Article(id=1241718971045564728, tenantId=1146029695717560320, journalId=1146032081894723586, issueId=1241718870671675569, articleNumber=null, orderNo=null, doi=10.3981/j.issn.2097-0781.2022.04.005, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1666540800000, receivedDateStr=2022-10-24, revisedDate=1667404800000, revisedDateStr=2022-11-03, acceptedDate=null, acceptedDateStr=null, onlineDate=1673884800000, onlineDateStr=2023-01-17, pubDate=1671465600000, pubDateStr=2022-12-20, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1673884800000, onlineIssueDateStr=2023-01-17, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1773978472716, creator=sys-migrate, updateTime=1773978472716, updator=sys-migrate, issue=Issue{id=1241718870671675569, tenantId=1146029695717560320, journalId=1146032081894723586, year='2022', volume='1', issue='4', pageStart='113', pageEnd='150', issueExtLink='null', onlineDate='null', pubDate='1671465600000', pubDateStr='2022-12-20', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=1, createTime=1773978448786, creator='sys-migrate', updateTime=1776075219003, updator='13041195026', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1250513362480742955, tenantId=1146029695717560320, journalId=1146032081894723586, issueId=1241718870671675569, language=EN, specialIssueTitle=Science and Technology Foresight, coverIllustrator=null, specialIssueEditor=null, specialIssueAbout=null), CN=IssueExt(id=1250513362480742956, tenantId=1146029695717560320, journalId=1146032081894723586, issueId=1241718870671675569, language=CN, specialIssueTitle=智能化弹药技术专刊, coverIllustrator=null, specialIssueEditor=null, specialIssueAbout=null)}, issueFiles=null, downloadFileDto=null}, startPage=69, endPage=80, ext={EN=ArticleExt(id=1241718978494648636, articleId=1241718971045564728, tenantId=1146029695717560320, journalId=1146032081894723586, language=EN, title=Overview of Target Detection and Recognition Technology in Complex Background, columnId=1149656489310208610, journalTitle=Science and Technology Foresight, columnName=Review and Commentary, runingTitle=null, highlight=null, articleAbstract=

Target detection and recognition technology is a popular research field in image information processing technology. How to maturely apply this technology to land battlefields with complex backgrounds is an urgent pain point to be resolved. This paper first introduces the main factors affecting the performance of target detection and recognition under complex background conditions of land battlefields and analyzes the complexity, diversity, and uncertainty of the target background of land battlefields. Then, it reviews the research status of target recognition algorithms. Furthermore, it expounds on the key technologies of target detection and recognition under complex backgrounds, including multispectral complex target detection, automatic target recognition, dim and small target detection, and multi-channel heterogeneous information fusion. Finally, this paper predicts the tendencies of target detection and recognition technology in land battlefields.

, authors=null, authorsList=Dedong CUI, Tao FENG, Kun BAI, Ting YANG, Long MA, Yi SHANG, authorCompany=null, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1241718978360430906, articleId=1241718971045564728, tenantId=1146029695717560320, journalId=1146032081894723586, language=CN, title=复杂背景目标探测识别技术综述, columnId=1148708266483446458, journalTitle=前瞻科技, columnName=综述与述评, runingTitle=null, highlight=null, articleAbstract=

目标探测识别技术是图像信息处理技术的热门研究领域,面向陆战场复杂背景条件的目标探测识别技术如何成熟应用更是该领域亟待解决的痛点问题。文章介绍了陆战场复杂背景条件下影响目标探测识别性能的主要因素;分析了陆战场目标背景的复杂性、多样性和不确定性;回顾了国内外目标识别技术的发展历程;阐述了陆战场复杂背景目标探测识别的关键技术,包括多波段复合探测技术、目标自主识别技术、弱小目标检测识别技术、多通道异构信息融合技术;展望了陆战场目标探测识别技术的发展趋势。

, authors=

崔得东,研究员,中国兵器科技带头人,国务院政府特殊津贴专家。主要研究方向为智能化弹药导引技术。担任国家重点型号项目副总设计师。获国家科学技术进步奖一等奖1项,国防科学技术进步奖二等奖、省部级科学技术进步奖二等奖4项。出版专著1部,发表论文10余篇,获授权国防发明专利11项、新型实用专利1项。电子信箱:

, authorsList=崔得东, 冯涛, 白昆, 杨挺, 马龙, 尚毅, authorCompany=null, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=fTZIf0agT/gvywHUZHZ0ow==, magXml=iA8VXEO24lId3R5NSrLYYQ==, pdfUrl=null, pdf=05gx+iK0Zfbhw4RvFm/M2g==, pdfFileSize=1593861, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=RpYCJElZkHcyT2NQby/WYg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=PVGvqRV8Duz8678TUkEXOg==, mapNumber=null, fund=null)}, authors=[Author(id=1241718997033480236, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=dedocui@126.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241718997138337840, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, authorId=1241718997033480236, language=EN, stringName=Dedong CUI, firstName=Dedong, middleName=null, lastName=CUI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1. Xi’an Modern Control Technology Research Institute, Xi’an 710065, China
2. Xi’an Guidance Technology Co., Ltd., Xi’an 710065, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241718997209641009, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, authorId=1241718997033480236, language=CN, stringName=崔得东, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.西安现代控制技术研究所,西安 710065
2.西安导引科技有限责任公司,西安 710065, bio={"img":"FhfatkLfmNa7VjuTAxFBEg==","content":"

崔得东,研究员,中国兵器科技带头人,国务院政府特殊津贴专家。主要研究方向为智能化弹药导引技术。担任国家重点型号项目副总设计师。获国家科学技术进步奖一等奖1项,国防科学技术进步奖二等奖、省部级科学技术进步奖二等奖4项。出版专著1部,发表论文10余篇,获授权国防发明专利11项、新型实用专利1项。电子信箱:

