Article(id=1297211744322081292, tenantId=1146029695717560320, journalId=1296125453100220459, issueId=1297211624738284246, articleNumber=null, orderNo=null, doi=10.11975/j.issn.1002-6819.202511017, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1762185600000, receivedDateStr=2025-11-04, revisedDate=1771948800000, revisedDateStr=2026-02-25, acceptedDate=null, acceptedDateStr=null, onlineDate=1787208980875, onlineDateStr=2026-08-20, pubDate=1782748800000, pubDateStr=2026-06-30, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1787208980875, onlineIssueDateStr=2026-08-20, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1787208980875, creator=13701087609, updateTime=1787208980875, 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=216, endPage=226, ext={EN=ArticleExt(id=1297211744720540173, articleId=1297211744322081292, tenantId=1146029695717560320, journalId=1296125453100220459, language=EN, title=Intelligent pruning recommendation model for fruit trees based on 3D canopy reconstruction and collaborative light-efficiency analysis, columnId=1297211683278189232, journalTitle=Transactions of the Chinese Society of Agricultural Engineering, columnName=Agricultural Information and Electrical Technologies, runingTitle=null, highlight=null, articleAbstract=

Fruit-tree canopies are typically characterized by complex branching architecture and dense foliage, leading to severe self-occlusion, uneven light distribution, and low light-use efficiency. However, experience-driven decisions cannot fully meet the large-scale pruning of the standard canopy shapes and optimal regulation of tree vigor in the orchard. In this study, an intelligent pruning model was proposed to optimize the canopy structure reconstruction and light-efficiency evaluation using Neural Radiance Fields (NeRF). A reproducible, quantitative, and visualization-friendly workflow was also provided for canopy analysis and pruning under a real orchard. Qingcuili plum (Prunus salicina cv. ‘Qingcuili’) was selected as the target species. Multi-view videos were captured around each tree from multiple angles for sufficient coverage of the canopy under field lighting and background. A NeRF reconstruction was used to learn volumetric radiance and density fields from the video frames. A high-fidelity 3D representation of the tree was generated from the reconstructed structure. Branch topology and geometric descriptors (e.g., branch order, orientation, length, and spatial distribution) were extracted for decision-making. The Monte Carlo Ray Tracing (MCRT) module was integrated to simulate ray–canopy interactions. Both direct and diffuse radiation pathways were estimated to quantify light conditions in the 3D canopy space. Two indicators were computed: light interception ratio (LIR) to characterize the proportion of incident light intercepted by the canopy, and energy interception ratio (EIR) to reflect the effective energy under the simulated radiation field. A pruning recommendation model was constructed to fuse: (i) branch-classification and geometric features, and (ii) light-efficiency weights derived from the MCRT outputs. Candidate-branch suggestions were given for the improved canopy illumination with structural feasibility. In addition, a virtual interactive pruning system was developed to support human-in-the-loop validation, intuitive visualization of light distribution, and pruning effects before field implementation. The framework was validated on a dataset of 102 Qingcuili plum trees with diverse canopies and growth. The NeRF-based reconstruction was achieved with high accuracy, with an average reconstruction error of 4.3%, indicating reliable recovery of canopy structure under complex occlusion. The pruning recommendation performance reached 93.2% accuracy, compared with expert labelling. Pruning recommendations were consistent with practical knowledge. The optimal pruning strategy was applied to substantially improve the canopy light conditions. LIR and EIR increased by approximately 15.2% and 18.9%, respectively, indicating enhanced light interception and more effective energy capture. From a deployment perspective, the end-to-end system response time remained stable in 2.3 min using cloud GPU acceleration (NVIDIA V100), indicating favorable real-time applicability for decision support and interactive analysis. A canopy structure–light-efficiency optimization was integrated with NeRF 3D reconstruction, MCRT light simulation, and feature–weight fusion for intelligent pruning. The 3D canopy reconstruction and quantitative pruning improved the light-use efficiency and the precision of tree vigor regulation in a real orchard. The finding can provide a feasible technical pathway toward digital twins and smart pruning for fruit-tree production.

, authors=Xun ZHANG1, Renpeng LIU1, Jishu ZHENG2, Bo FANG3, Hongchun QU4, *, authorsList=Xun ZHANG, Renpeng LIU, Jishu ZHENG, Bo FANG, Hongchun QU, authorCompany=null, correspAuthors=Hongchun QU, 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=1297211748898066976, articleId=1297211744322081292, tenantId=1146029695717560320, journalId=1296125453100220459, language=CN, title=基于冠层三维重建与光效协同分析的果树智能剪枝推荐模型, columnId=1297211683441767090, journalTitle=农业工程学报, columnName=农业信息与电气技术, runingTitle=null, highlight=null, articleAbstract=

针对果树冠层结构复杂、树枝密集遮挡导致光能利用率低及传统修剪经验依赖强、不规范的问题,该研究提出一种基于神经辐射场的树体三维重建与光效协同优化的剪枝推荐模型。该研究以青脆李为研究对象,通过多角度视频采集和神经辐射场建模实现果树树体结构的高精度三维重建,提取枝条拓扑特征并结合蒙特卡洛光线追踪算法,模拟冠层光能分布并计算光拦截比与能量截获比。在此基础上构建基于枝条分类几何特征与光效权重融合的剪枝推荐模型,并开发虚拟交互修剪系统用于验证与可视化。结果表明:模型在102株青脆李树中验证,平均重建误差为4.3%,剪枝推荐准确率达93.2%,光拦截比提升15.2%,能量截获比提升18.9%,且在云端GPU(V100)支持下系统响应时间稳定在2.3 min以内,具备良好的通用性与实时性。该研究所提出的果树冠层结构–光效协同优化模型能够在真实场景下实现果树三维重建与智能剪枝推荐,有效提升光能利用效率与树势调控精度,为果树数字孪生与智慧修剪提供可行路径和技术支撑。

, authors=张勋1, 刘仁鹏1, 郑吉澍2, 方波3, 屈洪春4, *, authorsList=张勋, 刘仁鹏, 郑吉澍, 方波, 屈洪春, authorCompany=null, correspAuthors=屈洪春, authorNote=

张勋,高级农艺师,研究方向为智慧农业。Email:

, correspAuthorsNote=
屈洪春,博士,教授,博士生导师,研究方向为作物表型量化数字模型、农业AI技术。Email:
, copyrightStatement=版权所有 © 2026 农业工程学报编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=77sBKxOMYgg25vYiI7qlcA==, magXml=fBQvmkXlR3E1+iVX1wdvjg==, pdfUrl=null, pdf=ZE8hjyP8US46wyK/r/aQ8Q==, pdfFileSize=3182274, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=0pBvNu5fmBbEtC3Rf69i/w==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=Y8IeU2wUoWKpP8fOhShUZg==, mapNumber=null, fund=null)}, authors=[Author(id=1299828246191825912, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=hcchyu@gmail.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1299828246254740474, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, authorId=1299828246191825912, language=EN, stringName=Xun ZHANG, firstName=Xun, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Wushan Fruit Industry Development Center, Chongqing 404716, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828246321849339, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, authorId=1299828246191825912, language=CN, stringName=张勋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1重庆市巫山县果品产业发展中心,重庆 404716, bio={"content":"

张勋,高级农艺师,研究方向为智慧农业。Email:

