Article(id=1263818968280777311, tenantId=1146029695717560320, journalId=1263530845441638439, issueId=1263818962224165389, articleNumber=null, orderNo=null, doi=10.19693/j.issn.1673-3185.04381, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1740153600000, receivedDateStr=2025-02-22, revisedDate=1747497600000, revisedDateStr=2025-05-18, acceptedDate=null, acceptedDateStr=null, onlineDate=1779247522658, onlineDateStr=2026-05-20, pubDate=1777478400000, pubDateStr=2026-04-30, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1779247522658, onlineIssueDateStr=2026-05-20, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1779247522658, creator=13041195026, updateTime=1779247522658, updator=13041195026, issue=Issue{id=1263818962224165389, tenantId=1146029695717560320, journalId=1263530845441638439, year='2026', volume='21', issue='2', pageStart='1', pageEnd='444', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1779247521215, creator=13041195026, updateTime=1779247861438, updator=13041195026, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1263820389638070544, tenantId=1146029695717560320, journalId=1263530845441638439, issueId=1263818962224165389, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1263820389638070545, tenantId=1146029695717560320, journalId=1263530845441638439, issueId=1263818962224165389, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=112, endPage=124, ext={EN=ArticleExt(id=1263818970017219183, articleId=1263818968280777311, tenantId=1146029695717560320, journalId=1263530845441638439, language=EN, title=Multi-feature fusion-based terminal visual autonomous docking technology for AUV, columnId=1263818964086436367, journalTitle=Chinese Journal of Ship Research, columnName=Overall Design Technology of Unmanned Underwater Systems, runingTitle=null, highlight=null, articleAbstract=
Objective

To address the low docking accuracy of autonomous underwater vehicles (AUVs) in complex underwater environments, a multi-feature fusion vision-based method is proposed.

Method

A self-developed rudderless vector propulsion AUV with four thrusters was used, and the dark channel prior (DCP) dehazing algorithm was adopted for image enhancement. An improved Canny edge detection algorithm was combined with color threshold segmentation to achieve multi-feature fusion. The minimum enclosing circle method was utilized for circle center positioning, and coordinate transformation was performed to calculate the relative position and orientation for docking.

Results

Unity 3D simulations and pool experiments revealed a distance-dependent trend: both mean difference and root mean square error decreased as docking distance decreased. Closer distances yielded higher visual ranging accuracy and docking precision. When the docking distance was less than 2 m, the positioning error was maintained below 5 cm, with an overall success rate of 88%.

Conclusion

The proposed method fulfills the accuracy requirements for AUV autonomous docking and provides a highly robust solution for underwater equipment recovery.

, correspAuthors=Xiangdong QI, authorNote=null, correspAuthorsNote=null, copyrightStatement=Copyright © 2026 Chinese Journal of Ship Research. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Pan XIONG, Xiangdong QI, Yanlin SUN, Zhengyang ZHAO, Juhao QIN), CN=ArticleExt(id=1263819052758254019, articleId=1263818968280777311, tenantId=1146029695717560320, journalId=1263530845441638439, language=CN, title=多特征融合的AUV末端视觉自主对接技术研究, columnId=1263818964476506641, journalTitle=中国舰船研究, columnName=水下无人系统总体设计技术, runingTitle=null, highlight=null, articleAbstract=
目的

为解决自主水下航行器(AUV)在复杂水下环境中自主对接精度不足的问题,提出一种基于多特征融合的视觉导引方法。

方法

依托实验室自主研发的四桨无舵矢量推进型AUV,使用暗通道先验去雾算法进行图像增强,结合改进的Canny边缘检测与颜色阈值分割实现多特征融合,利用最小包围圆法进行圆心定位,通过坐标系转换解算相对位姿完成对接。

结果

Unity 3D仿真和水池实验结果表明,均值差和均方根误差均呈现随对接距离接近而减小的距离相关性,距离越近,视觉测距越准确,对接精度越高,对接距离小于2 m时位姿精度误差小于5 cm,总体对接成功率为88%。

结论

所提方法满足AUV自主对接任务中对接精度要求,为水下装备自主回收提供了高鲁棒性的解决方案。

, correspAuthors=齐向东, authorNote=null, correspAuthorsNote=
* 齐向东
, copyrightStatement=版权所有 © 《中国舰船研究》编辑部 2026, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=AjiPszkSAumuHzsCPdkY8Q==, magXml=L+VPhZg0xdpe+qlSdW0qxQ==, pdfUrl=null, pdf=hN/qN+bxggwd8VriCzUXEg==, pdfFileSize=6433559, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=V1M4Hyp/uJppjvZRd4ca0g==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=2fWHyC9azFnxmr75I2+sSg==, mapNumber=null, authorCompany=null, fund=null, authors=

熊攀,男,2000年生,硕士生。研究方向:水下无人潜航器自主对接技术。E-mail:

齐向东,男,1967年生,教授。研究方向:水下无人潜航器系统技术。E-mail:

, authorsList=熊攀, 齐向东, 孙岩林, 赵正阳, 秦钜灏)}, authors=[Author(id=1263819053504840141, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=18175791992@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1263819053685195216, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, authorId=1263819053504840141, language=EN, stringName=Pan XIONG, firstName=Pan, middleName=null, lastName=XIONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=State Key Laboratory of Extreme Environment Optoelectronic Dynamic Measurement Technology and Instrument, North University of China, Taiyuan 030051, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1263819053840384466, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, authorId=1263819053504840141, language=CN, stringName=熊攀, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中北大学 极限环境光电动态测试技术与仪器全国重点实验室,山西 太原 030051, bio={"content":"

熊攀,男,2000年生,硕士生。研究方向:水下无人潜航器自主对接技术。E-mail:

"}, bioImg=null, bioContent=

熊攀,男,2000年生,硕士生。研究方向:水下无人潜航器自主对接技术。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1263819053169295815, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, xref=null, ext=[AuthorCompanyExt(id=1263819053177684424, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, companyId=1263819053169295815, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=State Key Laboratory of Extreme Environment Optoelectronic Dynamic Measurement Technology and Instrument, North University of China, Taiyuan 030051, China), AuthorCompanyExt(id=1263819053186073034, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, companyId=1263819053169295815, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中北大学 极限环境光电动态测试技术与仪器全国重点实验室,山西 太原 030051)])]), Author(id=1263819054037516757, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zbdxqxd@163.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1263819054435975640, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, authorId=1263819054037516757, language=EN, stringName=Xiangdong QI, firstName=Xiangdong, middleName=null, lastName=QI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=State Key Laboratory of Extreme Environment Optoelectronic Dynamic Measurement Technology and Instrument, North University of China, Taiyuan 030051, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1263819054888960473, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, authorId=1263819054037516757, language=CN, stringName=齐向东, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=中北大学 极限环境光电动态测试技术与仪器全国重点实验室,山西 太原 030051, bio={"content":"

齐向东,男,1967年生,教授。研究方向:水下无人潜航器系统技术。E-mail:

"}, bioImg=null, bioContent=

齐向东,男,1967年生,教授。研究方向:水下无人潜航器系统技术。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1263819053169295815, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, xref=null, ext=[AuthorCompanyExt(id=1263819053177684424, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, companyId=1263819053169295815, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=State Key Laboratory of Extreme Environment Optoelectronic Dynamic Measurement Technology and Instrument, North University of China, Taiyuan 030051, China), AuthorCompanyExt(id=1263819053186073034, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, companyId=1263819053169295815, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中北大学 极限环境光电动态测试技术与仪器全国重点实验室,山西 太原 030051)])]), Author(id=1263819056768008668, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, 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=1263819057162273246, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, authorId=1263819056768008668, language=EN, stringName=Yanlin SUN, firstName=Yanlin, middleName=null, lastName=SUN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=State Key Laboratory of Extreme Environment Optoelectronic Dynamic Measurement Technology and Instrument, North University of China, Taiyuan 030051, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1263819057606869472, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, authorId=1263819056768008668, language=CN, stringName=孙岩林, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中北大学 极限环境光电动态测试技术与仪器全国重点实验室,山西 太原 030051, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1263819053169295815, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, xref=null, ext=[AuthorCompanyExt(id=1263819053177684424, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, companyId=1263819053169295815, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=State Key Laboratory of Extreme Environment Optoelectronic Dynamic Measurement Technology and Instrument, North University of China, Taiyuan 030051, China), AuthorCompanyExt(id=1263819053186073034, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, companyId=1263819053169295815, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中北大学 极限环境光电动态测试技术与仪器全国重点实验室,山西 太原 030051)])]), Author(id=1263819057820778980, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, 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=1263819058227626471, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, authorId=1263819057820778980, language=EN, stringName=Zhengyang ZHAO, firstName=Zhengyang, middleName=null, lastName=ZHAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=State Key Laboratory of Extreme Environment Optoelectronic Dynamic Measurement Technology and Instrument, North University of China, Taiyuan 030051, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1263819058630279657, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, authorId=1263819057820778980, language=CN, stringName=赵正阳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中北大学 极限环境光电动态测试技术与仪器全国重点实验室,山西 太原 030051, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1263819053169295815, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, xref=null, ext=[AuthorCompanyExt(id=1263819053177684424, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, companyId=1263819053169295815, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=State Key Laboratory of Extreme Environment Optoelectronic Dynamic Measurement Technology and Instrument, North University of China, Taiyuan 030051, China), AuthorCompanyExt(id=1263819053186073034, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, companyId=1263819053169295815, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中北大学 极限环境光电动态测试技术与仪器全国重点实验室,山西 太原 030051)])]), Author(id=1263819058777080300, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, 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=1263819059003572718, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, authorId=1263819058777080300, language=EN, stringName=Juhao QIN, firstName=Juhao, middleName=null, lastName=QIN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=State Key Laboratory of Extreme Environment Optoelectronic Dynamic Measurement Technology and Instrument, North University of China, Taiyuan 030051, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1263819059116818927, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, authorId=1263819058777080300, language=CN, stringName=秦钜灏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中北大学 极限环境光电动态测试技术与仪器全国重点实验室,山西 太原 030051, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1263819053169295815, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, xref=null, ext=[AuthorCompanyExt(id=1263819053177684424, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, companyId=1263819053169295815, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=State Key Laboratory of Extreme Environment Optoelectronic Dynamic Measurement Technology and Instrument, North University of China, Taiyuan 030051, China), AuthorCompanyExt(id=1263819053186073034, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, companyId=1263819053169295815, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中北大学 极限环境光电动态测试技术与仪器全国重点实验室,山西 太原 030051)])])], keywords=[Keyword(id=1263819059532055025, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, orderNo=1, keyword=autonomous underwater vehicles (AUVs)), Keyword(id=1263819061134279155, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, orderNo=2, keyword=autonomous docking), Keyword(id=1263819061306245620, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, orderNo=3, keyword=Canny edge detection), Keyword(id=1263819061453046262, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, orderNo=4, keyword=color threshold segmentation), Keyword(id=1263819061608235511, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, orderNo=5, keyword=multi-feature fusion), Keyword(id=1263819061868282361, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, orderNo=1, keyword=自主水下航行器), Keyword(id=1263819062006694394, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, orderNo=2, keyword=自主对接), Keyword(id=1263819062199632380, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, orderNo=3, keyword=Canny边缘检测), Keyword(id=1263819062614868478, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, orderNo=4, keyword=颜色阈值分割), Keyword(id=1263819062757474816, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, orderNo=5, keyword=多特征融合)], refs=[Reference(id=1263819075579462242, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, 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=卢有旺, 夏英凯, 徐国华, 等. 面向UUV对接的视觉引导三维轨迹跟踪控制研究[J]. 中国舰船研究, 2024, 19(1): 290–304., articleTitle=null, refAbstract=null), Reference(id=1263819075764011619, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, 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=LU Y W, XIA Y K, XU G H, et al. Study on vision-guided 3D tracking control for UUV docking[J]. Chinese Journal of Ship Research, 2024, 19(1): 290–304., articleTitle=null, refAbstract=null), Reference(id=1263819075877257828, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, 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=袁学庆, 刁家宇, 李卫民, 等. AUV水下对接的发展与应用现状[J]. 舰船科学技术, 2023, 45(5): 1–8., articleTitle=null, refAbstract=null), Reference(id=1263819076007281253, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, 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=YUAN X Q, DIAO J Y, LI W M, et al. Development and application status of AUV underwater docking[J]. Ship Science and Technology, 2023, 45(5): 1–8 (in Chinese)., articleTitle=null, refAbstract=null), Reference(id=1263819076103750246, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, 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=孙叶义, 武皓微, 李晔, 等. 智能无人水下航行器水下回收对接技术综述[J]. 哈尔滨工程大学学报, 2019, 40(1): 1–11., articleTitle=null, refAbstract=null), Reference(id=1263819076242162279, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, 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=SUN Y Y, WU H W, LI Y, et al. Summary of AUV underwater recycle docking technology[J]. Journal of Harbin Engineering University, 2019, 40(1): 1–11 (in Chinese)., articleTitle=null, refAbstract=null), Reference(id=1263819076418323048, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, 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=WANG H Q, ZHONG G Q, SUN J X, et al. Simultaneous restoration and super-resolution GAN for underwater image enhancement[J]. Frontiers in Marine Science, 2023, 10: 1162295., articleTitle=null, refAbstract=null), Reference(id=1263819076560929385, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=WANG J, LI P, DENG J H, et al. CA-GAN: class-condition attention GAN for underwater image enhancement[J]. IEEE Access, 2020, 8: 130719–130728., articleTitle=null, refAbstract=null), Reference(id=1263819076644815466, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=XU S, JIANG Y Q, LI Y, et al. A stereo visual navigation method for docking autonomous underwater vehicles[J]. Journal of Field Robotics, 2024, 41(2): 374–395., articleTitle=null, refAbstract=null), Reference(id=1263819076724507243, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=REN R Z, ZHANG L C, LIU L, et al. Two AUVs guidance method for self-reconfiguration mission based on monocular vision[J]. IEEE Sensors Journal, 2021, 21(8): 10082–10090., articleTitle=null, refAbstract=null), Reference(id=1263819077005525612, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=FIGUEIREDO A B, MATOS A C. MViDO: a high performance monocular vision-based system for docking a hovering AUV[J]. Applied Sciences, 2020, 10(9): 2991., articleTitle=null, refAbstract=null), Reference(id=1263819077110383213, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=安平, 王亭亭, 赵渊, 等. 基于深度学习的AUV水下视觉导引检测方法[J]. 水下无人系统学报, 2023, 31(3): 421–429., articleTitle=null, refAbstract=null), Reference(id=1263819077177492078, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=AN P, WANG T T, ZHAO Y, et al. Underwater visual guidance deep learning detection method for AUV[J]. Journal of Unmanned Undersea Systems, 2023, 31(3): 421–429 (in Chinese)., articleTitle=null, refAbstract=null), Reference(id=1263819077315904111, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=SIM H, JOE H. Voronoi diagram-based USBL outlier rejection for AUV localization[J]. Journal of Ocean Engineering and Technology, 2024, 38(3): 115–123., articleTitle=null, refAbstract=null), Reference(id=1263819079018791536, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Algorithms; New algorithms findings from Southeast University discussed (AUV positioning method based on tightly coupled SINS/LBL for underwater acoustic multipath propagation)[J]. Journal of Technology, 2016, 15(3): 45-50., articleTitle=null, refAbstract=null), Reference(id=1263819079106871921, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=YANG Q S, LIU H T, HONG L, et al. Anti-disturbance control strategy in capture stage for AUV dynamic base docking with optical guided constraints[J]. Ocean Engineering, 2024, 311(Pt 2): 118946., articleTitle=null, refAbstract=null), Reference(id=1263819079190758002, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=燕奎臣, 吴利红. AUV水下对接关键技术研究[J]. 机器人, 2007, 29(3): 267–273., articleTitle=null, refAbstract=null), Reference(id=1263819079283032691, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=YAN K C, WU L H. A survey on the key technologies for underwater AUV docking[J]. Robot, 2007, 29(3): 267–273 (in Chinese)., articleTitle=null, refAbstract=null), Reference(id=1263819079475970676, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=周冰. 面向AUV回收的异色光源阵列视觉导引方法研究[D]. 长春: 吉林大学, 2024., articleTitle=null, refAbstract=null), Reference(id=1263819079568245365, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHOU B. Research on visual guidance method of heterochromatic light source array for AUV recovery[D]. Changchun: Jilin University, 2024 (in Chinese)., articleTitle=null, refAbstract=null), Reference(id=1263819079643742838, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=黄栩. 视觉和电磁组合导引的AUV自主对接技术研究[D]. 杭州: 杭州电子科技大学, 2024., articleTitle=null, refAbstract=null), Reference(id=1263819079769571959, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=HUANG X. Research on autonomous docking technology for AUVs utilizing visual and electromagnetic composite guidance[D]. Hangzhou: Hangzhou Dianzi University, 2024 (in Chinese)., articleTitle=null, refAbstract=null), Reference(id=1263819079849263736, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=孟令帅, 李明烁, 林扬, 等. 自主水下机器人布放回收技术综述[J]. 无人系统技术, 2024, 7(1): 1–19., articleTitle=null, refAbstract=null), Reference(id=1263819079962509945, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=MENG L S, LI M S, LIN Y, et al. Launch and recovery technology of autonomous underwater vehicle[J]. Unmanned Systems Technology, 2024, 7(1): 1–19 (in Chinese)., articleTitle=null, refAbstract=null), Reference(id=1263819080105116282, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=LIU S, XU H L, LIN Y, et al. Visual navigation for recovering an AUV by another AUV in shallow water[J]. Sensors, 2019, 19(8): 1889., articleTitle=null, refAbstract=null), Reference(id=1263819080209973883, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=羊云石, 顾海东. AUV水下对接技术发展现状[J]. 声学与电子工程, 2013(2): 43–46., articleTitle=null, refAbstract=null), Reference(id=1263819080356774524, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=YANG Y S, GU H D. Current development status of AUV underwater docking technology[J]. Acoustics and Electronics Engineering, 2013(2): 43–46 (in Chinese)., articleTitle=null, refAbstract=null), Reference(id=1263819080503575165, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=TRUCCO E, OLMOS-ANTILLON A T. Self-tuning underwater image restoration[J]. IEEE Journal of Oceanic Engineering, 2006, 31(2): 511–519., articleTitle=null, refAbstract=null), Reference(id=1263819080579072638, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=王蕊. 