"}, bioImg=FhfatkLfmNa7VjuTAxFBEg==, bioContent=

崔得东,研究员,中国兵器科技带头人,国务院政府特殊津贴专家。主要研究方向为智能化弹药导引技术。担任国家重点型号项目副总设计师。获国家科学技术进步奖一等奖1项,国防科学技术进步奖二等奖、省部级科学技术进步奖二等奖4项。出版专著1部,发表论文10余篇,获授权国防发明专利11项、新型实用专利1项。电子信箱:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241718996882485284, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, xref=null, ext=[AuthorCompanyExt(id=1241718996886679589, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996882485284, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. Xi’an Modern Control Technology Research Institute, Xi’an 710065, China), AuthorCompanyExt(id=1241718996890873894, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996882485284, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.西安现代控制技术研究所,西安 710065)]), AuthorCompany(id=1241718996949594151, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, xref=null, ext=[AuthorCompanyExt(id=1241718996957982760, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996949594151, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. Xi’an Guidance Technology Co., Ltd., Xi’an 710065, China), AuthorCompanyExt(id=1241718996970565673, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996949594151, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.西安导引科技有限责任公司,西安 710065)])]), Author(id=1241718997289332787, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241718997356441654, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, authorId=1241718997289332787, language=EN, stringName=Tao FENG, firstName=Tao, middleName=null, lastName=FENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1. Xi’an Modern Control Technology Research Institute, Xi’an 710065, China
2. Xi’an Guidance Technology Co., Ltd., Xi’an 710065, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241718997410967607, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, authorId=1241718997289332787, language=CN, stringName=冯涛, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.西安现代控制技术研究所,西安 710065
2.西安导引科技有限责任公司,西安 710065, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241718996882485284, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, xref=null, ext=[AuthorCompanyExt(id=1241718996886679589, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996882485284, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. Xi’an Modern Control Technology Research Institute, Xi’an 710065, China), AuthorCompanyExt(id=1241718996890873894, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996882485284, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.西安现代控制技术研究所,西安 710065)]), AuthorCompany(id=1241718996949594151, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, xref=null, ext=[AuthorCompanyExt(id=1241718996957982760, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996949594151, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. Xi’an Guidance Technology Co., Ltd., Xi’an 710065, China), AuthorCompanyExt(id=1241718996970565673, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996949594151, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.西安导引科技有限责任公司,西安 710065)])]), Author(id=1241718997486465082, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, 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=1241718997566156861, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, authorId=1241718997486465082, language=EN, stringName=Kun BAI, firstName=Kun, middleName=null, lastName=BAI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1. Xi’an Modern Control Technology Research Institute, Xi’an 710065, China
2. Xi’an Guidance Technology Co., Ltd., Xi’an 710065, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241718997629071422, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, authorId=1241718997486465082, language=CN, stringName=白昆, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.西安现代控制技术研究所,西安 710065
2.西安导引科技有限责任公司,西安 710065, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241718996882485284, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, xref=null, ext=[AuthorCompanyExt(id=1241718996886679589, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996882485284, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. Xi’an Modern Control Technology Research Institute, Xi’an 710065, China), AuthorCompanyExt(id=1241718996890873894, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996882485284, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.西安现代控制技术研究所,西安 710065)]), AuthorCompany(id=1241718996949594151, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, xref=null, ext=[AuthorCompanyExt(id=1241718996957982760, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996949594151, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. Xi’an Guidance Technology Co., Ltd., Xi’an 710065, China), AuthorCompanyExt(id=1241718996970565673, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996949594151, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.西安导引科技有限责任公司,西安 710065)])]), Author(id=1241718997721346112, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, 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=1241718997792649282, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, authorId=1241718997721346112, language=EN, stringName=Ting YANG, firstName=Ting, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2. Xi’an Guidance Technology Co., Ltd., Xi’an 710065, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241718997855563843, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, authorId=1241718997721346112, language=CN, stringName=杨挺, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.西安导引科技有限责任公司,西安 710065, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241718996949594151, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, xref=null, ext=[AuthorCompanyExt(id=1241718996957982760, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996949594151, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. Xi’an Guidance Technology Co., Ltd., Xi’an 710065, China), AuthorCompanyExt(id=1241718996970565673, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996949594151, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.西安导引科技有限责任公司,西安 710065)])]), Author(id=1241718997931061317, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, 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=1241718998006558792, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, authorId=1241718997931061317, language=EN, stringName=Long MA, firstName=Long, middleName=null, lastName=MA, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1. Xi’an Modern Control Technology Research Institute, Xi’an 710065, China
2. Xi’an Guidance Technology Co., Ltd., Xi’an 710065, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241718998065279049, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, authorId=1241718997931061317, language=CN, stringName=马龙, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.西安现代控制技术研究所,西安 710065
2.西安导引科技有限责任公司,西安 710065, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241718996882485284, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, xref=null, ext=[AuthorCompanyExt(id=1241718996886679589, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996882485284, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. Xi’an Modern Control Technology Research Institute, Xi’an 710065, China), AuthorCompanyExt(id=1241718996890873894, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996882485284, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.西安现代控制技术研究所,西安 710065)]), AuthorCompany(id=1241718996949594151, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, xref=null, ext=[AuthorCompanyExt(id=1241718996957982760, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996949594151, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. Xi’an Guidance Technology Co., Ltd., Xi’an 710065, China), AuthorCompanyExt(id=1241718996970565673, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996949594151, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.西安导引科技有限责任公司,西安 710065)])]), Author(id=1241718998119805003, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241718998245634125, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, authorId=1241718998119805003, language=EN, stringName=Yi SHANG, firstName=Yi, middleName=null, lastName=SHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2. Xi’an Guidance Technology Co., Ltd., Xi’an 710065, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241718999705251918, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, authorId=1241718998119805003, language=CN, stringName=尚毅, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.西安导引科技有限责任公司,西安 710065, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241718996949594151, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, xref=null, ext=[AuthorCompanyExt(id=1241718996957982760, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996949594151, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. Xi’an Guidance Technology Co., Ltd., Xi’an 710065, China), AuthorCompanyExt(id=1241718996970565673, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996949594151, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.