频域感知分支和形状约束分支的特征图包含了异构的信息,简单的逐元素相加或通道拼接无法区分不同模态特征的重要性,甚至可能引入冗余噪声。提出了MSAF模块,利用通道注意力机制实现多模态特征的自适应加权融合。为了实现异构特征分支间的精细空间交互,MSAF内部采用了三模态融合架构(如图8)。利用双线性插值消除语义特征提取分支、频域感知分支和形状约束分支间的空间分辨率差异,并经$ 1\times 1 $卷积将其投影至统一通道空间,确保特征对齐;引入类注意力机制进行跨模态协同:将RGB语义特征视为查询量(Query),将频域与形状特征拼接构建的“辅助上下文”视为键值对(Key/Value)。利用线性映射层提取辅助特征,通过Query与Key/Value的逐元素乘法捕获语义信息与物理先验(纹理及几何特征)之间的深度关联,最终经 Sigmoid 函数生成自适应注意力图。
$ \mathrm{Key}/\mathrm{Value}={{\boldsymbol{W}}}_{\text{key}}\left(\text{Concat}\left(\mathrm{\mathit{F}}_{\text{freq}}'\ ,\mathrm{\mathit{\ F\mathit{ }}}_{\text{shape}}'\right)\right) $
$ \mathrm{Attention}\_ \mathrm{Map}=\sigma (\mathrm{Query}\otimes \mathrm{Key}/\mathrm{Value}) $
式中$ \mathrm{Key/Value} $为等待被匹配检索的键和包含纹理和边缘信息的值,Concat为拼接操作,$ \mathit{\mathit{\mathrm{\mathit{F}}}}_{\text{freq}}'\ 、\mathrm{\mathit{F}}_{\text{shape}}' $为预处理后的频域特征和形状特征,$ {\boldsymbol{W}}_{\text{key}} $为可学习权重矩阵,$ \mathrm{Attention}\_ \text{Map}\mathrm{为最终注意力图},\sigma $将相关性得分映射到[0,1]区间,$ \otimes $为逐元素相乘。
通过在H/4、H/8等多个尺度下进行TMF模块级联,实现了从浅层细微边缘到深层全局语义的全方位特征动态互补。不同尺度下的特征维度变化如下表1所示,这种多维度特征的有机集成,显著增强了模型在复杂背景下对密集粘连、边界模糊平茬面的识别精度与拓扑分离能力。
针对野外平茬场景中从生树桩“极度粘连”导致的分割难点,在WoodGrainNet训练中采用了“语义-实例”双粒度联合监督策略。传统的通用语义分割模型仅关注像素分类,极易忽略同类物体间的拓扑边界,导致粘连树桩被误识为连通整体。为支撑后续章节中“单株萌蘖潜力追踪”的农艺需求,本策略通过引入实例级标注数据,强制形状约束分支学习个体间的边缘先验,从而赋予模型在语义分割任务中精准分离独立个体的能力。
针对野外平茬场景中从生树桩“极度粘连”导致的分割难点,采用了实例信息辅助的语义分割监督策略,在数据集构建阶段,利用LabelMe标注工具对所有分割数据集的平茬面进行了个体级轮廓标注(通过group_id区分)。该标注策略的核心是通过引入实例间的边缘先验,强制形状约束分支学习相邻桩头间的物理间隔特征,从而赋予语义分割模型精准分离独立个体的能力。同时在WoodGrainNet训练中采用了“语义-实例”双粒度联合监督策略。传统的通用语义分割模型仅关注像素分类[29],极易忽略同类物体间的拓扑边界,导致粘连树桩被误识为连通整体。为支撑后续章节中“单株萌蘖潜力追踪”的农艺需求。
为了实现精准的像素分类并兼顾边缘的独立性约束,设计了多任务联合损失函数,由主分割损失与边界辅助损失加权组成:
$ {L}_{total}={L}_{main}({P}_{seg},{G}_{seg})+\lambda {L}_{bound}({P}_{edge},{G}_{edge}) $