单幅雾天及水下图像的复原方法研究[D]. 青岛: 中国海洋大学, 2014., articleTitle=null, refAbstract=null), Reference(id=1263819080683930239, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=WANG R. The research of single image recovery in fog and underwater[D]. Qingdao: Ocean University of China, 2014 (in Chinese)., articleTitle=null, refAbstract=null), Reference(id=1263819080797176448, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=YAO B W, XIANG J. Underwater image dehazing using modified dark channel prior[C]//Proceedings of 2018 Chinese Control and Decision Conference (CCDC). Shenyang, China: IEEE, 2018: 5792-5797., articleTitle=null, refAbstract=null), Reference(id=1263819080889451137, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=杨爱萍, 郑佳, 王建, 等. 基于颜色失真去除与暗通道先验的水下图像复原[J]. 电子与信息学报, 2015, 37(11): 2541–2547., articleTitle=null, refAbstract=null), Reference(id=1263819081019474562, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=YANG A P, ZHENG J, WANG J, et al. Underwater image restoration based on color cast removal and dark channel prior[J]. Journal of Electronics & Information Technology, 2015, 37(11): 2541–2547 (in Chinese)., articleTitle=null, refAbstract=null), Reference(id=1263819081174663811, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=祝志坤, 卢丙举, 李一辰, 等. 基于单双目融合的AUV坐落式回收光视觉引导算法[J]. 控制与决策, 2025, 40(1): 28–37., articleTitle=null, refAbstract=null), Reference(id=1263819081254355588, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHU Z K, LU B J, LI Y C, et al. Light visual guidance algorithm for AUV situated recovery based on monocular and binocular fusion[J]. Control and Decision, 2025, 40(1): 28–37 (in Chinese)., articleTitle=null, refAbstract=null), Reference(id=1263819081384379013, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=季嘉诚. 基于视觉的水下AUV对接伺服控制系统研究[D]. 大连: 大连海事大学, 2023., articleTitle=null, refAbstract=null), Reference(id=1263819081472459398, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=JI J C. Research on strategy of underwater AUV docking system based on vision[D]. Dalian: Dalian Maritime University, 2023 (in Chinese)., articleTitle=null, refAbstract=null), Reference(id=1263819081594094215, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=刘旖恒. 基于光视觉引导的AUV姿态估计算法研究与实现[D]. 大连: 大连海事大学, 2022., articleTitle=null, refAbstract=null), Reference(id=1263819081686368904, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=LIU Y H. A research and implementation of AUV pose estimation algorithm based on optical vision guidance[D]. Dalian: Dalian Maritime University, 2022 (in Chinese)., articleTitle=null, refAbstract=null), Reference(id=1263819081770254985, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=唐松奇. 基于卷积神经网络的水下图像增强与拼接方法研究[D]. 哈尔滨: 哈尔滨工程大学, 2020., articleTitle=null, refAbstract=null), Reference(id=1263819081862529674, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=TANG S Q. Research on underwater image enhancement and mosaic method based on convolutional neural network[D]. Harbin: Harbin Engineering University, 2020 (in Chinese)., articleTitle=null, refAbstract=null), Reference(id=1263819083523474059, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=尉金强, 杜文正, 孙晓艳, 等. 基于目标HSV(色调−饱和度−亮度)空间图像自适应分割的直线检测算法[J]. 火箭军工程大学学报, 2024, 38(5): 59–68., articleTitle=null, refAbstract=null), Reference(id=1263819083611554444, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=WEI J Q, DU W Z, SUN X Y, et al. Straight line detection algorithm based on adaptive segmentation of target HSV space images[J]. Journal of Rocket Force University of Engineering, 2024, 38(5): 59–68 (in Chinese)., articleTitle=null, refAbstract=null), Reference(id=1263819083758355085, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=丁王杰. 面向水下自主航行器接驳的末端视觉导引关键技术研究[D]. 杭州: 浙江大学, 2023., articleTitle=null, refAbstract=null), Reference(id=1263819083930321550, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=DING W J. Research on key technologies of terminal visual-based guidance for AUV terminal docking[D]. Hangzhou: Zhejiang University, 2023 (in Chinese)., articleTitle=null, refAbstract=null), Reference(id=1263819084106482319, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=石建树. 基于视觉的AUV回收末端定位方法研究[D]. 镇江: 江苏科技大学, 2020., articleTitle=null, refAbstract=null), Reference(id=1263819084425249424, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=SHI J S. Research on vision-based AUV recovery end positioning method[D]. Zhenjiang: Jiangsu University of Science and Technology, 2020 (in Chinese)., articleTitle=null, refAbstract=null), Reference(id=1263819084551078545, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=CHERIAN A K, POOVAMMAL E, PHILIP N S, et al. Deep learning based filtering algorithm for noise removal in underwater images[J]. Water, 2021, 13(19): 2742., articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1263819053169295815, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, xref=null, ext=[AuthorCompanyExt(id=1263819053177684424, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, companyId=1263819053169295815, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=State Key Laboratory of Extreme Environment Optoelectronic Dynamic Measurement Technology and Instrument, North University of China, Taiyuan 030051, China), AuthorCompanyExt(id=1263819053186073034, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, companyId=1263819053169295815, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中北大学 极限环境光电动态测试技术与仪器全国重点实验室,山西 太原 030051)])], figs=[ArticleFig(id=1263819063256596995, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Fig.1, caption=Comparison of dark channels in foggy and fog-free images, figureFileSmall=zc//9Xhzxq2YiwUi9ywdQw==, figureFileBig=V1M4Hyp/uJppjvZRd4ca0g==, tableContent=null), ArticleFig(id=1263819063487283716, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=图1, caption=有雾和无雾图像暗通道对比, figureFileSmall=zc//9Xhzxq2YiwUi9ywdQw==, figureFileBig=V1M4Hyp/uJppjvZRd4ca0g==, tableContent=null), ArticleFig(id=1263819063881548295, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Fig.2, caption=Comparison of underwater images before and after processing, figureFileSmall=Rdd3qnT7VJKpWrFiv2QCfg==, figureFileBig=BnMD2hzRbvL+rogAQ+qPPg==, tableContent=null), ArticleFig(id=1263819065601212938, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=图2, caption=处理前后水下图像对比, figureFileSmall=Rdd3qnT7VJKpWrFiv2QCfg==, figureFileBig=BnMD2hzRbvL+rogAQ+qPPg==, tableContent=null), ArticleFig(id=1263819065697681931, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Fig.3, caption=Flowchart of adaptive threshold adjustment, figureFileSmall=4RDzA0SlQp30RzdWqWGQyA==, figureFileBig=56wTXd7+ys3OzQOGFyAJIQ==, tableContent=null), ArticleFig(id=1263819065781568012, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=图3, caption=自适应阈值调节流程图, figureFileSmall=4RDzA0SlQp30RzdWqWGQyA==, figureFileBig=56wTXd7+ys3OzQOGFyAJIQ==, tableContent=null), ArticleFig(id=1263819065886425614, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Fig.4, caption=Comparison of edge detection results, figureFileSmall=dTBPEJ+BDR14/mxNFISGIA==, figureFileBig=1Lv8vP20yh7Trb2JeoXQhA==, tableContent=null), ArticleFig(id=1263819066154861072, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=图4, caption=边缘检测效果对比图, figureFileSmall=dTBPEJ+BDR14/mxNFISGIA==, figureFileBig=1Lv8vP20yh7Trb2JeoXQhA==, tableContent=null), ArticleFig(id=1263819066289078803, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Fig.5, caption=Hue histogram of the blue-labeled light source, figureFileSmall=gABkUrOWe2RB6A2c2yU51g==, figureFileBig=fexFCYGJ+YlepVByuU3+NA==, tableContent=null), ArticleFig(id=1263819066414907925, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=图5, caption=蓝色标识光源的色调直方图, figureFileSmall=gABkUrOWe2RB6A2c2yU51g==, figureFileBig=fexFCYGJ+YlepVByuU3+NA==, tableContent=null), ArticleFig(id=1263819066528154136, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Fig.6, caption=Comparison of algorithm-processed images for underwater (3 m) docking guidance marker light sources, figureFileSmall=v9jMspI3/8XuSe4dwpScIw==, figureFileBig=FHGP4Z85B7Qi06nLvumxBg==, tableContent=null), ArticleFig(id=1263819066662371866, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=图6, caption=水下3 m对接导引标识光源经不同算法处理的图像对比结果, figureFileSmall=v9jMspI3/8XuSe4dwpScIw==, figureFileBig=FHGP4Z85B7Qi06nLvumxBg==, tableContent=null), ArticleFig(id=1263819066771423772, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Fig.7, caption=Image processing and recognition results under adequate illumination, figureFileSmall=hvYtupEsMWckMZwvg+XLDQ==, figureFileBig=hk4QaY+ZkOYf3+tCaVA++w==, tableContent=null), ArticleFig(id=1263819066914030110, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=图7, caption=光照充足时图像处理及识别效果图, figureFileSmall=hvYtupEsMWckMZwvg+XLDQ==, figureFileBig=hk4QaY+ZkOYf3+tCaVA++w==, tableContent=null), ArticleFig(id=1263819067006304800, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Fig.8, caption=Image processing and recognition results under insufficient illumination, figureFileSmall=6C0psCpMeafeuVUEMk9lXA==, figureFileBig=1sUa7EUYFHbBwjGnpIEH/Q==, tableContent=null), ArticleFig(id=1263819067123745314, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=图8, caption=光照不足时图像处理及识别效果图, figureFileSmall=6C0psCpMeafeuVUEMk9lXA==, figureFileBig=1sUa7EUYFHbBwjGnpIEH/Q==, tableContent=null), ArticleFig(id=1263819067329266212, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Fig.9, caption=Checkerboard images at different angles, figureFileSmall=62nI1iKsBdUE/rD4HMgFVQ==, figureFileBig=KBWbccCkKKX/jxYSsQjx/A==, tableContent=null), ArticleFig(id=1263819067438318118, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=图9, caption=不同角度的棋盘格图像, figureFileSmall=62nI1iKsBdUE/rD4HMgFVQ==, figureFileBig=KBWbccCkKKX/jxYSsQjx/A==, tableContent=null), ArticleFig(id=1263819067543175720, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Fig.10, caption=Simulation environment, figureFileSmall=Y9FcMaEBygh0jW0eXL/SMQ==, figureFileBig=fXlglrd+bq74soD3bfy14Q==, tableContent=null), ArticleFig(id=1263819067643839017, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=图10, caption=仿真环境, figureFileSmall=Y9FcMaEBygh0jW0eXL/SMQ==, figureFileBig=fXlglrd+bq74soD3bfy14Q==, tableContent=null), ArticleFig(id=1263819067882914349, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Fig.11, caption=First-person view of the AUV successfully entering the docking device, figureFileSmall=sZ8F4LU22H/IHaRE34L3WA==, figureFileBig=Lss7o7570q25tF/FjyRjpA==, tableContent=null), ArticleFig(id=1263819068117795375, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=图11, caption=AUV成功进入对接装置第一人称视角, figureFileSmall=sZ8F4LU22H/IHaRE34L3WA==, figureFileBig=Lss7o7570q25tF/FjyRjpA==, tableContent=null), ArticleFig(id=1263819068247818800, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Fig.12, caption=Experimental AUV platform, figureFileSmall=IjAK+MTNvCgX6WqmnVyhuQ==, figureFileBig=bXQnQ6OEcu5IcX67qkWCTQ==, tableContent=null), ArticleFig(id=1263819068331704883, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=图12, caption=实验AUV平台, figureFileSmall=IjAK+MTNvCgX6WqmnVyhuQ==, figureFileBig=bXQnQ6OEcu5IcX67qkWCTQ==, tableContent=null), ArticleFig(id=1263819070185587254, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Fig.13, caption=Docking device, figureFileSmall=ZKCMMNxALVMDolCjSxzJ9w==, figureFileBig=oKvKTkv6jE+wK1jExS99qA==, tableContent=null), ArticleFig(id=1263819070311416376, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=图13, caption=对接装置, figureFileSmall=ZKCMMNxALVMDolCjSxzJ9w==, figureFileBig=oKvKTkv6jE+wK1jExS99qA==, tableContent=null), ArticleFig(id=1263819070458217018, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Fig.14, caption=Experimental water tank, figureFileSmall=hY6gNdyBua4ZWOI44Imyaw==, figureFileBig=PADvE0Qjlq7/yYuC5DbQbg==, tableContent=null), ArticleFig(id=1263819070646960701, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=图14, caption=实验水池, figureFileSmall=hY6gNdyBua4ZWOI44Imyaw==, figureFileBig=PADvE0Qjlq7/yYuC5DbQbg==, tableContent=null), ArticleFig(id=1263819070781178431, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Fig.15, caption=Docking attitude variation and tracking process, figureFileSmall=w4E/KGTXlNXlQvLekLZ0xA==, figureFileBig=ONXzgtYndbVUOUzCPySoWg==, tableContent=null), ArticleFig(id=1263819071087362625, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=图15, caption=对接姿态变化及追踪过程图, figureFileSmall=w4E/KGTXlNXlQvLekLZ0xA==, figureFileBig=ONXzgtYndbVUOUzCPySoWg==, tableContent=null), ArticleFig(id=1263819071242551875, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Fig.16, caption=Process of AUV successfully entering the docking device in pool experiment, figureFileSmall=LVgv47urCOHLX6NRHqajow==, figureFileBig=ZeqRzS8lgZZM/3bSvRNuLg==, tableContent=null), ArticleFig(id=1263819071330632261, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=图16, caption=AUV水池实验进入对接装置过程图, figureFileSmall=LVgv47urCOHLX6NRHqajow==, figureFileBig=ZeqRzS8lgZZM/3bSvRNuLg==, tableContent=null), ArticleFig(id=1263819071448072775, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Fig.17, caption=Comparison of laser ranging and visual ranging at various distances, figureFileSmall=MPT6j8MVmhPA8vm2AQQ6Vw==, figureFileBig=qlX37Tb4WPKYSZxnb/ALXg==, tableContent=null), ArticleFig(id=1263819071657787977, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=图17, caption=各距离激光测距与视觉测距对比图, figureFileSmall=MPT6j8MVmhPA8vm2AQQ6Vw==, figureFileBig=qlX37Tb4WPKYSZxnb/ALXg==, tableContent=null), ArticleFig(id=1263819071800394314, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Fig.18, caption=Comparison of laser ranging and visual ranging during single docking process, figureFileSmall=s5pFUl6NxUimTXIWhQSj8w==, figureFileBig=kNvveZgl43O0dzUb26PdzA==, tableContent=null), ArticleFig(id=1263819072114967116, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=图18, caption=单次对接过程激光测距与视觉测距对比图, figureFileSmall=s5pFUl6NxUimTXIWhQSj8w==, figureFileBig=kNvveZgl43O0dzUb26PdzA==, tableContent=null), ArticleFig(id=1263819072253379150, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Tab.1, caption=