"}, bioImg=null, bioContent=

张勋,高级农艺师,研究方向为智慧农业。Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828245868864491, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, xref=1, ext=[AuthorCompanyExt(id=1299828245877253100, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828245868864491, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Wushan Fruit Industry Development Center, Chongqing 404716, China), AuthorCompanyExt(id=1299828245881447405, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828245868864491, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1重庆市巫山县果品产业发展中心,重庆 404716)])]), Author(id=1299828246384763901, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, 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=1299828246451872767, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, authorId=1299828246384763901, language=EN, stringName=Renpeng LIU, firstName=Renpeng, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Wushan Fruit Industry Development Center, Chongqing 404716, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828246535758848, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, authorId=1299828246384763901, language=CN, stringName=刘仁鹏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1重庆市巫山县果品产业发展中心,重庆 404716, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828245868864491, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, xref=1, ext=[AuthorCompanyExt(id=1299828245877253100, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828245868864491, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Wushan Fruit Industry Development Center, Chongqing 404716, China), AuthorCompanyExt(id=1299828245881447405, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828245868864491, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1重庆市巫山县果品产业发展中心,重庆 404716)])]), Author(id=1299828246615449601, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, 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=1299828246678364163, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, authorId=1299828246615449601, language=EN, stringName=Jishu ZHENG, firstName=Jishu, middleName=null, lastName=ZHENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2Institute of Agricultural Engineering, Chongqing Academy of Agricultural Sciences, Chongqing 401329, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828246741278724, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, authorId=1299828246615449601, language=CN, stringName=郑吉澍, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2重庆市农业科学院农业工程研究所,重庆 401329, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828245969527790, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, xref=2, ext=[AuthorCompanyExt(id=1299828245977916399, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828245969527790, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Institute of Agricultural Engineering, Chongqing Academy of Agricultural Sciences, Chongqing 401329, China), AuthorCompanyExt(id=1299828245982110704, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828245969527790, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2重庆市农业科学院农业工程研究所,重庆 401329)])]), Author(id=1299828246816776198, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, 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=1299828246888079368, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, authorId=1299828246816776198, language=EN, stringName=Bo FANG, firstName=Bo, middleName=null, lastName=FANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3Institute of Fruit Tree Research, Chongqing Academy of Agricultural Sciences, Chongqing 401329, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828246959382537, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, authorId=1299828246816776198, language=CN, stringName=方波, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3重庆市农业科学院果树研究所,重庆 401329, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828246040830961, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, xref=3, ext=[AuthorCompanyExt(id=1299828246049219570, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828246040830961, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Institute of Fruit Tree Research, Chongqing Academy of Agricultural Sciences, Chongqing 401329, China), AuthorCompanyExt(id=1299828246057608179, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828246040830961, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3重庆市农业科学院果树研究所,重庆 401329)])]), Author(id=1299828247030685707, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=quhc@cqupt.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1299828247106183181, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, authorId=1299828247030685707, language=EN, stringName=Hongchun QU, firstName=Hongchun, middleName=null, lastName=QU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, *, address=4Center for Ecological Security Research, Chongqing University of Posts and Telecommunications, Chongqing 400065, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828247177486350, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, authorId=1299828247030685707, language=CN, stringName=屈洪春, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, *, address=4重庆邮电大学生态安全研究中心,重庆 400065, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828246107939828, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, xref=4, ext=[AuthorCompanyExt(id=1299828246116328437, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828246107939828, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4Center for Ecological Security Research, Chongqing University of Posts and Telecommunications, Chongqing 400065, China), AuthorCompanyExt(id=1299828246128911350, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828246107939828, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4重庆邮电大学生态安全研究中心,重庆 400065)])])], keywords=[Keyword(id=1299828247353647119, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=EN, orderNo=1, keyword=fruit tree canopy management), Keyword(id=1299828247412367376, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=EN, orderNo=2, keyword=visual modeling), Keyword(id=1299828247496253457, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=EN, orderNo=3, keyword=canopy structure analysis), Keyword(id=1299828247554973714, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=EN, orderNo=4, keyword=light-efficiency simulation), Keyword(id=1299828247617888275, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=EN, orderNo=5, keyword=co-optimization), Keyword(id=1299828247689191444, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=EN, orderNo=6, keyword=pruning recommendation model), Keyword(id=1299828247760494613, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=CN, orderNo=1, keyword=果树树体管理), Keyword(id=1299828247831797782, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=CN, orderNo=2, keyword=视觉模型), Keyword(id=1299828247894712343, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=CN, orderNo=3, keyword=冠层结构分析), Keyword(id=1299828247957626904, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=CN, orderNo=4, keyword=光效模拟), Keyword(id=1299828248037318681, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=CN, orderNo=5, keyword=协同优化), Keyword(id=1299828248125399066, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=CN, orderNo=6, keyword=剪枝推荐模型)], refs=[Reference(id=1299828250121887795, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, 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=PEAVEY M, GOODWIN I, MCCLYMONT L. The effects of canopy height and bud light exposure on the early stages of flower development in Prunus persica (L.) Batsch [J]. Plants, 2020, 9(9): 1073., articleTitle=null, refAbstract=null), Reference(id=1299828250197385268, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, 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=ANTHONY M, MINAS S. Optimizing peach tree canopy architecture for efficient light use, increased productivity and improved fruit quality[J]. Agronomy, 2021, 11(10): 1961., articleTitle=null, refAbstract=null), Reference(id=1299828250260299829, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, 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=LI J, SUN H, WU G, et al. Structural parameter determination and pruning pattern analysis of pear tree shoots for dormant pruning [J]. Plant Phenomics, 2025, 100136., articleTitle=null, refAbstract=null), Reference(id=1299828250323214390, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, 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=LIU S, BARET F, ABICHOU, M, et al. Importance of the description of light interception in crop growth models[J]. Plant Physiology, 2021, 186(2): 977-997., articleTitle=null, refAbstract=null), Reference(id=1299828250386128951, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, 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=ARIESEN-VERSCHUUR N, VERDOUW C, TEKINERDOGAN B. Digital Twins in greenhouse horticulture: A review[J]. Computers and Electronics in Agriculture, 2022, 199: 107183., articleTitle=null, refAbstract=null), Reference(id=1299828250444849208, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=NAVONE A, MARTINI M, CHIABERGE M. Autonomous robotic pruning in orchards and vineyards: A review[J]. Smart Agricultural Technology,2025,12:101283., articleTitle=null, refAbstract=null), Reference(id=1299828250524540985, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=ELFIKY N. Application of artificial intelligence in the food industry: AI-based automatic pruning of dormant apple trees. In Artificial intelligence: A real opportunity in the food industry [M]. Cham: Springer International Publishing, 2022: 1-15., articleTitle=null, refAbstract=null), Reference(id=1299828250579066938, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=DEJON T. Simulating fruit tree growth, structure, and physiology using L-systems[J]. Crop Science, 2022, 62(6): 2091-2106., articleTitle=null, refAbstract=null), Reference(id=1299828250658758715, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=ROJO F, DEL RIO R, SNYDER L, et al. A novel simulation model to predict photosynthetic active radiation interception in micro-irrigated citrus production orchards based on tree spacing, canopy geometry, and row orientation[J]. Computers and Electronics in Agriculture, 2023, 212: 108062., articleTitle=null, refAbstract=null), Reference(id=1299828250738450492, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=QU H, RAN H, GONG W, et al. A simulation and evaluation method for fruit tree canopy light interception based on 3D reconstruction[J]. Journal of the ASABE, 2025, 68(5): 883-895., articleTitle=null, refAbstract=null), Reference(id=1299828250813947965, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=JIANG A, LIU J, ZHOU J, et al. Skeleton extraction from point clouds of trees with complex branches via graph contraction[J]. The Visual Computer, 2021, 37(8): 2235-2251., articleTitle=null, refAbstract=null), Reference(id=1299828250876862526, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=MEYER L, GILSON A, SCHOLZ O, et al. CherryPicker: Semantic skeletonization and topological reconstruction of cherry trees[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada: IEEE, 2023: 6244-6253., articleTitle=null, refAbstract=null), Reference(id=1299828250948165695, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=von HIRSCHHAUSEN S, MAGNUSSON S, KOVALENKO M, et al. AppleGrowthVision: A large-scale stereo dataset for phenological analysis, fruit detection, and 3D reconstruction in apple orchards[C]// Proceedings of the Computer Vision and Pattern Recognition Conference, Nashville, TN, USA: IEEE, 2025, 5443-5450., articleTitle=null, refAbstract=null), Reference(id=1299828251032051776, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHANG J, WANG X, NI X, et al. Neural radiance fields for multi-scale constraint-free 3D reconstruction and rendering in orchard scenes[J]. Computers and Electronics in Agriculture, 2024, 217: 108629., articleTitle=null, refAbstract=null), Reference(id=1299828251090772033, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=王红军, 林俊强, 邹湘军, 等. 基于数字孪生的果园虚拟交互系统构建[J]. 系统仿真学报, 2024, 36(6), 1493., articleTitle=null, refAbstract=null), Reference(id=1299828251157880898, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=WANG Hongjun, LIN Junqiang, ZOU Xiangjun, et al . Construction of a virtual interactive system for orchards based on digital twin[J]. Journal of System Simulation, 2024, 36(6): 1493-1508. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828251220795459, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=PENG H, GUO S, ZOU X, et al. UAVO-NeRF: 3D reconstruction of orchards and semantic segmentation of fruit trees based on neural radiance field in UAV images[J]. Computers and Electronics in Agriculture, 2025, 237(B): 110631., articleTitle=null, refAbstract=null), Reference(id=1299828251300487236, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=MA H, WANG K, MA J, et al. Calculation method of canopy effective volume for fruit tree based on LiDAR point cloud data[J]. Frontiers in Plant Science, 2025, 16: 1679027., articleTitle=null, refAbstract=null), Reference(id=1299828251359207493, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=LI S, van der WERF W, GOU F, et al. An evaluation of Goudriaan’s summary model for light interception in strip canopies, using functional-structural plant models[J]. in silico Plants, 2024, 6(1): diae002., articleTitle=null, refAbstract=null), Reference(id=1299828251426316358, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=马保建, 蒋焕煜. 休眠期果树修剪机器人视觉感知系统研究现状[J]. 农业工程, 2024, 14(2): 29-33., articleTitle=null, refAbstract=null), Reference(id=1299828251497619527, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=MA Baojian, JIANG Huanyu. Research status on visual perception system of pruning robot for dormant fruit tree[J]. Agricultural Engineering, 2024, 14(2): 29-33. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828251564728392, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=OKURA F. 3D modeling and reconstruction of plants and trees: A cross-cutting review across computer graphics, vision, and plant phenotyping[J]. Breeding Science, 2022, 72(1): 31-47., articleTitle=null, refAbstract=null), Reference(id=1299828251627642953, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=王志富, 马文强, 项斌斌, 等. 基于改进 UNet 模型的核桃树枝条分叉点定位与修剪位置选择[J]. 农业工程学报, 2025, 41(7): 165-172., articleTitle=null, refAbstract=null), Reference(id=1299828251686363210, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=WANG Zhifu, MA Wenqiang, XIANG Binbin, et al. Locating branch bifurcation points to select the pruning position of walnut trees using improved UNet model[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(7): 165-172. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828251745083467, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=BOUZIDI A, LAGA H, WANNOUS H, et al. GNF: Gaussian neural fields for multidimensional signal representation and reconstruction[J]. Computer Graphics Forum, 2025, 44(7): e70232., articleTitle=null, refAbstract=null), Reference(id=1299828251824775244, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=OSHIO H, ASAWA T. Simulating the 3D distribution of absorbed shortwave radiation in a tree crown: Comparison of simplified and Monte Carlo models[J]. Journal of Geophysical Research: Atmospheres, 2023, 128(21): e2023JD038612., articleTitle=null, refAbstract=null), Reference(id=1299828251891884109, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=LIN Z, LI B, LI H, et al. The physicochemical attributes, volatile compounds, and antioxidant activities of five plum cultivars in Sichuan[J]. Foods, 2023, 12(20): 3801., articleTitle=null, refAbstract=null), Reference(id=1299828251963187278, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=SABARIVASAN N, THANGAVEL K. Keyframe Extraction Approaches for Intelligent Video Analysis[C]// Proceedings of the 4th International Conference on Sentiment Analysis and Deep Learning (ICSADL), Janakpur, Nepal: IEEE, 2025: 1126-1133., articleTitle=null, refAbstract=null), Reference(id=1299828252021907535, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=CHEUNG W, HAMARNEH G. n-SIFT: n -dimensional scale invariant feature transform[J]. IEEE Transactions on Image Processing, 2009, 18(9): 2012-2021., articleTitle=null, refAbstract=null), Reference(id=1299828252093210704, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=LIANG X, LIN Y, FU H, et al. Rscfed: Random sampling consensus federated semi-supervised learning[C]// Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, New Orleans, USA: IEEE, 2022: 10154-10163., articleTitle=null, refAbstract=null), Reference(id=1299828252151930961, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=STARCZEWSKI A, GOETZEN P, et al. A new method for automatic determining of the DBSCAN parameters[J]. Journal of Artificial Intelligence and Soft Computing Research, 2020, 10(3): 209-221., articleTitle=null, refAbstract=null), Reference(id=1299828252227428434, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=RUCKER G, SCHIMEK-JASCH T, NESTLE U. Measuring inter-observer agreement in contour delineation of medical imaging in a dummy run using Fleiss’ kappa[J]. Methods of Information in Medicine, 2012, 51(6): 489-494., articleTitle=null, refAbstract=null), Reference(id=1299828252294537299, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=刘小军. 基于NeRF的树体结构三维重建方法研究[D]. 重庆: 重庆邮电大学, 2025., articleTitle=null, refAbstract=null), Reference(id=1299828252361646164, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=LIU Xiaojun. Research on NeRF-based tree canopy 3D reconstruction methods[D]. Chongqing: Chongqing University of Posts and Telecommunications, 2025. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828252453920853, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=LIANG Q, FALKINGHAM L, XING L. Virtual skeleton and body mass for revealing the life strategies of Sinosaurus[J]. Historical Biology, 2025, 37(7): 1729-1743., articleTitle=null, refAbstract=null), Reference(id=1299828252533612630, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=冉凰渝. 基于三维重建的果树冠层光截获模拟研究[D]. 重庆: 重庆邮电大学, 2025., articleTitle=null, refAbstract=null), Reference(id=1299828252609110103, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=RAN Huangyu. Research on Fruit Tree Canopy Light Interception Based on 3D Reconstruction[D]. Chongqing: Chongqing University of Posts and Telecommunications, 2025. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828252701384792, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=龚文俊. 基于三维重建的果树枝条分类与剪枝推荐系统研究与实现[D]. 重庆: 重庆邮电大学, 2025., articleTitle=null, refAbstract=null), Reference(id=1299828252764299353, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=GONG Wenjun. Research and Implementation on Fruit Tree Branching Classification and Pruning Recommendation Based on 3D Reconstruction[D]. Chongqing: Chongqing University of Posts and Telecommunications, 2025. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828252827213914, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=李含婷. 虚拟果树交互式修剪模拟系统研究[D]. 重庆: 重庆邮电大学, 2025., articleTitle=null, refAbstract=null), Reference(id=1299828252890128475, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=LI Hanting. Research on Interactive Virtual Fruit Tree Pruning Simulation [D]. Chongqing: Chongqing University of Posts and Telecommunications, 2025. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828252961431644, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=QU H, LIU X, LU D, et al. Geometric and multi-scale feature fusion for complete tree skeleton extraction[J]. Journal of the ASABE, 2025, 68(5): 869-882., articleTitle=null, refAbstract=null), Reference(id=1299828253036929117, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=HUANG J, HUANG L. Research on 3D modeling of Wupaolong based on sparse point cloud reconstruction of SFM algorithm[J]. Journal of Imaging Science and Technology. 2022, 66(3): 1-15., articleTitle=null, refAbstract=null), Reference(id=1299828253112426590, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=LI H, YANG X, ZHAI H, et al. Vox-surf: Voxel-based implicit surface representation[J]. IEEE Transactions on Visualization and Computer Graphics, 2022, 30(3): 1743-1755., articleTitle=null, refAbstract=null), Reference(id=1299828253179535455, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=JIANG S, YOU K, CHEN W, et al. 3D reconstruction of spherical images based on incremental structure from motion[J]. International Journal of Remote Sensing, 2024, 45(8): 2596-2621., articleTitle=null, refAbstract=null), Reference(id=1299828253259227232, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=TANG H, XU Z, CHEN S, et al. Light efficacy estimation for fruit trees based on LIDAR point clouds: A case study on pear trees[J]. Scientia Horticulturae, 2024, 324: 112590., articleTitle=null, refAbstract=null), Reference(id=1299828253330530401, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=YIN Y, LIU G, LI S, et al. A method for predicting canopy light distribution in cherry trees based on fused point cloud data[J]. Remote Sensing, 2023, 15(10): 2516., articleTitle=null, refAbstract=null), Reference(id=1299828253397639266, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=FOURIE J, HSIAO J, BATCHELOR O, et al. Generating realistic pruning solutions for automated grape vine pruning using graph neural networks[J]. Expert Systems with Applications, 2025, 298(C): 129778., articleTitle=null, refAbstract=null), Reference(id=1299828253464748131, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=MILDENHALL B, SRINIVASAN P, TANCIK M, et al. Nerf: Representing scenes as neural radiance fields for view synthesis[J]. Communications of the ACM, 2021, 65(1): 99-106., articleTitle=null, refAbstract=null), Reference(id=1299828253527662692, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=WILLIAMS H, SMITH D, SHAHABI J, et al. Modelling wine grapevines for autonomous robotic cane pruning[J]. Biosystems Engineering, 2023, 235: 31-49., articleTitle=null, refAbstract=null), Reference(id=1299828253590577253, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=LI X, LIU B, SHI Y, et al. Efficient three-dimensional reconstruction and skeleton extraction for intelligent pruning of fruit trees[J]. Computers and Electronics in Agriculture, 2024, 227: 109554., articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1299828245868864491, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, xref=1, ext=[AuthorCompanyExt(id=1299828245877253100, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828245868864491, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Wushan Fruit Industry Development Center, Chongqing 404716, China), AuthorCompanyExt(id=1299828245881447405, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828245868864491, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1重庆市巫山县果品产业发展中心,重庆 404716)]), AuthorCompany(id=1299828245969527790, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, xref=2, ext=[AuthorCompanyExt(id=1299828245977916399, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828245969527790, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Institute of Agricultural Engineering, Chongqing Academy of Agricultural Sciences, Chongqing 401329, China), AuthorCompanyExt(id=1299828245982110704, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828245969527790, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2重庆市农业科学院农业工程研究所,重庆 401329)]), AuthorCompany(id=1299828246040830961, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, xref=3, ext=[AuthorCompanyExt(id=1299828246049219570, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828246040830961, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Institute of Fruit Tree Research, Chongqing Academy of Agricultural Sciences, Chongqing 401329, China), AuthorCompanyExt(id=1299828246057608179, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828246040830961, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3重庆市农业科学院果树研究所,重庆 401329)]), AuthorCompany(id=1299828246107939828, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, xref=4, ext=[AuthorCompanyExt(id=1299828246116328437, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828246107939828, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4Center for Ecological Security Research, Chongqing University of Posts and Telecommunications, Chongqing 400065, China), AuthorCompanyExt(id=1299828246128911350, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828246107939828, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4重庆邮电大学生态安全研究中心,重庆 400065)])], figs=[ArticleFig(id=1299828248297365531, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=EN, label=Fig.1, caption=Flowchart of canopy light efficiency simulation and energy computation (MCRT), figureFileSmall=EbVxt1hAxfghdSfJ9Pk/jA==, figureFileBig=TfeXjuk2t+93OQYCBnzn5w==, tableContent=null), ArticleFig(id=1299828248385445916, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=CN, label=图1, caption=冠层光效模拟与能量计算(MCRT)流程图, figureFileSmall=EbVxt1hAxfghdSfJ9Pk/jA==, figureFileBig=TfeXjuk2t+93OQYCBnzn5w==, tableContent=null), ArticleFig(id=1299828248469331997, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=EN, label=Fig.2, caption=Flowchart of pruning recommendation iteration, figureFileSmall=SoVD712Hzgr6kv2oiMAa7A==, figureFileBig=+v/mn42jtd7sUQAgj6e1Zw==, tableContent=null), ArticleFig(id=1299828248536440862, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=CN, label=图2, caption=剪枝推荐迭代优化流程图, figureFileSmall=SoVD712Hzgr6kv2oiMAa7A==, figureFileBig=+v/mn42jtd7sUQAgj6e1Zw==, tableContent=null), ArticleFig(id=1299828248611938335, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=EN, label=Fig.3, caption=Visualization of NeRF-based plum tree canopy reconstruction, figureFileSmall=NZWtPbZE8ySgfDM/VGEDRA==, figureFileBig=xkJaycygv/nDlHDejGV0tw==, tableContent=null), ArticleFig(id=1299828248687435808, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=CN, label=图3, caption=基于NeRF的李树冠三维重建可视化, figureFileSmall=NZWtPbZE8ySgfDM/VGEDRA==, figureFileBig=xkJaycygv/nDlHDejGV0tw==, tableContent=null), ArticleFig(id=1299828248746156065, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=EN, label=Fig.4, caption=3D visualization of branch classification for 12 plum trees, figureFileSmall=lFnbj5/3j0XHd63ijZRhIA==, figureFileBig=H3BGmwLCaHXzSXp10wBxpQ==, tableContent=null), ArticleFig(id=1299828248834236450, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=CN, label=图4, caption=12棵李树枝条分类三维可视化

