Article(id=1297211766140855113, tenantId=1146029695717560320, journalId=1296125453100220459, issueId=1297211624738284246, articleNumber=null, orderNo=null, doi=10.11975/j.issn.1002-6819.202507134, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1752508800000, receivedDateStr=2025-07-15, revisedDate=1772035200000, revisedDateStr=2026-02-26, acceptedDate=null, acceptedDateStr=null, onlineDate=1787208986077, onlineDateStr=2026-08-20, pubDate=1782748800000, pubDateStr=2026-06-30, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1787208986077, onlineIssueDateStr=2026-08-20, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1787208986077, creator=13701087609, updateTime=1787208986077, 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=239, endPage=248, ext={EN=ArticleExt(id=1297211766363153226, articleId=1297211766140855113, tenantId=1146029695717560320, journalId=1296125453100220459, language=EN, title=A method for measuring phenotypic trait parameters of Sinohyriopsis cumingii based on an improved YOLOv8n model, columnId=1297211683278189232, journalTitle=Transactions of the Chinese Society of Agricultural Engineering, columnName=Agricultural Information and Electrical Technologies, runingTitle=null, highlight=null, articleAbstract=

Sinohyriopsis cumingii is one of the economically important freshwater mussels in the pearl aquaculture industry. Phenotypic traits of S. cumingii can be expected to evaluate the individual growth performance. Germplasm resources are identified to implement precise genetic breeding. However, conventional manual measurements cannot fully meet the scalability and applicability of the large-scale production in intelligent aquaculture, due to their labor-intensive, time-consuming, and highly susceptible to subjective errors. In this study, an improved measurement was proposed for the non-destructive, rapid, and accurate acquisition of phenotypic parameters using YOLOv8n, termed YOLOv8n-CBM. 1) An integrated phenotypic measurement for S. cumingii was constructed to combine the dynamic transmission, machine vision, and digital image processing. The system comprised a conveyor device, a high-precision industrial camera, and an image processing module. The mussel samples were automatically transported into the imaging area, thus enabling standardized image acquisition and high-throughput phenotypic measurement under continuous dynamic conditions. 2) Three targeted improvements were implemented in the original YOLOv8n network architecture, according to the characteristics of mussel images. In the backbone network, four convolutional block attention modules (CBAM) were embedded after each C2f block to enhance the extraction of contour edges and local features of mussel samples, while effectively suppressing irrelevant background interference. In the neck network, the bidirectional feature pyramid network (BiFPN) was introduced to strengthen bidirectional fusion of multi-scale features for the targets of different sizes and postures. Meanwhile, the original C2f module was replaced with a multi-scale dilated attention (MSDA) module to expand the network’s receptive field for the local fine-grained and global contextual information. Finally, the key phenotypic parameters were extracted, including shell length, full height, shell height, and radial rib length of the buttock angle, according to the geometric relationship between rotated bounding boxes and biological key points. A series of experiments was conducted on a dataset of 50 manually annotated S. cumingii samples with diverse sizes and postures. The results show that the mean average precision (mAP50-95) of the YOLOv8n-CBM model reached 98.2%, indicating the rotated object detection performance over the original YOLOv8n model. The average localization deviation of biological key points was less than 2.0 mm, indicating the high precision in feature detection. The mean absolute errors (MAE) of shell length, full height, shell height, and radial rib length of the buttock angle were 1.51, 1.08, 1.019, and 1.998 mm, respectively. In all groups stratified by different shell lengths and full heights, the measurement errors of YOLOv8n-CBM were consistently lower than those of the original YOLOv8n model, with the maximum absolute error within 2.879 mm. Measurement accuracy and robustness were effectively improved with diverse morphologies and postures. In conclusion, the reliable technical approach was used to realize the rapid, accurate, and non-destructive acquisition of phenotypic traits in S. cumingii. Shellfish growth evaluation and genetic breeding can be expected to support the transition of the pearl industry from empirical farming to data-driven and intelligent aquaculture. The findings can also offer a valuable reference for phenotypic measurement in the molluscan species.

, authors=Puluo ZHOU1, Jun ZHANG1, *, Shouqi CAO1, Zhiyi BAI2, Qingsong HU1, Xingguo LIU3, Bin WANG1, authorsList=Puluo ZHOU, Jun ZHANG, Shouqi CAO, Zhiyi BAI, Qingsong HU, Xingguo LIU, Bin WANG, authorCompany=null, correspAuthors=Jun ZHANG, 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=1297211770456793957, articleId=1297211766140855113, tenantId=1146029695717560320, journalId=1296125453100220459, language=CN, title=基于改进YOLOv8n的三角帆蚌表型性状参数测量方法, columnId=1297211683441767090, journalTitle=农业工程学报, columnName=农业信息与电气技术, runingTitle=null, highlight=null, articleAbstract=

三角帆蚌表型性状参数是其生长性能评价、种质资源鉴定和遗传育种研究的重要依据。为实现三角帆蚌表型性状参数的无损、快速和准确获取,该研究提出了一种改进YOLOv8n的三角帆蚌表型性状参数测量模型YOLOv8n-CBM。首先,集成动态传输、机器视觉及图像处理技术,构建三角帆蚌表型参数的自动测量系统;然后,在YOLOv8n骨干网络中,添加4个卷积注意力模块(convolutional block attention module, CBAM),以提高对三角帆蚌轮廓边缘及局部细节特征的提取效果;其次,在颈部网络中引入双向特征金字塔网络(bidirectional feature pyramid network, BiFPN)以加强不同尺度特征之间的双向融合,提高模型对多尺度目标的表征能力;同时,将原有C2f模块替换为多尺度空洞卷积模块(multi-scale dilated attention, MSDA),以扩大特征感受野,增强局部细节与全局上下文信息的联合建模能力;最后,结合旋转边界框与关键点的几何关系,提取壳长、全高、壳高与臀角放射肋长等数据。结果表明,YOLOv8n-CBM模型的平均精度均值(mAP50-95)达到98.2%,壳长、全高、壳高和臀角放射肋长的平均绝对误差分别为1.512、1.083、1.019与1.998 mm;在不同壳长与全高分组下,YOLO-CBM模型的测量误差均小于原始YOLOv8n模型,最大绝对误差不超过2.879 mm,提升了对多姿态下三角帆蚌表型数据的测量精度和鲁棒性。研究结果可为贝类生长性能评价和遗传育种等提供测量方法,对于推动珍珠产业从经验化养殖向科学化、自动化发展具有重要意义。

, authors=周普洛1, 张俊1, *, 曹守启1, 白志毅2, 胡庆松1, 刘兴国3, 王斌1, authorsList=周普洛, 张俊, 曹守启, 白志毅, 胡庆松, 刘兴国, 王斌, authorCompany=null, correspAuthors=张俊, authorNote=

周普洛,研究方向为鱼贝类表型数据精准测量技术。Email:

, correspAuthorsNote=
张俊,博士,教授,研究方向为智慧渔业工程与装备。Email:
, copyrightStatement=版权所有 © 2026 农业工程学报编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=Wj5H7BoQhgGJV2LO7jZZ5Q==, magXml=Z8Wmlu/+Gjn7epGUiBUvUg==, pdfUrl=null, pdf=uwA2YxOuaVlOOQmIVm+z0A==, pdfFileSize=3279977, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=t+Qcn1BSBL7+bG4VBkr4Iw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=dHzOxbWROoCjwQknzcHnMQ==, mapNumber=null, fund=null)}, authors=[Author(id=1299828231755026706, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=2416705346@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1299828231826329876, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828231755026706, language=EN, stringName=Puluo ZHOU, firstName=Puluo, middleName=null, lastName=ZHOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828231897633045, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828231755026706, language=CN, stringName=周普洛, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1上海海洋大学工程学院,上海 201306, bio={"content":"

周普洛,研究方向为鱼贝类表型数据精准测量技术。Email:

"}, bioImg=null, bioContent=

周普洛,研究方向为鱼贝类表型数据精准测量技术。Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828231461425416, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, xref=1, ext=[AuthorCompanyExt(id=1299828231469814025, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China), AuthorCompanyExt(id=1299828231482396938, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1上海海洋大学工程学院,上海 201306)])]), Author(id=1299828231956353303, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhangjun@shou.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1299828232023462169, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828231956353303, language=EN, stringName=Jun ZHANG, firstName=Jun, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828232082182426, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828231956353303, language=CN, stringName=张俊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1上海海洋大学工程学院,上海 201306, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828231461425416, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, xref=1, ext=[AuthorCompanyExt(id=1299828231469814025, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China), AuthorCompanyExt(id=1299828231482396938, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1上海海洋大学工程学院,上海 201306)])]), Author(id=1299828232140902684, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, 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=1299828232212205854, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828232140902684, language=EN, stringName=Shouqi CAO, firstName=Shouqi, middleName=null, lastName=CAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828232270926111, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828232140902684, language=CN, stringName=曹守启, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1上海海洋大学工程学院,上海 201306, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828231461425416, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, xref=1, ext=[AuthorCompanyExt(id=1299828231469814025, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China), AuthorCompanyExt(id=1299828231482396938, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1上海海洋大学工程学院,上海 201306)])]), Author(id=1299828232346423585, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, 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=1299828232417726755, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828232346423585, language=EN, stringName=Zhiyi BAI, firstName=Zhiyi, middleName=null, lastName=BAI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2College of Fisheries and Life Sciences, Shanghai Ocean University, Shanghai 201306, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828232505807140, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828232346423585, language=CN, stringName=白志毅, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2上海海洋大学水产与生命学院,上海 201306, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828231557894411, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, xref=2, ext=[AuthorCompanyExt(id=1299828231566283020, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231557894411, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2College of Fisheries and Life Sciences, Shanghai Ocean University, Shanghai 201306, China), AuthorCompanyExt(id=1299828231574671629, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231557894411, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2上海海洋大学水产与生命学院,上海 201306)])]), Author(id=1299828232564527398, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1299828232644219176, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828232564527398, language=EN, stringName=Qingsong HU, firstName=Qingsong, middleName=null, lastName=HU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828232711328041, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828232564527398, language=CN, stringName=胡庆松, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1上海海洋大学工程学院,上海 201306, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828231461425416, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, xref=1, ext=[AuthorCompanyExt(id=1299828231469814025, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China), AuthorCompanyExt(id=1299828231482396938, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1上海海洋大学工程学院,上海 201306)])]), Author(id=1299828232778436907, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, orderNo=5, 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=1299828232853934381, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828232778436907, language=EN, stringName=Xingguo LIU, firstName=Xingguo, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3China Fishery Machinery and Instrument Research Institute, Chinese Academy of Fishery Sciences, Shanghai200092, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828232908460334, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828232778436907, language=CN, stringName=刘兴国, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3中国水产科学研究院渔业机械仪器研究所,上海 200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828231666946318, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, xref=3, ext=[AuthorCompanyExt(id=1299828231675334927, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231666946318, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3China Fishery Machinery and Instrument Research Institute, Chinese Academy of Fishery Sciences, Shanghai200092, China), AuthorCompanyExt(id=1299828231683723536, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231666946318, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3中国水产科学研究院渔业机械仪器研究所,上海 200092)])]), Author(id=1299828232979763504, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, orderNo=6, 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=1299828233059455282, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828232979763504, language=EN, stringName=Bin WANG, firstName=Bin, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828233130758451, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828232979763504, language=CN, stringName=王斌, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1上海海洋大学工程学院,上海 201306, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828231461425416, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, xref=1, ext=[AuthorCompanyExt(id=1299828231469814025, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China), AuthorCompanyExt(id=1299828231482396938, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1上海海洋大学工程学院,上海 201306)])])], keywords=[Keyword(id=1299828233269170484, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, orderNo=1, keyword=image processing), Keyword(id=1299828233336279349, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, orderNo=2, keyword=deep learning), Keyword(id=1299828233407582518, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, orderNo=3, keyword=phenotype), Keyword(id=1299828233487274295, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, orderNo=4, keyword=Sinohyriopsis cumingii), Keyword(id=1299828233545994552, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, orderNo=5, keyword=YOLOv8n), Keyword(id=1299828233608909113, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, orderNo=1, keyword=图像处理), Keyword(id=1299828233676017978, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, orderNo=2, keyword=深度学习), Keyword(id=1299828233743126843, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, orderNo=3, keyword=表型), Keyword(id=1299828233806041404, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, orderNo=4, keyword=三角帆蚌), Keyword(id=1299828233868955965, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, orderNo=5, keyword=YOLOv8n)], refs=[Reference(id=1299828236867883362, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, 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=张根芳, 张文府, 罗雨, 等. 1龄三角帆蚌壳形态性状对体质量的通径分析[J]. 大连海洋大学学报, 2018, 33(6): 755-759., articleTitle=null, refAbstract=null), Reference(id=1299828236939186531, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHANG Genfang, ZHANG Wenfu, LUO Yu, et al. Path analysis of morphological traits on body weight of one-year-old freshwater mussel Hyriopsis cumingii[J]. Journal of Dalian Ocean University, 2018, 33(6): 755-759. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828237014684004, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=何志然, 胡宏辉, 冯上乐, 等. 三角帆蚌金色品系生长性状遗传参数及基因型与环境互作效应分析[J]. 大连海洋大学学报, 2021, 36(2): 254-259., articleTitle=null, refAbstract=null), Reference(id=1299828237090181477, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=HE Zhiran, HU Honghui, FENG Shangle, et al. Estimation of genetic parameters on growth traits and interaction between genotype and environment in golden strain of freshwater mussel Hyriopsis cumingii[J]. Journal of Dalian Ocean University, 2021, 36(2): 254-259. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828237148901734, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=吴雷明, 白志毅, 刘晓军, 等. 三角帆蚌F5壳色及生长性状选育效果评价[J]. 中国水产科学, 2021, 28(3): 325-334., articleTitle=null, refAbstract=null), Reference(id=1299828237228593511, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=WU Leiming, BAI Zhiyi, LIU Xiaojun, et al. Evaluation of shell color and growth traits for F5 of the freshwater pearl mussel[J]. Journal of Fishery Sciences of China, 2021, 28(3): 325-334. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828237291508072, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=闻海波, 顾若波, 华丹, 等. 两水系三角帆蚌亲本及杂交、自交组钩介幼虫形态性状比较[J]. 上海海洋大学学报, 2010, 19(5): 612-614., articleTitle=null, refAbstract=null), Reference(id=1299828237362811241, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=WEN Haibo, GU Ruobo, HUA Dan, et al. Comparsion of morphological characters of broodstocks and their glochidia in reciprocal hrybird of Hyriopsis cumingii from two drainage systems[J]. Journal of Shanghai Ocean University, 2010, 19(5): 612-614. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828237492834666, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=HU H H, WANG Z Y, JIA L, et al. Genetic differentiation and identification of key genes related to biomineralization and coloration in three Hyriopsis cumingii strains exhibiting different inner shell colors[J]. Aquaculture Reports, 2024, 35: 101939., articleTitle=null, refAbstract=null), Reference(id=1299828237551554923, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=吕高伦, 吕雪峰, 王昊, 等. 不同年龄三角帆蚌新生长性状臀角放射肋长与其他生长性状相关性和通径分析[J]. 上海海洋大学学报, 2024, 33(3): 562-571., articleTitle=null, refAbstract=null), Reference(id=1299828237627052396, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=LYU Gaolun, LYU Xuefeng, WANG Hao, et al. Correlation and path analysis of new growth traits including radial rib length in different-aged Hyriopsis cumingii[J]. Journal of Shanghai Ocean University, 2024, 33(3): 562-571. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828237694161261, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=刘刚, 曾雪婷, 刘晓文, 等. 基于改进YOLOv5-pose的群养生猪体尺自动测量方法[J]. 农业机械学报, 2025, 56(05): 455-465., articleTitle=null, refAbstract=null), Reference(id=1299828237773853038, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=LIU Gang, ZENG Xueting, LIU Xiaowen, et al. Automatic measurement method of body size of group-raised pigs based on improved YOLO v5-pose[J]. Transactions of the Chinese Society for Agricultural Machinery, 2025, 56(05): 455-465. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828237849350511, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=翟肇裕, 张梓涵, 徐焕良, 等. YOLO算法在动植物表型研究中应用综述[J]. 农业机械学报, 2024, 55(11): 1-20., articleTitle=null, refAbstract=null), Reference(id=1299828237916459376, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHAI Zhaoyu, ZHANG Zihan, XU Huanliang, et al. Review of applying YOLO family algorithms to analyze animals and plant phenotype[J]. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55(11): 1-20. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828238017122673, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=陈慧颖, 宋青峰, 常天根, 等. 基于YOLOv5m和CBAM-CPN的单分蘖水稻表型参数提取[J]. 农业工程学报, 2024, 40(2): 307-314., articleTitle=null, refAbstract=null), Reference(id=1299828238088425842, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=CHEN Huiying, SONG Qingfeng, CHANG Tiangen, et al. Extraction of the single-tiller rice phenotypic parameters based on YOLOv5m and CBAM-CPN[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(2): 307-314. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828238155534707, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=崔永超, 武栓虎, 牟春晓, 等. 基于深度学习的贝类目标定位与统计测量方法[J]. 烟台大学学报(自然科学与工程版), 2023, 36(02): 204-210., articleTitle=null, refAbstract=null), Reference(id=1299828238243615092, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=CUI Yongchao, WU Shuanhu, MOU Chunxiao, et al. Target location and statistical measurement method of shellfish based on deep learning[J]. Journal of Yantai University (Natural Science and Engineering Edition), 2023, 36(02): 204-210. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828238310723957, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=胡凯. 基于深度学习的青蟹测量和检测模型研究[D]. 杭州: 浙江大学, 2022., articleTitle=null, refAbstract=null), Reference(id=1299828238373638518, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=HU Kai. Deep Learning Based Scylla Measurement and Detection Model[D]. Hangzhou: Zhejiang University, 2022. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828238436553079, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=朱俊宇. 基于深度学习压缩模型的沼虾表型数据测定研究[D]. 杭州: 浙江大学, 2022., articleTitle=null, refAbstract=null), Reference(id=1299828238495273336, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHU Junyu. Research on Measurement of Phenotypic Data of Macro Shrimp Based on Deep-Learning Compressed Model[D]. Hangzhou: Zhejiang University, 2022. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828238562382201, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=SHEN K, WANG X, GAO K, et al. High-throughput 3D phenotyping in northern quahogs Mercenaria mercenaria for dimensional trait measurement and weight prediction[J]. Smart Agricultural Technology, 2025, 10: 100840., articleTitle=null, refAbstract=null), Reference(id=1299828238642073978, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=李健源, 柳春娜, 卢晓春, 等. 构建VED-SegNet分割模型提取鱼类表型比例[J]. 农业工程学报, 2024, 40(3): 175-183., articleTitle=null, refAbstract=null), Reference(id=1299828238721765755, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=LI Jianyuan, LIU Chunna, LU Xiaochun, et al. Constructing VED-SegNet segmentation model to extract fish phenotype proportions[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(3): 175-183. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828238784680316, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=李振波, 孙浩翔, 郭倩男, 等. 机器视觉技术在大体型家畜无接触体尺测量中的研究进展[J]. 农业工程学报, 2025, 41(7): 1-12., articleTitle=null, refAbstract=null), Reference(id=1299828238855983485, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=LI Zhenbo, SUN Haoxiang, GUO Qiannan, et al. Research progress on machine vision technology for non-contact body measurement of large livestock[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(7): 1-12. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828238939869566, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=罗慧, 刘星语, 韦骁, 等. 基于THz成像和集成学习的番茄根长表型提取及预测[J]. 农业工程学报, 2024, 40(18): 176-183., articleTitle=null, refAbstract=null), Reference(id=1299828239011172735, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=LUO Hui, LIU Xingyu, WEI Xiao, et al. Extracting and predicting tomato root length phenotype using THz imaging and ensemble learning[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(18): 176-183. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828239099253120, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=黄霞, 申笠蒙, 朱锋博, 等. 基于手持式扫描仪的种子几何参数高通量测量[J]. 农业工程学报, 2024, 40(21): 312-322., articleTitle=null, refAbstract=null), Reference(id=1299828239178944897, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=HUANG Xia, SHEN Limeng, ZHU Fengbo, et al. High-throughput measurement of seed geometric parameters using handheld scanner[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(21): 312-322. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828239246053762, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=叶秉良, 丰睿, 唐涛, 等. 基于改进YOLOv10n的自然环境下莲蓬成熟度检测方法[J]. 农业工程学报, 2025, 41(22): 145-153., articleTitle=null, refAbstract=null), Reference(id=1299828239325745539, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=YE Bingliang, FENG Rui, TANG Tao, et al. Ripeness detection of lotus seedpod in natural environment based on improved YOLOv10n[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(22): 145-153. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828239388660100, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=何志鹏, 巩高瑞, 熊阳, 等. 基于计算机视觉的黄颡鱼表型特征测量和体重预测模型研究[J]. 水生生物学报, 2024, 48(7): 1149-1158., articleTitle=null, refAbstract=null), Reference(id=1299828239455768965, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=HE Zhipeng, GONG Gaorui, XIONG Yang, et al. A phenotypic measurement and weight prediction model of Pelteobagrus fulvidraco based on computer vision[J]. Acta Hydrobiologica Sinica, 2024, 48(7): 1149-1158. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828239527072134, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=CHEN K, CHEN Z, WANG C, et al. Improved YOLO v8-based method for the carapace keypoint detection and size measurement of Chinese mitten crabs[J]. Animals, 2025, 15(7): 941., articleTitle=null, refAbstract=null), Reference(id=1299828239585792391, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=LIU W Z, TAN J Y, LAN G Y, et al. Benchmarking fish dataset and evaluation metric in keypoint detection - Towards precise fish morphological assessment in aquaculture breeding[C]// Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI-24). Jeju, South Korea: International Joint Conferences on Artificial Intelligence Organization, 2024: 7376-7384., articleTitle=null, refAbstract=null), Reference(id=1299828239644512648, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=YU Y Z, ZHANG H, YUAN F. Key point detection method for fish size measurement based on deep learning[J]. IET Image Processing, 2023, 17(14): 4142-4158., articleTitle=null, refAbstract=null), Reference(id=1299828239711621513, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=张瑞青, 刘攀, 陈文杰, 等. 基于改进YOLOv8-Seg模型的香菇子实体表型参数测量方法[J]. 农业工程学报, 2025, 41(23): 143-151., articleTitle=null, refAbstract=null), Reference(id=1299828239791313290, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHANG Ruiqing, LIU Pan, CHEN Wenjie, et al. Measurement method for the phenotypic parameters of Lentinula edodes fruiting bodies based on improved YOLOv8-Seg model[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(23): 143-151. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828239875199371, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=李国栋, 喻俊志, 秦新燕, 等. 基于YOLO-SDCG和椭圆傅里叶描述子的番茄苗表型检测[J]. 农业工程学报, 2026, 42(3): 179-191., articleTitle=null, refAbstract=null), Reference(id=1299828239963279756, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=LI Guodong, YU Junzhi, QIN Xinyan, et al. Phenotypic detection of tomato seedlings based on YOLO-SDCG and elliptic Fourier descriptors[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2026, 42(3): 179-191. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828240042971533, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=姚涛, 谈志鹏, 程娥, 等. 基于改进YOLOv7-seg的黄花菜检测与分割方法[J]. 农业工程学报, 2024, 40(9): 146-153., articleTitle=null, refAbstract=null), Reference(id=1299828240131051918, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=YAO Tao, TAN Zhipeng, CHENG E, et al. Method for daylily detection and segmentation based on improved YOLOv7-seg[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(9): 146-153. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828240210743695, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=郭希岳, 李劲松, 郑立华, 等. Re-YOLOv5和检测区域搜索算法获取大豆植株表型参数[J]. 农业工程学报, 2022, 38(15): 186-194., articleTitle=null, refAbstract=null), Reference(id=1299828240303018384, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Guo Xiyue, Li Jinsong, Zheng Lihua, et al. Acquiring soybean phenotypic parameters using Re-YOLOv5 and area search algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2022, 38(15): 186-194. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828240374321553, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=李新龙, 兰玉彬, 王会征. 基于改进YOLOv10n的自然场景下芒果果实与果梗检测方法[J]. 农业工程学报, 2025, 41(19): 167-175. (in Chinese with English abstract)., articleTitle=null, refAbstract=null), Reference(id=1299828240441430418, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=LI Xinlong, LAN Yubin, WANG Huizheng. Detecting mango fruits and peduncles in natural scenes using improved YOLOv10n[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(19): 167-175. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828240500150675, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=刘芹, 欧阳婧玟, 周智彬, 等. 基于YOLO-CRC的茄子及茄子梗分割与定位方法[J]. 农业工程学报, 2025, 41(19): 196-205., articleTitle=null, refAbstract=null), Reference(id=1299828240563065236, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=LIU Qin, OUYANG Jingwen, ZHOU Zhibin, et al. Segmentation and localization method for eggplants and stems based on YOLO-CRC[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(19): 196-205. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828240634368405, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=耿耀君, 马萍, 李雯敏, 等. 基于改进YOLOv8m的成熟柿子品种及表型特征多标签识别[J]. 农业工程学报, 2025, 41(17): 143-152., articleTitle=null, refAbstract=null), Reference(id=1299828240697282966, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=GENG Yaojun, MA Ping, LI Wenmin, et al. Multi-label recognition of ripen persimmons varieties and phenotypic characteristics based on improved YOLOv8m[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(17): 143-152. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828240756003223, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=李巨虎, 徐玉立, 路佳, 等. 基于改进YOLOv11n的轻量级多尺度水稻害虫识别模型[J]. 农业工程学报, 2025, 41(17): 175-183., articleTitle=null, refAbstract=null), Reference(id=1299828240852472216, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=LI Juhu, XU Yuli, LU Jia, et al. Lightweight multi-scale rice pest recognition model based on improved YOLOv11n[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(17): 175-183. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1299828240940552601, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=FENG S, HUANG Y, ZHANG N. An improved YOLO v8 OBB model for ship detection through stable diffusion data augmentation[J]. Sensors, 2024, 24(17): 5850., articleTitle=null, refAbstract=null), Reference(id=1299828241016050074, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=WOO S, PARK J, LEE J Y, et al. CBAM: Convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision (ECCV), Cham, Switzerland: Springer, 2018: 3-19., articleTitle=null, refAbstract=null), Reference(id=1299828241087353243, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=57, authorNames=null, journalName=null, refType=null, unstructuredReference=TAN M, PANG R, LE Q V. Efficient Det: Scalable and efficient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, USA: IEEE, 2020: 10778-10787., articleTitle=null, refAbstract=null), Reference(id=1299828241183822236, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=58, authorNames=null, journalName=null, refType=null, unstructuredReference=JIAO J, TANG Y M, LIN K Y, et al. DilateFormer: Multi-scale dilated transformer for visual recognition[J]. IEEE Transactions on Multimedia, 2023, 25: 8906-8919., articleTitle=null, refAbstract=null), Reference(id=1299828241259319709, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=59, authorNames=null, journalName=null, refType=null, unstructuredReference=WILLMOTT C J, MATSUURA K. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance[J]. Climate Research, 2005, 30(1): 79-82., articleTitle=null, refAbstract=null), Reference(id=1299828241355788702, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=60, authorNames=null, journalName=null, refType=null, unstructuredReference=KHAKI S, PHAM H, HAN Y, et al. DeepCorn: A semi-supervised deep learning method for high-throughput image-based corn kernel counting and yield estimation[J]. Knowledge-Based Systems, 2021, 218: 1068., articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1299828231461425416, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, xref=1, ext=[AuthorCompanyExt(id=1299828231469814025, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China), AuthorCompanyExt(id=1299828231482396938, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1上海海洋大学工程学院,上海 201306)]), AuthorCompany(id=1299828231557894411, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, xref=2, ext=[AuthorCompanyExt(id=1299828231566283020, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231557894411, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2College of Fisheries and Life Sciences, Shanghai Ocean University, Shanghai 201306, China), AuthorCompanyExt(id=1299828231574671629, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231557894411, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2上海海洋大学水产与生命学院,上海 201306)]), AuthorCompany(id=1299828231666946318, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, xref=3, ext=[AuthorCompanyExt(id=1299828231675334927, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231666946318, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3China Fishery Machinery and Instrument Research Institute, Chinese Academy of Fishery Sciences, Shanghai200092, China), AuthorCompanyExt(id=1299828231683723536, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231666946318, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3中国水产科学研究院渔业机械仪器研究所,上海 200092)])], figs=[ArticleFig(id=1299828234053505342, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, label=Fig.1, caption=Automatic measurement system for phenotypic trait parameters of the Sinohyriopsis cumingii, figureFileSmall=oiLt/Td5LkZ/R28k8K0f5w==, figureFileBig=Xl2D3LHfZW/q+N2lsFSHZg==, tableContent=null), ArticleFig(id=1299828234120614207, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, label=图1, caption=三角帆蚌表型性状参数自动测量系统