式中$ {L}_{total} $总损失函数,由主分割损失与边界辅助损失加权组成;$ {L}_{main} $$ {L}_{bound} $分别代表主分割头损失和边界辅助监督头损失;$ {P}_{seg}\text{为网络预测的区域分割掩码} $$ {G}_{seg} $为人工标注的真实分割标签;$ {P}_{edge} $为网络预测的边缘特征图;$ {G}_{edge} $为真实的边缘掩码;$ \lambda $边缘损失权重系数。
主分割损失作用于网络的主分割头Main Seg Head,该部分将前面提取到的所有特征,翻译并输出成一张分割预测图,采用交叉熵损失$ {L}_{BCE} $与Dice损失$ {L}_{Dice} $的组合,旨在通过语义标签监督全局的像素分类精度:
$ {L}_{main}={L}_{BCE}+{L}_{Dice} $
边界辅助损失作用于边界辅助头Boundary Aux Head,该部分利用实例标注数据提取出的个体边缘图作为真值,形状约束分支输出的边界概率图。通过最小化二元交叉熵损失,强制网络学习相邻树桩间的“空隙特征”,实现在特征空间内对粘连区域的“物理隔离”。
针对柠条平茬面内部年轮与撕裂纹理带来的高频干扰,平衡系数λ的取值至关重要,联合多任务损失平衡系数λ对网络分割性能的影响如表2所示。若λ过高,模型易将内部微观纹理误识别为边界;若过低,则难以有效约束边缘导致欠分割。研究设定λ=0.4以提供适度的正则化强度,使网络能够精准捕获平茬面外轮廓的显著梯度,同时有效抑制内部噪声干扰,边缘损失系数λ取值消融试验如表2。该联合损失策略通过引入显式的几何边界约束,显著增强了WoodGrainNet在复杂丛生场景下的个体识别精度与分割鲁棒性。
受限于柠条丛生生长的生物学特性,在数据集实地拍摄时,全景图像中往往包含大量密集的平茬口。若直接将全景图像输入识别模型进行身份锁定(Group_ID Matching),复杂的野外背景(如沙土、碎石、枯草)以及相邻茬口间的特征混淆会产生巨大的噪声干扰,导致重识别(Re-ID)准确率大幅下降。
提出的基于WoodGrainNet引导的个体特征解耦策略会通过自动化提取每一个独立的平茬口掩码,将目标从非结构化的背景中彻底剥离。这一步为了实现从“像素级语义”向“单体级特征”的转化,为后续跨时相(Week-1~Week-5)的长势追踪提供纯净的输入特征库。
利用自动化脚本实现了个体平茬面的高效提取,具体技术路径分为3个阶段:
1)高精度掩码生成:将输入的全景图像送入WoodGrainNet,通过主分割头(Main Head)输出像素级的分类概率图。为了确保对质量较差、边缘撕裂严重的茬口进行完整捕捉,阈值经交叉验证确定,旨在平衡撕裂纤维的完整捕获与虚假背景的滤除,因此采用了较低的置信度阈值0.4。
2)形态学修正与覆盖优化:针对撕裂边缘产生的微观纹理噪声,在生成深红色透明覆盖图(Overlay)时,引入了3×3卷积核的形态学膨胀操作。通过向外扩张2个像素,使掩码能完美包裹住平茬面的放射状撕裂纤维,从而提升了视觉评估的完整性。
3)严格排他性解耦裁剪:利用8连通域算法识别每一个独立的个体掩码块。在裁剪单体小图(Crops)时,采用排他性掩码策略:即在当前个体的ROI区域内,仅保留当前ID的像素纹理,而将属于背景或其他茬口的像素强制置黑。这种处理确保了生成的样本库中,每张图片仅包含一个绝对独立的表型目标,如图9
通过WoodGrainNet提取的纯净化单体掩码(Mask),利用图像处理技术对每个平茬个体的几何表型进行量化分析。由于WoodGrainNet在分割过程中成功剥离了土壤背景并修复了撕裂边缘的像素噪声,这使得计算得到的几何参数具有极高的物理保真度。
利用图像处理技术,系统自动计算每个独立ID平茬面的像素面积A与轮廓周长L。通过空间比例尺转换,将像素维度映射为实际物理尺寸(mm)。相较于传统人工目测法,这种基于计算机视觉的特征提取方式能够排除主观误差,实现对野外大规模作业场景下平茬质量的客观、高通量量化。
为科学量化平茬作业质量,依据《半干旱地区灌木林平茬与复壮技术规范(LY/T 2676-2016)》关于“茬口整齐、平滑、无劈裂撕裂”的要求,选取圆度(C)作为核心评价指标。圆度通过平茬面面积与轮廓周长的耦合计算,能灵敏捕捉因纤维撕裂导致的边缘不规则形变,是切口机械完整性的综合表征量。其计算式为