注:黑色表示主干、红色表示一级枝、蓝色表示二级枝、绿色表示三级枝、橙色表示四级枝。

, figureFileSmall=lFnbj5/3j0XHd63ijZRhIA==, figureFileBig=H3BGmwLCaHXzSXp10wBxpQ==, tableContent=null), ArticleFig(id=1299828248892956707, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=EN, label=Fig.5, caption=Visualization of the canopy light-efficiency analysis workflow: from 3D reconstruction and spatial discretization to ray-path simulation and light interception characterization, figureFileSmall=ORTFXXBwCi+qaCmnnlVPxw==, figureFileBig=qIVAB4zHY3CxLBGR0X3L3A==, tableContent=null), ArticleFig(id=1299828248964259876, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=CN, label=图5, caption=冠层光效分析流程可视化:从三维重建、空间离散到光线路径模拟与光截获表征, figureFileSmall=ORTFXXBwCi+qaCmnnlVPxw==, figureFileBig=qIVAB4zHY3CxLBGR0X3L3A==, tableContent=null), ArticleFig(id=1299828249073311781, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=EN, label=Fig.6, caption=Analysis of canopy light distribution characteristics, figureFileSmall=1PUp5i060NPCwcDShd7TRA==, figureFileBig=jngff/0R9QYyFHRrOU9Tsw==, tableContent=null), ArticleFig(id=1299828249136226342, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=CN, label=图6, caption=冠层光照分布特性分析, figureFileSmall=1PUp5i060NPCwcDShd7TRA==, figureFileBig=jngff/0R9QYyFHRrOU9Tsw==, tableContent=null), ArticleFig(id=1299828249190752295, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=EN, label=Fig.7, caption=Visualization of pruning types in 12 plum trees, figureFileSmall=4ZuYwxH/9f5fzh+yE8alhA==, figureFileBig=YO4xavz8KGJu9PXoIKjtzQ==, tableContent=null), ArticleFig(id=1299828249245278248, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=CN, label=图7, caption=12棵李树枝条分类可视化

注:绿色代表直立枝、蓝色代表下垂枝、紫色代表竞争枝、红色代表密集枝。

, figureFileSmall=4ZuYwxH/9f5fzh+yE8alhA==, figureFileBig=YO4xavz8KGJu9PXoIKjtzQ==, tableContent=null), ArticleFig(id=1299828249320775721, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=EN, label=Fig.8, caption=User interface of plum tree canopy analysis and pruning simulation-recommendation system, figureFileSmall=27XYzuMI2sgLlkZyxjYhcw==, figureFileBig=IGQnsSlyRuIbto9x5zdTTw==, tableContent=null), ArticleFig(id=1299828249379495978, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=CN, label=图8, caption=李树冠层分析与剪枝模拟-推荐系统界面, figureFileSmall=27XYzuMI2sgLlkZyxjYhcw==, figureFileBig=IGQnsSlyRuIbto9x5zdTTw==, tableContent=null), ArticleFig(id=1299828249442410539, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=EN, label=Fig.9, caption=Mobile APP for pruning recommendation and cloud platform for pruning recommendation model, figureFileSmall=BpINRJOv+TXEBGa6FidPXQ==, figureFileBig=XDtpfbtZ9OoUDDbNg8BVDg==, tableContent=null), ArticleFig(id=1299828249501130796, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=CN, label=图9, caption=推荐剪枝小程序与模型服务云平台, figureFileSmall=BpINRJOv+TXEBGa6FidPXQ==, figureFileBig=XDtpfbtZ9OoUDDbNg8BVDg==, tableContent=null), ArticleFig(id=1299828249568239661, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=EN, label=Tab.1, caption=

Comparisons on reconstruction accuracy for plum trees with various complexity in canopy structure

, figureFileSmall=null, figureFileBig=null, tableContent=
冠高、冠幅、透光率
(Canopy height, canopy width, light transmittance)
断点(枝)数量
Number of breakpoints
提取时间
Extraction time/s
补全时间
Completion time /s
准确率
Accuracy /%
相对误差
Relative error/%
(1.63, 1.55, 0.23)96971.955.581.670.93
(1.44, 1.56, 0.26)100978.569.682.680.89
(1.57, 1.66, 0.28)104884.877.584.390.95
(1.61, 1.44, 0.42)75992.728.585.122.64
(1.29, 1.38, 0.41)78898.131.985.962.41
(1.67, 1.45, 0.39)815104.136.886.842.09
(1.02, 1.33, 0.48)599169.216.581.744.01
(1.23, 1.26, 0.46)605171.215.482.653.80
(1.07, 1.24, 0.51)605172.914.283.853.80
), ArticleFig(id=1299828249652125742, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=CN, label=表1, caption=

不同树冠复杂度下精确度的比较

, figureFileSmall=null, figureFileBig=null, tableContent=
冠高、冠幅、透光率
(Canopy height, canopy width, light transmittance)
断点(枝)数量
Number of breakpoints
提取时间
Extraction time/s
补全时间
Completion time /s
准确率
Accuracy /%
相对误差
Relative error/%
(1.63, 1.55, 0.23)96971.955.581.670.93
(1.44, 1.56, 0.26)100978.569.682.680.89
(1.57, 1.66, 0.28)104884.877.584.390.95
(1.61, 1.44, 0.42)75992.728.585.122.64
(1.29, 1.38, 0.41)78898.131.985.962.41
(1.67, 1.45, 0.39)815104.136.886.842.09
(1.02, 1.33, 0.48)599169.216.581.744.01
(1.23, 1.26, 0.46)605171.215.482.653.80
(1.07, 1.24, 0.51)605172.914.283.853.80
), ArticleFig(id=1299828249736011823, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=EN, label=Tab.2, caption=

Effectiveness metrics of post-screening constraints

, figureFileSmall=null, figureFileBig=null, tableContent=
样本ID
Sample ID
光效提升
Light-use efficiency
improvement /%
结果枝保留率
Fruit-bearing branch
retention rate /%
剪除强度
Pruning
intensity/%
是否满足上限
Upper-limit
constraint
satisfied
注:其中结果枝保留率定义为最终未被模型建议剪除的结果枝数量占结果枝总数的比例。
Note: Fruiting-branch retention rate is defined as the percentage of fruiting branches not recommended for removal by the model relative to the total number of fruiting branches.
T0115.896.714.8
T0216.995.816.5
T0317.695.118.0
T0418.394.419.6
T0518.993.720.8
T0619.493.121.7
T0720.192.422.8
T0821.091.824.1
T0918.794.020.2
T1019.293.421.1
T1117.994.818.9
T1222.091.224.7
), ArticleFig(id=1299828249807314992, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=CN, label=表2, caption=