Performance specifications of navigation sensors

, figureFileSmall=null, figureFileBig=null, tableContent=
传感器作用距离/m导航精度精度影响因素
声学2000信号延迟,噪声干扰
电磁<20~30较高设备本身的电磁噪声,外磁场干扰
光学<10~28较高背景光变化,海水浑浊程度,光源强弱
视觉<10~28较高分辨率,镜头畸变
), ArticleFig(id=1263819072454705744, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=表1, caption=

导航传感器性能列表

, figureFileSmall=null, figureFileBig=null, tableContent=
传感器作用距离/m导航精度精度影响因素
声学2000信号延迟,噪声干扰
电磁<20~30较高设备本身的电磁噪声,外磁场干扰
光学<10~28较高背景光变化,海水浑浊程度,光源强弱
视觉<10~28较高分辨率,镜头畸变
), ArticleFig(id=1263819072651838033, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Tab.2, caption=

Calculation results of evaluation metrics

, figureFileSmall=null, figureFileBig=null, tableContent=
算法QUIQMQUCIQE
暗通道先验去雾算法0.45400114.665210
HE算法0.62315219.151030
MSRCR算法0.4187827.980382
), ArticleFig(id=1263819072773472851, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=表2, caption=

评估指标计算结果

, figureFileSmall=null, figureFileBig=null, tableContent=
算法QUIQMQUCIQE
暗通道先验去雾算法0.45400114.665210
HE算法0.62315219.151030
MSRCR算法0.4187827.980382
), ArticleFig(id=1263819074463777365, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Tab.3, caption=