$ C=\frac{4\pi A}{{L}^{2}} $
式中$ A $为平茬面有效面积,mm2$ L $为平茬面轮廓周长,mm。该指标能够综合反映平茬面的几何规整度与边缘平滑度。
从农艺的的角度讲,圆度越接近1,说明平茬面越圆滑、撕裂概率越低[30]。圆度低则代表平茬机切割力道不匀,存在严重毛刺,易导致病虫害或腐烂。在植物生理学层面,规整平滑的平茬面有助于保护平茬面的输导组织,减少水分过度蒸发,并促进愈伤组织的快速形成[31]。相反,低圆度的撕裂状平茬面会增加植株暴露面积,引发病原菌入侵,从而抑制侧枝的萌蘖能力。
基于多维几何指标量化结果,建立了一套自动化的平茬质量分级体系。通过对第一周基线特征的统计,系统将质量划分为优秀($ C\geq 0.75 $)、一般($ 0.55\leq C< 0.75 $)与较差($ C< 0.55 $)。该标准结合了WoodGrainNet对微小撕裂的敏感识别,能有效识别出肉眼难以察觉的初期机械损伤。
在分割任务中,由于作用对象的边界模糊同时细节纹理较多,为了客观、全面地评估WoodGrainNet模型在柠条平茬切口分割任务中的性能,因此从分割精度和算法复杂度两个维度选取了4个核心指标。其中,平均交并比(mIoU)、召回率 (Recall) 、F1分数 (F1-Score)用于验证模型对复杂野外图像的特征解析能力与分割准确性;参数量(Params)用于评估网络架构设计的紧凑性与计算效率。其中运行设备及版本号如表3
为了直观评估WoodGrainNet在特征学习过程中的稳定性与收敛速度,记录了各模型在150个Epoch训练周期内的验证集性能变化。图10展示了各模型在平均交并比(mIoU)指标上的收敛曲线。
取mIoU作为衡量训练质量的核心可视化指标,mIoU直接量化了预测掩码与真实平茬面在物理面积与空间形态上的重合程度。由于后续的萌蘖潜力预测高度依赖于平茬面圆度、面积等形态学特征的精确计算,因此,mIoU的收敛水平直接决定了下游农艺指标测算的可靠性边界。
结合图10可以观察到以下显著趋势:1)WoodGrainNet在训练初期(0~50 Epochs)即展现出快速的学习能力,并在约80Epoch后与其他模型拉开差距,最终稳定在86.99%的最高位,证明了引入的频域与形状先验有效加速了网络对特征的聚焦。2)相比于U-Net和PSPNet在训练后期的剧烈震荡,WoodGrainNet的曲线表现更为平滑。这表明多模态注意力融合机制有效抑制了背景噪声对梯度的干扰,使得模型在优化过程中并未陷入局部极小值,展现出优异的泛化鲁棒性。3)SegFormer-B1表在最终的收敛精度上仍略逊于WoodGrainNet。进一步证实,虽然Transformer架构具有全局感受野,但在处理缺乏纹理细节的微小树桩边缘时,仍需专用的物理约束模块来辅助精细化分割。
为了验证WoodGrainNet在非结构化野外环境下对柠条平茬平茬面的分割性能,将其与U-Net、PSPNet、DeepLabV3+以及SegFormer-B1等主流语义分割网络进行了横向对比。表4展示了各模型在测试集上的量化评估结果。
从分割精度的维度来看,WoodGrainNet 展现出了显著的性能优势。mIoU约为86.99%,分别比DeepLabV3+和SegFormer-B1提升了2.60和4.01个百分点。这表明本模型在处理复杂的背景干扰(如黄土、枯草)时具有更强的特征辨别能力。
受限于平茬面在原始图像中占比极小,属于典型的密集小目标分割任务 。由于小目标的边界像素基数较低,指标对像素级的偏移具有极高的敏感性,仅1~2像素的分割偏差即会导致该指标显著下降。在衡量平茬面轮廓完整度的Boundary IoU指标上,WoodGrainNet为22.59%,优于SegFormer-B1 (18.29%)和PSPNet (10.58%)。传统的卷积网络(如PSPNet)在经过多次下采样后往往丢失了高频空间细节,导致分割出的树桩边缘模糊或粘连。而WoodGrainNet得益于引入的形状约束分支,能够显式地保留平茬面的高频梯度信息,从而有效解决了部分柠条平茬面的“粘连”问题,为后续精准计算平茬面圆度和面积提供了可靠的几何基础。