西安导引科技有限责任公司,西安 710065)])])], keywords=[Keyword(id=1241718999826886735, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, language=EN, orderNo=1, keyword=land battlefield), Keyword(id=1241718999919161424, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, language=EN, orderNo=2, keyword=complex background), Keyword(id=1241718999990464593, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, language=EN, orderNo=3, keyword=target detection and recognition), Keyword(id=1241719000061767762, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, language=CN, orderNo=1, keyword=陆战场), Keyword(id=1241719000124682323, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, language=CN, orderNo=2, keyword=复杂背景), Keyword(id=1241719000204374100, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, language=CN, orderNo=3, keyword=目标探测识别)], refs=[Reference(id=1241719001617854564, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2008, volume=28, issue=5, pageStart=17, pageEnd=21, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=陈健, 王永明, 赵革, journalName=舰船电子工程, refType=null, unstructuredReference=陈健, 王永明, 赵革, 等. 舰船目标特性研究综述[J]. 舰船电子工程, 2008, 28(5): 17-21., articleTitle=舰船目标特性研究综述, refAbstract=null), Reference(id=1241719001684963429, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2003, volume=31, issue=3, pageStart=1, pageEnd=3, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=刘进, 张天序, journalName=华中科技大学学报(自然科学版), refType=null, unstructuredReference=刘进, 张天序. 不变矩构造方法的研究[J]. 华中科技大学学报(自然科学版), 2003, 31(3): 1-3., articleTitle=不变矩构造方法的研究, refAbstract=null), Reference(id=1241719001747877990, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2004, volume=27, issue=10, pageStart=1335, pageEnd=1340, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=张天序, 刘进, journalName=计算机学报, refType=null, unstructuredReference=张天序, 刘进. 不变矩稳定性及基于多级特征模型的目标识别研究[J]. 计算机学报, 2004, 27(10): 1335-1340., articleTitle=不变矩稳定性及基于多级特征模型的目标识别研究, refAbstract=null), Reference(id=1241719001823375463, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2007, volume=35, issue=1, pageStart=17, pageEnd=19, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=张天序, 曹杨, 刘进, journalName=华中科技大学学报(自然科学版), refType=null, unstructuredReference=张天序, 曹杨, 刘进, 等. 基于不变矩的前视红外图像机场目标识别[J]. 华中科技大学学报(自然科学版), 2007, 35(1): 17-19., articleTitle=基于不变矩的前视红外图像机场目标识别, refAbstract=null), Reference(id=1241719001886290024, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2011, volume=28, issue=3, pageStart=63, pageEnd=65, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=孙红辉, 王红霞, 田涛, journalName=微电子学与计算机, refType=null, unstructuredReference=孙红辉, 王红霞, 田涛. 一种基于不变矩和BP网络的目标识别方法[J]. 微电子学与计算机, 2011, 28(3): 63-65., articleTitle=一种基于不变矩和BP网络的目标识别方法, refAbstract=null), Reference(id=1241719001974370409, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=10.1016/S0925-2312(01)00625-7, pmid=null, pmcid=null, year=2002, volume=43, issue=1-4, pageStart=145, pageEnd=172, url=https://linkinghub.elsevier.com/retrieve/pii/S0925231201006257, language=null, rfNumber=[6], rfOrder=5, authorNames=Tabb K, Davey N, Adams R, journalName=Neurocomputing, refType=null, unstructuredReference=Tabb K, Davey N, Adams R, et al. The recognition and analysis of animate objects using neural networks and active contour models[J]. Neurocomputing, 2002, 43(1-4): 145-172., articleTitle=The recognition and analysis of animate objects using neural networks and active contour models, refAbstract=null), Reference(id=1241719002041479274, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2003, volume=31, issue=11, pageStart=47, pageEnd=49, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=桑农, 唐红卫, 曹治国, journalName=华中科技大学学报(自然科学版), refType=null, unstructuredReference=桑农, 唐红卫, 曹治国, 等. 基于Gabor滤波器组和特征分组神经网络目标识别[J]. 华中科技大学学报(自然科学版), 2003, 31(11): 47-49., articleTitle=基于Gabor滤波器组和特征分组神经网络目标识别, refAbstract=null), Reference(id=1241719002108588139, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2006, volume=31, issue=10, pageStart=88, pageEnd=90, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=杨福平, 白振兴, journalName=火力与指挥控制, refType=null, unstructuredReference=杨福平, 白振兴. BP神经网络和D-S证据理论的目标识别[J]. 火力与指挥控制, 2006, 31(10): 88-90., articleTitle=BP神经网络和D-S证据理论的目标识别, refAbstract=null), Reference(id=1241719002184085612, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=10.1109/34.910878, pmid=null, pmcid=null, year=2001, volume=23, issue=3, pageStart=257, pageEnd=267, url=http://ieeexplore.ieee.org/document/910878/, language=null, rfNumber=[9], rfOrder=8, authorNames=Bobick A F, Davis J W, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=Bobick A F, Davis J W. The recognition of human movement using temporal templates[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(3): 257-267., articleTitle=The recognition of human movement using temporal templates, refAbstract=null), Reference(id=1241719002251194477, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2007, volume=null, issue=null, pageStart=179, pageEnd=182, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=牛照东, 许旻, 王卫华, journalName=北京: 中国仪器仪表学会, 中国电子学会, refType=null, unstructuredReference=牛照东, 许旻, 王卫华, 等. 一种利用层次化模板匹配的地面建筑红外图像自动识别方法[C]// 第十三届全国信号处理学术年会(CCSP-2007)论文集. 北京: 中国仪器仪表学会, 中国电子学会, 2007: 179-182., articleTitle=一种利用层次化模板匹配的地面建筑红外图像自动识别方法, refAbstract=null), Reference(id=1241719002314109038, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2007, volume=37, issue=12, pageStart=1322, pageEnd=1324, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=张义广, 冯志高, 张天序, journalName=激光与红外, refType=null, unstructuredReference=张义广, 冯志高, 张天序, 等. 基于可见光图像模板匹配的目标识别算法[J]. 激光与红外, 2007, 37(12): 1322-1324., articleTitle=基于可见光图像模板匹配的目标识别算法, refAbstract=null), Reference(id=1241719002402189423, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2006, volume=null, issue=null, pageStart=133, pageEnd=140, url=null, language=null, rfNumber=[12], rfOrder=11, authorNames=Han F, Shan Y, Cekander R, journalName=Performance Metrics for Intelligent Systems 2006 Workshop, refType=null, unstructuredReference=Han F, Shan Y, Cekander R, et al. A two-stage approach to people and vehicle detection with HOG-based SVM[C]// Performance Metrics for Intelligent Systems 2006 Workshop. 2006: 133-140., articleTitle=A two-stage approach to people and vehicle detection with HOG-based SVM, refAbstract=null), Reference(id=1241719002465103984, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2013, volume=null, issue=null, pageStart=263, pageEnd=266, url=null, language=null, rfNumber=[13], rfOrder=12, authorNames=Li X, Guo X S, journalName=A HOG feature and SVM based method for forward vehicle detection with single camera, refType=null, unstructuredReference=Li X, Guo X S. A HOG feature and SVM based method for forward vehicle detection with single camera[C]// 2013 5th International Conference on Intelligent Human-Machine Systems and Cybernetics. Piscataway: IEEE Press, 2013: 263-266., articleTitle=null, refAbstract=null), Reference(id=1241719002528018545, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=10.1016/j.sigpro.2010.08.010, pmid=null, pmcid=null, year=2011, volume=91, issue=4, pageStart=773, pageEnd=781, url=https://linkinghub.elsevier.com/retrieve/pii/S0165168410003476, language=null, rfNumber=[14], rfOrder=13, authorNames=Pang Y W, Yuan Y, Li X L, journalName=Signal Processing, refType=null, unstructuredReference=Pang Y W, Yuan Y, Li X L, et al. Efficient HOG human detection[J]. Signal Processing, 2011, 91(4): 773-781., articleTitle=Efficient HOG human detection, refAbstract=null), Reference(id=1241719002582544498, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2001, volume=1, issue=null, pageStart=511, pageEnd=518, url=null, language=null, rfNumber=[15], rfOrder=14, authorNames=Viola P, Jones M, journalName=Rapid object detection using a boosted cascade of simple features, refType=null, unstructuredReference=Viola P, Jones M. Rapid object detection using a boosted cascade of simple features[C]// Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2001, 1: 511-518., articleTitle=null, refAbstract=null), Reference(id=1241719002649653363, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=10.1016/j.cviu.2010.03.010, pmid=null, pmcid=null, year=2010, volume=114, issue=11, pageStart=1116, pageEnd=1125, url=https://linkinghub.elsevier.com/retrieve/pii/S1077314210000871, language=null, rfNumber=[16], rfOrder=15, authorNames=Yang M, Crenshaw J, Augustine B, journalName=Computer Vision and Image Understanding, refType=null, unstructuredReference=Yang M, Crenshaw J, Augustine B, et al. AdaBoost-based face detection for embedded systems[J]. Computer Vision and Image Understanding, 2010, 114(11): 1116-1125., articleTitle=AdaBoost-based face detection for embedded systems, refAbstract=null), Reference(id=1241719002708373620, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2012, volume=6, issue=4, pageStart=466, pageEnd=469, url=null, language=null, rfNumber=[17], rfOrder=16, authorNames=Padilla R, Filho Costa C F F, Costa M G F, journalName=International Journal of Computer, Electrical, Automation, Control and Information Engineering, refType=null, unstructuredReference=Padilla R, Filho Costa C F F, Costa M G F. Evaluation of haar cascade classifiers designed for face detection[J]. International Journal of Computer, Electrical, Automation, Control and Information Engineering, 2012, 6(4): 466-469., articleTitle=Evaluation of haar cascade classifiers designed for face detection, refAbstract=null), Reference(id=1241719004197351542, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=580, pageEnd=587, url=null, language=null, rfNumber=[18], rfOrder=17, authorNames=Girshick R, Donahue J, Darrell T, journalName=Rich feature hierarchies for accurate object detection and semantic segmentation, refType=null, unstructuredReference=Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]// 