1. 激光阵列测距模块 2. 工业摄像机 3. 扫码器固定结构 4. 扫码器 5. 传送带 6. 上支架 7. 动态电子秤 8. 封板 9. 下支架 10. 支撑板 11. 结构框架 12. 轴承及轴承座 13. 传送带罩 14. 传送轮 15. 张紧结构 16. 传送带 17. 电机 18. 支撑脚

, figureFileSmall=oiLt/Td5LkZ/R28k8K0f5w==, figureFileBig=Xl2D3LHfZW/q+N2lsFSHZg==, tableContent=null), ArticleFig(id=1299828234217083200, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, label=Fig.2, caption=Improved YOLOv8n model structure, figureFileSmall=HhM6FvZUXaNaJw7PRbS91w==, figureFileBig=ObDMPVGYRmNT6df7Ir8oag==, tableContent=null), ArticleFig(id=1299828234279997761, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, label=图2, caption=改进YOLOv8n的模型结构

注:Conv为卷积模块;C2f为特征聚合模块;CBAM为卷积注意力模块;SPPF为空间金字塔池化模块;UpSample为上采样模块;BiFPN为双向特征金字塔网络;C2f_MSDA为多尺度空洞卷积注意力模块;OBB为旋转边界框检测头;①~⑤为BiFPN模块编号;Size为特征图尺寸(高×宽×通道数)。下同。

, figureFileSmall=HhM6FvZUXaNaJw7PRbS91w==, figureFileBig=ObDMPVGYRmNT6df7Ir8oag==, tableContent=null), ArticleFig(id=1299828234351300930, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, label=Fig.3, caption=Typical characteristics of the Sinohyriopsis cumingii, figureFileSmall=l4vPu8jtYSghNbMSjQXnqQ==, figureFileBig=F9O7JWwJApxru84F0ZleJQ==, tableContent=null), ArticleFig(id=1299828234426798403, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, label=图3, caption=三角帆蚌的典型特征, figureFileSmall=l4vPu8jtYSghNbMSjQXnqQ==, figureFileBig=F9O7JWwJApxru84F0ZleJQ==, tableContent=null), ArticleFig(id=1299828234498101572, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, label=Fig.4, caption=Structural diagram of convolutional attention module, figureFileSmall=3V1Vhc3B1h34C93Zif4pfQ==, figureFileBig=Xe+9VyVNjobhYcF4Eee5Lg==, tableContent=null), ArticleFig(id=1299828234581987653, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, label=图4, caption=卷积注意力模块结构图

注:⊕为加法符号,表示将平均池化与最大池化两种特征信息叠加;Sigmoid表示激活函数。

, figureFileSmall=3V1Vhc3B1h34C93Zif4pfQ==, figureFileBig=Xe+9VyVNjobhYcF4Eee5Lg==, tableContent=null), ArticleFig(id=1299828234661679430, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, label=Fig.5, caption=Structural diagram of BiFPN module, figureFileSmall=vjhrmKJrPWK016cKOncxuQ==, figureFileBig=bOys+xMxtQJ66kEGIoRAkQ==, tableContent=null), ArticleFig(id=1299828234741371207, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, label=图5, caption=BiFPN模块结构图

注:P1~P5分别表示由Backbone不同阶段输出的多尺度特征图,其中,P1为高分辨率浅层特征图;P2为中高分辨率中浅层特征图;P3为中分辨率中层特征图;P4为中低分辨率中深层特征图;P5为低分辨率深层特征图。

, figureFileSmall=vjhrmKJrPWK016cKOncxuQ==, figureFileBig=bOys+xMxtQJ66kEGIoRAkQ==, tableContent=null), ArticleFig(id=1299828234816868680, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, label=Fig.6, caption=Structural diagram of multi-scale dilated attention module, figureFileSmall=XaLzShGqIlSNzN7RtaGAFg==, figureFileBig=37lpfGr88swH5WDzzbcUvQ==, tableContent=null), ArticleFig(id=1299828234883977545, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, label=图6, caption=多尺度空洞卷积模块结构图

注:Linear为线性映射层,Concat为特征拼接操作,r为空洞率,Q为查询向量,K为键向量,V为值向量。

, figureFileSmall=XaLzShGqIlSNzN7RtaGAFg==, figureFileBig=37lpfGr88swH5WDzzbcUvQ==, tableContent=null), ArticleFig(id=1299828234955280714, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, label=Fig.7, caption=Phenotypic measurement parameters and shell height perpendicular determination for the Sinohyriopsis cumingii, figureFileSmall=mFIfBbABVLjwbJqPJXKWwg==, figureFileBig=U8otHT170Chg7iw7TEgEmw==, tableContent=null), ArticleFig(id=1299828235030778187, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, label=图7, caption=三角帆蚌表型测量参数与壳高垂线判定

注:αβ分别表示旋转框长边和短边与臀角放射肋长的夹角。

, figureFileSmall=mFIfBbABVLjwbJqPJXKWwg==, figureFileBig=U8otHT170Chg7iw7TEgEmw==, tableContent=null), ArticleFig(id=1299828235102081356, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, label=Fig.8, caption=Bounding box loss on the validation set, figureFileSmall=iv7ehQcCsa8/p8F0oKntug==, figureFileBig=Sgc5n9NQWNT326Y7riZYFw==, tableContent=null), ArticleFig(id=1299828235177578829, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, label=图8, caption=验证集边界框损失, figureFileSmall=iv7ehQcCsa8/p8F0oKntug==, figureFileBig=Sgc5n9NQWNT326Y7riZYFw==, tableContent=null), ArticleFig(id=1299828235240493390, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, label=Fig.9, caption=Distribution focal loss on the validation set, figureFileSmall=gsIS/nhvrNBstGrhRen40w==, figureFileBig=eFAjjBlWm3ZYfyDBhuJNUg==, tableContent=null), ArticleFig(id=1299828235307602255, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, label=图9, caption=验证集分布式焦点损失, figureFileSmall=gsIS/nhvrNBstGrhRen40w==, figureFileBig=eFAjjBlWm3ZYfyDBhuJNUg==, tableContent=null), ArticleFig(id=1299828235387294032, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, label=Fig.10, caption=Detection results of different models, figureFileSmall=/CZE5rWUxbvd3rGDC4M60g==, figureFileBig=l1gjWAZFcONpkplzOw77cQ==, tableContent=null), ArticleFig(id=1299828235450208593, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, label=图10, caption=不同模型的检测结果