后验约束筛选有效性指标

, figureFileSmall=null, figureFileBig=null, tableContent=
样本ID
Sample ID
光效提升
Light-use efficiency
improvement /%
结果枝保留率
Fruit-bearing branch
retention rate /%
剪除强度
Pruning
intensity/%
是否满足上限
Upper-limit
constraint
satisfied
注:其中结果枝保留率定义为最终未被模型建议剪除的结果枝数量占结果枝总数的比例。
Note: Fruiting-branch retention rate is defined as the percentage of fruiting branches not recommended for removal by the model relative to the total number of fruiting branches.
T0115.896.714.8
T0216.995.816.5
T0317.695.118.0
T0418.394.419.6
T0518.993.720.8
T0619.493.121.7
T0720.192.422.8
T0821.091.824.1
T0918.794.020.2
T1019.293.421.1
T1117.994.818.9
T1222.091.224.7
), ArticleFig(id=1299828249874423857, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=EN, label=Tab.3, caption=

Comparisons on model performance for 3D reconstruction and light interception analysis methods

, figureFileSmall=null, figureFileBig=null, tableContent=
对比指标
Comparison metric
本文方法(视频+NeRF+骨架化+MCRT)
Proposed method (video + NeRF +
skeletonization + MCRT)
传统 SfM/MVS
Conventional
SfM/MVS [36]
LiDAR 点云法
LiDAR point-cloud
method [37]
虚拟修剪/规则模型
Virtual pruning/rule-based
model [8, 12]
注:表中“细枝连接完整率”*等结构重建验证指标包含真实+合成对照(用于模块有效性验证);其余跨方法比较指标均基于真实树体统计。不同口径指标不作直接合并比较。
Note:Structural reconstruction verification indicators marked with an asterisk in the table, such as the "complete connection rate of fine branches", include both real and synthetic controls (for module effectiveness verification). All other cross-method comparison indicators are calculated based on real tree bodies. Indicators from different statistical calibers shall not be directly combined or compared.
输入数据类型
Input data type
多视角视频帧RGB,720~1 080 p单/双相机高分辨率
影像
激光扫描点云手工参数或模板
重建精度
Reconstruction accuracy/cm
1.25 ± 0.342.87 ± 0.910.95 ± 0.27
细枝连接完整率
Fine branch connectivity completeness */%
85.96 (真实) / 88.80 (合成)67.4293.1270.15
平均峰值信噪比/结构相似性指数PSNR/SSIM28.6 / 0.93222.3 / 0.87131.1 / 0.945
单株建模响应时间
Model response time per tree/s
122 ± 15185 ± 30290 ± 6060 (手工)
光能截获比Energy interception ratio EIR ↑/%+18.4 vs 未剪枝+9.7+21.2+6.1
剪枝后光照均匀性
Post-pruning light uniformity ΔU/ %
+12.6+5.3+14.8+3.9
枝条分类准确率 / Kappa一致性
Branch classification accuracy/ Kappa agreement/%
93.2 / 91.578.4 / 75.685.7 / 82.170.3 / 68.9
系统实时响应
Real-time system response/(帧·s-1
18~226~83~520(仅动画)
总体评价
Overall evaluation
平衡精度与工程性;
适合果园规模化应用
精度中等,速度慢精度高,成本高交互强,缺定量指标
), ArticleFig(id=1299828249941532722, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, language=CN, label=表3, caption=

三维重建与光效分析方法性能对比

, figureFileSmall=null, figureFileBig=null, tableContent=
对比指标
Comparison metric
本文方法(视频+NeRF+骨架化+MCRT)
Proposed method (video + NeRF +
skeletonization + MCRT)
传统 SfM/MVS
Conventional
SfM/MVS [36]
LiDAR 点云法
LiDAR point-cloud
method [37]
虚拟修剪/规则模型
Virtual pruning/rule-based
model [8, 12]
注:表中“细枝连接完整率”*等结构重建验证指标包含真实+合成对照(用于模块有效性验证);其余跨方法比较指标均基于真实树体统计。不同口径指标不作直接合并比较。
Note:Structural reconstruction verification indicators marked with an asterisk in the table, such as the "complete connection rate of fine branches", include both real and synthetic controls (for module effectiveness verification). All other cross-method comparison indicators are calculated based on real tree bodies. Indicators from different statistical calibers shall not be directly combined or compared.
输入数据类型
Input data type
多视角视频帧RGB,720~1 080 p单/双相机高分辨率
影像
激光扫描点云手工参数或模板
重建精度
Reconstruction accuracy/cm
1.25 ± 0.342.87 ± 0.910.95 ± 0.27
细枝连接完整率
Fine branch connectivity completeness */%
85.96 (真实) / 88.80 (合成)67.4293.1270.15
平均峰值信噪比/结构相似性指数PSNR/SSIM28.6 / 0.93222.3 / 0.87131.1 / 0.945
单株建模响应时间
Model response time per tree/s
122 ± 15185 ± 30290 ± 6060 (手工)
光能截获比Energy interception ratio EIR ↑/%+18.4 vs 未剪枝+9.7+21.2+6.1
剪枝后光照均匀性
Post-pruning light uniformity ΔU/ %
+12.6+5.3+14.8+3.9
枝条分类准确率 / Kappa一致性
Branch classification accuracy/ Kappa agreement/%
93.2 / 91.578.4 / 75.685.7 / 82.170.3 / 68.9
系统实时响应
Real-time system response/(帧·s-1
18~226~83~520(仅动画)
总体评价
Overall evaluation
平衡精度与工程性;
适合果园规模化应用
精度中等,速度慢精度高,成本高交互强,缺定量指标
)], 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.1002-6819.202511017, detailUrlEn=https://castjournals.cast.org.cn/joweb/nygcxb/EN/10.11975/j.issn.1002-6819.202511017, pdfUrlCn=https://castjournals.cast.org.cn/joweb/nygcxb/CN/PDF/10.11975/j.issn.1002-6819.202511017, pdfUrlEn=https://castjournals.cast.org.cn/joweb/nygcxb/EN/PDF/10.11975/j.issn.1002-6819.202511017, 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
基于冠层三维重建与光效协同分析的果树智能剪枝推荐模型
收藏切换
PDF下载
张勋 1 , 刘仁鹏 1 , 郑吉澍 2 , 方波 3 , 屈洪春 4, *
农业工程学报 | 农业信息与电气技术 2026,42(12): 216-226
收起
收藏切换
农业工程学报 |农业信息与电气技术 2026 , 42 (12) : 216 -226
基于冠层三维重建与光效协同分析的果树智能剪枝推荐模型
全屏
[Author(id=1299828246191825912, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=hcchyu@gmail.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1299828246254740474, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, authorId=1299828246191825912, language=EN, stringName=Xun ZHANG, firstName=Xun, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Wushan Fruit Industry Development Center, Chongqing 404716, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828246321849339, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, authorId=1299828246191825912, language=CN, stringName=张勋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1重庆市巫山县果品产业发展中心,重庆 404716, bio={"content":"

张勋,高级农艺师,研究方向为智慧农业。Email:

"}, bioImg=null, bioContent=

张勋,高级农艺师,研究方向为智慧农业。Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828245868864491, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, xref=1, ext=[AuthorCompanyExt(id=1299828245877253100, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828245868864491, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Wushan Fruit Industry Development Center, Chongqing 404716, China), AuthorCompanyExt(id=1299828245881447405, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828245868864491, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1重庆市巫山县果品产业发展中心,重庆 404716)])]), Author(id=1299828246384763901, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, 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=1299828246451872767, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, authorId=1299828246384763901, language=EN, stringName=Renpeng LIU, firstName=Renpeng, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Wushan Fruit Industry Development Center, Chongqing 404716, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828246535758848, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, authorId=1299828246384763901, language=CN, stringName=刘仁鹏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1重庆市巫山县果品产业发展中心,重庆 404716, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828245868864491, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, xref=1, ext=[AuthorCompanyExt(id=1299828245877253100, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828245868864491, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Wushan Fruit Industry Development Center, Chongqing 404716, China), AuthorCompanyExt(id=1299828245881447405, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828245868864491, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1重庆市巫山县果品产业发展中心,重庆 404716)])]), Author(id=1299828246615449601, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, 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=1299828246678364163, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, authorId=1299828246615449601, language=EN, stringName=Jishu ZHENG, firstName=Jishu, middleName=null, lastName=ZHENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2Institute of Agricultural Engineering, Chongqing Academy of Agricultural Sciences, Chongqing 401329, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828246741278724, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, authorId=1299828246615449601, language=CN, stringName=郑吉澍, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2重庆市农业科学院农业工程研究所,重庆 401329, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828245969527790, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, xref=2, ext=[AuthorCompanyExt(id=1299828245977916399, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828245969527790, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Institute of Agricultural Engineering, Chongqing Academy of Agricultural Sciences, Chongqing 401329, China), AuthorCompanyExt(id=1299828245982110704, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828245969527790, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2重庆市农业科学院农业工程研究所,重庆 401329)])]), Author(id=1299828246816776198, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, 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=1299828246888079368, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, authorId=1299828246816776198, language=EN, stringName=Bo FANG, firstName=Bo, middleName=null, lastName=FANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3Institute of Fruit Tree Research, Chongqing Academy of Agricultural Sciences, Chongqing 401329, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828246959382537, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, authorId=1299828246816776198, language=CN, stringName=方波, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3重庆市农业科学院果树研究所,重庆 401329, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828246040830961, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, xref=3, ext=[AuthorCompanyExt(id=1299828246049219570, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828246040830961, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Institute of Fruit Tree Research, Chongqing Academy of Agricultural Sciences, Chongqing 401329, China), AuthorCompanyExt(id=1299828246057608179, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828246040830961, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3重庆市农业科学院果树研究所,重庆 401329)])]), Author(id=1299828247030685707, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=quhc@cqupt.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1299828247106183181, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, authorId=1299828247030685707, language=EN, stringName=Hongchun QU, firstName=Hongchun, middleName=null, lastName=QU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, *, address=4Center for Ecological Security Research, Chongqing University of Posts and Telecommunications, Chongqing 400065, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828247177486350, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, authorId=1299828247030685707, language=CN, stringName=屈洪春, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, *, address=4重庆邮电大学生态安全研究中心,重庆 400065, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828246107939828, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, xref=4, ext=[AuthorCompanyExt(id=1299828246116328437, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828246107939828, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4Center for Ecological Security Research, Chongqing University of Posts and Telecommunications, Chongqing 400065, China), AuthorCompanyExt(id=1299828246128911350, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211744322081292, companyId=1299828246107939828, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4重庆邮电大学生态安全研究中心,重庆 400065)])])]
张勋1 , 刘仁鹏1, 郑吉澍2, 方波3, 屈洪春4, *
作者信息
  • 1重庆市巫山县果品产业发展中心,重庆 404716
  • 2重庆市农业科学院农业工程研究所,重庆 401329
  • 3重庆市农业科学院果树研究所,重庆 401329
  • 4重庆邮电大学生态安全研究中心,重庆 400065
通讯作者:
屈洪春,博士,教授,博士生导师,研究方向为作物表型量化数字模型、农业AI技术。Email:
作者简介:

张勋,高级农艺师,研究方向为智慧农业。Email:

Intelligent pruning recommendation model for fruit trees based on 3D canopy reconstruction and collaborative light-efficiency analysis
Xun ZHANG1 , Renpeng LIU1, Jishu ZHENG2, Bo FANG3, Hongchun QU4, *
Affiliations
  • 1Wushan Fruit Industry Development Center, Chongqing 404716, China
  • 2Institute of Agricultural Engineering, Chongqing Academy of Agricultural Sciences, Chongqing 401329, China
  • 3Institute of Fruit Tree Research, Chongqing Academy of Agricultural Sciences, Chongqing 401329, China
  • 4Center for Ecological Security Research, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
出版时间: 2026-06-30 doi: 10.11975/j.issn.1002-6819.202511017
文章导航
收藏切换