在模型复杂度与推理速度的权衡方面,为客观验证 WoodGrainNet在实际生产环境中的工程实用性,本研究进一步明确并评估了其端到端的全链路处理性能。将输入分辨率统一设定为512×512像素,并将批处理大小设定为8,以测试移动式智能评估系统在处理连续视频流或批量采集序列时的并发解析场景。测试结果显示DeepLabV3+虽然精度尚可,但其参数量高达40.52 M,导致推理速度仅为17.83帧/s,难以满足平茬作业的实时性需求。相比之下,WoodGrainNet通过轻量化的编码器设计,将参数量控制在7.59 M,推理速度更是达到了51.78帧/s,该模型能具有工程落地价值。
WoodGrainNet的F1-Score达到86.52%,模型在保证高查全率的同时,降低了将相似背景(如圆形石块、断裂枯枝)误判为新鲜平茬面的概率。相比之下,SegFormer-B1虽然利用Transformer架构捕捉了全局上下文,但在缺乏针对性物理先验的情况下,其F1-Score仍低于本方法3.78个百分点,进一步验证了专用模型设计的必要性。
为了更直观地评估各模型在真实野外复杂环境下的泛化能力,选取了具有代表性的挑战场景进行可视化对比,如图11
为了探究WoodGrainNet中各个模块对整体性能的贡献,以 SegFormer-B0为基线模型,通过逐步添加频域分支、形状分支及融合模块,设计了多组消融试验,如表5所示。
频域感知分支对“视觉伪装”的破解在基线模型的基础上引入频域分支后,mIoU从84.70%提升至 85.67%。在野外光照强烈或阴影覆盖的场景下,平茬面与沙壤土在RGB颜色空间中极度相似,产生视觉相似性高现象,导致基线模型误判。频域分支通过 Haar小波变换提取图像的频谱特征,利用木质平茬面特有的年轮周期性高频信号,成功在频域维度将前景与背景解耦。试验表明,该分支显著降低了背景误检率,证明了引入频谱物理先验的有效性。
单独引入形状分支后,mIoU提升至84.86%。虽然整体mIoU的提升幅度看似有限,但该分支的核心贡献在于对边缘像素的精细化修正。通过引入Sobel算子提取的边缘梯度图,网络被强制关注图像中的高频轮廓区域,充当了“语义剪刀”的角色。这使得模型能够有效切断相邻树桩之间错误的弱连接区域,提升了分割结果的拓扑正确性,这对于后续基于连通域分析的萌蘖数统计至关重要。
在试验中分别对三分支使用了简单通道拼接和三模态注意力融合机制拼接。当仅使用简单的通道拼接整合三分支特征时,mIoU为85.29%。而当采用本文提出的多分支注意力融合模块后,mIoU跃升至86.99%,相比简单拼接提升了1.7个百分点。
为了定量评估WoodGrainNet系统所提取的形态学特征对植株后续生长的实际影响,基于1016组经过形态学滤波清洗的野外实测样本,构建了平茬面圆度指数($ C $)与第五周侧枝萌蘖数($ N $)之间的统计分析模型。较高的mIoU保证了模型对柠条平茬面区域提取的完整性,这是准确计算几何指标的前提。虽然受限于小目标像素敏感性,Boundary IoU指标表现稍弱,但由于mIoU确保了目标主体的精准锁定,使得计算得到的圆度能够稳定地反映平茬质量的物理特征。
统计结果显示(如图12a),二者之间存在正线性相关关系,决定系数为$ {R}^{2}=0.764 $,且显著性水平满足$ P< 0.001 $。回归线表明,随着平茬面圆度的提升,样本点紧密收敛于拟合线周围,证明了圆度指标能够解释超过76%的萌蘖数量变化。尽管回归趋势显著,但在样本数据中仍观察到约5%的离群个体。例如,部分具有高圆度特征($ C> 0.90 $)的样本实际萌蘖数较低,这反映了植物生长受局部环境因子(如土壤水分胁迫、微地形差异)和植株基础生命活力多重限制的生物学特性。这一高拟合度有力地排除了野外环境噪声的干扰,证实了平滑完整的平茬面是保障水分传输与养分留存的物理基础。