注:红色框为实际检测框,绿色框为理想检测框,黄色圆形为检测框未包围部分。

, figureFileSmall=/CZE5rWUxbvd3rGDC4M60g==, figureFileBig=l1gjWAZFcONpkplzOw77cQ==, tableContent=null), ArticleFig(id=1299828235521511762, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, label=Fig.11, caption=Visualization results of the prediction model, figureFileSmall=qwS9thsOXtmYl5VcLj7Zog==, figureFileBig=QLa69mOLDnjGf3AwGe5XxQ==, tableContent=null), ArticleFig(id=1299828235592814931, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, label=图11, caption=预测模型的可视化结果, figureFileSmall=qwS9thsOXtmYl5VcLj7Zog==, figureFileBig=QLa69mOLDnjGf3AwGe5XxQ==, tableContent=null), ArticleFig(id=1299828235668312404, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, label=Fig.12, caption=Regression comparison of shell height, figureFileSmall=Euf4f0poLp3FdxMjLyfAMw==, figureFileBig=8Noa1G9if9gsvyW+/KCxZQ==, tableContent=null), ArticleFig(id=1299828235743809877, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, label=图12, caption=壳高回归对比

注:颜色梯度表示样本密度,红色表示该数值区间附近的样本数最多。下同。

, figureFileSmall=Euf4f0poLp3FdxMjLyfAMw==, figureFileBig=8Noa1G9if9gsvyW+/KCxZQ==, tableContent=null), ArticleFig(id=1299828235815113046, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, label=Fig.13, caption=Regression comparison of radial rib length, figureFileSmall=/21E66u56RcVi7CGX3yBHA==, figureFileBig=s6oP+feFxXDe6OEnVvhcmQ==, tableContent=null), ArticleFig(id=1299828235903193431, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, label=图13, caption=臀角放射肋长回归对比, figureFileSmall=/21E66u56RcVi7CGX3yBHA==, figureFileBig=s6oP+feFxXDe6OEnVvhcmQ==, tableContent=null), ArticleFig(id=1299828235970302296, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, label=Tab.1, caption=

Ablation experiment results

, figureFileSmall=null, figureFileBig=null, tableContent=
CBAMBiFPNMSDAmAP50-95/%参数量Params/MFLOPs/G
注:“√”表示该改进模块被引入模型;“/”表示该改进模块未被引入模型;mAP50-95表示交并比阈值为0.50~0.95时的平均精度均值;FLOPs表示浮点计算量。下同。
Note: “√” denote that the improved module is introduced into the model; “/” denote that the improved module is not introduced; mAP50-95 denote mean average precision at intersection over union thresholds of 0.50-0.95; FLOPs denote the computational cost in terms of floating-point operations. The same below.
///96.63.088.3
//96.93.188.5
//97.13.289.3
//96.42.587.8
/97.43.389.5
/97.02.688.0
/97.32.788.8
98.22.899.0
), ArticleFig(id=1299828236045799769, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, label=表1, caption=

消融试验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
CBAMBiFPNMSDAmAP50-95/%参数量Params/MFLOPs/G
注:“√”表示该改进模块被引入模型;“/”表示该改进模块未被引入模型;mAP50-95表示交并比阈值为0.50~0.95时的平均精度均值;FLOPs表示浮点计算量。下同。
Note: “√” denote that the improved module is introduced into the model; “/” denote that the improved module is not introduced; mAP50-95 denote mean average precision at intersection over union thresholds of 0.50-0.95; FLOPs denote the computational cost in terms of floating-point operations. The same below.
///96.63.088.3
//96.93.188.5
//97.13.289.3
//96.42.587.8
/97.43.389.5
/97.02.688.0
/97.32.788.8
98.22.899.0
), ArticleFig(id=1299828236133880154, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, label=Tab.2, caption=

Performance comparison of different models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型
Model
mAP50-95/%参数量
Paras/M
FLOPs/G
YOLOv8n96.63.088.3
YOLO11n97.02.666.7
YOLOv8n-CBM98.22.899.0
), ArticleFig(id=1299828236200989019, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, label=表2, caption=

不同模型的性能对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型
Model
mAP50-95/%参数量
Paras/M
FLOPs/G
YOLOv8n96.63.088.3
YOLO11n97.02.666.7
YOLOv8n-CBM98.22.899.0
), ArticleFig(id=1299828236272292188, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, label=Tab.3, caption=

Error analysis of shell length and total height

, figureFileSmall=null, figureFileBig=null, tableContent=
表型参数
Phenotypic parameters
平均值
Mean/mm
模型
Models
MAE/
mm
MRE/
%
RMSE/
mm
MSE/
mm2
注:MAE表示平均绝对误差,MRE表示平均相对误差,RMSE表示均方根误差,MSE表示均方误差。下同。
Note: MAE denotes mean absolute error, MRE denotes mean relative error, RMSE denotes root mean square error, MSE denotes mean square error. The same below.
壳长
Shell length
133.48YOLOv8n2.9972.3473.71613.809
YOLOv8n-CBM1.5121.1681.7463.049
全高
Full height
111.18YOLOv8n1.9281.7962.4455.978
YOLOv8n-CBM1.0830.9971.2171.481
), ArticleFig(id=1299828236335206749, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, label=表3, caption=

壳长与全高的误差分析

, figureFileSmall=null, figureFileBig=null, tableContent=
表型参数
Phenotypic parameters
平均值
Mean/mm
模型
Models
MAE/
mm
MRE/
%
RMSE/
mm
MSE/
mm2
注:MAE表示平均绝对误差,MRE表示平均相对误差,RMSE表示均方根误差,MSE表示均方误差。下同。
Note: MAE denotes mean absolute error, MRE denotes mean relative error, RMSE denotes root mean square error, MSE denotes mean square error. The same below.
壳长
Shell length
133.48YOLOv8n2.9972.3473.71613.809
YOLOv8n-CBM1.5121.1681.7463.049
全高
Full height
111.18YOLOv8n1.9281.7962.4455.978
YOLOv8n-CBM1.0830.9971.2171.481
), ArticleFig(id=1299828236419092830, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, label=Tab.4, caption=

Comparison of shell length measurement errors mm

, figureFileSmall=null, figureFileBig=null, tableContent=
组别
Group
YOLOv8nYOLOv8n-CBM
MAEMaAEMAEMaAE
注:MaAE表示最大绝对误差。下同。
Note: MaAE denotes maximum absolute error. The same below.
第1组Group 12.5567.5281.6562.876
第2组Group 23.7676.5811.2351.977
第3组Group 33.3969.5121.3832.704
第4组Group 43.5516.9091.3532.819
第5组Group 51.7294.1571.9242.794
), ArticleFig(id=1299828236486201695, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, label=表4, caption=

壳长测量误差对比

, figureFileSmall=null, figureFileBig=null, tableContent=
组别
Group
YOLOv8nYOLOv8n-CBM
MAEMaAEMAEMaAE
注:MaAE表示最大绝对误差。下同。
Note: MaAE denotes maximum absolute error. The same below.
第1组Group 12.5567.5281.6562.876
第2组Group 23.7676.5811.2351.977
第3组Group 33.3969.5121.3832.704
第4组Group 43.5516.9091.3532.819
第5组Group 51.7294.1571.9242.794
), ArticleFig(id=1299828236557504864, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=EN, label=Tab.5, caption=

Comparison of full height measurement errors mm

, figureFileSmall=null, figureFileBig=null, tableContent=
组别
Group
YOLOv8nYOLOv8n-CBM
MAEMaAEMAEMaAE
第1组Group 12.0355.9881.2591.978
第2组Group 21.5163.5170.9901.948
第3组Group 32.2714.9851.1631.758
第4组Group 41.7714.7591.0221.646
第5组Group 52.0625.0630.9761.746
), ArticleFig(id=1299828236637196641, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, language=CN, label=表5, caption=

全高测量误差对比

, figureFileSmall=null, figureFileBig=null, tableContent=
组别
Group
YOLOv8nYOLOv8n-CBM
MAEMaAEMAEMaAE
第1组Group 12.0355.9881.2591.978
第2组Group 21.5163.5170.9901.948
第3组Group 32.2714.9851.1631.758
第4组Group 41.7714.7591.0221.646
第5组Group 52.0625.0630.9761.746
)], 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.1002-6819.202507134, detailUrlEn=https://castjournals.cast.org.cn/joweb/nygcxb/EN/10.11975/j.issn.1002-6819.202507134, pdfUrlCn=https://castjournals.cast.org.cn/joweb/nygcxb/CN/PDF/10.11975/j.issn.1002-6819.202507134, pdfUrlEn=https://castjournals.cast.org.cn/joweb/nygcxb/EN/PDF/10.11975/j.issn.1002-6819.202507134, 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
基于改进YOLOv8n的三角帆蚌表型性状参数测量方法
收藏切换
PDF下载
周普洛 1 , 张俊 1, * , 曹守启 1 , 白志毅 2 , 胡庆松 1 , 刘兴国 3 , 王斌 1
农业工程学报 | 农业信息与电气技术 2026,42(12): 239-248
收起
收藏切换
农业工程学报 |农业信息与电气技术 2026 , 42 (12) : 239 -248
基于改进YOLOv8n的三角帆蚌表型性状参数测量方法
全屏
[Author(id=1299828231755026706, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=2416705346@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1299828231826329876, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828231755026706, language=EN, stringName=Puluo ZHOU, firstName=Puluo, middleName=null, lastName=ZHOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828231897633045, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828231755026706, language=CN, stringName=周普洛, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1上海海洋大学工程学院,上海 201306, bio={"content":"

周普洛,研究方向为鱼贝类表型数据精准测量技术。Email:

"}, bioImg=null, bioContent=

周普洛,研究方向为鱼贝类表型数据精准测量技术。Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828231461425416, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, xref=1, ext=[AuthorCompanyExt(id=1299828231469814025, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China), AuthorCompanyExt(id=1299828231482396938, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1上海海洋大学工程学院,上海 201306)])]), Author(id=1299828231956353303, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhangjun@shou.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1299828232023462169, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828231956353303, language=EN, stringName=Jun ZHANG, firstName=Jun, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828232082182426, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828231956353303, language=CN, stringName=张俊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1上海海洋大学工程学院,上海 201306, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828231461425416, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, xref=1, ext=[AuthorCompanyExt(id=1299828231469814025, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China), AuthorCompanyExt(id=1299828231482396938, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1上海海洋大学工程学院,上海 201306)])]), Author(id=1299828232140902684, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, 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=1299828232212205854, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828232140902684, language=EN, stringName=Shouqi CAO, firstName=Shouqi, middleName=null, lastName=CAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828232270926111, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828232140902684, language=CN, stringName=曹守启, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1上海海洋大学工程学院,上海 201306, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828231461425416, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, xref=1, ext=[AuthorCompanyExt(id=1299828231469814025, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China), AuthorCompanyExt(id=1299828231482396938, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1上海海洋大学工程学院,上海 201306)])]), Author(id=1299828232346423585, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, 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=1299828232417726755, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828232346423585, language=EN, stringName=Zhiyi BAI, firstName=Zhiyi, middleName=null, lastName=BAI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2College of Fisheries and Life Sciences, Shanghai Ocean University, Shanghai 201306, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828232505807140, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828232346423585, language=CN, stringName=白志毅, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2上海海洋大学水产与生命学院,上海 201306, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828231557894411, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, xref=2, ext=[AuthorCompanyExt(id=1299828231566283020, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231557894411, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2College of Fisheries and Life Sciences, Shanghai Ocean University, Shanghai 201306, China), AuthorCompanyExt(id=1299828231574671629, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231557894411, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2上海海洋大学水产与生命学院,上海 201306)])]), Author(id=1299828232564527398, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1299828232644219176, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828232564527398, language=EN, stringName=Qingsong HU, firstName=Qingsong, middleName=null, lastName=HU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828232711328041, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828232564527398, language=CN, stringName=胡庆松, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1上海海洋大学工程学院,上海 201306, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828231461425416, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, xref=1, ext=[AuthorCompanyExt(id=1299828231469814025, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China), AuthorCompanyExt(id=1299828231482396938, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1上海海洋大学工程学院,上海 201306)])]), Author(id=1299828232778436907, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, orderNo=5, 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=1299828232853934381, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828232778436907, language=EN, stringName=Xingguo LIU, firstName=Xingguo, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3China Fishery Machinery and Instrument Research Institute, Chinese Academy of Fishery Sciences, Shanghai200092, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828232908460334, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828232778436907, language=CN, stringName=刘兴国, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3中国水产科学研究院渔业机械仪器研究所,上海 200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828231666946318, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, xref=3, ext=[AuthorCompanyExt(id=1299828231675334927, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231666946318, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3China Fishery Machinery and Instrument Research Institute, Chinese Academy of Fishery Sciences, Shanghai200092, China), AuthorCompanyExt(id=1299828231683723536, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231666946318, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3中国水产科学研究院渔业机械仪器研究所,上海 200092)])]), Author(id=1299828232979763504, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, orderNo=6, 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=1299828233059455282, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828232979763504, language=EN, stringName=Bin WANG, firstName=Bin, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1299828233130758451, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, authorId=1299828232979763504, language=CN, stringName=王斌, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1上海海洋大学工程学院,上海 201306, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1299828231461425416, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, xref=1, ext=[AuthorCompanyExt(id=1299828231469814025, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China), AuthorCompanyExt(id=1299828231482396938, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211766140855113, companyId=1299828231461425416, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1上海海洋大学工程学院,上海 201306)])])]
周普洛1 , 张俊1, * , 曹守启1, 白志毅2, 胡庆松1, 刘兴国3, 王斌1
作者信息
  • 1上海海洋大学工程学院,上海 201306
  • 2上海海洋大学水产与生命学院,上海 201306
  • 3中国水产科学研究院渔业机械仪器研究所,上海 200092
通讯作者:
张俊,博士,教授,研究方向为智慧渔业工程与装备。Email:
作者简介:

周普洛,研究方向为鱼贝类表型数据精准测量技术。Email:

A method for measuring phenotypic trait parameters of Sinohyriopsis cumingii based on an improved YOLOv8n model
Puluo ZHOU1 , Jun ZHANG1, * , Shouqi CAO1, Zhiyi BAI2, Qingsong HU1, Xingguo LIU3, Bin WANG1
Affiliations
  • 1College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China
  • 2College of Fisheries and Life Sciences, Shanghai Ocean University, Shanghai 201306, China
  • 3China Fishery Machinery and Instrument Research Institute, Chinese Academy of Fishery Sciences, Shanghai200092, China
出版时间: 2026-06-30 doi: 10.11975/j.issn.1002-6819.202507134
文章导航
收藏切换

三角帆蚌表型性状参数是其生长性能评价、种质资源鉴定和遗传育种研究的重要依据。为实现三角帆蚌表型性状参数的无损、快速和准确获取,该研究提出了一种改进YOLOv8n的三角帆蚌表型性状参数测量模型YOLOv8n-CBM。首先,集成动态传输、机器视觉及图像处理技术,构建三角帆蚌表型参数的自动测量系统;然后,在YOLOv8n骨干网络中,添加4个卷积注意力模块(convolutional block attention module, CBAM),以提高对三角帆蚌轮廓边缘及局部细节特征的提取效果;其次,在颈部网络中引入双向特征金字塔网络(bidirectional feature pyramid network, BiFPN)以加强不同尺度特征之间的双向融合,提高模型对多尺度目标的表征能力;同时,将原有C2f模块替换为多尺度空洞卷积模块(multi-scale dilated attention, MSDA),以扩大特征感受野,增强局部细节与全局上下文信息的联合建模能力;最后,结合旋转边界框与关键点的几何关系,提取壳长、全高、壳高与臀角放射肋长等数据。结果表明,YOLOv8n-CBM模型的平均精度均值(mAP50-95)达到98.2%,壳长、全高、壳高和臀角放射肋长的平均绝对误差分别为1.512、1.083、1.019与1.998 mm;在不同壳长与全高分组下,YOLO-CBM模型的测量误差均小于原始YOLOv8n模型,最大绝对误差不超过2.879 mm,提升了对多姿态下三角帆蚌表型数据的测量精度和鲁棒性。研究结果可为贝类生长性能评价和遗传育种等提供测量方法,对于推动珍珠产业从经验化养殖向科学化、自动化发展具有重要意义。

图像处理  /  深度学习  /  表型  /  三角帆蚌  /  YOLOv8n

Sinohyriopsis cumingii is one of the economically important freshwater mussels in the pearl aquaculture industry. Phenotypic traits of S. cumingii can be expected to evaluate the individual growth performance. Germplasm resources are identified to implement precise genetic breeding. However, conventional manual measurements cannot fully meet the scalability and applicability of the large-scale production in intelligent aquaculture, due to their labor-intensive, time-consuming, and highly susceptible to subjective errors. In this study, an improved measurement was proposed for the non-destructive, rapid, and accurate acquisition of phenotypic parameters using YOLOv8n, termed YOLOv8n-CBM. 1) An integrated phenotypic measurement for S. cumingii was constructed to combine the dynamic transmission, machine vision, and digital image processing. The system comprised a conveyor device, a high-precision industrial camera, and an image processing module. The mussel samples were automatically transported into the imaging area, thus enabling standardized image acquisition and high-throughput phenotypic measurement under continuous dynamic conditions. 2) Three targeted improvements were implemented in the original YOLOv8n network architecture, according to the characteristics of mussel images. In the backbone network, four convolutional block attention modules (CBAM) were embedded after each C2f block to enhance the extraction of contour edges and local features of mussel samples, while effectively suppressing irrelevant background interference. In the neck network, the bidirectional feature pyramid network (BiFPN) was introduced to strengthen bidirectional fusion of multi-scale features for the targets of different sizes and postures. Meanwhile, the original C2f module was replaced with a multi-scale dilated attention (MSDA) module to expand the network’s receptive field for the local fine-grained and global contextual information. Finally, the key phenotypic parameters were extracted, including shell length, full height, shell height, and radial rib length of the buttock angle, according to the geometric relationship between rotated bounding boxes and biological key points. A series of experiments was conducted on a dataset of 50 manually annotated S. cumingii samples with diverse sizes and postures. The results show that the mean average precision (mAP50-95) of the YOLOv8n-CBM model reached 98.2%, indicating the rotated object detection performance over the original YOLOv8n model. The average localization deviation of biological key points was less than 2.0 mm, indicating the high precision in feature detection. The mean absolute errors (MAE) of shell length, full height, shell height, and radial rib length of the buttock angle were 1.51, 1.08, 1.019, and 1.998 mm, respectively. In all groups stratified by different shell lengths and full heights, the measurement errors of YOLOv8n-CBM were consistently lower than those of the original YOLOv8n model, with the maximum absolute error within 2.879 mm. Measurement accuracy and robustness were effectively improved with diverse morphologies and postures. In conclusion, the reliable technical approach was used to realize the rapid, accurate, and non-destructive acquisition of phenotypic traits in S. cumingii. Shellfish growth evaluation and genetic breeding can be expected to support the transition of the pearl industry from empirical farming to data-driven and intelligent aquaculture. The findings can also offer a valuable reference for phenotypic measurement in the molluscan species.