针对果树冠层结构复杂、树枝密集遮挡导致光能利用率低及传统修剪经验依赖强、不规范的问题,该研究提出一种基于神经辐射场的树体三维重建与光效协同优化的剪枝推荐模型。该研究以青脆李为研究对象,通过多角度视频采集和神经辐射场建模实现果树树体结构的高精度三维重建,提取枝条拓扑特征并结合蒙特卡洛光线追踪算法,模拟冠层光能分布并计算光拦截比与能量截获比。在此基础上构建基于枝条分类几何特征与光效权重融合的剪枝推荐模型,并开发虚拟交互修剪系统用于验证与可视化。结果表明:模型在102株青脆李树中验证,平均重建误差为4.3%,剪枝推荐准确率达93.2%,光拦截比提升15.2%,能量截获比提升18.9%,且在云端GPU(V100)支持下系统响应时间稳定在2.3 min以内,具备良好的通用性与实时性。该研究所提出的果树冠层结构–光效协同优化模型能够在真实场景下实现果树三维重建与智能剪枝推荐,有效提升光能利用效率与树势调控精度,为果树数字孪生与智慧修剪提供可行路径和技术支撑。

果树树体管理  /  视觉模型  /  冠层结构分析  /  光效模拟  /  协同优化  /  剪枝推荐模型

Fruit-tree canopies are typically characterized by complex branching architecture and dense foliage, leading to severe self-occlusion, uneven light distribution, and low light-use efficiency. However, experience-driven decisions cannot fully meet the large-scale pruning of the standard canopy shapes and optimal regulation of tree vigor in the orchard. In this study, an intelligent pruning model was proposed to optimize the canopy structure reconstruction and light-efficiency evaluation using Neural Radiance Fields (NeRF). A reproducible, quantitative, and visualization-friendly workflow was also provided for canopy analysis and pruning under a real orchard. Qingcuili plum (Prunus salicina cv. ‘Qingcuili’) was selected as the target species. Multi-view videos were captured around each tree from multiple angles for sufficient coverage of the canopy under field lighting and background. A NeRF reconstruction was used to learn volumetric radiance and density fields from the video frames. A high-fidelity 3D representation of the tree was generated from the reconstructed structure. Branch topology and geometric descriptors (e.g., branch order, orientation, length, and spatial distribution) were extracted for decision-making. The Monte Carlo Ray Tracing (MCRT) module was integrated to simulate ray–canopy interactions. Both direct and diffuse radiation pathways were estimated to quantify light conditions in the 3D canopy space. Two indicators were computed: light interception ratio (LIR) to characterize the proportion of incident light intercepted by the canopy, and energy interception ratio (EIR) to reflect the effective energy under the simulated radiation field. A pruning recommendation model was constructed to fuse: (i) branch-classification and geometric features, and (ii) light-efficiency weights derived from the MCRT outputs. Candidate-branch suggestions were given for the improved canopy illumination with structural feasibility. In addition, a virtual interactive pruning system was developed to support human-in-the-loop validation, intuitive visualization of light distribution, and pruning effects before field implementation. The framework was validated on a dataset of 102 Qingcuili plum trees with diverse canopies and growth. The NeRF-based reconstruction was achieved with high accuracy, with an average reconstruction error of 4.3%, indicating reliable recovery of canopy structure under complex occlusion. The pruning recommendation performance reached 93.2% accuracy, compared with expert labelling. Pruning recommendations were consistent with practical knowledge. The optimal pruning strategy was applied to substantially improve the canopy light conditions. LIR and EIR increased by approximately 15.2% and 18.9%, respectively, indicating enhanced light interception and more effective energy capture. From a deployment perspective, the end-to-end system response time remained stable in 2.3 min using cloud GPU acceleration (NVIDIA V100), indicating favorable real-time applicability for decision support and interactive analysis. A canopy structure–light-efficiency optimization was integrated with NeRF 3D reconstruction, MCRT light simulation, and feature–weight fusion for intelligent pruning. The 3D canopy reconstruction and quantitative pruning improved the light-use efficiency and the precision of tree vigor regulation in a real orchard. The finding can provide a feasible technical pathway toward digital twins and smart pruning for fruit-tree production.