Calculation results of evaluation metrics

, figureFileSmall=null, figureFileBig=null, tableContent=
算法QPSNRQSSIMQLPIPS
传统Canny检测18.217 3150.894 8420.751 748
改进的Canny检测>21.751 180>0.938 2210.497 714
), ArticleFig(id=1263819074585412184, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=表3, caption=

评估指标计算结果

, figureFileSmall=null, figureFileBig=null, tableContent=
算法QPSNRQSSIMQLPIPS
传统Canny检测18.217 3150.894 8420.751 748
改进的Canny检测>21.751 180>0.938 2210.497 714
), ArticleFig(id=1263819074690269785, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Tab.4, caption=

Absorption and scattering coefficients in different water bodies

, figureFileSmall=null, figureFileBig=null, tableContent=
水域类型吸收系数散射系数
纯净海水0.1140.037
海岸海水0.1790.220
码头海水0.3661.829
), ArticleFig(id=1263819074811904603, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=表4, caption=

不同水域吸收和散射系数

, figureFileSmall=null, figureFileBig=null, tableContent=
水域类型吸收系数散射系数
纯净海水0.1140.037
海岸海水0.1790.220
码头海水0.3661.829
), ArticleFig(id=1263819074958705244, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Tab.5, caption=

Parameters of underwater camera

, figureFileSmall=null, figureFileBig=null, tableContent=
参数数值
焦距/mm3.6
分辨率/px1 920×1 080
水平视野角/(°)142
垂直视野角/(°)102
防水等级IP68
工作温度/(°C)−20~55
), ArticleFig(id=1263819075059368541, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=表5, caption=

水下相机参数

, figureFileSmall=null, figureFileBig=null, tableContent=
参数数值
焦距/mm3.6
分辨率/px1 920×1 080
水平视野角/(°)142
垂直视野角/(°)102
防水等级IP68
工作温度/(°C)−20~55
), ArticleFig(id=1263819075130671710, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Tab.6, caption=

Intrinsic parameters and geometric distortion coefficients of the camera

, figureFileSmall=null, figureFileBig=null, tableContent=
相机内参和几何畸变系数数值(水下)
焦距${f_x}$/px1 696.8
焦距${f_y}$/px1 686.7
主点${u_0}$/px1 156.5
主点${v_0}$/px1 115.1
径向畸变$ {k_v}_1 $−0.062 8
径向畸变$ {k_v}_2 $−0.087 8
切向畸变${k_u}_1$0
切向畸变${k_u}_2$0
), ArticleFig(id=1263819075260695135, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=表6, caption=

相机内参和几何畸变系数

, figureFileSmall=null, figureFileBig=null, tableContent=
相机内参和几何畸变系数数值(水下)
焦距${f_x}$/px1 696.8
焦距${f_y}$/px1 686.7
主点${u_0}$/px1 156.5
主点${v_0}$/px1 115.1
径向畸变$ {k_v}_1 $−0.062 8
径向畸变$ {k_v}_2 $−0.087 8
切向畸变${k_u}_1$0
切向畸变${k_u}_2$0
), ArticleFig(id=1263819075352969824, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=EN, label=Tab.7, caption=

Data analysis of laser ranging and visual ranging at various distances

, figureFileSmall=null, figureFileBig=null, tableContent=
测距条件均值/mm均方根误差/mm
10 m视觉测距9 923.21277.43
10 m激光测距10 103.46
6 m视觉测距5 914.39163.83
6 m激光测距6 034.75
2 m视觉测距1 963.4776.44
2 m激光测距2 014.68
), ArticleFig(id=1263819075466216033, tenantId=1146029695717560320, journalId=1263530845441638439, articleId=1263818968280777311, language=CN, label=表7, caption=

各距离激光测距与视觉测距数据分析

, figureFileSmall=null, figureFileBig=null, tableContent=
测距条件均值/mm均方根误差/mm
10 m视觉测距9 923.21277.43
10 m激光测距10 103.46
6 m视觉测距5 914.39163.83
6 m激光测距6 034.75
2 m视觉测距1 963.4776.44
2 m激光测距2 014.68
)], attaches=null, journal=Journal(id=1263530641632018469, delFlag=0, nameCn=中国舰船研究, nameEn=Chinese Journal of Ship Research, nameHistory1=null, nameHistory2=null, issn=1673-3185, eissn=null, cn=42-1755/TJ, coden=null, periodic=1, 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=uuiC2KHI0RbgmeHEYieSVQ==, journalPrice=null, startedYear=null, abbrevIsoEn=Chinese Journal of Ship Research, journalRemark=null, publicationField=null, createdTime=1779178780231, updatedTime=1779179141739, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=C, firstLetterEn=C, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=uuiC2KHI0RbgmeHEYieSVQ==, picEn=742/gRTuoSZweF2ujSJArQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1263532158132564178, language=CN, name=中国舰船研究, 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=1779179141791, updatedTime=1779179141791, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://zgjcyjauthor.manuscriptcloud.com/, submissionEditorUrl=https://zgjcyjeditor.manuscriptcloud.com/, submissionReviewUrl=https://zgjcyjauthor.manuscriptcloud.com/, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1263532158254198995, language=EN, name=Chinese Journal of Ship Research, 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=1779179141820, updatedTime=1779179141820, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://zgjcyjauthor.manuscriptcloud.com/, submissionEditorUrl=https://zgjcyjeditor.manuscriptcloud.com/, submissionReviewUrl=https://zgjcyjauthor.manuscriptcloud.com/, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1263530845441638439, websiteList=[Website(id=1263532309169451247, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1263530845441638439, 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/zgjcyj/CN, language=CN, createTime=1779179177801, createBy=18614031015, updateTime=1779180752761, updateBy=18614031015, name=中国舰船研究-中文, tplId=1146099689490845704, title=中国舰船研究, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1263552162215375681, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263532309169451247, code=articleTextType, value=kx, createTime=1779183911136, updateTime=1779183911136, creator=18614031015, updator=18614031015), WebsiteProps(id=1263552162181821246, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263532309169451247, code=banner, value=null, createTime=1779183911128, updateTime=1779183911128, creator=18614031015, updator=18614031015), WebsiteProps(id=1263552162253124420, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263532309169451247, code=grayFlag, value=0, createTime=1779183911145, updateTime=1779183911145, creator=18614031015, updator=18614031015), WebsiteProps(id=1263552162173432637, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263532309169451247, code=logo, value=https://castjournals.cast.org.cn/joweb/zgjcyj/CN/file/pic?fileId=nJodoAVDNU0dVNGTgYrzsA==, createTime=1779183911126, updateTime=1779183911126, creator=18614031015, updator=18614031015), WebsiteProps(id=1263552162299261766, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263532309169451247, code=minRunFlag, value=0, createTime=1779183911156, updateTime=1779183911156, creator=18614031015, updator=18614031015), WebsiteProps(id=1263552162198598464, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263532309169451247, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zgjcyj/CN/file/pic, createTime=1779183911132, updateTime=1779183911132, creator=18614031015, updator=18614031015), WebsiteProps(id=1263552162286678853, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263532309169451247, code=silenceFlag, value=0, createTime=1779183911153, updateTime=1779183911153, creator=18614031015, updator=18614031015), WebsiteProps(id=1263552162190209855, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263532309169451247, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1779183911130, updateTime=1779183911130, creator=18614031015, updator=18614031015), WebsiteProps(id=1263552162232152898, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263532309169451247, code=themeColor, value=null, createTime=1779183911140, updateTime=1779183911140, creator=18614031015, updator=18614031015), WebsiteProps(id=1263552162240541507, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263532309169451247, code=themeStyle, value=null, createTime=1779183911142, updateTime=1779183911142, creator=18614031015, updator=18614031015)]), Website(id=1263532309249143025, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1263530845441638439, 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/zgjcyj/EN, language=EN, createTime=1779179177820, createBy=18614031015, updateTime=1779180748021, updateBy=18614031015, name=中国舰船研究-英文, tplId=1146101810881728533, title=Chinese Journal of Ship Research, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1263552187725132620, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263532309249143025, code=articleTextType, value=kx, createTime=1779183917218, updateTime=1779183917218, creator=18614031015, updator=18614031015), WebsiteProps(id=1263552187704161097, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263532309249143025, code=banner, value=null, createTime=1779183917213, updateTime=1779183917213, creator=18614031015, updator=18614031015), WebsiteProps(id=1263552187754492751, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263532309249143025, code=grayFlag, value=0, createTime=1779183917225, updateTime=1779183917225, creator=18614031015, updator=18614031015), WebsiteProps(id=1263552187695772488, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263532309249143025, code=logo, value=https://castjournals.cast.org.cn/joweb/zgjcyj/EN/file/pic?fileId=nJodoAVDNU0dVNGTgYrzsA==, createTime=1779183917211, updateTime=1779183917211, creator=18614031015, updator=18614031015), WebsiteProps(id=1263552187779658577, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263532309249143025, code=minRunFlag, value=0, createTime=1779183917231, updateTime=1779183917231, creator=18614031015, updator=18614031015), WebsiteProps(id=1263552187720938315, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263532309249143025, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zgjcyj/EN/file/pic, createTime=1779183917217, updateTime=1779183917217, creator=18614031015, updator=18614031015), WebsiteProps(id=1263552187762881360, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263532309249143025, code=silenceFlag, value=0, createTime=1779183917228, updateTime=1779183917228, creator=18614031015, updator=18614031015), WebsiteProps(id=1263552187712549706, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263532309249143025, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1779183917215, updateTime=1779183917215, creator=18614031015, updator=18614031015), WebsiteProps(id=1263552187733521229, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263532309249143025, code=themeColor, value=null, createTime=1779183917220, updateTime=1779183917220, creator=18614031015, updator=18614031015), WebsiteProps(id=1263552187737715534, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263532309249143025, code=themeStyle, value=null, createTime=1779183917222, updateTime=1779183917222, creator=18614031015, updator=18614031015)])], journalTitle=中国舰船研究, weixinUrl=null, journalUrl=https://www.ship-research.com/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Chinese Journal of Ship Research, journalPhotoCn=uuiC2KHI0RbgmeHEYieSVQ==, journalPhotoEn=742/gRTuoSZweF2ujSJArQ==, journalFirstLetter=C, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/zgjcyj/CN/10.19693/j.issn.1673-3185.04381, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgjcyj/EN/10.19693/j.issn.1673-3185.04381, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgjcyj/CN/PDF/10.19693/j.issn.1673-3185.04381, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgjcyj/EN/PDF/10.19693/j.issn.1673-3185.04381, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
多特征融合的AUV末端视觉自主对接技术研究
收藏切换
PDF下载
熊攀 , 齐向东 * , 孙岩林 , 赵正阳 , 秦钜灏
中国舰船研究 | 水下无人系统总体设计技术 2026,21(2): 112-124
收起
收藏切换
中国舰船研究 | 水下无人系统总体设计技术 2026, 21(2): 112-124
多特征融合的AUV末端视觉自主对接技术研究
全屏
熊攀 , 齐向东* , 孙岩林, 赵正阳, 秦钜灏
作者信息
  • 中北大学 极限环境光电动态测试技术与仪器全国重点实验室,山西 太原 030051
  • 熊攀,男,2000年生,硕士生。研究方向:水下无人潜航器自主对接技术。E-mail:

    齐向东,男,1967年生,教授。研究方向:水下无人潜航器系统技术。E-mail:

通讯作者:

* 齐向东
Multi-feature fusion-based terminal visual autonomous docking technology for AUV
Pan XIONG , Xiangdong QI* , Yanlin SUN, Zhengyang ZHAO, Juhao QIN
Affiliations
  • State Key Laboratory of Extreme Environment Optoelectronic Dynamic Measurement Technology and Instrument, North University of China, Taiyuan 030051, China
出版时间: 2026-04-30 doi: 10.19693/j.issn.1673-3185.04381
文章导航
收藏切换
目的

为解决自主水下航行器(AUV)在复杂水下环境中自主对接精度不足的问题,提出一种基于多特征融合的视觉导引方法。

方法

依托实验室自主研发的四桨无舵矢量推进型AUV,使用暗通道先验去雾算法进行图像增强,结合改进的Canny边缘检测与颜色阈值分割实现多特征融合,利用最小包围圆法进行圆心定位,通过坐标系转换解算相对位姿完成对接。

结果

Unity 3D仿真和水池实验结果表明,均值差和均方根误差均呈现随对接距离接近而减小的距离相关性,距离越近,视觉测距越准确,对接精度越高,对接距离小于2 m时位姿精度误差小于5 cm,总体对接成功率为88%。

结论

所提方法满足AUV自主对接任务中对接精度要求,为水下装备自主回收提供了高鲁棒性的解决方案。

自主水下航行器  /  自主对接  /  Canny边缘检测  /  颜色阈值分割  /  多特征融合
Objective

To address the low docking accuracy of autonomous underwater vehicles (AUVs) in complex underwater environments, a multi-feature fusion vision-based method is proposed.