image processing  /  deep learning  /  phenotype  /  Sinohyriopsis cumingii  /  YOLOv8n
周普洛, 张俊, 曹守启, 白志毅, 胡庆松, 刘兴国, 王斌. 基于改进YOLOv8n的三角帆蚌表型性状参数测量方法. 农业工程学报, 2026 , 42 (12) : 239 -248 . DOI: 10.11975/j.issn.1002-6819.202507134
Puluo ZHOU, Jun ZHANG, Shouqi CAO, Zhiyi BAI, Qingsong HU, Xingguo LIU, Bin WANG. A method for measuring phenotypic trait parameters of Sinohyriopsis cumingii based on an improved YOLOv8n model[J]. Transactions of the Chinese Society of Agricultural Engineering, 2026 , 42 (12) : 239 -248 . DOI: 10.11975/j.issn.1002-6819.202507134
三角帆蚌(Sinohyriopsis cumingii)是中国重要的淡水育珠蚌类,具有优良的育珠性能和较高的产业化价值,也是淡水珍珠产业的主导物种[1-2]。蚌体的壳长、壳高、臀角放射肋长等表型性状参数,是评估其育珠性能与种质质量的关键指标,对于种质资源评价、遗传育种等研究具有重要应用价值[3-6]。然而,传统测量方法主要依靠人工逐个称重与测量,该过程繁琐复杂、测量精度较低且费时费力,难以满足短时间内准确采集蚌体生长特征数据的需求。此外,人工测量过程中易对蚌体造成损伤,影响其后续生长发育,进而导致信息采集不准确,影响物种选育与遗传指标评价的科学性。
国内外学者在目标表型性状参数提取领域开展了大量研究[7-9]。崔永超等[10]提出了基于ResNet50和混合域注意力机制的贝类尺寸测量方法,为复杂边缘识别提供了新思路;胡凯[11]和朱俊宇[12]分别在青蟹和沼虾的形态参数检测中引入注意力机制与网络结构压缩技术,实现了精度与效率的双提升;SHEN等[13]通过构建3D点云模型对硬蛤进行高通量表型数据分析,证实了三维重建与机器学习在贝类壳体几何参数与体重预测中的应用潜力;李健源等[14]提出VED-SegNet模型用于提取鱼类体型比例,解决了鱼类姿态差异带来的轮廓误判问题;李振波等[15]则对大型家畜体尺无接触测量方法开展综述,总结了多种深度学习模型在不同物种中的应用基础;罗慧等[16]融合THz成像与集成学习,在低对比度番茄根系图像中实现93%的表型数据预测准确率,展示了多模态特征融合在复杂目标识别中的适应性:黄霞等[17]基于手持式扫描仪实现了种子几何参数的高通量测量,为小尺度目标表型参数的快速采集提供了新路径。
YOLO算法因其检测速度快、精度高等优势被广泛应用于目标检测和表型数据分析[18-22]。张瑞青等[23]提出基于改进YOLOv8-Seg模型的香菇子实体表型参数测量方法,为真菌类表型参数的精准测量提供了技术参考;李国栋等[24]基于YOLO-SDCG和椭圆傅里叶描述子开展番茄苗表型检测,为作物幼苗表型信息提取提供了新方法;姚涛等[25]提出基于改进YOLOv7-seg的黄花菜检测与分割方法,提升了农业目标检测与分割任务的效果;郭希岳等[26]利用Re-YOLOv5和检测区域搜索算法获取大豆植株表型参数,为作物表型参数的智能化测量提供了参考;李新龙等[27]提出基于改进YOLOv10n的自然场景下芒果果实与果梗检测方法,平均精度均值达到95.5%,并在降低计算复杂度和模型规模的同时实现了119.6帧/s的检测速度;刘芹等[28]构建了YOLO-CRC模型,实现茄子及其果梗的分割与定位,有效提升了细粒度目标识别能力;耿耀君等[29]利用改进YOLOv8m实现成熟柿子品种及表型特征的多标签识别,为果树表型自动化评估提供了新思路;李巨虎等[30]则提出了基于改进YOLOv11n的轻量级多尺度水稻害虫识别模型,在保持高检测精度的同时显著降低了模型参数量与计算成本。虽然以上研究均取得了较高精度,但这些方法大多集中于农作物与果蔬类静态图像处理,针对形态不规则、姿态差异大的贝类表型参数高精度测量研究较少。
本文提出一种基于YOLOv8n-CBM的测量模型,通过对三角帆蚌的准确旋转定位,增强蚌壳边缘与局部纹理特征提取能力,进而实现关键表型性状参数的自动测量。主要工作包括:1)构建CBAM模块,以提升模型对蚌壳关键特征区域的关注能力;2)引入BiFPN结构,以增强不同尺度特征之间的融合效果;3)设计C2f_MSDA模块,以提高模型对多尺度信息的提取能力并降低模型复杂度;4)结合旋转边界框检测结果与关键特征点定位结果,构建三角帆蚌表型性状参数自动测量方法,实现壳长、全高、壳高和臀角放射肋长等参数的精准提取。
为快速准确测量三角帆蚌的表型性状参数,本研究集成动态传输、机器视觉及图像处理、自动控制等技术,设计了三角帆蚌表型性状参数测量系统,其结构组成如图1所示。
三角帆蚌经清洗去除表面附着物后,利用自动测量系统进行图像采集。相机成像单元的光轴与传送带平面保持垂直,当蚌体匀速传送至成像区域时,采集控制模块对蚌体进入成像区域进行位置判定,并在蚌体到达相机视场中心附近时,发送触发信号完成一次曝光采集,同时,在上位机端自动保存图像并记录对应的拍摄面信息,130只蚌体正反面拍摄共获得260张原始图像。
将数据集按8:2随机划分为训练集和验证集,为提升模型的泛化能力和鲁棒性,对图像进行增强处理,每张图像以15°为间隔进行旋转,增强后得到6 240张图像。将图像归一化处理为640×640像素。旋转边界框采用Label Studio进行标注,关键点利用Labelme进行标注,并将生成的JSON格式数据集转换为YOLO格式。
YOLOv8根据不同的应用需求分为n、s、m、l、x共5种模型,网络深度依次增加,检测精度、参数量及计算量也随之增大。考虑到三角帆蚌表型性状参数自动测量方法需要兼顾检测精度、运算效率以及后续在边缘设备上的部署需求,因此,选择YOLOv8n作为基础模型。同时采用同系列YOLOv8n-pose模型构建关键点检测支路,用于定位壳顶、腹缘顶端两处特征点以支撑表型参数的几何计算;经预试验验证,原生模型的关键点定位精度已满足测量要求,故未对其做额外结构改进。由于常规YOLO检测任务采用水平边界框进行目标定位,难以适应三角帆蚌的姿态旋转特征,所以在YOLOv8n基础上,将常规水平边界框检测头替换为旋转边界框(oriented bounding box, OBB)检测头[31],并引入卷积注意力模块(CBAM)、多尺度特征金字塔网络(BiFPN)和多尺度空洞注意力模块(C2f_MSDA),改进的YOLOv8n模型结构如图2所示。
1)CBAM模块
三角帆蚌个体形态结构稳定、关键点视觉特征显著(壳顶突出,腹缘顶段白且收缩),但壳体边缘凹凸不规则、表面粗糙,常引起模型检测偏差,如图3所示。
CBAM[32]是一种轻量级注意力机制模块,能够在较小计算开销下提升网络对关键特征信息的提取能力,其结构如图4所示。为提升模型对三角帆蚌图像的关键表型特征提取,在骨干网络新增CBAM注意力模块,首先,通过通道注意力模块对不同通道特征进行自适应调整,强化壳体纹理、边缘和凸起等关键信息;然后,通过空间注意力模块进一步突出目标在特征图中的重要位置,抑制无关背景干扰,进一步增强多尺度目标的检测精度与鲁棒性,其计算式为
$ F{'}={M}_{c}(F)\otimes F $
$ F{'}{'}={M}_{s}(F{'})\otimes F{'} $
式中$ F $为输入图像的特征信息;$ F{'} $为中间加权结果;$ F{'}{'} $为输出图像的特征信息;Mc为通道注意力权重;Ms为空间注意力权重;$\otimes $为矩阵运算。
2)BiFPN模块
三角帆蚌在不同生长阶段个体差异明显,对检测网络的多尺度特征表达能力提出了更高要求。本研究在YOLOv8n的颈部网络引入双向特征金字塔网络BiFPN[33],替代原有的特征金字塔网络(feature pyramid network, FPN)结构,实现跨层级的高效特征融合。
BiFPN模块通过自顶向下与自底向上的双向路径连接,使模型的深层语义特征能够经上采样与浅层高分辨率特征逐级融合,从而保留蚌壳边缘的细节纹理;同时,浅层增强后的特征再与深层特征二次融合,使得网络在处理壳缘凹凸、破损区域以及小体型蚌体时具备更高的检测置信度。
BiFPN通过引入跨层连接实现多尺度特征的重复利用,并利用自适应权重分配机制对不同分支的特征贡献进行动态调整,以避免浅层与深层特征融合时出现信息冗余或特征冲突,相比传统的FPN或路径聚合网络(path aggregation network, PANet),BiFPN在保持计算效率的同时,提升了网络对多尺度目标的表达能力,尤其适合解决蚌体尺寸差异较大的检测任务,其结构如图5所示。
3)C2f_MSDA模块
为增强C2f模块的上下文建模能力,本文在其特征提取单元中引入多尺度空洞注意力机制,构建C2f_MSDA[34],如图6所示。输入特征经线性映射得到查询向量Q、键向量K、值向量V,并在局部滑动窗口内执行注意力计算,不同注意力头采用不同的空洞率,以实现对多尺度邻域信息的稀疏采样。其中,小空洞率侧重局部纹理建模,大空洞率扩展感受野以捕获更丰富的上下文信息。多头输出经拼接与线性融合后生成最终特征表示,从而提升模块对复杂目标和多尺度目标的表征能力。
在三角帆蚌表型性状参数定义中,臀角放射肋长定义为关键点壳顶与腹缘顶端之间的距离;壳长定义为壳体沿主轴方向的长度,以旋转边界框长边表征;全高定义为与壳长方向垂直的最大宽度,以旋转边界框短边表征;壳高定义为除帆部后蚌体的高度特征,由腹缘顶端到壳长边的垂直距离表征。各参数的几何关系如图7所示。
检测框与关键点坐标均为图像中的归一化像素位置,为确保测量结果具有实际物理意义,首先,将网络输出的归一化坐标反归一化为像素坐标(u, v);然后,在传送带上沿横向(传输方向)和纵向分别放置带有刻度的直尺,并利用ImageJ测量软件的直线工具测得对应的像素长度,依据实测的真实长度,定义横向尺度系数sx和纵向尺度系数sy;最后,将像素坐标分别乘以对应的尺度系数,即可得到蚌体关键点与检测框在实际空间中的物理坐标。
$ u={u}_{n}W $
$ v={v}_{n}H $
$ s_x=\frac{L_x^{\mathrm{mm}}}{L_x^{\mathrm{px}}} $
$ s_y=\frac{L_y^{\mathrm{mm}}}{L_y^{\mathrm{px}}} $
式中u为图像横坐标像素值;un为归一化横坐标;W为图像宽;v为纵坐标像素值;vn为归一化纵坐标;H为图像高;sx为横向尺度系数;sy为纵向尺度系数;$ L_x^{\mathrm{mm}} $为标尺横向实际长度,mm;$ L_y^{\mathrm{mm}} $为标尺纵向实际长度,mm;$ L_x^{\mathrm{px}} $为标尺横向像素长度,px;$ L_y^{\mathrm{px}} $为标尺纵向像素长度,px。
由于壳长和全高可分别由旋转边界框的长边和短边直接表征,而壳高不能直接由边界框某一边长获得,因此需进一步确定用于壳高计算的目标边,并构造腹缘顶端到该边的垂线。首先,连接壳顶与腹缘顶端两个关键点,该连线的长度即为蚌体的臀角放射肋长。然后,计算该连线与旋转框四条边之间的夹角;由于旋转边界框的四条边两两平行且相邻边互相正交,因此,只需计算其与两条相邻边的夹角即可,分别记为$ \alpha $$ \beta $。在理想情况下,该连线方向应更接近蚌体主轴方向,从而与旋转框长边的夹角应小于45°。但受端点定位误差、分割边界噪声及旋转框拟合偏差影响,当夹角接近45°时易出现两条相邻边夹角同时接近、候选边不唯一甚至误选短边的判别不稳定情形。因此,在45°判别边界的基础上引入安全裕度,将阈值设定为40°(余弦值大于0.766),以避开45°附近的歧义区间并提高候选边的鲁棒性。首先,筛选夹角小于40°的边作为候选边,然后,选择腹缘顶端到该边的距离大于壳顶到该边距离的候选边作为计算壳高的壳长边,最后,从腹缘顶端向该壳长边作垂线,计算该垂线的长度,即为蚌体的壳高。
试验软件环境采用Python 3.12.7编程语言,Pytorch 2.3.0深度学习框架,运行于Windows 11操作系统。硬件环境为第13代英特尔酷睿i5-13500HX中央处理器(2.50 GHz,14核20线程),16 GB内存,显卡为NVIDIA RTX 4060系列笔记本GPU。图像训练过程均使用了一致的超参数,学习率为0.002,迭代200次,优化器为AdamW,权重衰减为0.000 5,动量为0.937。