fruit tree canopy management  /  visual modeling  /  canopy structure analysis  /  light-efficiency simulation  /  co-optimization  /  pruning recommendation model
张勋, 刘仁鹏, 郑吉澍, 方波, 屈洪春. 基于冠层三维重建与光效协同分析的果树智能剪枝推荐模型. 农业工程学报, 2026 , 42 (12) : 216 -226 . DOI: 10.11975/j.issn.1002-6819.202511017
Xun ZHANG, Renpeng LIU, Jishu ZHENG, Bo FANG, Hongchun QU. Intelligent pruning recommendation model for fruit trees based on 3D canopy reconstruction and collaborative light-efficiency analysis[J]. Transactions of the Chinese Society of Agricultural Engineering, 2026 , 42 (12) : 216 -226 . DOI: 10.11975/j.issn.1002-6819.202511017
果树冠层结构及其光能利用效率是决定果实产量与品质的关键因素之一[1]。合理的树体结构不仅影响光能截获与光合产物的运输分配,还直接决定了花芽分化、果实发育和树势平衡[2]。在实际生产中,修剪(pruning)作为调节树势与载果关系的核心措施,是实现高光效、优质稳产的关键环节[3]。然而,传统修剪依赖人工经验,难以量化评估枝条结构与营养传输关系,不仅导致果园整体光能利用率偏低,也导致树势调节失效,难以最大限度将养分转化为产量[4]。随着智慧农业与数字孪生(digital twin)技术的发展[5],如何通过三维重建与光效分析实现果树结构优化和智能剪枝推荐,已成为数字果业应用场景如代替人工技术的机器剪枝与树体管理的重要科学问题[6]
近年来,随着植物结构建模与农业AI技术的迅速发展,果树冠层结构的精细化表征与光能利用分析成为数字果业研究的核心方向之一[7]。为表达植物形态的层级结构特征,研究者开始借助参数化与程序化生成方法建立三维可视化模型。DEJON等利用图生成规则与分形约束建立了自动生长式树体模型,能够在不同参数条件下重现果树形态变异,为冠层空间结构分析提供了形态学依据[8]。与此同时,基于高精度三维几何的光照模拟方法逐渐成熟。ROJO等和 QU等通过结合激光雷达与多视角影像重建,实现了果树冠层光能截获(light interception)与能量分布的空间定量分析,揭示了结构参数(枝角、密度、层级)与光照均匀性之间的耦合关系[9-10]
在果树冠层结构量化方面,3D 点云骨架化(skeletonization)技术的发展为树体结构解析提供了高效工具。JIANG等提出了基于图收缩的多层级骨架提取算法,可在复杂枝叶遮挡条件下保持主干连贯性[11];MEYER等通过语义分割与拓扑约束实现了樱桃树点云的精确骨架重构,显著提升了分枝检测精度[12]。与此同时,神经辐射场(neural radiance fields, NeRF)技术被引入植物与果树三维重建领域。VON HIRSCHHAUSEN等在果园环境中实现了基于 NeRF 的多视角重建,克服了传统结构光与 SfM 方法在稠密枝叶遮挡条件下的失真问题[13];ZHANG等进一步提出了 Plant-NeRF 框架,使果树冠层在光照变化与风致抖动条件下仍能实现稳定建模[14]
在国内研究方面,王红军等开发了基于 Web3D 的果树修剪可视化系统,实现了树体结构与修剪过程的三维交互,为现场修剪训练与虚拟验证提供了技术原型[15]。然而,现有研究多集中于几何层面的结构重建与可视化[16],尚缺乏将结构信息与光效指标联合建模的协同优化框架[17],也未形成可直接服务于剪枝决策与树势调控的实用模型[18]
尽管已有研究在果树冠层光照建模、三维结构可视化等方面取得了显著进展,但仍存在3个主要薄弱环节:1)树冠结构建模与光效分析尚未在统一框架下实现耦合,难以同时反映真实几何与能量传递 [19];2)现有重建方法对复杂枝叶遮挡的鲁棒性不足,限制了实际应用 [20];3)剪枝决策仍停留于经验判断,缺乏基于光效反馈的智能优化机制[21]。因此,亟需构建一种兼具几何真实性与光能计算能力的果树三维模型,实现结构—光效协同优化,并以此为基础提出智能剪枝推荐方法。
本研究以青脆李为代表的典型落叶果树为对象,综合利用神经辐射场(neural radiance fields, NeRF)三维重建[22]、蒙特卡洛光线追踪(Monte Carlo ray tracing, MCRT)模拟[23]与光效评估,建立果树冠层结构—光效协同优化模型。研究目标包括:1)构建基于多视角视频的高精度果树冠层三维重建方法;2)量化分析冠层结构参数与光能分布关系;3)提出融合几何、光效特征与农艺约束的剪枝推荐算法;4)开发虚拟交互修剪系统,实现模型的可视化与应用验证。通过该研究,期望为果树树体结构量化管理与智能修剪提供数据支撑与模块化的AI模型支持,为下一步运用到自动机器修剪提供技术基础和积累应用数据,推动果树树体管理向数字化、精准化和智能化转型。
本研究以青脆李(Prunus salicina cv. ‘Qingcuili’)[24]为研究对象,围绕“结构重建与修复—光效定量计算—剪枝智能推荐—交互系统验证”4个核心环节,构建果树冠层结构–光效协同优化模型。研究及实现过程包括:数据采集与预处理、三维结构重建、光照与能量分布模拟、枝条拓扑分析与分类、剪枝推荐模型建立以及虚拟修剪系统实现。
数据采集在重庆巫山县6个青脆李标准化示范园(曲池乡、官渡镇)进行。研究建立了两级样本库:一个是结构分析样本库(样本量n=102,实测树体82+虚拟树体20),用于三维重建与结构评估;另一个是光效分析样本库(样本量n=58),用于MCRT计算与剪枝策略验证。图像采集对象选取不同生长势和树龄(3~5 a)、树形结构为自然开心形/纺锤形/自由纺锤形等,以丰富模型学习特征。
为确保冠层结构信息完整,采用环绕式多视角视频采集方式,使用手机端和无人机(DJI Mavic 3)相结合获取果树全景影像。手持端:iPhone 13 Pro Max,4K分辨率,帧率30 帧/s,等效焦距26 mm;UAV:DJI Mavic 3,航高为1~3 m,旁向重叠≥70%,前向重叠≥80%。环绕拍摄距离为2~3 m,水平±60°俯仰,时段9:00—11:00晴天微风以降低阴影变化与风致抖动。
数据预处理流程包含如下关键步骤。首先通过OpenCV库从单个视频中抽取关键帧[25];然后利用尺度不变特征变换(scale invariant feature transform, SIFT)[26]与随机采样一致性算法(random sample consensus, RANSAC)[27]进行特征匹配与配准。随后采用密度聚类(density-based spatial clustering of applications with noise, DBSCAN),结合统计滤波滤除冗余点并生成结构化样本集[28],包括点云样本库与光照模拟样本库。最后进行尺度与姿态标准化、曝光归一化。为提升数据多样性,研究对样树按树形、树龄与冠幅分层抽样,以保证样本的代表性和模型泛化能力。
数据样本中剪枝推荐准确率所用真值由专家标注获得。为降低主观差异影响,采用“统一规范—独立标注—分歧复核—共识输出”的质量控制流程:首先制定枝条类别与剪除标准的标注手册,并进行小样本试标以统一判定口径;随后由3名果树修剪专家在盲态条件下独立标注;对不一致样本进行复核讨论并形成共识标签(多数一致直接通过,分歧样本复核后确定);同时采用Fleiss’ Kappa评估标注一致性,以量化真值可靠性[29]
为获得高保真树体几何结构,采用神经辐射场NeRF实现三维重建。NeRF 模型通过对多视角影像进行体素辐射场拟合,建立空间坐标与辐射强度的非线性映射关系:
$ ({c},{{{\sigma}}})=F_{\Theta}(x,y,z,\boldsymbol{d}) $
其中FΘ为多层感知机(multi-layer perceptron, MLP),输入为空间位置(x, y, z)与方向向量d,输出为颜色c与体积密度σ。沿射线$ r\left(t\right)=o+t\boldsymbol{d} $的颜色渲染通过体积积分计算:
$ C(r)=\int\nolimits_{t_n}^{t_f}T(t)\sigma(r(t))c(r(t)){\mathrm{d}}t $
其中C(r)为射线最终颜色,r(t)为射线方程,t为采样深度,tftn分别为射线采样的远近边界,T(t)为累积透射率,定义如下:
$T(t)=\exp\left(-\int\nolimits_{t_n}^t \sigma(r(s)){\mathrm{d}}s \right) $
其中s为积分中介变量。
模型训练基于Instant-NGP 框架(其中:分辨率层级=16,每层特征维度=2,基础分辨率=16),采用哈希编码以实现体积空间的快速映射。网络结构设为8层×256节点,激活函数为 ReLU,学习率从2×10−3线性衰减至2×10−4,每次训练光线样本4096条,粗、细采样点分别为64与32个[30]
模型输出的稠密点云经泊松重建与体素化(3~5 mm 分辨率)后,采用基于几何约束的骨架提取算法识别主干与分枝结构,并以最小生成树(minimum spanning tree, MST)保持拓扑连通性。枝条分叉角与半径关系满足幂律关系r=αlβ,其中r为枝条半径,l为枝条长度,α为比例系数,β为幂指数(典型范围β≈0.47~0.55)。对于枝条间断区段,通过方向向量插值P' = P+λvλ∈(0, dmax)进行形态修复,从而实现结构的连续重建。其中,P为起始点坐标,P'为修复后的新点坐标,v为方向向量,λ为插值步长,dmax为最大间断距离。
重建完成后,点云经泊松重建与体素化稀疏化处理。骨架提取采用 MeshLab 基于网格收缩的算法(meshlab shrink skeleton),通过体素几何中心建立节点,再以MST约束连接生成骨架线框[31]。为确保结构连续性与力学合理性,结合前期样树验证结果,本研究引入了基于方向向量与旋转-平移联合补偿的迭代点云补全策略,以改善骨架断裂并保持拓扑一致性。以此为基础进行体积密度与颜色分布建模,实现高精度的果树体积重建。该步骤为光效建模和枝条分类提供了结构支撑。
点云断枝补全的评估采用拓扑正确性与几何偏差两类指标。
1)补全准确率(Accuracy)定义为:
$ {\mathrm{Accuracy}}=\frac{{N}_{correct}}{{N}_{all}}\times 100\mathrm{\text{%} } $
其中$ {N}_{all} $为待评估断裂段总数,$ {N}_{correct} $为判定为补全正确的断裂段数量。补全正确判据为:将补全骨架与完整骨架叠加,在补全区域选取端点并定位参考节点,若参考节点间拓扑节点数差异不超过阈值(≤3),则判定该段连接正确。
2)相对误差(relative error, RE)定义为:
$ {\mathrm{RE}}=\frac{\mid {L}_{pred}-{L}_{gt}\mid }{{L}_{gt}}\times 100\mathrm{\text{%} } $
其中$ {L}_{pred} $为补全后枝段长度,$ {L}_{gt} $为对应真值长度。文中相对误差均按该定义统计。
3)真值(ground truth)构建:合成数据试验中,以完整点云提取的完整骨架作为拓扑真值;真实树体试验中,几何真值由多视角人工测量并经专家复核后确定。上述真值分别用于补全准确率与相对误差计算。
在重建模型的基础上,为了定量评估冠层内光能利用效率,本研究采用蒙特卡洛光线追踪进行三维光照模拟 [32]。太阳直射辐照度依据重庆地区夏季典型值设置为900~1000 W/m2,天空散射采用 Perez 半球模型近似。叶片光学性质由 Beer–Lambert 定律描述:I=I0ekL,其中I0为入射光强,k为消光系数,L为穿透路径长度。通过模拟光线的吸收、散射与透射过程,计算冠层光拦截率LIR(light intercept rate)与能量截获率EIR(energy intercept rate)如下:
$ {\mathrm{LIR}}=\frac{{E}_{i}}{{E}_{t}} $
$ {\mathrm{EIR}}=\frac{{E}_{a}}{{E}_{i}} $
其中Ei为拦截能量,Et为总入射能量,Ea为吸收能量,能量单位均为W/m2
模型中每株样树投射约5×106条光线,能量体素分辨率1~2 cm,统计冠层上、中、下层光照分布。最终结果以伪彩热图形式可视化,为后续剪枝策略提供能量分布依据。
算法1冠层光效模拟与能量计算(MCRT)核心流程如图1所示。其关键思想是将光线能量按传播路径在体素中逐步分配,并通过多次随机散射迭代近似真实光场。
为建立冠层分支拓扑结构与光效的耦合关系,首先从骨架模型中提取每个枝条的几何特征,包括夹角、方位角、长度、半径、曲率、分叉密度及层级深度等参数。每枝条同时计算局部LIR与EIR指标,构成复合特征向量 fI={θ, φ, l, r, κ, ρ, h, LIRi, EIRi}。
为去除冗余信息,研究采用主成分分析(principal component analysis, PCA)进行特征降维,再利用K-means聚类划分枝型(直立枝、竞争枝、密集枝、下垂枝)。综合特征评分采用线性加权:
$ S_i= a \hat f_i+ b \widehat{{\mathrm{EIR}}}_i,\; a=0.7,b=0.3$
其中Si为第i个枝条的综合特征评分,a为几何特征的权重系数,$ \widehat{{f}_{i}} $为经PCA降维及归一化后的几何特征向量评分,b为光效指标的权重系数,EIRi为第i个枝条的有效辐射指标,i为枝条编号。
前期参数探索试验与参数校准过程的数据表明,聚类后的分类准确率达到91%,与人工分型结果的Kappa一致性达到0.93。该方法既保留了枝条的几何差异,也反映了其对光能贡献的差异性[33]
在拓扑结构和光效参数的基础上,构建剪枝推荐模型。每枝条的保留权重Wi由局部能量截获率和空间位置(枝条层级和类型)加权决定:
$W_i=\frac{{\mathrm{EIR}}_i}{1+\lambda\left(\dfrac{d_i}{d'_{\max}}\right)}\cdot\gamma(h_i) $
其中di为枝条至冠层中心距离,cm;$d'_{\max} $为冠层最大半径,cm;λ为边界惩罚因子(设定为0.5);$ {\gamma (h}_{i}) $为枝条层级权重系数,给定如下:
$ r(h)=\left\{\begin{aligned} & 1.0\;\;h \le 2\\& 0.8\;\; h=3\\& 0.6\;\; h\ge 4\end{aligned}\right.$
Wi<0.25时,枝条被判定为低效并纳入候选剪除集。为了优化整体光照均匀性与能量利用率,评分目标函数J定义为
$ J={\mathrm{EIR}}-\mu .{\mathrm{Std}}\left(I\left(x\right)\right),\mu =0.2, $
其中EIR为全树整体光效,$ \mu $为均匀性惩罚系数(设定为0.2,用于平衡光效和均匀性之间的关系),Std(I(x))为均匀性惩罚,代表光效分布的标准差。当目标函数提升幅度ΔJ<1%或迭代步K达到上限(典型K=5,连续K次迭代提升幅度低于1%)时,优化过程终止[34]
算法2给出了剪枝推荐的迭代流程(如图2所示),采用贪心策略逐步删除对目标函数贡献最小的枝条,每次剪枝后调用光效模拟重新计算指标。