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2014: 580-587., articleTitle=null, refAbstract=null), Reference(id=1241719004256071799, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=18, authorNames=Sultana F, Sufian A, Dutta P, journalName=A review of object detection models based on convolutional neural network, refType=null, unstructuredReference=Sultana F, Sufian A, Dutta P. A review of object detection models based on convolutional neural network[M]// Advances in Intelligent Systems and Computing. Singapore: Springer Singapore, 2020: 1-16., articleTitle=null, refAbstract=null), Reference(id=1241719004327374969, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2005, volume=null, issue=null, pageStart=1440, pageEnd=1448, url=null, language=null, rfNumber=[20], rfOrder=19, authorNames=Girshick R, journalName=Fast R-CNN, refType=null, unstructuredReference=Girshick R. Fast R-CNN[C]// 2015 IEEE International Conference on Computer Vision. Piscataway: IEEE Press, 2005: 1440-1448., articleTitle=null, refAbstract=null), Reference(id=1241719004398678138, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=10.1109/TPAMI.2016.2577031, pmid=27295650, pmcid=null, year=2017, volume=39, issue=6, pageStart=1137, pageEnd=1149, url=null, language=null, rfNumber=[21], rfOrder=20, authorNames=Ren S Q, He K M, Girshick R, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=Ren S Q, He K M, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149., articleTitle=Faster R-CNN: towards real-time object detection with region proposal networks, refAbstract=State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [1] and Fast R-CNN [2] have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. We further merge RPN and Fast R-CNN into a single network by sharing their convolutional features-using the recently popular terminology of neural networks with 'attention' mechanisms, the RPN component tells the unified network where to look. For the very deep VGG-16 model [3], our detection system has a frame rate of 5 fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007, 2012, and MS COCO datasets with only 300 proposals per image. In ILSVRC and COCO 2015 competitions, Faster R-CNN and RPN are the foundations of the 1st-place winning entries in several tracks. Code has been made publicly available.), Reference(id=1241719004474175612, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=21, authorNames=Purkait P, Zhao C, Zach C, journalName=arXiv Preprint: 1712.03452, 2017, refType=null, unstructuredReference=Purkait P, Zhao C, Zach C. SPP-net: Deep absolute pose regression with synthetic views[DB/OL]. arXiv Preprint: 1712.03452, 2017., articleTitle=SPP-net: Deep absolute pose regression with synthetic views, refAbstract=null), Reference(id=1241719004574838909, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=21, pageEnd=37, url=null, language=null, rfNumber=[23], rfOrder=22, authorNames=Liu W, Anguelov D, Erhan D, journalName=SSD: Single shot MultiBox detector, refType=null, unstructuredReference=Liu W, Anguelov D, Erhan D, et al. SSD: Single shot MultiBox detector[C]// Computer Vision-ECCV 2016. Cham: Springer International Publishing, 2016: 21-37., articleTitle=null, refAbstract=null), Reference(id=1241719004679696511, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2020, volume=11, issue=null, pageStart=554, pageEnd=557, url=null, language=null, rfNumber=[24], rfOrder=23, authorNames=Arya M C, Rawat A, journalName=International Journal of Engineering Science, refType=null, unstructuredReference=Arya M C, Rawat A. A review on YOLO (You Look Only One): An algorithm for real time object detection[J]. International Journal of Engineering Science 2020, 11: 554-557., articleTitle=A review on YOLO (You Look Only One): An algorithm for real time object detection, refAbstract=null), Reference(id=1241719004759388288, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=779, pageEnd=788, url=null, language=null, rfNumber=[25], rfOrder=24, authorNames=Redmon J, Divvala S, Girshick R, journalName=You only look once: Unified, real-time object detection, refType=null, unstructuredReference=Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detection[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2016: 779-788., articleTitle=null, refAbstract=null), Reference(id=1241719004834885761, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=6517, pageEnd=6525, url=null, language=null, rfNumber=[26], rfOrder=25, authorNames=Redmon J, Farhadi A, journalName=YOLO9000: Better, faster, stronger, refType=null, unstructuredReference=Redmon J, Farhadi A. YOLO9000: Better, faster, stronger[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2017: 6517-6525., articleTitle=null, refAbstract=null), Reference(id=1241719004893606018, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[27], rfOrder=26, authorNames=Redmon J, Farhadi A, journalName=arXiv Preprint: 1804.02767, 2018, refType=null, unstructuredReference=Redmon J, Farhadi A. YOLOv3: An incremental improvement[DB/OL]. arXiv Preprint: 1804.02767, 2018., articleTitle=YOLOv3: An incremental improvement, refAbstract=null), Reference(id=1241719004952326275, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[28], rfOrder=27, authorNames=Bochkovskiy A, Wang C Y, Liao H Y M, journalName=arXiv Preprint: 2004.10934, 2004, refType=null, unstructuredReference=Bochkovskiy A, Wang C Y, Liao H Y M. YOLOv4: Optimal speed and accuracy of object detection[DB/OL]. arXiv Preprint: 2004.10934, 2004., articleTitle=YOLOv4: Optimal speed and accuracy of object detection, refAbstract=null), Reference(id=1241719005032018052, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=687, pageEnd=694, url=null, language=null, rfNumber=[29], rfOrder=28, authorNames=Adarsh P, Rathi P, Kumar M, journalName=Piscataway:IEEE Press, refType=null, unstructuredReference=Adarsh P, Rathi P, Kumar M. YOLOv3-tiny: Object Detection and Recognition using one stage improved model[C]// 2020 6th International Conference on Advanced Computing and Communication Systems (ICACCS). Piscataway:IEEE Press, 2020: 687-694., articleTitle=Object Detection and Recognition using one stage improved model, refAbstract=null), Reference(id=1241719005099126917, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=213, pageEnd=229, url=null, language=null, rfNumber=[30], rfOrder=29, authorNames=Carion N, Massa F, Synnaeve G, journalName=End-to-end object detection with transformers, refType=null, unstructuredReference=Carion N, Massa F, Synnaeve G, et al. End-to-end object detection with transformers[C]// Computer Vision-ECCV 2020. Cham: Springer International Publishing, 2020: 213-229., articleTitle=null, refAbstract=null), Reference(id=1241719005250121862, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=2325, pageEnd=2333, url=null, language=null, rfNumber=[31], rfOrder=30, authorNames=Stewart R, Andriluka M, Ng A Y, journalName=End-to-end people detection in crowded scenes, refType=null, unstructuredReference=Stewart R, Andriluka M, Ng A Y. End-to-end people detection in crowded scenes[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2016: 2325-2333., articleTitle=null, refAbstract=null), Reference(id=1241719005313036423, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=6469, pageEnd=6477, url=null, language=null, rfNumber=[32], rfOrder=31, authorNames=Hosang J, Benenson R, Schiele B, journalName=Learning non-maximum suppression, refType=null, unstructuredReference=Hosang J, Benenson R, Schiele B. Learning non-maximum suppression[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2017: 6469-6477., articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1241718996882485284, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, xref=null, ext=[AuthorCompanyExt(id=1241718996886679589, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996882485284, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. Xi’an Modern Control Technology Research Institute, Xi’an 710065, China), AuthorCompanyExt(id=1241718996890873894, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996882485284, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.西安现代控制技术研究所,西安 710065)]), AuthorCompany(id=1241718996949594151, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, xref=null, ext=[AuthorCompanyExt(id=1241718996957982760, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996949594151, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. Xi’an Guidance Technology Co., Ltd., Xi’an 710065, China), AuthorCompanyExt(id=1241718996970565673, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, companyId=1241718996949594151, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.西安导引科技有限责任公司,西安 710065)])], figs=[ArticleFig(id=1241719000397312085, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, language=EN, label=null, caption=null, figureFileSmall=tYTJM9ATBBmNZv6wxLumfg==, figureFileBig=RpYCJElZkHcyT2NQby/WYg==, tableContent=null), ArticleFig(id=1241719000464420950, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, language=CN, label=图1, caption=主动毫米波/红外成像/半主动激光三模复合导引头及其复合探测系统, figureFileSmall=tYTJM9ATBBmNZv6wxLumfg==, figureFileBig=RpYCJElZkHcyT2NQby/WYg==, tableContent=null), ArticleFig(id=1241719000682524759, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, language=EN, label=null, caption=null, figureFileSmall=hWlS/H8hEcjJ7p98vyvIpQ==, figureFileBig=mUBMTw/MdZCH4WpaXB4Jag==, tableContent=null), ArticleFig(id=1241719000753827928, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, language=CN, label=图2, caption=目标表征技术的发展里程碑