本研究以平均精度均值(mean average precision, mAP)、参数量(params)和浮点数计算量(floating point of operations, FLOPs)3项指标作为模型性能评价标准,其中,mAP采用的是交并比(intersection over union, IoU)阈值为0.5~0.95时的平均精度均值(mAP50-95)。
${\text{mAP50-95}} =\frac{1}{10}\displaystyle\sum \nolimits_{t=0.50,0.55,\ldots ,0.95}\left(\frac{1}{B}\displaystyle\sum \nolimits_{b=1}^{B}AP_{B}^{(t)}\right) $
$ {\mathrm{Params}}=\displaystyle\sum \nolimits_{d=1}^{D}{P}_{d} $
$ {\mathrm{FLOPs}}=\displaystyle\sum \nolimits_{d=1}^{D}{{\mathrm{FLOPs}}}_{d} $
式中B为类别总数;b为第b个类别;$ AP_{B}^{\left(t\right)} $表示在IoU阈值t下第b类的平均精度;D表示网络总层数,Pd为第d层的可学习参数数量;FLOPsd为第d层的计算量。
为验证改进后模型(YOLOv8n-CBM)的有效性,设计消融试验来验证模型性能,计算结果如表1所示。结果表明,与基线模型(YOLOv8n)相比,在计算精度方面,单独引入CBAM和BiFPN模块后,模型的平均精度均值(mAP50-95)分别提升0.3和0.5个百分点,表明CBAM模块能够增强模型对关键特征信息的关注能力,BiFPN模块能够有效加强不同尺度特征之间的融合,从而提升模型检测精度;同时引入CBAM+BiFPN、CBAM+MSDA和BiFPN+MSDA模块后,模块的mAP50-95分别提升0.8、0.4和0.7个百分点;同时引入以上3个模块后,即使浮点计算量较基线模型增加了8.4%,但参数量降低了6.2%,同时模型的mAP50-95提升了1.6个百分点,在精度、参数量与计算量三者之间取得了更优的平衡。
验证集边界框损失用于表征模型在验证集上的目标定位误差,能够直接反映不同模型边界框回归性能的优劣,选择YOLO11n作为对照基线的原因是本研究采用旋转框检测,早期YOLO系列无原生支持,传统专用旋转框模型与YOLO-pose技术栈不兼容,其为与YOLOv8n同量级的同系列最新原生支持版本,对照公平且具先进性,结果如图8所示。
图8可知,与YOLOv8n相比,YOLO11n的边界框损失降低了3.0%,说明其边界框回归能力有所提升;在此基础上,YOLOv8n-CBM的边界框损失较YOLOv8n和YOLO11n分别降低了32.3%和30.2%,表明改进模型能够更准确地拟合目标位置与形状,具有更优的边界框回归性能和更稳定的验证效果。
验证集分布式焦点损失用于衡量模型对目标边界位置分布的建模效果,能够反映不同模型在边界细粒度回归过程中的学习能力。由图9可以看出,YOLOv8n与YOLO11n的分布式焦点损失在训练初期均存在不同程度的波动。而YOLOv8n-CBM的下降过程更为平滑,整体收敛趋势更稳定。相较于YOLOv8n和YOLO11n,YOLOv8n-CBM的最终损失分别降低了21.1%和27.6%,表明改进模型对目标边界位置的预测更加精确,有助于提升旋转目标检测中的定位精度。
为验证YOLOv8n-CBM的合理性与有效性,对YOLOv8n、YOLO11n与YOLOv8n-CBM的检测性能进行对比分析,结果如表2所示。
表2可知,YOLOv8n-CBM的mAP50-95较YOLOv8n和YOLO11n分别提高1.6和1.2个百分点,说明改进模块的引入有效增强了模型的特征提取能力与目标检测性能。YOLOv8n-CBM的参数量较YOLO11n增加了8.6%,但较YOLOv8n仍减少了6.2%;其FLOPs较YOLOv8n和YOLO11n分别增加了8.4%和34.3%。YOLO11n在轻量化与计算效率上优势显著,而YOLOv8n-CBM在检测精度上表现更优,能够在精度、参数量与计算复杂度之间实现更优的平衡,展现出更佳的综合性能,可进一步实现表型性状参数的精准计算。
为对比模型改进前后对不同旋转姿态下的检测效果,选取0°、60°、120°、180°、240°和300°共6种旋转角度的三角帆蚌样本进行检测。由图10可以看出,YOLOv8n在0°和180°时存在检测框角度偏差和包围不完整的问题。相比之下,YOLOv8n-CBM在各个旋转角度下均能够较好地贴合三角帆蚌外轮廓,其检测框方向与目标姿态基本一致,包围结果更加完整,表现出更高的检测准确性和方向稳定性。
为进一步验证YOLOv8n-CBM与YOLOv8n-pose在目标定位与关键结构的识别性能,对模型预测结果进行可视化分析,包括旋转框(粉紫色框)、壳顶(蓝色圆点)与腹缘顶端(红色圆点)关键点、壳顶与腹缘顶端关键点连线(绿色线)和腹缘顶端到旋转框边缘的壳高垂线(黄色线),预测模型的可视化结果如图11所示。结果表明,旋转目标框能够较好贴合三角帆蚌壳体轮廓,避免了水平框检测中易出现的过度包围或边界错位现象。同时,壳顶、壳顶放射肋末端、腹缘顶端和壳顶等关键点均落在相应的形态学特征区域,基于关键点构建的壳长、全高、臀角放射肋长及壳高几何关系清晰,说明基于旋转框特征提取方法,可在目标检测的基础上实现表型性状参数的准确计算。
使用平均绝对误差(mean absolute error, MAE)、平均相对误差(mean relative error, MRE)、均方根误差(root mean square error, RMSE)、均方误差(mean square error, MSE)、最大绝对误差(maximum absolute error, MaAE)和决定系数(R2)评估指标[35-36],分析模型预测的误差,计算式分别为
$ \text{MAE}=\frac{1}{N}\displaystyle\sum \nolimits_{\textit{i}=1}^{N}\left| {y}_{\mathrm{i}}-\widetilde{{y}_{i}}\right| $
$ \text{MRE}=\frac{1}{N}\displaystyle\sum \nolimits_{i=1}^{N}\left(\frac{\left| {\text{y}}_{i}-\widetilde{{y}_{i}}\right| }{{y}_{i}}\right) $
$ \text{RMSE}=\sqrt{\frac{1}{N}\displaystyle\sum \nolimits_{\textit{i}=1}^{N}{({{y}_{\mathrm{i}}}-\widetilde{{y}_{i}})}^{2}} $
$ \text{MSE}=\frac{1}{N}\displaystyle\sum \nolimits_{\textit{i}=1}^{N}{({{y}_{\mathrm{i}}}-\widetilde{{y}_{i}})}^{2} $
$ \text{MaAE}=\max \left| {y}_{i}-\widetilde{{y}_{i}}\right| $
$ {R}^{\text{2}}=\frac{\displaystyle\sum \nolimits_{i=1}^{N}{\left({y}_{i}-\widetilde{{y}_{i}}\right)}^{2}}{\displaystyle\sum \nolimits_{i=1}^{N}{\left({y}_{i}-\overline{{y}_{i}}\right)}^{2}} $
式中$ {y}_{i} $为手工测量值,mm;$ \widetilde{{y}_{i}} $为模型预测值,mm;$ \overline{{y}_{i}} $为手工测量值的平均值,mm;N为预测值的个数。
本文选用YOLOv8n作为对比模型,其为当前主流旋转框轻量检测模型,且与YOLO11n检测性能差异不大,为评估YOLOv8n与YOLOv8n-CBM在三角帆蚌表型性状参数测量中的性能,对壳长和全高两个性状的预测结果进行误差统计分析,结果如表3所示。
对比分析表3可知,YOLOv8n-CBM在壳长和全高测量的四项评估指标上均优于YOLOv8n。对于壳长测量,YOLOv8n-CBM的MAE、MRE、RMSE和MSE较YOLOv8n分别降低49.7%、50.2%、53.0%和77.9%;对于全高测量,YOLOv8n-CBM的MAE、MRE、RMSE和MSE较YOLOv8n分别降低44.0%、44.4%、50.2%和75.3%。结果表明,改进模型在壳长与全高测量中均具有更高的精度和稳定性,验证了所提模块组合改进策略能够有效提升多姿态条件下三角帆蚌表型性状参数的测量性能。
表4给出了由小到大5个分组内YOLOv8n模型与YOLOv8n-CBM在壳长预测任务中的MAE与MaAE。结果表明,在所有分组中,YOLOv8n-CBM的MAE始终低于YOLOv8n模型,第2组MAE下降67.22%,MaAE下降69.96%;第3组MAE下降59.28%,MaAE下降71.57%。此外,YOLOv8n模型在部分组别中出现较大MaAE,表明其在复杂壳长形态下的稳定性较差,而YOLOv8n-CBM的MaAE低于2.879 mm,误差波动幅度明显降低,在不同尺寸样本下均表现出更稳定的测量性能。
表5给出了5个壳长分组中YOLOv8n模型与YOLOv8n-CBM在全高预测任务中的MAE与MaAE变化规律。结果表明:YOLOv8n-CBM在所有分组中均保持不高于1.259 mm的MAE,MaAE控制在1.978 mm以内;YOLOv8n模型在第3组与第5组中MAE超过2.035 mm,MaAE分别为4.985、5.063 mm,说明在姿态变化条件下存在一定范围内的误差波动;YOLOv8n-CBM在全高预测任务中同样展现出更高的精度和稳定性,适用于多尺度、多变形体态下的三角帆蚌性状自动识别。
为评估测量系统在关键特征提取任务中的精度表现,对比分析模型预测值与人工实测值在壳高与臀角放射肋长两个指标上的差异。基于50组样本数据,分别计算MAE、RMSE与R2,以量化模型预测的准确性与稳定性,结果如图12图13所示。
图12可知,大多数样本点均密集分布在理想预测线(y = x)附近,呈现出较高的一致性与收敛性,说明模型对壳体高度特征的识别与建模能力较强,模型预测结果与人工标注值之间的MAE为1.019 mm,RMSE为1.299 mm,R2达到0.932,MaAE为4.080 mm,表明预测结果与真实值之间具有高度线性相关性,误差分布稳定可控。
图13可知,臀角放射肋长的大多数点仍密集分布于理想预测线附近,未出现大幅度偏离或系统性偏差。尽管个别样本在边缘区域存在一定预测偏差,但整体趋势稳定,拟合性能强,对复杂特征线条同样有较好预测能力,MAE为1.998 mm,RMSE为2.515 mm,R2达到0.960,MaAE为6.168 mm。
本文基于改进YOLOv8n算法与YOLOv8n-pose模型相结合的自动测量方法,构建了三角帆蚌表型性状参数自动测量系统,实现了三角帆蚌壳长、全高、壳高与臀角放射肋长等关键表型性状参数的精准测量,主要得到以下结论:
1)消融试验结果表明,单独引入卷积注意力模块(convolutional block attention module, CBAM)和双向特征金字塔网络(bidirectional feature pyramid network, BiFPN)后,模型的平均精度均值(mAP50-95)分别提升至96.9%和97.1%;单独引入多尺度空洞卷积模块(multi-scale dilated attention, MSDA)虽使mAP50-95略降至96.4%,但有效降低了参数量与计算量。进一步组合引入各模块后,YOLOv8n-CBM模型综合性能最优,与原始模型(YOLOv8n)相比,其mAP50-95提升了1.6个百分点,参数量降低了6.2%。
2)不同模型对比试验和可视化检测结果表明,YOLOv8n-CBM模型在三角帆蚌目标检测任务中表现最优。YOLOv8n-CBM模型的mAP50-95达到98.2%,与YOLOv8n(96.6%)、YOLO11n(97.0%)相比,检测精度分别提升1.6和1.2个百分点。
3)三角帆蚌的表型性状参数测量结果表明,YOLOv8n-pose与YOLOv8n-CBM结合测量,壳长、全高、壳高和臀角放射肋长的平均绝对误差分别为1.512、1.083、1.019与1.998 mm。与原始YOLOv8n相比,YOLOv8n-CBM在各分组下测量误差大幅降低。
未来可进一步开展以下研究:1)引入三维建模与多模态信息融合,结合深度相机采集的点云数据与二维图像特征,修正因角度和遮挡造成的误差;2)优化数据集构建策略,通过增加多源异构数据、引入跨物种迁移学习与数据增强技术,进一步提高模型的适应性与稳定性。