为了验证系统分级标准的有效性,分类箱线图(如图12b)进一步展示了萌蘖潜力在“较差”“良好”与“优秀”3个等级间的分布差异。数据呈现出清晰的“阶梯式”跨越特征:当$ C< 0.55 $时,植株萌蘖数中位数为1,且分布区间狭窄,表明粗糙撕裂的平茬面严重抑制了生长;当圆度提升至$ 0.55\leq C< 0.75 $区间时,中位数上升至2~3;而当$ C\geq 0.75 $时,萌蘖潜力被最大程度激活,中位数稳定在4~5的高位水平。这种显著的层级区分度表明,设定的分级阈值不仅在几何上可分,更在生物学产量上具有高度的预测可靠性。
综上,上述分析图中的离群点虽然反映了野外植物个体的生理异质性(如根系受损导致的生长停滞),但并未改变整体的统计规律。该结果充分证明,通过优化平茬作业参数以获得高圆度平茬面,是实现旱区柠条资源高效复壮的关键农艺手段。
田间试验于2025年7月5日、7月22日和7月30日在宁夏盐池宁夏大学柠条野外试验基地进行(如图13),试验设备为智慧农业信息获取平台,感知系统为深度相机ZED 2i;工控机硬件为NVIDIA RTX 4060 8 GB。
为全面检验柠条平茬质量移动监测系统在真实非结构化环境中的工程可靠性,本试验首先开展了基于边缘计算的模型部署与实时性评估。试验将训练优化的 WoodGrainNet 算法部署于移动终端的工控机中,重点考察其在受限算力条件下的推理帧率与识别稳定性,旨在验证该视觉系统能否满足自动化平茬作业对高实时性与高精度的双重工程需求。
此外,为评估模型的场景适应性与实际应用价值,试验进一步开展了野外泛化测试与农艺预测验证。一方面,通过随机平茬采样,检验网络在复杂野外背景与干扰下的精准分割能力;另一方面,结合定点追踪观测,系统验证了基于网络提取的形态学特征来预测柠条萌蘖再生潜力的生物学准确性,从而深入论证了“形态-农艺”协同评估方法的可行性。
针对野外环境中存在的枯草、沙砾及高饱和度人工标签干扰(如图14)。WoodGrainNet模型展现了卓越的抗干扰性能。在移动机器人行进视场中,模型通过三模态特征融合,有效抑制了蓝色标签等非生物噪声,精准锁定具备年轮纹理的木质部区域。可视化结果显示,生成的黄色识别框紧密贴合不规则平茬面轮廓,证实了系统在非结构化复杂场景下对语义目标的鲁棒锁定能力。
为了客观评价系统在野外大规模作业场景下的综合性能与普适性,在试验区内随机选取了120株平茬样本进行批量化验证。通过对比系统自动化输出的评估结果与人工实地观测真值,从“质量分级一致性”与“萌蘖预测准确性”两个维度进行了定量分析。
统计结果显示,系统在120个测试样本中正确分类了112例,总体分级准确率高达93.3%。这表明系统能够有效应对野外复杂背景和不同质量等级的平茬面进行精准区分。主要的分类误差集中在“良好(Good)”与“较差(Poor)”的临界区域(约3.1% 的较差样本被误判为良好)。经现场复查,这类误判主要归因于部分低矮茬口被风沙轻微掩埋,导致提取的轮廓周长L产生偏差,进而影响了圆度计算的精确度。
图15进一步展示了系统预测萌蘖数与第5周实地观测真值之间的线性回归关系。两者呈现出显著的正相关趋势,决定系数$ {R}^{2}=0.56 $N=120, P< 0.001)。绝大多数数据点紧密分布在$ y=x $参考线两侧的$ \pm 1 $误差带内,表明系统能够准确捕捉到“平茬面几何形态”与“萌蘖潜力”之间的生物学映射关系。
相较于4.4节在静态数据集上获得的理想基准值($ {R}^{2} $=0.764),野外实测的相关性出现了轻微下降。这种精度衰减客观反映了野外非结构化环境的真实挑战——移动底盘的震动、扬尘遮挡及光照剧变不可避免地对特征提取造成了细微干扰。然而,系统依然保持了较高水平的预测能力,证明了WoodGrainNet模型具有卓越的工程鲁棒性。图中存在的少量离群点(如预测值偏高但实测值为0的样本)揭示了植物生长的多因子驱动特性。
这表明除了本系统监测的“机械损伤”外,萌蘖本质上是受内源激素调控的生理过程,部分样本可能处于深度生理休眠或衰老期,其内源激素系统对平茬刺激的感应失效,导致预测模型失效,另外,根系活力衰退或地下病虫害等不可视因子也是限制萌蘖的重要变量。尽管如此,本系统依然在仅依靠视觉表型的情况下实现了有效的长势预判。
图16展示了基于120组野外实测样本生成的平茬质量分级混淆矩阵,统计结果表明,系统在复杂非结构化环境下的总体分级准确率达到了90.8%(109/120)。绝大多数样本点集中分布在矩阵的主对角线上,直观地反映了系统预测结果与人工评级的高度一致性。