LBP:Local Binary Pattern,局部二值模式特征;Haar:Haar-like Features,哈尔特征;HOG:Histogram of Oriented Gradient,方向梯度直方图特征;DPM:Deformable Parts Model,部件可变模型。

, figureFileSmall=hWlS/H8hEcjJ7p98vyvIpQ==, figureFileBig=mUBMTw/MdZCH4WpaXB4Jag==, tableContent=null), ArticleFig(id=1241719000812548185, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, language=EN, label=null, caption=null, figureFileSmall=p9holiOj332OPQPTXAlYZg==, figureFileBig=63Kbi/UlyfPR4z1P5J02RA==, tableContent=null), ArticleFig(id=1241719000879657051, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, language=CN, label=图3, caption=传统目标表征技术流程, figureFileSmall=p9holiOj332OPQPTXAlYZg==, figureFileBig=63Kbi/UlyfPR4z1P5J02RA==, tableContent=null), ArticleFig(id=1241719000950960220, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, language=EN, label=null, caption=null, figureFileSmall=d1gkiUfZtENMd/7fLKsARw==, figureFileBig=OU4K/5sOy3MORjntxPM8oQ==, tableContent=null), ArticleFig(id=1241719001047429213, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, language=CN, label=图4, caption=典型的基于深度学习的多波段图像融合模型结构, figureFileSmall=d1gkiUfZtENMd/7fLKsARw==, figureFileBig=OU4K/5sOy3MORjntxPM8oQ==, tableContent=null), ArticleFig(id=1241719001148092510, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, language=EN, label=null, caption=null, figureFileSmall=Xf5f+wJbsCGloos31HAK4w==, figureFileBig=H69WQKpf/5MJaXoL9w38VA==, tableContent=null), ArticleFig(id=1241719001223589983, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, language=CN, label=图5, caption=特征提取器示意图, figureFileSmall=Xf5f+wJbsCGloos31HAK4w==, figureFileBig=H69WQKpf/5MJaXoL9w38VA==, tableContent=null), ArticleFig(id=1241719001311670368, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, language=EN, label=null, caption=null, figureFileSmall=NlXJpV13spemXsvzhPYP3Q==, figureFileBig=An45dC9tEk6722qT7Gzw5g==, tableContent=null), ArticleFig(id=1241719001366196321, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, language=CN, label=图6, caption=基于目标识别的战场态势感知模型, figureFileSmall=NlXJpV13spemXsvzhPYP3Q==, figureFileBig=An45dC9tEk6722qT7Gzw5g==, tableContent=null), ArticleFig(id=1241719001437499490, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
特征 优点 缺点 适用范围
LBP 对光照不敏感;运算速度快 计算量大 模板匹配
HOG 忽略光照颜色影响;表征数据维数降低 描述子生成过程长,实时性差;难以处理遮挡问题;噪点敏感 目标探测
SIFT 旋转、尺度缩放、亮度不变性;抗遮挡 方向信息敏感 目标识别
目标分类
), ArticleFig(id=1241719001508802659, tenantId=1146029695717560320, journalId=1146032081894723586, articleId=1241718971045564728, language=CN, label=表1, caption=