Method

A self-developed rudderless vector propulsion AUV with four thrusters was used, and the dark channel prior (DCP) dehazing algorithm was adopted for image enhancement. An improved Canny edge detection algorithm was combined with color threshold segmentation to achieve multi-feature fusion. The minimum enclosing circle method was utilized for circle center positioning, and coordinate transformation was performed to calculate the relative position and orientation for docking.

Results

Unity 3D simulations and pool experiments revealed a distance-dependent trend: both mean difference and root mean square error decreased as docking distance decreased. Closer distances yielded higher visual ranging accuracy and docking precision. When the docking distance was less than 2 m, the positioning error was maintained below 5 cm, with an overall success rate of 88%.

Conclusion

The proposed method fulfills the accuracy requirements for AUV autonomous docking and provides a highly robust solution for underwater equipment recovery.

autonomous underwater vehicles (AUVs)  /  autonomous docking  /  Canny edge detection  /  color threshold segmentation  /  multi-feature fusion
熊攀, 齐向东, 孙岩林, 赵正阳, 秦钜灏. 多特征融合的AUV末端视觉自主对接技术研究. 中国舰船研究, 2026 , 21 (2) : 112 -124 . DOI: 10.19693/j.issn.1673-3185.04381
Pan XIONG, Xiangdong QI, Yanlin SUN, Zhengyang ZHAO, Juhao QIN. Multi-feature fusion-based terminal visual autonomous docking technology for AUV[J]. Chinese Journal of Ship Research, 2026 , 21 (2) : 112 -124 . DOI: 10.19693/j.issn.1673-3185.04381
自主水下航行器(AUV)凭借低成本、高机动性与强可操作性,在海底测绘、海洋环境监测、海洋资源勘查、打捞救助及定位跟踪等方面发挥着关键作用,已成为海洋探索的重要装备[1]
尽管AUV技术在不断发展完善,实际应用仍面临多项挑战:1)AUV作为一个嵌入式系统,在复杂水下环境中执行精确检测任务时,其传感器等设备需要定期维护和校准;2)AUV运行能耗较高,自身携带的电源容量有限,导致续航能力差,水下常驻作业难以实现持续能源补充[2];3)水下环境中强噪声干扰及传输媒介限制导致水下数据传输速率慢,在任务指令更新和数据下载时需要上浮母船进行操作,易受风浪影响,隐蔽性差,难以满足AUV大规模部署和执行隐蔽任务的需求[3]。为了提升AUV运维效率,确保能源补给并减少对水面母船的依赖,需开展AUV水下自主对接技术研究。
随着光学传感器技术的不断发展和图像处理技术、计算性能的持续提升,水下视觉图像质量得到显著提高,畸变和噪声问题得到有效控制,为AUV高精度对接奠定了技术基础。
学者在利用视觉进行水下对接方面开展了一些研究。Wang等[4]提出一种基于生成对抗网络的水下图像复原模型,通过训练实现了较好的去噪和色彩校正,但在实时性方面难以满足AUV动态对接需求。Wang等[5]提出了类条件注意力生成对抗网络,该网络通过构建包含不同水域条件的数据集,利用类条件标签引导生成器学习多对一的映射关系,通过通道和空间注意力模块融合特征增强水下图像的颜色和细节。但该系统在复杂水域中仍存在颜色校正不足问题。Xu等[6]提出了基于立体视觉的AUV对接导航方法,通过融合自适应选择算法、几何串行算法和滤波器算法,实现对光信标的精确检测与识别。但其计算复杂度较高,仅适用于高算力场景。Ren等[7]提出基于单目视觉的水下自重构AUV自主对接方法,结合蓝绿光信标引导和Aruco标记,实现从长距离到近距离的精确引导,但其深度估计精度有限,在低光照环境中的鲁棒性不足。Figueiredo 等[8]提出基于单目视觉的悬停AUV自主对接系统MViDO,集成姿态估计、跟踪和引导模块,利用单个摄像头和3个球形彩色标记目标实现对接站的定位和跟踪,在部分遮挡和异常值情况下仍保持较高精度,但该系统依赖特定标记,仅适用于悬停AUV,应用范围受限。
基于上述背景,本文拟对多特征融合的AUV末端视觉自主对接技术进行研究。以实验室自主研发的四桨无舵矢量推进型AUV为研究对象,采用蓝色环形灯带为水下对接导引标识光源,通过暗通道先验去雾算法提高图像细节和质量,采用权重合并阈值自整定Canny边缘检测算法和颜色阈值分割算法提取水下光源特征,提高不同情况下目标轮廓识别精度。随后通过最小包围圆法确定对接装置中心坐标,并进行坐标转换,解算出对接装置与AUV的相对位置。最后开展Unity 3D仿真和多次水池实验,验证该方案提高AUV水下自主对接成功率的有效性。
AUV与水下对接装置的对接过程通常依据两者间距划分为3个阶段:远程导航阶段、中程导航阶段、近程导引阶段[9]。在远程导航阶段,使用水声定位方法或多源信息融合导航策略,实现对对接装置的大范围搜索和接近。在中程导航阶段,采用超短基线定位系统(USBL)或长基线定位系统(LBL)进行声学定位导航[10-11]。远、中程阶段对导航精度要求较低,近程导引阶段应采用更高导航精度的传感器,精确测定AUV与对接装置之间的相对位置和姿态关系,确保成功对接。表1列出主要水下对接导航传感器,包括声学传感器、电磁传感器、光学传感器以及视觉传感器[12-15]
表1可知,使用声学传感器进行声学导引会存在信号延迟、噪声干扰、近距离精度较差的问题,仅适用于中远距离对精度要求不高的阶段;电磁传感器易受到内外磁场干扰,且该传感器尺寸较大、技术复杂,在目前各类对接场景中基本不用该类传感器[16];光学传感器依赖单一光信号的强度或飞行时间检测,其功能局限于测距或光斑定位,难以克服海水浑浊程度以及背景光和海水散射的影响,探测距离十分有限;视觉传感器本质上属于光学传感器的子集,但其功能已从单纯的光信号测量拓展至图像采集与解析,通过算法处理不仅能提取几何特征,还可解析颜色、纹理等多模态数据,具备更强的环境感知与自适应能力[17-18]。所以,视觉传感器成为较优选择。
根据Jaffe-McGlamery水下光学成像模型可知,水下图像可以由直接衰减、前向衰减和后向衰减3个分量线性叠加得到。直接衰减分量表示由物体反射且未经水中悬浮粒子散射进入相机的光线,前向衰减分量表示由物体反射但经水中悬浮粒子散射进入相机的光线,后向衰减分量表示自然光经水中悬浮粒子散射进入相机的光线[19]。受水深与水质影响,这些分量在进入相机之前产生强烈衰减,导致相机拍摄的水下图像出现颜色偏差、对比度损失、细节模糊、亮度不均匀、杂光和眩光等问题,严重影响图像的特征提取成功率。所以为了增强图像质量和还原图像细节,需要对图像进行预处理。
大气雾天成像模型和Jaffe-McGlamery水下光学成像模型在物理机制上具有相似性。大气中的雾霭与水体均属于散射介质,当光线穿透这些介质时,部分光源的白光成分在抵达目标前便发生后向散射,直接进入成像传感器。这种光学现象导致两类图像均会因介质散射作用导致图像对比度和可见度显著下降。事实上,雾气由空气中凝结的小水滴构成,与纯净水体类似,两种介质本身均呈现近似无色透明特性,其对各种颜色光的散射作用一致,这使得后向散射光完整保留了自然光的全光谱特征,造成成像画面整体呈现色彩饱和度降低、白色光晕增强的视觉效果[20]
暗通道先验去雾算法可以有效去除图像中的雾气,恢复图像的原始色彩和细节,且水下场景普遍存在的暗色物体、彩色表面以及自然阴影等视觉元素,能够满足暗通道先验的成立条件。因此可以采用图像去雾方法去除水下图像的背景散射[21-22]
暗通道是指在自然图像中,由各像素局部区域内 RGB 三通道的最小像素值所构成的灰度图像。暗通道的数学定义为
$ {I}_{\text{dark}}(x)=\underset{y\in \varOmega (x)}{\mathrm{min}}(\underset{c\in \{r,g,b\}}{\mathrm{min}}{I}^{c}(y)) $
式中:$ {I_{{\text{dark}}}}(x) $为在像素点x处的暗通道值;$ \varOmega (x) $为以x为中心的局部区域;$ {I^c}(y) $为在像素点y处的颜色通道c的亮度值,其中c表示RGB三通道中的某一个通道。
暗通道先验理论指出,有雾图像暗通道会呈现灰色,而无雾图像暗通道会呈现黑色,即无雾图像暗通道趋近于0,如图1所示。
基于此现象,利用暗通道估计全球大气光成分和透射率[23],推断图像中的雾气信息,消除雾气,得到增强图像。构建雾天成像模型为
$ I{(}x{) = }J{(}x{)}t{(}x{) + }A{(1} - t{(}x{))} $
式中:$ I{(}x{)} $为待去雾的原始图像在像素点x处的像素值;$ J{(}x{)} $为去雾算法恢复的无雾图像在像素点x处的像素值;A为全球大气光成分,表示在没有物体遮挡情况下,从场景中直接进入摄像机的环境光;$ t{(}x{)} $为透射率,表示光线穿过雾到达摄像机的比例。
在暗通道中提取亮度前0.1% 的像素点,在原始雾图$ I{(}x{)} $中找到对应像素点,获取这些像素点的最大亮度值,作为全球大气光成分A
对于图像上的点x及以x为中心的局部区域$ \varOmega (x) $,其透射率$ t{(}x{)} $
$ t(x)=1-\omega \times \underset{y\in \varOmega (x)}{\mathrm{min}}\left(\underset{c\in \{r,g,b\}}{\mathrm{min}}\frac{{I}^{c}(y)}{{A}^{c}}\right) $
式中:$ \omega $为去雾程度,$ \omega $ = 0表示不去雾,$ \omega $ = 1表示全部去雾,通常$ \omega $ = 0.95。
将全球大气光成分A和透射率$ t{(}x{)} $代入式(2),得到恢复的无雾图像:
$ {J^c}(x) = \frac{{{I^c}(x) - {A^c}}}{{t(x)}} + {A^c} $
为直观评估暗通道先验去雾算法的图像增强效果,选取直方图均衡化算法(HE)和多尺度反射消除算法(MSRCR)进行对比。HE算法通过重新分配图像像素的灰度级别,使图像中的灰度值分布更均匀,增强图像的整体对比度。MSRCR算法基于多尺度Retinex理论,通过估计图像的光照分量和反射分量减少图像的光照不均匀性,改善图像的质量和视觉效果。
图2所示为水下3 m对接导引光源的原始图像及分别经暗通道先验去雾算法、HE算法和MSRCR算法处理的图像。由图可见,HE算法处理的图像对比度增强不均匀,图像上部出现了明显的伪影问题,增加了噪声和虚假边缘,会干扰边缘检测;MSRCR算法处理的图像中导引光源和背景对比度不足,目标难以区分,图像特征提取的准确性会降低;相比之下,暗通道先验去雾算法处理的图像虽然整体色调偏暗,但有效减少了悬浮颗粒和光散射的影响,导引光源和背景对比度明显,有利于后续图像特征提取。
引用水下图像质量评估(UIQM)和水下彩色图像质量评估(UCIQE)作为指标对水下图像进行性能比较。UIQM和UCIQE都是专门为水下图像设计的无参考图像质量评价指标。其中,UIQM综合考虑了图像的色彩、清晰度和对比度三个维度,并通过加权平均的方式计算整体质量。值越大,图像质量越好,其计算公式如下:
$ Q_{\text{UIQM}} = {c_1} \times Q_{\text{UICM}} + {c_2} \times Q_{\text{UISM}} + {c_3} \times Q_{\text{UIConM}} $
式中:${c_1}$${c_2}$${c_3}$为加权系数;$Q_{\text{UIQM}}$为色彩测量指标;$Q_{\text{UISM}}$为清晰度测量指标;${Q_{{\mathrm{UIConM}}}}$为对比度测量指标。
UCIQE通过色度、饱和度和对比度的线性组合来量化水下图像的非均匀色偏、模糊和低对比度问题。值越高代表图像质量越好。其公式为
$ Q_{\text{UCIQE}} = {c_1} \times {\sigma _{\text{c}}} + {c_2} \times {b_{\text{l}}} + {c_3} \times {\mu _{\text{s}}} $
式中: ${\sigma _{\text{c}}}$为色度标准差,反映色度噪声,下标${{\text{c}}_{}}$为色度;${b_{\text{l}}}$为亮度对比,反映图像清晰度,${\text{l}}$表示亮度;${\mu _{\text{s}}}$为饱和度平均值,${{\text{s}}_{}}$为饱和度。
3种算法计算得到的UIQM和UCIQE指标结果如表2所示。可以看出,MSRCR算法的得分最低,目标区分度不足;HE算法的得分最高,显示其在颜色保真度和清晰度方面具有优势。但HE算法的高评分主要源于对整体对比度的线性增强,其引入的伪影会严重干扰导引光源的边缘检测效果。暗通道先验去雾算法得分处于中等水平,是由于其对比度增强方式通过减少散射光干扰来恢复图像对比度,更具有针对性且更加温和,避免了对比度过度增强导致的伪影问题,其图像效果在实际应用中表现出色,更适合动态水下环境的鲁棒性需求。
在AUV执行水下对接任务过程中,通过水下图像特征提取确定对接装置位置,为导航系统提供关键数据支持。本文通过改进Canny边缘检测,采用自适应阈值优化轮廓提取,并融合颜色阈值分割进行权重分配,提高不同场景下目标轮廓识别精度。
Canny边缘检测存在一些局限:高斯滤波器参数需人工设定,主观性较强,难以平衡噪声抑制与边缘保持;算法对图像噪声较敏感,易产生伪边缘并丢失部分真实边缘细节;处理动态变化图像时,固定阈值无法适应图像亮度和对比度变化,边缘检测不稳定。本文采用小波去噪滤除噪声,Scharr算子获取梯度,自适应阈值处理动态变化图像。
小波去噪是对高斯滤波的改进,通过多尺度分析可多尺度处理噪声,以适应不同频率的噪声特性。小波变换将图像分解为一系列小波基函数,表达式为
$ W(a,b) = \int_{ - \infty }^\infty f (x){\psi _{a,b}}(x){\mkern 1mu} {\text{d}}x $
式中:$ W(a,b) $为函数$f(x)$的卷积型小波变换;a为尺度特征,表示小波变换的分解层级;b为平移参数;$ {\psi _{a,b}}(x) $为小波基函数。在小波域中,边缘和噪声表现为小波系数的局部极大值,边缘通常在大尺度上具有显著响应,而噪声在小尺度上更明显。假设函数$f(x)$在某点处的奇异性指数为k,则小波变换的模极大值满足
$ \left| {W(a,b)} \right| \leqslant K{a^k} $
式中:K为常数;k为奇异性指数,描述函数的局部光滑性。
式(8)描述了奇异性指数与小波变换尺度特征之间的关系:当$k \lt 0$时,小波变换的模极大值随尺度a的增加而减小;反之,则增大。这一规律为区分边缘点和噪声点提供了理论基础,基于此可以有效实现噪声滤除[24]。去噪过程如下:
1) 对噪声图像进行3层小波变换,得到小波系数x
2) 计算每一层小波系数x的阈值$ \delta $,并根据式(9)处理小波系数,得到新的系数y
$ y = \left\{ \begin{aligned} &{{\mathrm{sgn}}} (x)(\left| x \right| - \delta ),&& \left| x \right| \geqslant \delta \\ & 0, && \left| x \right| \lt \delta \end{aligned} \right. $
3) 利用新的小波系数进行图像重构,通过小波逆变换得到去噪图像。
Scharr算子是对Sobel算子的改进,通过优化卷积核的权重分布,使得边缘检测具有更高的精度和更平滑的响应特性。Scharr算子与Sobel算子具有相似的计算时间和复杂度,但前者鲁棒性更好。Scharr算子在x方向和y方向的卷积核为