在种质资源筛选最为关注的优秀等级中,系统的查准率为94.9%(37/39)。相较于理想试验环境,野外实测中出现了2例误判将良好误识为优秀。经回溯分析,这种约5%的误差主要归因于拍摄时的强光直射导致平茬面边缘产生高光溢出,使得图像分割算法提取的轮廓平滑度略高于真实值。这种极小范围内的高估误差符合野外光照多变的客观规律,且在实际抚育管理中处于可接受的安全阈值内。
针对柠条平茬作业中缺乏客观质量评价手段、依赖人工经验、效率低下等痛点,以计算机视觉与深度学习技术为核心,开展了从算法模型构建、农艺机理量化到智能装备集成的系统性研究。主要结论如下:
1)提出了面向柠条平茬面纹理特征的WoodGrainNet分割网络。针对野外复杂背景下平茬面边缘模糊、纹理多变的问题,设计了RGB图像、频域特征与边缘梯度的三模态融合机制。试验表明,该模型在自建数据集上的分割精度mIoU为86.99%优于DeepLabV3+等主流网络,有效解决了沙土掩埋与枯草遮挡下的微小目标识别难题。
2)建立了基于几何表型的平茬质量分级与萌蘖预测体系。通过大规模统计分析,确立了以圆度($ C $)为核心的量化评价指标,制定了“优/良/差”三级质量标准。揭示了平茬面几何完整性与后期侧枝萌蘖潜力之间的正相关生物学机制,为平茬质量的农艺解释提供了理论依据。
3)开发了柠条平茬质量移动式智能化评估系统。将轻量化算法部署于移动机器人平台,实现了作业现场的实时监测。野外实地验证表明,系统在移动工况下的分级准确率达到90.8%,萌蘖预测趋势与实测真值显著相关,具备了替代人工巡检的工程应用能力。
该文章主要通过几何学的角度揭示了柠条平茬面与侧枝萌蘖数的关系,尽管在大样本下取得了显著的相关性,但仍存在一定局限性。生物学研究表明,内部激素的影响和原始植株径的大小直接决定了桩头潜伏芽的基数。结合植物生理学试验与代谢组学分析手段,动态监测平茬后桩头组织中内源激素变化。通过探究不同平茬质量产生的“机械刺激”如何诱导信号分子表达并激活潜伏芽,从分子层面阐明“形态-激素-再生”的耦合机理。
在未来的研究中,将考虑引入原始地径作为协变量,同时,引入表面粗糙度、撕裂深度,构建基于“生物潜力(潜伏芽)-机械干扰(平茬质量)-环境变量(土壤、气候条件)”的多因素耦合回归模型,以期实现对柠条再生能力更全面、更精准的量化评估。同时,利用本系统开展针对不同切割机构(如圆盘式、往复式、剪切式)作业性能的横向对比与参数优化,是实现柠条精准抚育机械选型的关键方向。

参考文献 引证文献
排序方式:
1
GAO Y Y, WANG Y T, QU A L, et al. Study of sawing parameters for Caragana korshinskii (C. K. ) branches[J]. Forests, 2022, 13(2): 327-327.
2
CHE C, ZHANG M, YANG W, et al. Dissimilarity in radial growth and response to drought of Korshinsk peashrub (Caragana korshinskii Kom.) under different management practices in the western Loess Plateau[J]. Frontiers in Plant Science, 2024, 15: 1-11.
3
WANG X Q, HUANG X Y, ZHANG Z C, et al. Effect of Caragana korshinskii Kom. as a partial substitution for sheep forage on intake, digestibility, growth, carcass features, and the rumen bacterial community[J]. Tropical Animal Health and Production, 2022, 54(3): 190.