典型的传统目标表征技术的优缺点

, figureFileSmall=null, figureFileBig=null, tableContent=
特征 优点 缺点 适用范围
LBP 对光照不敏感;运算速度快 计算量大 模板匹配
HOG 忽略光照颜色影响;表征数据维数降低 描述子生成过程长,实时性差;难以处理遮挡问题;噪点敏感 目标探测
SIFT 旋转、尺度缩放、亮度不变性;抗遮挡 方向信息敏感 目标识别
目标分类
)], attaches=null, journal=Journal(id=1129340393107079197, delFlag=0, nameCn=前瞻科技, nameEn=Science and Technology Foresight, nameHistory1=null, nameHistory2=null, issn=2097-0781, eissn=, cn=10-1786/N, coden=null, periodic=2, 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=ti95jJIJzXaf02YNe1UF2A==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Fore, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1788948782472, createdBy=null, updatedBy=13041195026, firstLetterCn=Q, firstLetterEn=Q, subjectCode=Multidisciplinary, subjectName=自然科学, subjectCodeEn=Multidisciplinary, subjectNameEn=null, picCn=ti95jJIJzXaf02YNe1UF2A==, picEn=cuGsq8KPhoqtfsQROuZvoQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1304509001228641229, language=CN, name=前瞻科技, nameHistory1=null, nameHistory2=null, managedBy=中国科学技术协会, sponsoredBy=科技导报社, publishedBy=科技导报社, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=包为民, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=《前瞻科技》是由中国科学技术协会主管,科技导报社主办、出版的科技智库型自然科学综合类学术期刊,于2022年创刊。办刊宗旨:紧扣国家科技创新需求,联合全国学会和科技智库机构,汇聚战略科学家、主流智库学者,通过提供战略性、前瞻性、权威性的思想观点和政策建议,为科技管理者和科研管理者供给高质量决策参考。, submitArticleUrl=null, websiteUrl=http://www.qianzhankeji.cn/CN/2097-0781/home.shtml, createdTime=1788948782498, updatedTime=1788948782498, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=http://www.qianzhankeji.cn/CN/column/column7.shtml, submissionAuthorUrl=https://qzkjauthor.cast.org.cn/webm/, submissionEditorUrl=https://qzkjeditor.cast.org.cn/webm/, submissionReviewUrl=https://qzkjauthor.cast.org.cn/webm/, submissionCeEditorUrl=https://qzkjeditor.cast.org.cn/webm/, submissionAeEditorUrl=https://qzkjeditor.cast.org.cn/webm/, option={"copyright":""}), JournalExt(id=1304509001270584270, language=EN, name=Science and Technology Foresight, nameHistory1=null, nameHistory2=null, managedBy=China Association for Science and Technology, sponsoredBy=Science and Technology Review Publishing House, publishedBy=Science and Technology Review Publishing House, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=BAO Weimin, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=Science and Technology Foresight is a comprehensive academic journal in natural sciences with a focus on technology think tanks. It is dedicated to publishing reviews and commentaries on research findings related to major national strategic tasks, important areas at the forefront of technology, and key core technologies and aims to promote academic exchange, advance technological progress, and support the high-quality development of China’s economy and society. The regular sections include “Foresight”, “Review and Commentary”, “Focus”, “Forum”, “Culture”, and “Book Review”. Specifically, “Foresight” and “Review and Commentary” are fixed sections, while the others are variable., submitArticleUrl=null, websiteUrl=http://www.qianzhankeji.cn/EN/2097-0781/home.shtml, createdTime=1788948782508, updatedTime=1788948782508, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=http://www.qianzhankeji.cn/EN/column/column7.shtml, submissionAuthorUrl=https://qzkjauthor.manuscriptcloud.com/login, submissionEditorUrl=https://qzkjeditor.manuscriptcloud.com/login, submissionReviewUrl=https://qzkjauthor.manuscriptcloud.com/login, submissionCeEditorUrl=https://qzkjeditor.manuscriptcloud.com/login, submissionAeEditorUrl=https://qzkjeditor.manuscriptcloud.com/login, option={"copyright":""})], databaseList=null, tenantJournalId=1146032081894723586, websiteList=[Website(id=1148243202353652128, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146032081894723586, 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/qzkjold/CN, language=CHT, createTime=1751692112768, createBy=18614031015, updateTime=1776048748052, updateBy=18614031015, name=《前瞻科技》中文站点, tplId=1146099689490845704, title=前瞻科技, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148618977242275853, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202353652128, code=articleTextType, value=kx, createTime=1751781704483, updateTime=1751781704483, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618977217110026, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202353652128, code=banner, value=null, createTime=1751781704477, updateTime=1751781704477, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618977204527113, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202353652128, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=skpCN5mVIzgEJbdUXu8/8A==, createTime=1751781704474, updateTime=1751781704474, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618977233887244, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202353652128, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751781704481, updateTime=1751781704481, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618977225498635, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202353652128, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751781704479, updateTime=1751781704479, creator=18614031015, updator=18614031015)]), Website(id=1155894377965830154, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146032081894723586, 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/qzkjold/EN, language=CHT, createTime=1753516295187, createBy=18614031015, updateTime=1776048768686, updateBy=18614031015, name=《前瞻科技》英文站点, tplId=1146101810881728533, title=Science and Technology Foresight, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155894740970233959, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155894377965830154, code=articleTextType, value=kx, createTime=1753516381733, updateTime=1753516381733, creator=18614031015, updator=18614031015), WebsiteProps(id=1155894740953456740, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155894377965830154, code=banner, value=null, createTime=1753516381729, updateTime=1753516381729, creator=18614031015, updator=18614031015), WebsiteProps(id=1155894740945068131, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155894377965830154, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=skpCN5mVIzgEJbdUXu8/8A==, createTime=1753516381727, updateTime=1753516381727, creator=18614031015, updator=18614031015), WebsiteProps(id=1155894740966039654, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155894377965830154, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753516381732, updateTime=1753516381732, creator=18614031015, updator=18614031015), WebsiteProps(id=1155894740961845349, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155894377965830154, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753516381731, updateTime=1753516381731, creator=18614031015, updator=18614031015)]), Website(id=1246151820205146149, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146032081894723586, 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/qzkj/CN, language=CN, createTime=1775035346323, createBy=18614031015, updateTime=1776149900371, updateBy=18614031015, name=《前瞻科技》中文站点最新, tplId=1246420490248675410, title=前瞻科技, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1246420037846848371, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1246151820205146149, code=articleTextType, value=kx, createTime=1775099294387, updateTime=1775099294387, creator=18614031015, updator=18614031015), WebsiteProps(id=1246420037825876848, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1246151820205146149, code=banner, value=null, createTime=1775099294382, updateTime=1775099294382, creator=18614031015, updator=18614031015), WebsiteProps(id=1246420037863625590, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1246151820205146149, code=grayFlag, value=0, createTime=1775099294391, updateTime=1775099294391, creator=18614031015, updator=18614031015), WebsiteProps(id=1246420037817488239, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1246151820205146149, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=skpCN5mVIzgEJbdUXu8/8A==, createTime=1775099294380, updateTime=1775099294380, creator=18614031015, updator=18614031015), WebsiteProps(id=1246420037876208504, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1246151820205146149, code=minRunFlag, value=0, createTime=1775099294394, updateTime=1775099294394, creator=18614031015, updator=18614031015), WebsiteProps(id=1246420037838459762, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1246151820205146149, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1775099294385, updateTime=1775099294385, creator=18614031015, updator=18614031015), WebsiteProps(id=1246420037872014199, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1246151820205146149, code=silenceFlag, value=0, createTime=1775099294393, updateTime=1775099294393, creator=18614031015, updator=18614031015), WebsiteProps(id=1246420037834265457, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1246151820205146149, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_qzkj_cn_319/, createTime=1775099294384, updateTime=1775099294384, creator=18614031015, updator=18614031015), WebsiteProps(id=1246420037851042676, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1246151820205146149, code=themeColor, value=null, createTime=1775099294388, updateTime=1775099294388, creator=18614031015, updator=18614031015), WebsiteProps(id=1246420037859431285, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1246151820205146149, code=themeStyle, value=null, createTime=1775099294390, updateTime=1775099294390, creator=18614031015, updator=18614031015)]), Website(id=1246404284338716725, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146032081894723586, 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/qzkj/EN, language=EN, createTime=1775095538466, createBy=18614031015, updateTime=1776333732508, updateBy=18614031015, name=《前瞻科技》英文站点最新, tplId=1246420682825945997, title=Science and Technology Foresight, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1246420311713931340, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1246404284338716725, code=articleTextType, value=kx, createTime=1775099359682, updateTime=1775099359682, creator=18614031015, updator=18614031015), WebsiteProps(id=1246420311692959817, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1246404284338716725, code=banner, value=null, createTime=1775099359677, updateTime=1775099359677, creator=18614031015, updator=18614031015), WebsiteProps(id=1246420311734902863, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1246404284338716725, code=grayFlag, value=0, createTime=1775099359687, updateTime=1775099359687, creator=18614031015, updator=18614031015), WebsiteProps(id=1246420311680376904, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1246404284338716725, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=skpCN5mVIzgEJbdUXu8/8A==, createTime=1775099359674, updateTime=1775099359674, creator=18614031015, updator=18614031015), WebsiteProps(id=1246420311747485777, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1246404284338716725, code=minRunFlag, value=0, createTime=1775099359690, updateTime=1775099359690, creator=18614031015, updator=18614031015), WebsiteProps(id=1246420311705542731, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1246404284338716725, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1775099359680, updateTime=1775099359680, creator=18614031015, updator=18614031015), WebsiteProps(id=1246420311739097168, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1246404284338716725, code=silenceFlag, value=0, createTime=1775099359688, updateTime=1775099359688, creator=18614031015, updator=18614031015), WebsiteProps(id=1246420311697154122, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1246404284338716725, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_qzkj_cn_319/, createTime=1775099359678, updateTime=1775099359678, creator=18614031015, updator=18614031015), WebsiteProps(id=1246420311718125645, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1246404284338716725, code=themeColor, value=null, createTime=1775099359683, updateTime=1775099359683, creator=18614031015, updator=18614031015), WebsiteProps(id=1246420311726514254, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1246404284338716725, code=themeStyle, value=null, createTime=1775099359685, updateTime=1775099359685, creator=18614031015, updator=18614031015)])], journalTitle=前瞻科技, weixinUrl=null, journalUrl=null, iacademicId=null, status=1, seqNo=null, journalTitleEn=Science and Technology Foresight, journalPhotoCn=ti95jJIJzXaf02YNe1UF2A==, journalPhotoEn=cuGsq8KPhoqtfsQROuZvoQ==, journalFirstLetter=Q, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/qzkj/CN/10.3981/j.issn.2097-0781.2022.04.005, detailUrlEn=https://castjournals.cast.org.cn/joweb/qzkj/EN/10.3981/j.issn.2097-0781.2022.04.005, pdfUrlCn=https://castjournals.cast.org.cn/joweb/qzkj/CN/PDF/10.3981/j.issn.2097-0781.2022.04.005, pdfUrlEn=https://castjournals.cast.org.cn/joweb/qzkj/EN/PDF/10.3981/j.issn.2097-0781.2022.04.005, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1671465600000, fullTextJson=null, articleText=null, reference=null)
收藏切换
复杂背景目标探测识别技术综述
收藏切换
PDF下载
崔得东 1, 2 , 冯涛 1, 2 , 白昆 1, 2 , 杨挺 2 , 马龙 1, 2 , 尚毅 2
前瞻科技 | 综述与述评 2022,1(4): 69-80
收起
收藏切换
前瞻科技 | 综述与述评 2022, 1(4): 69-80
复杂背景目标探测识别技术综述
全屏
崔得东1, 2 , 冯涛1, 2, 白昆1, 2, 杨挺2, 马龙1, 2, 尚毅2
作者信息
  • 1.西安现代控制技术研究所,西安 710065
  • 2.西安导引科技有限责任公司,西安 710065
  • 崔得东,研究员,中国兵器科技带头人,国务院政府特殊津贴专家。主要研究方向为智能化弹药导引技术。担任国家重点型号项目副总设计师。获国家科学技术进步奖一等奖1项,国防科学技术进步奖二等奖、省部级科学技术进步奖二等奖4项。出版专著1部,发表论文10余篇,获授权国防发明专利11项、新型实用专利1项。电子信箱:

通信作者:

Overview of Target Detection and Recognition Technology in Complex Background
Dedong CUI1, 2 , Tao FENG1, 2, Kun BAI1, 2, Ting YANG2, Long MA1, 2, Yi SHANG2
Affiliations
  • 1. Xi’an Modern Control Technology Research Institute, Xi’an 710065, China
  • 2. Xi’an Guidance Technology Co., Ltd., Xi’an 710065, China
出版时间: 2022-12-20 doi: 10.3981/j.issn.2097-0781.2022.04.005
文章导航
收藏切换