$ {{\boldsymbol{K}}_x}{ = }\left[ {\begin{array}{*{20}{c}} { - {3}}&{0}&{3} \\ { - {10}}&{0}&{{10}} \\ { - {3}}&{0}&{3} \end{array}} \right] $
$ {{\boldsymbol{K}}_y} = \left[ {\begin{array}{*{20}{c}} { - 3}&{ - 10}&{ - 3} \\ 0&0&0 \\ 3&{10}&3 \end{array}} \right] $
梯度计算通过将卷积核与图像进行卷积实现。则x方向和y方向的梯度计算公式为
$ {{\boldsymbol{G}}_x} = {{\boldsymbol{K}}_x}{*}{\boldsymbol{I}}{ = }\left[ {\begin{array}{*{20}{c}} { - {3}}&{0}&{3} \\ { - {10}}&{0}&{{10}} \\ { - {3}}&{0}&{3} \end{array}} \right]{*}{\boldsymbol{I}} $
$ {{\boldsymbol{G}}_y} = {{\boldsymbol{K}}_y} * {\boldsymbol{I}} = \left[ {\begin{array}{*{20}{c}} { - 3}&{ - 10}&{ - 3} \\ 0&0&0 \\ 3&{10}&3 \end{array}} \right] * {\boldsymbol{I}} $
式中:I为原始图像;$ {{\boldsymbol{G}}_x} $${{\boldsymbol{G}}_y}$分别为xy方向的梯度值。通过梯度值,计算梯度幅值G和梯度方向$\theta $
$ {\boldsymbol{G}} = \sqrt {{\boldsymbol{G}}_x^2 + {\boldsymbol{G}}_y^2} $
$ \theta = \arctan \left( {\frac{{{{\boldsymbol{G}}_y}}}{{{{\boldsymbol{G}}_x}}}} \right) $
在AUV动态对接过程中,导引标识光源的成像光圈大小和光强随距离呈非线性变化。固定阈值无法适应此类动态特性,易导致误检或漏检。自适应阈值能够根据图像内容实时动态调整,适应AUV水下对接。
在远距离时,标识光源在相机中的成像小且光强较弱,需要小阈值来接收更多光源,提升目标检测概率;在近距离时,标识光源在相机中的成像大且光强较强,需要大阈值来筛选光源,提高识别精度。自适应阈值调节过程如图3所示。
首先输入图像,将标志器N初始化为0,并设置一个初始阈值T,使用阈值T进行边缘检测,计算最大轮廓面积S。将S与参考轮廓面积$S_0$进行比较:若$S \gt S_0$,说明阈值设置较低,误检到伪边缘,此时需增大阈值T来削弱伪边缘,提高识别精度。阈值增加X且标志器N加1后进入下一次检测,随着阈值T增加,边缘检测的最大轮廓面积S会逐渐减小,直到第1次出现$S \lt S_0$,说明此时阈值T检测的最大轮廓面积S与参考轮廓面积$S_0$最接近,且此时标志器N > 0,则最佳阈值为此时的阈值T;若$S \lt S_0$,说明阈值设置较高,光圈弱边缘被抑制,造成漏检,此时需要减少阈值T来识别微弱光源,增大检测概率。标志器N = 0,不满足N > 0条件,阈值减小Y后进入下一次检测,随着阈值T减小,边缘检测的最大轮廓面积S逐渐增大,直到出现$S \gt S_0$,进入$S \gt S_0$的判断循环,直到获得最佳阈值T。每次阈值增加幅度为X,减少幅度为YXY值需要根据实际情况和硬件设备性能确定。一般设置$X \lt Y$,目的是为了实现减少阈值时粗调节,增加阈值时细调节,进一步提高识别精度。
水下3 m经暗通道先验去雾算法处理的对接导引标识光源图像、传统Canny边缘检测图像和改进的Canny边缘检测图像对比结果如图4所示。
图4可以看出,传统Canny算法的边缘检测结果受噪声污染严重,并伴随大量伪边缘信息,导致图像边缘呈现杂乱和不规则特性;而改进Canny算法在保留真实边缘特征的同时,降低了非边缘区域的误检概率,保持边缘细节信息完整,并有效抑制噪声,提高了边缘检测的准确性。
为了进一步验证改进算法的优越性,使用峰值信噪比(PSNR)、结构相似性(SSIM)和学习型感知图像块相似性(LPIPS)来评估算法改进前后的图像质量。
PSNR是通过计算均方误差(MSE)来衡量信号与噪声之间像素差异的指标,值越大表示图像噪声越少,劣化程度越轻。其计算公式为
$ \left\{ \begin{aligned} &Q_{\text{MSE}} = \frac{1}{{mn}}\sum\limits_{i = 1}^m {\sum\limits_{j = 1}^n {{{\left( {{\boldsymbol{I}}\left[ {i,j} \right] - {\boldsymbol{K}}\left[ {i,j} \right]} \right)}^2}} } \\ & Q_{\text{PSNR}} = 20 \times \lg \left( {\frac{P}{{\sqrt {Q_{\text{MSE}}} }}} \right)\end{aligned}\right. $
式中:mn表示图像尺寸为m×n$ {\boldsymbol{I}} $为原始图像;K为算法处理后图像;P为图像像素强度最大值。
SSIM是一种基于人类视觉系统特性的图像质量评估指标,同时考虑图像的亮度、对比度和结构信息,值越大表示图像质量越高。常用的SSIM计算公式为
$ Q_{\text{SSIM(x,y)}} = \frac{{(2{\mu _x}{\mu _y} + {C_1})(2{\sigma _{xy}} + {C_2})}}{{(\mu _x^2 + \mu _y^2 + {C_1})(\sigma _x^2 + \sigma _y^2 + {C_2})}} $
式中:x为原始图像数据;y为经算法处理的图像数据;$ {\mu _x} $$ {\mu _y} $分别为xy的均值;$ {\sigma _x} $$ {\sigma _y} $分别为xy的方差;$ {\sigma _{xy}} $xy之间的协方差;$ {C_1} $$ {C_2} $为常数,用于维持结果的稳定。
LPIPS是一种基于深度学习的图像质量评估指标,通过模拟人类视觉系统对图像的感知特性,衡量两幅图像在特征空间中的相似性,值越低表示两张图像越相似。计算公式为
$ Q_{\text{LPIPS}}(x{\text{,}}{x_{_{\text{0}}}}{\text{)}} = \sum\limits_l {{w_{_l}}} \cdot ||{F_{_l}}(x) - {F_{_l}}({x_{_0}})||_2^2 $
式中:$ {x_{_0}} $为原始图像数据;x为经算法处理的图像数据;$ {w_{_l}} $为层权重,用于衡量不同层特征对感知相似度的贡献;$ {F_{_l}}(x) $为预训练网络的第l层特征提取结果。
将经算法处理的图像与原始图像进行对比,计算结果如表3所示。可以看到,改进的Canny检测算法得到的PSNR和SSIM分别增加19.4%和4.8%,LPIPS降低33.8%。表明改进的Canny检测在增强图像降噪能力的同时,更精确地保留了图像结构与细节特征,整体性能优于传统Canny检测方法。
光信号在水中传播的衰减程度受水体环境影响显著。表4列出不同水域的吸收和散射系数[25]。由表4可见,不同水域光强衰减的影响因素也不相同,应根据具体情况来选择不同波长的光。
在清澈的海域,如远洋深海,由于水中颗粒物少,散射作用较弱,光强的衰减主要受吸收系数的影响,因此选择吸收系数较小波段的蓝绿光,以减少光能损失。而在近海或沿岸区域,尤其在受陆地径流和人类活动影响较大的水域,散射系数显著增加,成为光强衰减的主要因素,因此选择散射系数较小波段的黄绿光,以提升光信号传播能力[26]
本研究在水池中进行对接实验,水质较为清澈,所以对接导引标识光源采用蓝色光源,以减少光能损失。
主流颜色空间包括RGB,Lab和HSV,选择合适的颜色空间对颜色阈值分割至关重要。本文采用HSV颜色空间进行目标提取,因其更符合人类对颜色的感知方式且受光照条件影响较小。
利用HSV颜色空间进行目标分割时,先设定色调(H)的区间实现初步的大范围分割,再通过膨胀、腐蚀等形态学操作进行精细化调整[27]。为了精确界定色调区间,提取水下对接导引蓝色标识光源的颜色直方图,统计目标像素在色调通道的区间分布特征,为分割算法提供区间界定依据,如图5所示。
图5可得,颜色阈值分割算法中HSV的阈值范围为
$ \begin{split} & \; b_{\text{lower }}=\text{np.array}([110,200,60]) \\ & b_{\text{upper }}=\text{np.array}([125,255,255])\end{split} $
其中,np.array是 NumPy 库中创建多维数组的函数。
水下3 m对接导引标识光源经暗通道先验去雾算法和经颜色阈值分割处理的图像对比结果如图6所示。可见颜色阈值分割算法能够有效提取蓝色标识光源,同时抑制背景噪声与非目标区域。
海洋环境的动态性与复杂性使得单一特征提取方法难以适应多变的成像条件。为此,本文提出一种基于多特征融合的图像提取方法,即融合改进Canny算法提取的边缘特征和颜色阈值分割得到的颜色特征,分配合适的权重,实现特征互补,提升算法在复杂海洋图像环境中的适应性和鲁棒性。特征融合能确保边缘和颜色特征都得到利用,为后续目标识别和图像分析提供丰富信息源。
在实际应用中,环境光照的变化对图像特征的影响最为明显。在光照充足的情况下,周围环境影响会干扰边缘特征提取,易识别到伪边缘,但此时颜色特征对比度强,可以通过适当增加颜色特征权重,减少边缘特征权重,提高识别精度。如图7所示,边缘特征与颜色特征权重比为0.3∶0.7。
在光照不足的环境中,光晕现象使得颜色特征提取不准确,此时可以提高边缘特征的权重,降低颜色特征的权重,如图8所示,边缘特征与颜色特征权重比为0.8∶0.2。通过这种方式,能够提高算法的灵活性和适应性。
水下成像存在畸变问题。为消除成像偏差,提高成像的准确性,需要通过畸变参数对成像中心点坐标进行校正。完成畸变校正后,将修正的中心点坐标从像素坐标系转换为相机坐标系,解算AUV与对接装置的相对位置。
相机畸变主要分为径向畸变和切向畸变。计算时一般采用2阶径向畸变模型,模型公式为
$ r = \sqrt {{{({u_{\text{d}}} - {u_0})}^2} + {{({v_{\text{d}}} - {v_0})}^2}} $
$ u - {u_0} = ({u_d} - {u_{\text{0}}})( {1 + {k_u}{r^2}} ) $
$ v - {v_0} = ({v_d} - {v_0})( {1 + {k_v}{r^2}} ) $
式中:r为畸变半径;$({u_{\text{d}}},{v_{\text{d}}})$为理想图像坐标;$({u_0},{v_0})$为光学图像中心坐标;$(u,v)$为畸变图像坐标;${k_u}$${k_v}$分别为uv方向2阶径向畸变系数。
单目视觉成像模型本质上就是将三维世界中的物体通过光学系统映射到二维图像平面上,可以简化为相机针孔模型。针孔成像模型中包括世界坐标系、相机坐标系、图像坐标系和像素坐标系[28],像素坐标系与相机坐标系的转换公式为
$ \begin{split} &{Z_{\text{c}}}\left[ {\begin{array}{*{20}{c}} u \\ v \\ 1 \end{array}} \right] = \left[ {\begin{array}{*{20}{c}} {\dfrac{1}{{{\text{d}}x}}}&0&{{u_0}} \\ 0&{\dfrac{1}{{{\text{d}}y}}}&{{v_0}} \\ 0&0&1 \end{array}} \right]\left[ {\begin{array}{*{20}{c}} f&0&0&0 \\ 0&f&0&0 \\ 0&0&1&0 \end{array}} \right]\left[ {\begin{array}{*{20}{c}} {{X_{\text{c}}}} \\ {{Y_{\text{c}}}} \\ {{Z_{\text{c}}}} \\ 1 \end{array}} \right] = \\&\qquad\qquad \left[ {\begin{array}{*{20}{c}} {{f_x}}&0&{{u_0}}&0 \\ 0&{{f_y}}&{{v_0}}&0 \\ 0&0&1&0 \end{array}} \right]\left[ {\begin{array}{*{20}{c}} {{X_{\text{c}}}} \\ {{Y_{\text{c}}}} \\ {{Z_{\text{c}}}} \\ 1 \end{array}} \right] \\[-1pt]\end{split} $
式中:$(u,v)$为像素坐标系下的目标点坐标; ${f_x}$${f_y}$分别为相机在xy方向的焦距;$\left( {{X_{\text{c}}},{Y_{\text{c}}},{Z_{\text{c}}}} \right)$为相机坐标系下的目标点坐标;$\left( {{u_0},{v_0}} \right)$为像素坐标系下的图像中心点坐标;$\left[ {\begin{array}{*{20}{c}} {{f_x}}&0&{{u_0}}&0 \\ 0&{{f_y}}&{{v_0}}&0 \\ 0&0&1&0 \end{array}} \right]$为四参数的相机内参数矩阵。
准确的相机标定是视觉系统实现位置检测的关键环节。通过标定可以确定相机的内参和外参,其中内参描述相机自身的光学特性,如焦距和畸变系数等,外参描述相机在世界坐标系中的位置和姿态。这些参数是图像处理和三维重建的基础。
张正友标定法[29]是基于平面棋盘格图案的相机自标定技术。这种方法因其简单、有效且不需要特殊设备而被广泛应用于计算机视觉领域。
本文使用张正友标定法进行相机标定。标定对象为Barlus M-T2-4DCX10型水下相机,该相机配置1/2.8英寸SONY CMOS图像传感器,支持1920 px×1080 px分辨率的50 FPS高帧率视频流采集;全局电子快门有效抑制卷帘快门畸变;具备0.01 Lux超低照度彩色成像能力,能够满足复杂水下作业场景的视觉感知需求。Barlus水下相机的具体参数如表5所示。
通过拍摄不同角度的标定板,共获取16组图像,如图9所示。利用MATLAB Camera Calibration工具箱读取图像,得到相机内参数及几何畸变系数,如表6所示。这些参数用于消除镜头畸变,并建立坐标系之间的转换关系。
本研究采用Unity 3D引擎进行半实物仿真,验证所提出自主对接技术的有效性和算法的准确性。仿真环境包括四桨无舵矢量推进型AUV模型、对接装置三维模型以及模拟的水下环境。为模拟真实的水流场和光照情况,通过Gerstner波叠加算法模拟动态水流场,结合球体追踪光线步进技术完成水下光源渲染,如图10所示。该仿真环境能够模拟AUV在水下对接过程中的动力学特性和光学成像条件,为算法测试和参数调整提供可控平台。
仿真环境中,水下光源为蓝色环形灯带,固定于对接装置笼口;AUV艏部虚拟相机分辨率为1920 px×1080 px,水平视野角142°,垂直视野角102°。在图像采集环节叠加均值0、标准差0.1的高斯噪声及5%椒盐噪声,模拟电路噪声与水下悬浮颗粒散射[30]。AUV初始位置距对接装置入口20 m,预设AUV自主对接任务航速1 kn,通过第一人称视角进行视景显示观察AUV航行状态(图11)。仿真实验共进行12次,其中10次成功对接。
在水池对接实验时,将AUV布置于距对接装置入口相同距离、不同角度处,以验证算法的准确性和鲁棒性。当摄像头识别到导引光源后,AUV自动调整姿态直至进入对接装置。
实验用AUV为中小型AUV,总长约为4.3 m,直径为323 mm,采用鱼雷型设计,如图12所示。对接装置为圆柱形铁笼,长度为3.5 m,直径为550 mm,笼口安装防撞缓冲轮胎。对接装置如图13所示。
实验水池长30 m,宽5 m,深5 m,池壁采用绿色防反射涂层,抑制杂散光干扰,水质清澈,满足对接实验条件,水池上方配备航车,方便进行设备吊放,如图14所示。
对接装置置于水下3 m处,AUV在距对接装置20 m处入水,下潜至3 m后以定速1 kn航行,于12 m处开启视觉识别引导,通过不断调整姿态,修正自身航向和俯仰偏差实现对接,整个对接过程耗时约50 s。AUV对接过程中航向和俯仰姿态变化如图15所示,航向偏差修正约22°,俯仰偏差修正约10°,且能快速、连续地跟踪目标曲线。对接过程如图16所示,图像识别单帧耗时约100 ms。
水池实验时,无法从外部准确获取AUV与对接装置之间的角度,故将激光测距仪测得的实际距离与视觉算法测得的距离进行比较,验证算法精度。实际距离使用SXCJ-P1型激光测距仪获取,其水下测距量程覆盖0.1~20.0 m,测距精度达±5 mm,采样率为10 Hz,可实时反馈数据并跟踪动态目标。
末端视觉导引开启距离为12 m,选取离对接装置入口约10,6,2 m的位置进行定位分析。水池实验共进行25次,选取其中20次作为数据分析样本,距离曲线如图17所示,数据分析如表7所示。