参考文献 引证文献
排序方式:
1
张根芳, 张文府, 罗雨, 等. 1龄三角帆蚌壳形态性状对体质量的通径分析[J]. 大连海洋大学学报, 2018, 33(6): 755-759.
ZHANG Genfang, ZHANG Wenfu, LUO Yu, et al. Path analysis of morphological traits on body weight of one-year-old freshwater mussel Hyriopsis cumingii[J]. Journal of Dalian Ocean University, 2018, 33(6): 755-759. (in Chinese with English abstract)
2
何志然, 胡宏辉, 冯上乐, 等. 三角帆蚌金色品系生长性状遗传参数及基因型与环境互作效应分析[J]. 大连海洋大学学报, 2021, 36(2): 254-259.
HE Zhiran, HU Honghui, FENG Shangle, et al. Estimation of genetic parameters on growth traits and interaction between genotype and environment in golden strain of freshwater mussel Hyriopsis cumingii[J]. Journal of Dalian Ocean University, 2021, 36(2): 254-259. (in Chinese with English abstract)
3
吴雷明, 白志毅, 刘晓军, 等. 三角帆蚌F5壳色及生长性状选育效果评价[J]. 中国水产科学, 2021, 28(3): 325-334.
WU Leiming, BAI Zhiyi, LIU Xiaojun, et al. Evaluation of shell color and growth traits for F5 of the freshwater pearl mussel[J]. Journal of Fishery Sciences of China, 2021, 28(3): 325-334. (in Chinese with English abstract)
4
闻海波, 顾若波, 华丹, 等. 两水系三角帆蚌亲本及杂交、自交组钩介幼虫形态性状比较[J]. 上海海洋大学学报, 2010, 19(5): 612-614.
WEN Haibo, GU Ruobo, HUA Dan, et al. Comparsion of morphological characters of broodstocks and their glochidia in reciprocal hrybird of Hyriopsis cumingii from two drainage systems[J]. Journal of Shanghai Ocean University, 2010, 19(5): 612-614. (in Chinese with English abstract)
5
HU H H, WANG Z Y, JIA L, et al. Genetic differentiation and identification of key genes related to biomineralization and coloration in three Hyriopsis cumingii strains exhibiting different inner shell colors[J]. Aquaculture Reports, 2024, 35: 101939.
6
吕高伦, 吕雪峰, 王昊, 等. 不同年龄三角帆蚌新生长性状臀角放射肋长与其他生长性状相关性和通径分析[J]. 上海海洋大学学报, 2024, 33(3): 562-571.
LYU Gaolun, LYU Xuefeng, WANG Hao, et al. Correlation and path analysis of new growth traits including radial rib length in different-aged Hyriopsis cumingii[J]. Journal of Shanghai Ocean University, 2024, 33(3): 562-571. (in Chinese with English abstract)
7
刘刚, 曾雪婷, 刘晓文, 等. 基于改进YOLOv5-pose的群养生猪体尺自动测量方法[J]. 农业机械学报, 2025, 56(05): 455-465.
LIU Gang, ZENG Xueting, LIU Xiaowen, et al. Automatic measurement method of body size of group-raised pigs based on improved YOLO v5-pose[J]. Transactions of the Chinese Society for Agricultural Machinery, 2025, 56(05): 455-465. (in Chinese with English abstract)
8
翟肇裕, 张梓涵, 徐焕良, 等. YOLO算法在动植物表型研究中应用综述[J]. 农业机械学报, 2024, 55(11): 1-20.
ZHAI Zhaoyu, ZHANG Zihan, XU Huanliang, et al. Review of applying YOLO family algorithms to analyze animals and plant phenotype[J]. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55(11): 1-20. (in Chinese with English abstract)
9
陈慧颖, 宋青峰, 常天根, 等. 基于YOLOv5m和CBAM-CPN的单分蘖水稻表型参数提取[J]. 农业工程学报, 2024, 40(2): 307-314.
CHEN Huiying, SONG Qingfeng, CHANG Tiangen, et al. Extraction of the single-tiller rice phenotypic parameters based on YOLOv5m and CBAM-CPN[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(2): 307-314. (in Chinese with English abstract)
10
崔永超, 武栓虎, 牟春晓, 等. 基于深度学习的贝类目标定位与统计测量方法[J]. 烟台大学学报(自然科学与工程版), 2023, 36(02): 204-210.
CUI Yongchao, WU Shuanhu, MOU Chunxiao, et al. Target location and statistical measurement method of shellfish based on deep learning[J]. Journal of Yantai University (Natural Science and Engineering Edition), 2023, 36(02): 204-210. (in Chinese with English abstract)
11
胡凯. 基于深度学习的青蟹测量和检测模型研究[D]. 杭州: 浙江大学, 2022.
HU Kai. Deep Learning Based Scylla Measurement and Detection Model[D]. Hangzhou: Zhejiang University, 2022. (in Chinese with English abstract)
12
朱俊宇. 基于深度学习压缩模型的沼虾表型数据测定研究[D]. 杭州: 浙江大学, 2022.
ZHU Junyu. Research on Measurement of Phenotypic Data of Macro Shrimp Based on Deep-Learning Compressed Model[D]. Hangzhou: Zhejiang University, 2022. (in Chinese with English abstract)
13
SHEN K, WANG X, GAO K, et al. High-throughput 3D phenotyping in northern quahogs Mercenaria mercenaria for dimensional trait measurement and weight prediction[J]. Smart Agricultural Technology, 2025, 10: 100840.
14
李健源, 柳春娜, 卢晓春, 等. 构建VED-SegNet分割模型提取鱼类表型比例[J]. 农业工程学报, 2024, 40(3): 175-183.
LI Jianyuan, LIU Chunna, LU Xiaochun, et al. Constructing VED-SegNet segmentation model to extract fish phenotype proportions[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(3): 175-183. (in Chinese with English abstract)
15
李振波, 孙浩翔, 郭倩男, 等. 机器视觉技术在大体型家畜无接触体尺测量中的研究进展[J]. 农业工程学报, 2025, 41(7): 1-12.
LI Zhenbo, SUN Haoxiang, GUO Qiannan, et al. Research progress on machine vision technology for non-contact body measurement of large livestock[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(7): 1-12. (in Chinese with English abstract)
16
罗慧, 刘星语, 韦骁, 等. 基于THz成像和集成学习的番茄根长表型提取及预测[J]. 农业工程学报, 2024, 40(18): 176-183.
LUO Hui, LIU Xingyu, WEI Xiao, et al. Extracting and predicting tomato root length phenotype using THz imaging and ensemble learning[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(18): 176-183. (in Chinese with English abstract)
17
黄霞, 申笠蒙, 朱锋博, 等. 基于手持式扫描仪的种子几何参数高通量测量[J]. 农业工程学报, 2024, 40(21): 312-322.
HUANG Xia, SHEN Limeng, ZHU Fengbo, et al. High-throughput measurement of seed geometric parameters using handheld scanner[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(21): 312-322. (in Chinese with English abstract)
18
叶秉良, 丰睿, 唐涛, 等. 基于改进YOLOv10n的自然环境下莲蓬成熟度检测方法[J]. 农业工程学报, 2025, 41(22): 145-153.
YE Bingliang, FENG Rui, TANG Tao, et al. Ripeness detection of lotus seedpod in natural environment based on improved YOLOv10n[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(22): 145-153. (in Chinese with English abstract)
19
何志鹏, 巩高瑞, 熊阳, 等. 基于计算机视觉的黄颡鱼表型特征测量和体重预测模型研究[J]. 水生生物学报, 2024, 48(7): 1149-1158.
HE Zhipeng, GONG Gaorui, XIONG Yang, et al. A phenotypic measurement and weight prediction model of Pelteobagrus fulvidraco based on computer vision[J]. Acta Hydrobiologica Sinica, 2024, 48(7): 1149-1158. (in Chinese with English abstract)
20
CHEN K, CHEN Z, WANG C, et al. Improved YOLO v8-based method for the carapace keypoint detection and size measurement of Chinese mitten crabs[J]. Animals, 2025, 15(7): 941.
21
LIU W Z, TAN J Y, LAN G Y, et al. Benchmarking fish dataset and evaluation metric in keypoint detection - Towards precise fish morphological assessment in aquaculture breeding[C]// Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI-24). Jeju, South Korea: International Joint Conferences on Artificial Intelligence Organization, 2024: 7376-7384.
22
YU Y Z, ZHANG H, YUAN F. Key point detection method for fish size measurement based on deep learning[J]. IET Image Processing, 2023, 17(14): 4142-4158.
23
张瑞青, 刘攀, 陈文杰, 等. 基于改进YOLOv8-Seg模型的香菇子实体表型参数测量方法[J]. 农业工程学报, 2025, 41(23): 143-151.
ZHANG Ruiqing, LIU Pan, CHEN Wenjie, et al. Measurement method for the phenotypic parameters of Lentinula edodes fruiting bodies based on improved YOLOv8-Seg model[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(23): 143-151. (in Chinese with English abstract)
24
李国栋, 喻俊志, 秦新燕, 等. 基于YOLO-SDCG和椭圆傅里叶描述子的番茄苗表型检测[J]. 农业工程学报, 2026, 42(3): 179-191.
LI Guodong, YU Junzhi, QIN Xinyan, et al. Phenotypic detection of tomato seedlings based on YOLO-SDCG and elliptic Fourier descriptors[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2026, 42(3): 179-191. (in Chinese with English abstract)
25
姚涛, 谈志鹏, 程娥, 等. 基于改进YOLOv7-seg的黄花菜检测与分割方法[J]. 农业工程学报, 2024, 40(9): 146-153.
YAO Tao, TAN Zhipeng, CHENG E, et al. Method for daylily detection and segmentation based on improved YOLOv7-seg[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(9): 146-153. (in Chinese with English abstract)
26
郭希岳, 李劲松, 郑立华, 等. Re-YOLOv5和检测区域搜索算法获取大豆植株表型参数[J]. 农业工程学报, 2022, 38(15): 186-194.
Guo Xiyue, Li Jinsong, Zheng Lihua, et al. Acquiring soybean phenotypic parameters using Re-YOLOv5 and area search algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2022, 38(15): 186-194. (in Chinese with English abstract)
27
李新龙, 兰玉彬, 王会征. 基于改进YOLOv10n的自然场景下芒果果实与果梗检测方法[J]. 农业工程学报, 2025, 41(19): 167-175. (in Chinese with English abstract).
LI Xinlong, LAN Yubin, WANG Huizheng. Detecting mango fruits and peduncles in natural scenes using improved YOLOv10n[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(19): 167-175. (in Chinese with English abstract)
28
刘芹, 欧阳婧玟, 周智彬, 等. 基于YOLO-CRC的茄子及茄子梗分割与定位方法[J]. 农业工程学报, 2025, 41(19): 196-205.
LIU Qin, OUYANG Jingwen, ZHOU Zhibin, et al. Segmentation and localization method for eggplants and stems based on YOLO-CRC[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(19): 196-205. (in Chinese with English abstract)
29
耿耀君, 马萍, 李雯敏, 等. 基于改进YOLOv8m的成熟柿子品种及表型特征多标签识别[J]. 农业工程学报, 2025, 41(17): 143-152.
GENG Yaojun, MA Ping, LI Wenmin, et al. Multi-label recognition of ripen persimmons varieties and phenotypic characteristics based on improved YOLOv8m[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(17): 143-152. (in Chinese with English abstract)
30
李巨虎, 徐玉立, 路佳, 等. 基于改进YOLOv11n的轻量级多尺度水稻害虫识别模型[J]. 农业工程学报, 2025, 41(17): 175-183.
LI Juhu, XU Yuli, LU Jia, et al. Lightweight multi-scale rice pest recognition model based on improved YOLOv11n[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2025, 41(17): 175-183. (in Chinese with English abstract)
31
FENG S, HUANG Y, ZHANG N. An improved YOLO v8 OBB model for ship detection through stable diffusion data augmentation[J]. Sensors, 2024, 24(17): 5850.
32
WOO S, PARK J, LEE J Y, et al. CBAM: Convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision (ECCV), Cham, Switzerland: Springer, 2018: 3-19.
33
TAN M, PANG R, LE Q V. Efficient Det: Scalable and efficient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, USA: IEEE, 2020: 10778-10787.
34
JIAO J, TANG Y M, LIN K Y, et al. DilateFormer: Multi-scale dilated transformer for visual recognition[J]. IEEE Transactions on Multimedia, 2023, 25: 8906-8919.
35
WILLMOTT C J, MATSUURA K. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance[J]. Climate Research, 2005, 30(1): 79-82.
36
KHAKI S, PHAM H, HAN Y, et al. DeepCorn: A semi-supervised deep learning method for high-throughput image-based corn kernel counting and yield estimation[J]. Knowledge-Based Systems, 2021, 218: 1068.
2026年第42卷第12期
PDF下载
179
82
引用本文
BibTeX
文章信息
doi: 10.11975/j.issn.1002-6819.202507134
  • 接收时间:2025-07-15
  • 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:2025-07-15
  • 修回日期:2026-02-26
基金
作者信息
    1上海海洋大学工程学院,上海 201306
    2上海海洋大学水产与生命学院,上海 201306
    3中国水产科学研究院渔业机械仪器研究所,上海 200092

通讯作者:

张俊,博士,教授,研究方向为智慧渔业工程与装备。Email:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/nygcxb/CN/10.11975/j.issn.1002-6819.202507134
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