目标探测识别技术是图像信息处理技术的热门研究领域,面向陆战场复杂背景条件的目标探测识别技术如何成熟应用更是该领域亟待解决的痛点问题。文章介绍了陆战场复杂背景条件下影响目标探测识别性能的主要因素;分析了陆战场目标背景的复杂性、多样性和不确定性;回顾了国内外目标识别技术的发展历程;阐述了陆战场复杂背景目标探测识别的关键技术,包括多波段复合探测技术、目标自主识别技术、弱小目标检测识别技术、多通道异构信息融合技术;展望了陆战场目标探测识别技术的发展趋势。

陆战场  /  复杂背景  /  目标探测识别

Target detection and recognition technology is a popular research field in image information processing technology. How to maturely apply this technology to land battlefields with complex backgrounds is an urgent pain point to be resolved. This paper first introduces the main factors affecting the performance of target detection and recognition under complex background conditions of land battlefields and analyzes the complexity, diversity, and uncertainty of the target background of land battlefields. Then, it reviews the research status of target recognition algorithms. Furthermore, it expounds on the key technologies of target detection and recognition under complex backgrounds, including multispectral complex target detection, automatic target recognition, dim and small target detection, and multi-channel heterogeneous information fusion. Finally, this paper predicts the tendencies of target detection and recognition technology in land battlefields.