4
GAO Y Y, WANG Y T, KANG F, et al. Multi-objective optimization of cross-section integrity rate and sawing power consumption in sawing Caragana korshinskii Kom. branches[J]. Industrial Crops and Products, 2023, 193: 116244.
5
王昱潭, 张加欣, 高垚垚, 等. 液压剪式柠条平茬机的设计与试验[J]. 农业工程学报, 2025, 41(14): 71-81.
WANG Yutan, ZHANG Jiaxin, GAO Yaoyao, et al. Design and test of the hydraulic shear-type Caragana korshinski Kom. coppicing machine[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(14): 71-81. (in Chinese with English abstract)
6
苏飞保, 王振华, 翟改霞, 等. 柠条机械化收获技术与装备研究现状及发展趋势[J]. 农业工程, 2021, 11(10): 20-27.
SU Feibao, WANG Zhenhua, ZHAI Gaixia, et al. Research status and development trend of Caragana korshinski mechanized harvesting technology and equipment[J]. Agricultural Engineering 2021(11): 20-27 (in Chinese with English abstract)
7
JI W, LI J, BI Q, et al. Correction to: segment anything Is not always perfect: an investigation of SAM on different real-world applications[J]. Machine Intelligence Research, 2024, 21(6): 1215.
8
WANG Y, YANG L, LIU X, et al. An improved semantic segmentation algorithm for high-resolution remote sensing images based on DeepLabv3[J]. Scientific Reports, 2024, 14(1): 60375.
9
张睿, 王骞, 张延军, 等. 基于多任务分割与自适应压缩的黄花菜采摘点三维定位[J]. 农业工程学报, 2026, 42(4): 66-77.
ZHANG Rui, WANG Qian, ZHANG Yanjun, et al. Three-dimensional positioning of the picking points for daylilies based onmulti-task segmentation and adaptive compression[J]. Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE), 2026, 42(4): 66-77. (in Chinese with English abstract)
10
王发明, 周洁, 莫昊一, 等. 基于改进DeepLabv3+的收获机视角下小麦倒伏区域在线检测[J]. 农业工程学报, 2026: 455-463.
WANG Faming, ZHOU Jie, MO Haoyi, et al. Online detection of wheat lodging area from the perspective of harvester based on improved DeepLabv3+[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2026, 455-463. (in Chinese with English abstract)
11
边振兴, 姚舒译, 刘晓雨, 等. 基于边缘感知DeepLabV3+模型的耕地系统生境类型识别方法[J]. 农业工程学报, 2025, 41(18): 280-290.
BIAN Zhenxing, YAO Shuyi, LIU Xiaoyu, et al. Habitat type recognition method for cultivated land system based on edge perception DeepLabV3+ model[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(18): 280-290. (in Chinese with English abstract)
12
LEI L, YANG Q, YANG L, et al. Deep learning implementation of image segmentation in agricultural applications: a comprehensive review[J]. Artificial Intelligence Review, 2024, 57(1): 149.
13
张羽丰, 杨景, 邓寒冰, 等. 基于RGB和深度双模态的温室番茄图像语义分割模型[J]. 农业工程学报, 2024, 40(2): 295-306.
ZHANG Yufeng, YANG Jing, DENG Hanbing, et al. Semantic segmentation model for greenhouse tomato images using RGB and depth bimodal[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(2): 295-306. (in Chinese with English abstract)
14
高垚垚. 柠条切割工艺参数优化及平茬装备研发[D]. 北京: 北京林业大学, 2023.
GAO Yaoyao. Optimization of Caragana korshinskii Cutting Process Parameters and Development of Stubble-flattening Equipment [D]. Beijing: Beijing Forestry University, 2023.
15
农业部农业机械试验鉴定总站. GB/T 5262-2008 农业机械 试验条件测定方法的一般规定[S]. 北京: 中国标准出版社, 2008.
16
CHE C, ZHANG M, YANG W, et al. Dissimilarity in radial growth and response to drought of Korshinsk peashrub (Caragana korshinskii Kom.) under different management practices in the western Loess Plateau[J]. Frontiers in Plant Science, 2024, 151357472-1357472.
17
LUO Z, YANG W, YUAN Y, et al. Semantic segmentation of agricultural images: A survey[J]. Information Processing in Agriculture, 2024, 11(2): 172-186.
18
ZONG Z, GUO S, PEI X, et al. Semantic segmentation of Caragana korshinskii stubble in complex environments based on an improved DeepLabV3+ network[J]. Agriculture, 2024, 14(2): 226.