为避免模型仅以光效增益排序导致潜在过度修剪风险,在不改变原有候选枝条评分与排序主流程的前提下,施加约束后验筛选模块(post-screening)。该模块在初始推荐列表(算法2输出)$ {{\boldsymbol{R}}}_{0}=\{{b}_{1},{b}_{2},\ldots ,{b}_{K}\} $的基础上进行规则过滤,得到最终推荐集合 $ {{\boldsymbol{R}}}^{\text{\*}} $
后验筛选规则如下:
1)结果枝保护规则:若候选枝条被标记为潜在结果枝,则默认不纳入最终剪除集合;仅当其遮挡贡献显著且与邻枝竞争强度超过阈值时,才允许进入人工复核候选池。
2)剪除强度上限规则:按排序依次加入候选枝条,累计剪除强度不超过上限 $ {\eta }_{\max } $。本文以总枝长比例定义剪除强度:
$ {I}_{prune}=\frac{\displaystyle\sum \nolimits_{b\in {R}^{\text{\*}}}{L}_{b}}{\displaystyle\sum \nolimits_{t\in T}{L}_{t}} $
其中,$ {L}_{b} $ 为候选枝条长度,$ T $ 为该树全部可评估枝条集合。约束为 $ {I}_{prune}\leq {\eta }_{\max } $
3)骨架安全规则:主干及一级骨干枝不参与剪除;若某候选枝条剪除后引发骨架连通性破坏风险,则跳过该枝条并顺延至下一候选。
4)局部均衡规则(可选):同一方位/层位的剪除比例不超过局部阈值,以降低局部“掏空式”修剪风险。
据此,最终推荐集合R定义为:
$ {{\boldsymbol{R}}}^{\text{\*}}=\text{PostScreen(}{{\boldsymbol{R}}}_{0}\text{,}{\mathcal{G}}_{fruit}\text{,}{\eta }_{max}\text{,}{\mathcal{G}}_{skeleton}\text{)} $
其中 $ {\mathcal{G}}_{fruit} $表示结果枝保护规则,$ {\mathcal{G}}_{skeleton} $ 表示骨架安全规则。该设计保持原算法可解释性与可复现性,同时提升推荐结果的农艺可执行性。
后验筛选参数设置为 “$ {\eta }_{\max }\in [0.20,0.30] $,本文试验取0.25(单次剪除总枝长不超过25%)。结果枝保护采用“默认保护+高竞争例外复核”策略;主干与一级骨干枝设置为不可剪标签。上述参数依据预试验与农艺经验确定,并在小范围扰动下进行稳定性检查,结论趋势一致。
为实现剪枝结果的直观可视化与实时验证,本研究开发了一个基于WebGL与FastAPI架构的虚拟修剪交互系统。前端采用Three.js实现三维模型渲染与交互操作,可视化展示冠层能量分布、枝条属性及剪枝方案。后端则集成NeRF推理与MCRT光效计算模块,以搭载GPU的云端算力提供模型计算支持,通过FastAPI实现模型推理、剪枝计算与结果反馈。
系统支持浏览器端与移动端双平台运行。关键接口包括:POST /prune用于输入枝条ID并返回剪枝后ΔLIR与ΔEIR;GET/branch/{id}用于查询枝条几何和光效属性;POST /rerender用于重新计算能量栅格。
模型所涉及主要参数分为三类:1)预试验校准参数,主要包括DBSCAN参数($ \varepsilon $、MinPts)、候选阈值$ \theta $、惩罚系数$ \lambda $、迭代次数$ K $等,此类参数基于本数据集通过网格搜索与灵敏度分析确定;2)文献先验参数,主要包括NeRF网络结构与采样设置、MCRT相关物理参数(如叶片消光系数$ k $)等,先采用文献推荐范围,再结合本研究场景做小范围校正;3)工程经验参数,主要包括光线数量$ {N}_{rays} $、体素分辨率与收敛阈值等,以“结果稳定性与计算开销平衡”为原则设定。整体参数选择遵循“文献给范围—预试验定初值—灵敏度检验稳健性”的流程,最终以在验证集上兼顾精度、稳定性与计算效率的组合作为默认参数。
模型性能从三方面评估:重建精度、分类性能与光效优化效果[35]。重建精度包含:枝条尺度相对误差、主干/一级枝长度相对误差、体素交并比IoU;分类性能包含:准确率、召回率、F1、Kappa一致性;光效与剪枝包含:ΔLIR、ΔEIR、光照标准差下降幅度;系统性能涉及:响应延迟、吞吐(req/s)等关键指标。跨环境条件稳健性方面,考虑在输入影像数减半、光照±15%、不同树形/树龄条件下交叉验证:重建误差是否<5%,分类Kappa的区间,ΔEIR提升趋势一致性。
同时,为了可验证模型性能与稳定性,本文提供可复现试验环境如下,其中硬件环境:CPU Intel Xeon 6226R ×2训练;GPU NVIDIA V100(16 GB)推理;RAM 128 GB; 软件环境:Ubuntu 22.04、CUDA 12.x、Python 3.10、PyTorch 2.x、tiny-cuda-nn/Instant-NGP、OpenCV 4.7、scikit-learn 1.4、FastAPI 0.110、Three.js r157。
图3为基于神经辐射场(NeRF)的青脆李单树三维重建、点云断枝补全及拓扑一致性形态修复优化后的结果。从视觉上看,树体枝叶结构完整,主干及一级分枝形态清晰,局部叶簇纹理保持良好细节。
选取9棵有代表性的,不同树冠高、冠幅及透光率的树,将人工测量的枝条长度、角度与模型重建结果进行对比(表1),证实了重建精度的鲁棒性。平均重建相对误差2.39%(102株为4.3%),单株NeRF训练4~6 min(含提取和补全)。与传统SfM+Poisson重建方法相比[36],NeRF在枝叶交叠区域的点云完整度提高约18%,表明该方法在复杂冠层环境中具有更高的结构保真度和稳定性。
模型在后期渲染中支持任意视角查看及光照条件切换,为后续光效模拟提供了真实几何基础。重建结果验证了利用视频影像进行低成本、高精度树体建模的可行性。
通过骨架提取与拓扑优化,成功获取树体的主干–分枝层级结构。图4可视化了12棵不同树龄和冠层复杂度李树的拓扑结构分析结果。主干平均分枝角约46°,一级分枝平均长度0.81 m,二级分枝平均0.42 m,符合典型青脆李冠层生长参数。枝条长度与半径的幂函数拟合系数R2为0.93,说明几何拟合良好。
光效模拟结果见图5,可视化了从NeRF重建细节(3D网格面)、冠层结构空间离散化(八叉树边界盒)、光线传播路径模拟[37-38]、直射/散射光空间分布和冠层光截获能力分区的全部过程。
未剪枝状态下,冠层内部光照呈显著梯度分布,如图6所示。外层LIR(光拦截比)约0.78,内层降至0.42。EIR(能量截获比)在上冠层最高,内层下降明显,形成明显“光饱和–光亏缺”结构。该分布与TANG等对果树冠层光截获分层规律的结论一致[39]。在模拟不同冠层透光率下,开放型冠层的平均LIR提高约16%,EIR提高约20%,光照分布更加均匀,说明适度剪枝可显著改善光能利用环境,为后续剪枝策略优化提供依据。
基于枝条几何参数与光效反馈,系统自动识别出直立枝、下垂枝、竞争枝和密集枝四类剪枝对象(图7)。与人工专家标注结果对比,识别准确率为91.4%,召回率88.7%,F1值0.90,表明模型在枝条识别与剪枝对象定位上具备较高可靠性。
模拟试验分析和实地验证数据表明,不同剪枝策略对冠层光效影响显著。轻剪模式(去除部分密集枝)可使冠层平均LIR提升8.5%;中剪模式(同步去除密集枝与竞争枝)LIR提升15.2%,EIR提升18.9%;强剪模式(增加对直立枝处理)虽可进一步提高光能截获效率,但局部光照差异扩大。综合比较可见,中度剪枝在光效均匀性与截获效率之间取得较优平衡,剪后冠层光照标准差下降约25%,光能利用更趋合理。该结论与ANTHONY等在桃树中的发现一致,即适度开张冠层有利于光分配均匀化与果实发育潜力提升[2]
在此基础上,本文进一步引入后验约束筛选(结果枝保护、剪除强度上限与骨架安全规则)对初始推荐结果进行过滤。表2显示,在$ {\eta }_{\max }=25\mathrm{\text{%} } $约束(中度修剪范围)下,全部样本剪除强度均满足上限(100%),平均结果枝保留率为$ 93.9\mathrm{\text{%} } $,同时仍保持$ 18.8\mathrm{\text{%} } $的光效提升。说明后验约束并未削弱中度剪枝的主要光效收益,而是在“提升光效”与“控制生产风险”之间提供了可执行的折中方案。
为验证本文提出的“视频–NeRF–骨架–光效协同优化模型”的性能,选取典型的三类现有方法进行对比:1)基于图像匹配的结构重建(SfM/MVS)[38];2)基于激光雷达的几何扫描[39];3)基于规则的虚拟修剪系统[8, 12],比较结果如表3所示。
从重建精度与细节连续性来看,本文方法在部分枝条遮挡环境下可将重建精度控制在 1.25 cm 以内,较传统SfM法提高约56%;细枝连接完整率达 85.96%,比LiDAR略低,但计算代价显著下降。在光效模拟方面,本文集成的蒙特卡洛光线追踪(MCRT)能实现结构–能量映射的物理一致性,剪枝后光照均匀性(ΔU)提升 12% 以上,优于SfM与规则法(仅 5.3%)。在剪枝推荐模块中,准确率达93.2%,显著优于其他分类方法(70%~85%)。
此外,系统采用WebGL+FastAPI交互架构,支持实时剪枝与光效重算。在云端GPU(NVIDIA V100 16G)环境下,模型平均响应时间(122±15)s,不超过2.3 min,帧率保持在18~22帧/s。综合比较可见,本文方法兼顾了精度、速度与工程部署性,相较于高成本的LiDAR扫描与传统虚拟系统,更适合面向果园现场的智能修剪决策与光效优化应用场景。需要注意的是,此综合比较仅在断裂补全验证环节同时报告真实与合成数据,目的是利用合成样本的可控结构信息检验补全正确性;其余横向比较指标均在真实树体下完成,以保持方法间可比性。
在输入影像数量减半的情况下,NeRF模型重建误差仍保持在5%以内,枝条识别一致性Kappa值保持在90%~94%的范围内。在光照强度变化±15%的条件下,剪枝推荐结果一致性仍不低于90%。此外,为检验模型的可推广性,研究在苹果、梨和桃树(模拟)样本(n=10)上进行了模型的迁移与适应性试验,在仅微调消光系数k与层级权重γ条件下保持与青脆李相近的ΔEIR与均匀性改善幅度(准确率退化<8%),显示良好跨物种可迁移性。
本文基于WebGL的交互系统实现了剪枝前后结构与光效分布的实时可视化(图8)。剪枝操作后,系统实时计算LIR/EIR变化并渲染光效热图,可通过撤销与对比评估不同剪枝方案的光效改善效果。
在农业部产业集群资金推动下,深入种植户应用的用户体验评估显示,系统界面友好,剪枝反馈直观,能够显著提升果农在树体管理中的操作可视性。与传统经验式剪枝相比,在云端GPU算力支持下,系统在决策精度上提升20%~30%,为现场数字化指导提供技术支持(图9)。
这些结果验证了本研究提出的果树冠层结构–光效协同优化模型的有效性,为后续在更大样本和不同果树类型上的推广研究奠定了技术基础。
果树冠层结构与光能利用之间存在着复杂的耦合关系。树体的空间形态不仅决定了光线的入射路径,也直接影响光合产物在不同器官之间的分配效率[4]。传统果树修剪往往依赖经验性判断,对冠层内部光照分布缺乏量化认识,容易造成“光饱和区”与“光亏缺区”并存,从而影响花芽分化和果实发育[18]
本研究的结果揭示了冠层结构调整在光能优化中的关键作用:枝条角度、分枝层级和空间密度共同决定了光线在冠层内部的穿透深度和能量分配。通过NeRF三维重建与光线追踪模拟,发现青脆李冠层的光能分布呈现明显的分层特征,上层枝叶主要承担光能截获功能,而中下层通过散射和反射补偿光照不足[10]。适度的枝条开张能够显著改善光照均匀性,使光能利用率与树体生长势达到更合理的平衡。这一结论与当前研究关于果树冠层“光能均衡化优于极大化”的认识相吻合,表明结构–光效协同优化是一种兼顾产量与生理稳态的可行路径[40]
从方法论角度看,本研究最大的突破在于实现了从理想化模型到真实果树个体的跨越。以往的冠层建模多基于参数化的几何生成规则,如L系统或体素模型,其形态与实际树体存在显著差距[8, 12]。本文提出的基于神经辐射场的建模框架能够直接从果园实景视频中重建高保真的三维树体,解决了复杂枝叶遮挡条件下结构重建难的问题,也降低了对激光雷达等昂贵扫描设备的依赖。在此基础上,将光线追踪与能量分布计算引入结构分析环节,实现了从“形态重建”到“光能优化”的模型扩展[17]。这种融合思路让剪枝决策从经验判断走向数据驱动,通过光效反馈确定枝条去留,为果树管理提供了新的技术范式。
与国内外已有研究相比,本文提出的协同优化模型在3个方面具有明显优势。其一是数据来源的普适性。模型可直接利用手机或无人机拍摄视频进行重建,适用于多种果树和多样环境[41];其二是评价体系的量化性。通过定义光拦截比(LIR)和能量截获比(EIR)两项指标,使得光效分析具备统一的计算尺度[1, 4];其三是系统的交互性[3]。基于WebGL的可视化平台使剪枝效果能够即时呈现,用户可在虚拟环境中试验多种修剪方案,从而在实际操作前获得决策依据。这种“虚拟仿真—现实验证”的闭环,不仅提升了操作效率,也增强了果农的理解与参与度。
当然,本研究仍存在一些局限性。NeRF重建在枝叶动态变化和强光反射环境下的精度仍受限制,光线追踪算法在处理非均质反射和阴影交互时可能导致局部能量估算偏差[42]。计算资源仍是制约模型在大规模果园实时部署的瓶颈,尽管通过Instant-NGP加速已大幅降低训练时间,但在上百株样本并行分析时,仍需依赖GPU云计算环境。此外,由于当前数据条件与算法复杂度的限制,本研究的剪枝策略主要针对静态冠层结构,尚未考虑生长季节变化或树体营养反馈的动态过程,如花芽分化、结果枝形成等。未来若能结合多时序观测与生理模拟,将有望实现真正意义上的动态树势调控[43]
从应用层面看,该模型不仅适用于青脆李等落叶果树,也可迁移至苹果、梨、桃等多种经济林木。随着果园数字化程度的提升,模型可与无人机巡检、RGB/红外影像分析和物联网传感数据融合,形成多源信息驱动的果树数字孪生系统[5]。通过对结构与光效的综合分析,管理者可以在虚拟空间中预测修剪、施肥或灌溉的连锁反应,从而制定更科学的管理计划。在果业生产端,该系统有潜力成为智能修剪决策支持工具;在科研和教学场景中,则可作为树体结构与光能分配研究的可视化平台,帮助学生直观理解光合作用与结构调控的关系。随着数据积累和模型优化,这种基于三维重建的智能剪枝体系有望成为果树管理数字化转型的重要技术支点[44]
综上所述,本研究提出的果树冠层结构–光效协同优化模型,不仅为结构量化与光能分析提供了统一框架,也为实现数据驱动的智能修剪奠定了基础。模型的稳定性验证和多场景适应性分析表明,其具备推广至不同作物和管理体系的潜力。未来的工作将重点关注动态生长建模、能量平衡机制的生理耦合以及模型轻量化部署,以实现从试验验证到果园常态化应用的跨越。
1)本研究基于神经辐射场NeRF技术,实现了青脆李果树冠层的高精度三维重建,并在百株以上样本中验证了结构重现的稳定性与普适性。结果表明,该方法能在复杂枝条交叠条件下准确还原树体拓扑结构,为果树个体化建模提供了可靠路径。
2)通过光线追踪模型模拟冠层光照分布,揭示了果树结构参数(分枝角度、层级密度)与光能截获效率的定量关系。光拦截比与能量截获比表明,适度剪枝可显著提升光能利用率并改善光照均匀性,验证了结构–光效协同优化的生理合理性。
3)基于几何与光效双特征的剪枝推荐算法,实现了对直立枝、竞争枝及密集枝的智能识别与优化决策,准确率超过90%,并通过WebGL交互系统实现实时可视化。该体系为果树智能修剪与光效分析提供了数据驱动的新途径。
模型在实际应用中仍受叶片动态变化、光反射建模及计算资源限制的影响。未来研究应结合多时序生长观测与轻量化计算框架,进一步完善动态树势调控与果园实时决策能力。本研究建立的冠层结构–光效协同优化模型为果树数字孪生与智慧修剪提供了理论基础与工程方法,对推动果业智能化与精准化管理具有重要的理论意义与实践价值。