结果表明, 10 m时视觉测距与激光测距的均值差为180.25 mm, 6 m处均值差降至120.36 mm, 2 m处均值差进一步缩减至51.21 mm,可见均值差随距离缩短而递减,当末端对接距离小于2 m时位姿精度误差小于5 cm。均方根误差呈相同趋势,对接距离越近,两条测距曲线拟合度越高,视觉测距结果越准确,对接精度越高。这种现象可归因于近距离条件下图像特征分辨率的提升。
图18所示为单次对接过程的激光测距和视觉测距曲线。可以看到,在远距离时视觉测距与激光测距偏差较大,随距离减小逐渐趋近,与实验定量分析结果一致。视觉测距曲线平滑无明显抖动,稳定性较高,表明该方法近程导引鲁棒性强,具有良好的动态测量能力。
水池对接实验共进行25次,成功对接22次,成功率为88%。结果表明,该方法在AUV自主对接过程中能够准确识别对接装置的导引光源,并对AUV的位置姿态信息进行有效调整,满足AUV自主对接精度和实时性要求,具有实际应用价值。
对失败的3次对接实验进行分析后发现:
1)其中1次因之前进行过多次对接实验,AUV姿态调整时尾流扰动带起大量池底沉积物,水质浑浊度增加,导致图像质量下降,特征提取失败。
2)另外2次因AUV运动控制系统动态响应延迟,未能及时修正航向偏差,导致撞击笼口缓冲轮胎。
针对水质浑浊引起的特征提取失败问题,未来可优化图像特征提取算法,引入自适应滤波算法,根据水质浑浊度动态调整去噪强度,以增强图像处理的鲁棒性。针对AUV姿态调整滞后问题,未来可改进姿态控制策略,构建运动预测模型,提前预测AUV的航向偏差,同步优化矢量推进器的动态响应参数,缩短姿态修正延迟。
本文针对AUV自主对接过程中存在的环境干扰、特征提取精度不足及动态适应性差等问题,提出了一种基于多特征融合的视觉导引方法。通过暗通道先验去雾算法增强水下图像质量,结合改进的Canny边缘检测与颜色阈值分割技术实现边缘与颜色特征互补,并使用自适应阈值调节机制和权重分配策略,提升了不同光照条件下的目标识别准确度和鲁棒性。利用视觉定位和相机标定技术,解算AUV与对接装置的相对位置,并通过Unity 3D半实物仿真与水池实验验证了算法的可行性与精度。
实验结果表明,该方法在水下环境中具有较高的适应性,视觉测距误差随距离减小而显著降低,末端对接距离小于2 m时位姿精度误差小于5 cm,总体对接成功率达88%。相比传统单特征提取方法,多特征融合技术有效抑制了噪声干扰,在光照变化和复杂背景下仍能保持稳定的识别性能,为AUV水下自主回收、能源补给及隐蔽作业提供了可靠的技术支撑。下一阶段将开展海洋环境下的实地试验,验证技术方案的工程适用性。
参考文献 引证文献
排序方式:
1
卢有旺, 夏英凯, 徐国华, 等. 面向UUV对接的视觉引导三维轨迹跟踪控制研究[J]. 中国舰船研究, 2024, 19(1): 290–304.
LU Y W, XIA Y K, XU G H, et al. Study on vision-guided 3D tracking control for UUV docking[J]. Chinese Journal of Ship Research, 2024, 19(1): 290–304.
2
袁学庆, 刁家宇, 李卫民, 等. AUV水下对接的发展与应用现状[J]. 舰船科学技术, 2023, 45(5): 1–8.
YUAN X Q, DIAO J Y, LI W M, et al. Development and application status of AUV underwater docking[J]. Ship Science and Technology, 2023, 45(5): 1–8 (in Chinese).
3
孙叶义, 武皓微, 李晔, 等. 智能无人水下航行器水下回收对接技术综述[J]. 哈尔滨工程大学学报, 2019, 40(1): 1–11.
SUN Y Y, WU H W, LI Y, et al. Summary of AUV underwater recycle docking technology[J]. Journal of Harbin Engineering University, 2019, 40(1): 1–11 (in Chinese).
4
WANG H Q, ZHONG G Q, SUN J X, et al. Simultaneous restoration and super-resolution GAN for underwater image enhancement[J]. Frontiers in Marine Science, 2023, 10: 1162295.
5
WANG J, LI P, DENG J H, et al. CA-GAN: class-condition attention GAN for underwater image enhancement[J]. IEEE Access, 2020, 8: 130719–130728.
6
XU S, JIANG Y Q, LI Y, et al. A stereo visual navigation method for docking autonomous underwater vehicles[J]. Journal of Field Robotics, 2024, 41(2): 374–395.
7
REN R Z, ZHANG L C, LIU L, et al. Two AUVs guidance method for self-reconfiguration mission based on monocular vision[J]. IEEE Sensors Journal, 2021, 21(8): 10082–10090.
8
FIGUEIREDO A B, MATOS A C. MViDO: a high performance monocular vision-based system for docking a hovering AUV[J]. Applied Sciences, 2020, 10(9): 2991.
9
安平, 王亭亭, 赵渊, 等. 基于深度学习的AUV水下视觉导引检测方法[J]. 水下无人系统学报, 2023, 31(3): 421–429.
AN P, WANG T T, ZHAO Y, et al. Underwater visual guidance deep learning detection method for AUV[J]. Journal of Unmanned Undersea Systems, 2023, 31(3): 421–429 (in Chinese).
10
SIM H, JOE H. Voronoi diagram-based USBL outlier rejection for AUV localization[J]. Journal of Ocean Engineering and Technology, 2024, 38(3): 115–123.
11
Algorithms; New algorithms findings from Southeast University discussed (AUV positioning method based on tightly coupled SINS/LBL for underwater acoustic multipath propagation)[J]. Journal of Technology, 2016, 15(3): 45-50.
12
YANG Q S, LIU H T, HONG L, et al. Anti-disturbance control strategy in capture stage for AUV dynamic base docking with optical guided constraints[J]. Ocean Engineering, 2024, 311(Pt 2): 118946.
13
燕奎臣, 吴利红. AUV水下对接关键技术研究[J]. 机器人, 2007, 29(3): 267–273.
YAN K C, WU L H. A survey on the key technologies for underwater AUV docking[J]. Robot, 2007, 29(3): 267–273 (in Chinese).
14
周冰. 面向AUV回收的异色光源阵列视觉导引方法研究[D]. 长春: 吉林大学, 2024.
ZHOU B. Research on visual guidance method of heterochromatic light source array for AUV recovery[D]. Changchun: Jilin University, 2024 (in Chinese).
15
黄栩. 视觉和电磁组合导引的AUV自主对接技术研究[D]. 杭州: 杭州电子科技大学, 2024.
HUANG X. Research on autonomous docking technology for AUVs utilizing visual and electromagnetic composite guidance[D]. Hangzhou: Hangzhou Dianzi University, 2024 (in Chinese).
16
孟令帅, 李明烁, 林扬, 等. 自主水下机器人布放回收技术综述[J]. 无人系统技术, 2024, 7(1): 1–19.
MENG L S, LI M S, LIN Y, et al. Launch and recovery technology of autonomous underwater vehicle[J]. Unmanned Systems Technology, 2024, 7(1): 1–19 (in Chinese).
17
LIU S, XU H L, LIN Y, et al. Visual navigation for recovering an AUV by another AUV in shallow water[J]. Sensors, 2019, 19(8): 1889.
18
羊云石, 顾海东. AUV水下对接技术发展现状[J]. 声学与电子工程, 2013(2): 43–46.
YANG Y S, GU H D. Current development status of AUV underwater docking technology[J]. Acoustics and Electronics Engineering, 2013(2): 43–46 (in Chinese).
19
TRUCCO E, OLMOS-ANTILLON A T. Self-tuning underwater image restoration[J]. IEEE Journal of Oceanic Engineering, 2006, 31(2): 511–519.
20
王蕊. 单幅雾天及水下图像的复原方法研究[D]. 青岛: 中国海洋大学, 2014.
WANG R. The research of single image recovery in fog and underwater[D]. Qingdao: Ocean University of China, 2014 (in Chinese).
21
YAO B W, XIANG J. Underwater image dehazing using modified dark channel prior[C]//Proceedings of 2018 Chinese Control and Decision Conference (CCDC). Shenyang, China: IEEE, 2018: 5792-5797.
22
杨爱萍, 郑佳, 王建, 等. 基于颜色失真去除与暗通道先验的水下图像复原[J]. 电子与信息学报, 2015, 37(11): 2541–2547.
YANG A P, ZHENG J, WANG J, et al. Underwater image restoration based on color cast removal and dark channel prior[J]. Journal of Electronics & Information Technology, 2015, 37(11): 2541–2547 (in Chinese).
23
祝志坤, 卢丙举, 李一辰, 等. 基于单双目融合的AUV坐落式回收光视觉引导算法[J]. 控制与决策, 2025, 40(1): 28–37.
ZHU Z K, LU B J, LI Y C, et al. Light visual guidance algorithm for AUV situated recovery based on monocular and binocular fusion[J]. Control and Decision, 2025, 40(1): 28–37 (in Chinese).
24
季嘉诚. 基于视觉的水下AUV对接伺服控制系统研究[D]. 大连: 大连海事大学, 2023.
JI J C. Research on strategy of underwater AUV docking system based on vision[D]. Dalian: Dalian Maritime University, 2023 (in Chinese).
25
刘旖恒. 基于光视觉引导的AUV姿态估计算法研究与实现[D]. 大连: 大连海事大学, 2022.
LIU Y H. A research and implementation of AUV pose estimation algorithm based on optical vision guidance[D]. Dalian: Dalian Maritime University, 2022 (in Chinese).
26
唐松奇. 基于卷积神经网络的水下图像增强与拼接方法研究[D]. 哈尔滨: 哈尔滨工程大学, 2020.
TANG S Q. Research on underwater image enhancement and mosaic method based on convolutional neural network[D]. Harbin: Harbin Engineering University, 2020 (in Chinese).
27
尉金强, 杜文正, 孙晓艳, 等. 基于目标HSV(色调−饱和度−亮度)空间图像自适应分割的直线检测算法[J]. 火箭军工程大学学报, 2024, 38(5): 59–68.
WEI J Q, DU W Z, SUN X Y, et al. Straight line detection algorithm based on adaptive segmentation of target HSV space images[J]. Journal of Rocket Force University of Engineering, 2024, 38(5): 59–68 (in Chinese).
28
丁王杰. 面向水下自主航行器接驳的末端视觉导引关键技术研究[D]. 杭州: 浙江大学, 2023.
DING W J. Research on key technologies of terminal visual-based guidance for AUV terminal docking[D]. Hangzhou: Zhejiang University, 2023 (in Chinese).
29
石建树. 基于视觉的AUV回收末端定位方法研究[D]. 镇江: 江苏科技大学, 2020.
SHI J S. Research on vision-based AUV recovery end positioning method[D]. Zhenjiang: Jiangsu University of Science and Technology, 2020 (in Chinese).
30
CHERIAN A K, POOVAMMAL E, PHILIP N S, et al. Deep learning based filtering algorithm for noise removal in underwater images[J]. Water, 2021, 13(19): 2742.
2026年第21卷第2期
PDF下载
27
9
引用本文
BibTeX
文章信息
doi: 10.19693/j.issn.1673-3185.04381
  • 接收时间:2025-02-22
  • 首发时间:2026-05-20
  • 出版时间:2026-04-30
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-02-22
  • 修回日期:2025-05-18
基金
作者信息
    中北大学 极限环境光电动态测试技术与仪器全国重点实验室,山西 太原 030051

通讯作者:

* 齐向东
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zgjcyj/CN/10.19693/j.issn.1673-3185.04381
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