19
ZHAO S, XIN G, LIU Y, et al. Semantic segmentation of remote sensing rooftops based on DAnet-SegFormer[C]// Proceedings of the 2024 4th International Conference on Artificial Intelligence, Automation and Algorithms, 2024: 200-205.
20
刘茜, 易诗, 李立, 等. 基于轻量级CNN-Transformer混合网络的梯田图像语义分割[J]. 农业工程学报, 2023, 39(13): 171-181.
LIU Xi, YI Shi, LI Li, et al. Semantic segmentation of terrace image regions based on lightweight CNN-Transformer hybrid networks[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2023, 39(13): 171-181. (in Chinese with English abstract)
21
GUI B, BHARDWAJ A, SAM L. Evaluating the efficacy of segment anything model for delineating agriculture and urban green spaces in multiresolution aerial and spaceborne remote sensing images[J]. Remote Sensing, 2024, 16(2): 414.
22
祝诗平, 林曦, 冯川, 等. 基于改进DeepLabv3+的马铃薯幼苗与杂草识别方法[J]. 农业工程学报, 2025, 41(10): 147-156.
ZHU Shiping, LIN Xi, FENG Chuan, et al. Potato seeding and weed identification based on improved DeepLabv3+[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(10): 147-156. (in Chinese with English abstract)
23
蒲应俊, 张文州, 李金广, 等. 基于改进U-Net与RGB-D图像的青花椒枝条“下桩”剪切点定位[J]. 农业工程学报, 2026, 42(1): 160-170.
PU Yingjun, ZHANG Wenzhou, Ll Jinguang, et al. Locating the pile picking points for green pepper branches using improved U-Net and R GB-D images[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2026, 42(1): 160-170. (in Chinese with English abstract)
24
LI Y, WANG D, YUAN C, et al Enhancing agricultural image segmentation with an agricultural segment anything model adapter[J]. Sensors, 2023, 23(18): 7884.
25
HE Y, LU Z, HUAN H. SF3Net: Frequency-domain enhanced segmentation network for high-resolution remote sensing imagery[J]. Remote Sensing, 2025, 17(22): 3734.
26
向玉云, 陈思远, 高爽, 等. 基于自适应BayesShrink和频-空特征融合的作物病害识别方法[J]. 农业工程学报, 2025, 41 (06): 204-215.
XIANG Yuyun, CHEN Siyuan. GAO Shuang. et al. Crop disease identification method based on adaptive BayesShrink and firequency-spatial feature fusion[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE)2025, 41(6): 204-215. (in Chinese with English abstract)
27
QIN Z, ZHANG P, WU F, et al. FcaNet: Frequency channel attention networks[C]// 2021 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway: IEEE, 2021: 763-772.
28
LI Z P, HU J, WU K Y, MIAO J W, ZHAO Z X, WU J S. Local feature acquisition and global context understanding network for very high-resolution land cover classification[J]. Scientific Reports, 2024, 14: 12597.
29
ZHANG X, CHENG B, CHEN J, et al. High-resolution boundary refined convolutional neural network for automatic agricultural greenhouses extraction from GaoFen-2 satellite imageries[J]. Remote Sensing, 2021, 13(21): 4237.
30
ODUNTAN Y A, STUBBS C J, ROBERTSON D J. High throughput phenotyping of cross-sectional morphology to assess stalk lodging resistance[J]. Plant Methods, 2022, 18(1): 1-15.
31
POLIVANOVA O B, BEDAREV V A. Hyperhydricity in plant tissue culture[J]. Plants, 2022, 11(23): 3313.
2026年第42卷第12期
PDF下载
186
79
引用本文
BibTeX
文章信息
doi: 10.11975/j.issn.1002-6819.202601133
  • 接收时间:2026-01-16
  • 首发时间:2026-08-20
  • 出版时间:2026-06-30
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2026-01-16
  • 修回日期:2026-04-02
基金
作者信息
    1宁夏大学机械工程学院,银川 750021
    2宁夏贺兰山国家级自然保护区管理局,银川 750021
    3宁夏农林科学院林业与草业生态研究所,银川 750002

通讯作者:

王昱潭,博士,博士生导师,研究方向为现代农业装备与智慧农业。Email:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/nygcxb/CN/10.11975/j.issn.1002-6819.202601133
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

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

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