参考文献 引证文献
排序方式:
1
PEAVEY M, GOODWIN I, MCCLYMONT L. The effects of canopy height and bud light exposure on the early stages of flower development in Prunus persica (L.) Batsch [J]. Plants, 2020, 9(9): 1073.
2
ANTHONY M, MINAS S. Optimizing peach tree canopy architecture for efficient light use, increased productivity and improved fruit quality[J]. Agronomy, 2021, 11(10): 1961.
3
LI J, SUN H, WU G, et al. Structural parameter determination and pruning pattern analysis of pear tree shoots for dormant pruning [J]. Plant Phenomics, 2025, 100136.
4
LIU S, BARET F, ABICHOU, M, et al. Importance of the description of light interception in crop growth models[J]. Plant Physiology, 2021, 186(2): 977-997.
5
ARIESEN-VERSCHUUR N, VERDOUW C, TEKINERDOGAN B. Digital Twins in greenhouse horticulture: A review[J]. Computers and Electronics in Agriculture, 2022, 199: 107183.
6
NAVONE A, MARTINI M, CHIABERGE M. Autonomous robotic pruning in orchards and vineyards: A review[J]. Smart Agricultural Technology,2025,12:101283.
7
ELFIKY N. Application of artificial intelligence in the food industry: AI-based automatic pruning of dormant apple trees. In Artificial intelligence: A real opportunity in the food industry [M]. Cham: Springer International Publishing, 2022: 1-15.
8
DEJON T. Simulating fruit tree growth, structure, and physiology using L-systems[J]. Crop Science, 2022, 62(6): 2091-2106.
9
ROJO F, DEL RIO R, SNYDER L, et al. A novel simulation model to predict photosynthetic active radiation interception in micro-irrigated citrus production orchards based on tree spacing, canopy geometry, and row orientation[J]. Computers and Electronics in Agriculture, 2023, 212: 108062.
10
QU H, RAN H, GONG W, et al. A simulation and evaluation method for fruit tree canopy light interception based on 3D reconstruction[J]. Journal of the ASABE, 2025, 68(5): 883-895.
11
JIANG A, LIU J, ZHOU J, et al. Skeleton extraction from point clouds of trees with complex branches via graph contraction[J]. The Visual Computer, 2021, 37(8): 2235-2251.
12
MEYER L, GILSON A, SCHOLZ O, et al. CherryPicker: Semantic skeletonization and topological reconstruction of cherry trees[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada: IEEE, 2023: 6244-6253.
13
von HIRSCHHAUSEN S, MAGNUSSON S, KOVALENKO M, et al. AppleGrowthVision: A large-scale stereo dataset for phenological analysis, fruit detection, and 3D reconstruction in apple orchards[C]// Proceedings of the Computer Vision and Pattern Recognition Conference, Nashville, TN, USA: IEEE, 2025, 5443-5450.
14
ZHANG J, WANG X, NI X, et al. Neural radiance fields for multi-scale constraint-free 3D reconstruction and rendering in orchard scenes[J]. Computers and Electronics in Agriculture, 2024, 217: 108629.
15
王红军, 林俊强, 邹湘军, 等. 基于数字孪生的果园虚拟交互系统构建[J]. 系统仿真学报, 2024, 36(6), 1493.
WANG Hongjun, LIN Junqiang, ZOU Xiangjun, et al . Construction of a virtual interactive system for orchards based on digital twin[J]. Journal of System Simulation, 2024, 36(6): 1493-1508. (in Chinese with English abstract)
16
PENG H, GUO S, ZOU X, et al. UAVO-NeRF: 3D reconstruction of orchards and semantic segmentation of fruit trees based on neural radiance field in UAV images[J]. Computers and Electronics in Agriculture, 2025, 237(B): 110631.
17
MA H, WANG K, MA J, et al. Calculation method of canopy effective volume for fruit tree based on LiDAR point cloud data[J]. Frontiers in Plant Science, 2025, 16: 1679027.
18
LI S, van der WERF W, GOU F, et al. An evaluation of Goudriaan’s summary model for light interception in strip canopies, using functional-structural plant models[J]. in silico Plants, 2024, 6(1): diae002.
19
马保建, 蒋焕煜. 休眠期果树修剪机器人视觉感知系统研究现状[J]. 农业工程, 2024, 14(2): 29-33.
MA Baojian, JIANG Huanyu. Research status on visual perception system of pruning robot for dormant fruit tree[J]. Agricultural Engineering, 2024, 14(2): 29-33. (in Chinese with English abstract)
20
OKURA F. 3D modeling and reconstruction of plants and trees: A cross-cutting review across computer graphics, vision, and plant phenotyping[J]. Breeding Science, 2022, 72(1): 31-47.
21
王志富, 马文强, 项斌斌, 等. 基于改进 UNet 模型的核桃树枝条分叉点定位与修剪位置选择[J]. 农业工程学报, 2025, 41(7): 165-172.
WANG Zhifu, MA Wenqiang, XIANG Binbin, et al. Locating branch bifurcation points to select the pruning position of walnut trees using improved UNet model[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(7): 165-172. (in Chinese with English abstract)
22
BOUZIDI A, LAGA H, WANNOUS H, et al. GNF: Gaussian neural fields for multidimensional signal representation and reconstruction[J]. Computer Graphics Forum, 2025, 44(7): e70232.
23
OSHIO H, ASAWA T. Simulating the 3D distribution of absorbed shortwave radiation in a tree crown: Comparison of simplified and Monte Carlo models[J]. Journal of Geophysical Research: Atmospheres, 2023, 128(21): e2023JD038612.
24
LIN Z, LI B, LI H, et al. The physicochemical attributes, volatile compounds, and antioxidant activities of five plum cultivars in Sichuan[J]. Foods, 2023, 12(20): 3801.
25
SABARIVASAN N, THANGAVEL K. Keyframe Extraction Approaches for Intelligent Video Analysis[C]// Proceedings of the 4th International Conference on Sentiment Analysis and Deep Learning (ICSADL), Janakpur, Nepal: IEEE, 2025: 1126-1133.
26
CHEUNG W, HAMARNEH G. n-SIFT: n -dimensional scale invariant feature transform[J]. IEEE Transactions on Image Processing, 2009, 18(9): 2012-2021.
27
LIANG X, LIN Y, FU H, et al. Rscfed: Random sampling consensus federated semi-supervised learning[C]// Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, New Orleans, USA: IEEE, 2022: 10154-10163.
28
STARCZEWSKI A, GOETZEN P, et al. A new method for automatic determining of the DBSCAN parameters[J]. Journal of Artificial Intelligence and Soft Computing Research, 2020, 10(3): 209-221.
29
RUCKER G, SCHIMEK-JASCH T, NESTLE U. Measuring inter-observer agreement in contour delineation of medical imaging in a dummy run using Fleiss’ kappa[J]. Methods of Information in Medicine, 2012, 51(6): 489-494.
30
刘小军. 基于NeRF的树体结构三维重建方法研究[D]. 重庆: 重庆邮电大学, 2025.
LIU Xiaojun. Research on NeRF-based tree canopy 3D reconstruction methods[D]. Chongqing: Chongqing University of Posts and Telecommunications, 2025. (in Chinese with English abstract)
31
LIANG Q, FALKINGHAM L, XING L. Virtual skeleton and body mass for revealing the life strategies of Sinosaurus[J]. Historical Biology, 2025, 37(7): 1729-1743.
32
冉凰渝. 基于三维重建的果树冠层光截获模拟研究[D]. 重庆: 重庆邮电大学, 2025.
RAN Huangyu. Research on Fruit Tree Canopy Light Interception Based on 3D Reconstruction[D]. Chongqing: Chongqing University of Posts and Telecommunications, 2025. (in Chinese with English abstract)
33
龚文俊. 基于三维重建的果树枝条分类与剪枝推荐系统研究与实现[D]. 重庆: 重庆邮电大学, 2025.
GONG Wenjun. Research and Implementation on Fruit Tree Branching Classification and Pruning Recommendation Based on 3D Reconstruction[D]. Chongqing: Chongqing University of Posts and Telecommunications, 2025. (in Chinese with English abstract)
34
李含婷. 虚拟果树交互式修剪模拟系统研究[D]. 重庆: 重庆邮电大学, 2025.
LI Hanting. Research on Interactive Virtual Fruit Tree Pruning Simulation [D]. Chongqing: Chongqing University of Posts and Telecommunications, 2025. (in Chinese with English abstract)
35
QU H, LIU X, LU D, et al. Geometric and multi-scale feature fusion for complete tree skeleton extraction[J]. Journal of the ASABE, 2025, 68(5): 869-882.
36
HUANG J, HUANG L. Research on 3D modeling of Wupaolong based on sparse point cloud reconstruction of SFM algorithm[J]. Journal of Imaging Science and Technology. 2022, 66(3): 1-15.
37
LI H, YANG X, ZHAI H, et al. Vox-surf: Voxel-based implicit surface representation[J]. IEEE Transactions on Visualization and Computer Graphics, 2022, 30(3): 1743-1755.
38
JIANG S, YOU K, CHEN W, et al. 3D reconstruction of spherical images based on incremental structure from motion[J]. International Journal of Remote Sensing, 2024, 45(8): 2596-2621.
39
TANG H, XU Z, CHEN S, et al. Light efficacy estimation for fruit trees based on LIDAR point clouds: A case study on pear trees[J]. Scientia Horticulturae, 2024, 324: 112590.
40
YIN Y, LIU G, LI S, et al. A method for predicting canopy light distribution in cherry trees based on fused point cloud data[J]. Remote Sensing, 2023, 15(10): 2516.
41
FOURIE J, HSIAO J, BATCHELOR O, et al. Generating realistic pruning solutions for automated grape vine pruning using graph neural networks[J]. Expert Systems with Applications, 2025, 298(C): 129778.
42
MILDENHALL B, SRINIVASAN P, TANCIK M, et al. Nerf: Representing scenes as neural radiance fields for view synthesis[J]. Communications of the ACM, 2021, 65(1): 99-106.
43
WILLIAMS H, SMITH D, SHAHABI J, et al. Modelling wine grapevines for autonomous robotic cane pruning[J]. Biosystems Engineering, 2023, 235: 31-49.
44
LI X, LIU B, SHI Y, et al. Efficient three-dimensional reconstruction and skeleton extraction for intelligent pruning of fruit trees[J]. Computers and Electronics in Agriculture, 2024, 227: 109554.
2026年第42卷第12期
PDF下载
198
85
引用本文
BibTeX
文章信息
doi: 10.11975/j.issn.1002-6819.202511017
  • 接收时间:2025-11-04
  • 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:2025-11-04
  • 修回日期:2026-02-25
基金
作者信息
    1重庆市巫山县果品产业发展中心,重庆 404716
    2重庆市农业科学院农业工程研究所,重庆 401329
    3重庆市农业科学院果树研究所,重庆 401329
    4重庆邮电大学生态安全研究中心,重庆 400065

通讯作者:

屈洪春,博士,教授,博士生导师,研究方向为作物表型量化数字模型、农业AI技术。Email:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/nygcxb/CN/10.11975/j.issn.1002-6819.202511017
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