land battlefield  /  complex background  /  target detection and recognition
崔得东, 冯涛, 白昆, 杨挺, 马龙, 尚毅. 复杂背景目标探测识别技术综述. 前瞻科技, 2022 , 1 (4) : 69 -80 . DOI: 10.3981/j.issn.2097-0781.2022.04.005
Dedong CUI, Tao FENG, Kun BAI, Ting YANG, Long MA, Yi SHANG. Overview of Target Detection and Recognition Technology in Complex Background[J]. Science and Technology Foresight, 2022 , 1 (4) : 69 -80 . DOI: 10.3981/j.issn.2097-0781.2022.04.005
现代战场涉及陆、海、空、天、电磁和网络等多个维度。其中,陆战场是传统、典型的战场形式,但是在现代信息化战争条件下面临着新的巨大挑战。如何在复杂背景条件下探测并识别出各类战术目标就是挑战之一,而提高陆战场复杂背景条件下的目标探测识别技术能力是现代陆战场制胜的关键。文章主要针对陆战场目标背景的特点,对地目标探测识别技术的发展现状、关键技术、典型算法,以及未来技术发展的方向进行论述。
目标是指交战双方为实现某种作战意图,彼此进行跟踪、打击、压制、攻占或摧毁的对象[1]。陆战目标一般包括敌我双方参与作战的直升机、坦克、车辆、技术装备、来袭导弹、作战机器人、各类作战工事、指挥所、部队甚至人员等。成像制导是陆战精确制导武器的主要制导方式之一,广泛应用于多种类型的导弹、炮弹、火箭、炸弹和巡飞弹等武器装备。目标探测识别是成像制导首先需要解决的问题,即将目标从包含背景信息的探测图像中标识出来,然后对目标进行跟踪,并输出相应的制导信息至武器装备。相对来讲,陆战场存在地形地物复杂、目标类型多样、伪装/干扰方式众多、多波次打击以及场景不定等目标背景特点,这些陆战场的复杂性、多样性、不确定性特点会极大影响目标探测识别性能。成像探测技术是陆战场复杂背景目标探测的主要形式,除常见的可见光成像和红外成像之外,还存在射频波段的合成孔径雷达(Synthetic Aperture Radar, SAR)成像技术、激光波段的激光雷达成像技术等。限于篇幅,文章将主要介绍可见光和红外波段陆战场复杂目标背景的特点。
陆战场影响目标探测识别因素复杂繁多,根据影响要素类型的不同,主要可分为背景、目标、大气和成像传感器4类。其中,背景类相关的因素包括总体概况、位置、周边环境、地表类型、地表状况及干湿度、地表温度、植被类型、植被状况及干湿度、非目标类人造物及目标伪装、日出日落时间和日期等;目标类相关的因素包括目标类型、工作状况、表面温度、姿态、造型、伪装、动力学特性、探测瞄准角度、视线动态和平台振动等;大气类相关的因素包括气温、相对湿度、露点、气溶胶、大气压、降水、风速、能见度、太阳辐射、大气传输、云层和太阳角等;成像传感器类相关的因素包括类型、扫描方式、增益、偏置、动态范围、漂移率、最小可分辨温差、调制传递函数、失真、斑点、扫描(凝)视场和瞬时视场等。
1)目标的多样性
陆战场目标种类多样,如存在坦克、装甲车、移动车辆、建筑工事等多种类型的目标。每类作战目标类内差异巨大,如不同作战用途的车辆目标差异较大,工事类目标也不存在较好的一致性。
2)背景的多样性
在陆战场光学图像制导中,绝大多数探测采集的图像中大部分区域都是背景。因此,研究陆战场背景对陆战场复杂目标探测识别也非常重要。陆战场目标探测背景主要受探测位置、周边环境、地表类型、干湿度、温度、日期和时间等相关因素的影响。探测位置主要指目标背景所处的经纬度;周边环境主要指非目标类人造物;地表类型主要包括戈壁、沙漠、高原、草原等;干湿度和温度主要对红外图像有较大影响;太阳高度角与日期、时间和经纬度等因素相关,即不同太阳高度角目标与背景的阴影不同。综上所述,在考虑陆战场复杂目标探测问题时,背景呈现出多样性特征。
3)干扰的多样性
除了目标和背景呈现出多样性特征之外,陆战场针对图像制导的干扰模式也是多样的,主要有作战平台释放的烟幕干扰弹、干扰机、伪装、烟雾等。
陆战场中存在着大量与时间和环境变量相关的因素,这些因素使目标和背景具有不确定性。在战场环境条件下,目标会随着战术机动、隐蔽防护变化,天气天候状况、日照光线条件、战场烟幕尘烟、目标运动尾迹等也随时发生变化。总体来讲,陆战场的不确定性特性可以分为多波次打击和目标特性时间敏感两类。
1)多波次打击
短时多波次打击是陆战场的一个主要特征,打击区域在经过打击后,无论是目标特性还是背景环境特性都会发生改变。这种情况下,精确打击系统预装订的目标模板或者区域遥感图像都与打击区域有较大不同。多波次打击后,区域内的目标或场景变化均是不确定的,无法通过预装订的模板进行匹配。因此,多波次打击会给陆战场的复杂目标探测识别带来不确定性。
2)目标特性时间敏感
目标特性时间敏感是指在不同的“攻击窗口”或者“交战机会”下,目标呈现出不同的特性。陆战场的目标特性时间敏感主要由两类因素造成:一类是指陆战场目标的高机动性,如坦克、装甲车、低空直升机等,其高机动性会为陆战场目标探测识别带来极大的不确定性;另一类是指静止目标特性受时间影响也较大,例如冬至日不同时段目标的阴影特性变化剧烈。
综上所述,陆战场存在复杂性、多样性和不确定性的特性,相同尺寸、相同分辨率的图像往往拥有更高的信息熵。因此,相比于海空等场景,陆战场图像目标识别算法需要处理更多的信息以实现目标的甄别,这给陆战场目标探测识别的算力资源、算法模型复杂度等多方面带来了巨大挑战。
自动目标识别领域的研究始于20世纪60年代初期,在神经网络和自组织系统的理论和实践方面掀起了第一次研究的高潮。研究工作主要集中于完成某些特定功能的算法,包括特定类型目标的检测、分割、分类等,大部分研究利用统计模式识别、非参数化分类、神经网络和启发性技术等方法,提取图像中的具体特征,并利用这些特征与被认定目标的先验特征进行关联计算来实现目标识别。
这个时期自动目标识别算法的研究主要有:①与更有效的启发性特征提取算法相结合的统计模式识别研究;②图像处理相关的数学形态和图像代数方法研究;③综合诸如知识系统、世界模型、模糊推理等实用概念的人工智能研究;④新的神经网络研究和开发,包括调整参数的网络结构和训练技术。
此后,随着计算机设备、体系结构和软件技术的进步,更多单位开始基于图像处理和机器视觉方面的研究成果开发自动目标识别算法。这一时期的自动目标识别算法技术在20世纪70年代开始走向成熟,并在实际的防务系统中发挥了重要的作用。这一时期的目标识别算法分为3个步骤:区域建议、特征提取、分类回归。区域建议是通过不同尺度的滑动窗口对图像进行多次遍历得到感兴趣目标可能存在的区域,即候选区域;特征提取是使用人工特征抽取方式把候选区域中的图像转换为特征向量,常用方法包括局部二值模式特征、梯度直方图特征等;分类回归是用预训练的分类器预测候选区中目标的类别。其中,具有代表性的目标识别方法主要有:①基于目标不变矩的目标识别方法;②基于传统神经网络的目标识别方法;③基于图像模板匹配的目标识别方法;④基于机器学习分类器的目标识别方法。
基于目标不变矩的目标识别方法有基于Hu矩的目标识别方法、基于Zernike矩的目标识别方法[2-5]。基于传统神经网络的目标识别算法,最为典型的是基于反向传播(Back Propagation, BP)神经网络的目标识别算法[5-8]。基于图像模板匹配的目标识别方法主要采用目标图像灰度、边缘等信息模板实现目标模板匹配识别[9-11]。基于机器学习分类器的目标识别方法主要依靠支持向量机(Support Vector Machine, SVM)、自适应增强(Adaptive Boosting, AdaBoost)等分类器完成目标识别[12-17]
基于深度学习的目标识别算法兴起于2014年,以基于区域的卷积神经网络(Region-based Convolutional Neural Networks, R-CNN)算法[18,19]的提出为开端,先后涌现出了基于区域的快速卷积神经网络(Fast Region-based Convolutional Neural Networks, Fast R-CNN)算法[20]、Faster R-CNN算法[21]、空间金字塔池化网络(Spatial Pyramid Pooling Network, SPPNet)算法 [22]、单步多框目标检测(Sin-gle Shot MultiBox Detector, SSD)算法[23]和YOLO(You Only Look Once)系列[24-29]算法等。这些算法可以根据其是否有区域建议模块分为两类:两阶段(Two-stage)目标识别算法和一阶段(One-stage)目标识别算法。两阶段目标识别算法又称为基于区域建议的目标识别算法,通过显式的区域建议将识别问题转化为对生成的建议区域内的局部图片的分类问题。这类算法在第1阶段生成区域建议,在第2阶段对感兴趣区域中的内容进行分类和回归。代表性算法有Fast R-CNN、Faster R-CNN、SPPNet算法等。一阶段目标识别算法又称为基于回归的目标识别算法,该算法不直接生成感兴趣区域,而是将目标识别任务看作对整幅图像的回归任务。代表的算法有YOLO系列和SSD算法等。2020年,随着Transformer编解码在计算机视觉领域大放异彩,研究人员利用Transformer构建端到端的目标识别方法,其中最具代表性的算法为DETR(Detection Transformer)[30],其将目标检测问题转化为图像中所有目标集合的预测问题[31,32]。DETR不再需要人工先验知识输入,完全从训练集中完成目标特征的学习,能够更加鲁棒地描述目标特征,其采用端到端的训练方式,极大地简化了目标检测识别算法流程框架,能够便捷地在任何包含Transformer和CNN的深度框架中实现。
国内研究机构前期主要跟随国外研究成果进行算法能力提升和弹载化应用研究,如国防科技大学自动目标识别国防科技重点实验室和华中科技大学图像识别与人工智能研究所都独立自主开发了基于模板匹配的目标识别算法[10,11],并在对地目标识别方面取得了较好的成果。近年来,国内开始在深度目标检测技术方面,特别是在一阶段目标识别技术和端到端目标识别技术方面持续发力,已取得了与国外水平相当的研究成果。当前国内高水平研究工作,如发表在电气与电子工程师协会举办的国际计算机视觉与模式识别会议(IEEE Conference on Computer Vision and Pattern Recognition, CVPR)上的论文数量方面存在一定的优势,但是在代表性工作方面相对欠缺,存在较大的发展与提升空间。目前,国内在目标识别方向具有代表性的研究机构包括清华大学、中国科学院、香港中文大学、商汤科技、旷视科技和华为等。此外,国内诸多研究所基于弹载平台开展了大量的深度学习目标识别模型弹载轻量化研究,支撑了对地制导武器装备的智能化发展。
目标识别算法的嵌入式平台主要经历了微处理器(Microprocessor Unit, MPU)、数字信号处理器(Digital Signal Processor, DSP)、现场可编程逻辑门阵列(Field Programmable Gate Array, FPGA)芯片及嵌入式神经网络处理器(Neural-network Processing Unit, NPU)芯片4个时期。早期的研究人员主要是依靠MPU实现目标识别算法,这一阶段芯片的计算能力、存储大小及硬件体系架构限制了目标识别算法的开发和应用。20世纪80年代后期,随着DSP芯片的成熟,计算性能的提高极大地促进了目标自动识别技术的发展,特别是德州仪器(Texas Instruments, TI)的TMS320C64xx系列和TMS320C66xx系列问世以来,大量的研究机构都基于这些芯片开发了基于模板匹配的目标识别算法和基于模式分类的目标识别算法。近年来,高性能FPGA芯片的问世,特别是赛灵思(Xilinx)的ZYNC XC7X+系列,其数据并行处理能力的大幅度提升和内部配备的更灵活的先进微处理器(Advanced RISC Machine, ARM)核心,极大地推动了深度学习目标识别算法的嵌入式平台轻量化移植。随着采用“数据驱动并行计算”的架构和更先进的半导体工艺技术制造的NPU逐渐成熟,目标识别嵌入式平台进入到快速发展阶段。NPU凭借着高性能、小型化、低功耗、低成本和易部署的优势已经成为目标识别嵌入式平台的绝对核心,尤其是在弹载化目标识别方面更是拥有不可替代的地位。
国内前期高速信号处理电路开发工作主要跟随国际主流芯片的发展,如TI公司的各类DSP芯片,美国超威半导体公司(AMD)和英特尔公司的各型FPGA等,在此基础上开发相应的算法软件。近年来,中国加速了核心关键器件的国产化研制工作,并在部分型号任务中得到了相关的应用验证,如国防科技大学的飞腾DSP FT6678系列和复旦微电子的FPGA A7、K7、Z7、V7等系列。此外,中国的智能芯片发展迅速,形成了各种国产化的NPU芯片,如瑞芯微电子RK1808、华为海思Hi3559AV100等,并在目标识别应用中得到了大量的验证。
多波段复合探测包括双波段复合探测及两个以上波段复合探测形式。其中,双波段探测有图像/激光复合、图像/雷达复合、激光/雷达复合探测等,两个以上波段复合探测形式在对陆领域,特别是在弹药制导领域,主要指的是三模复合探测,即激光/图像/雷达三模复合探测技术。
多波段复合探测技术通过采集多个波段或体制下的目标同背景的信息,发挥各波段的优势,扬长避短,是陆战场复杂背景目标探测发展的方向。
与单一制导体制相比,多波段复合探测技术具有较多的优势,归纳起来,主要表现在以下几方面。①可以获取更多的目标信息,提高探测目标和捕获目标的能力。多波段复合探测利用不同的体制和不同的波段激励、捕获目标信息,并进行信息融合处理,可以获得更加准确的目标数据。②具有较强的抗干扰能力。当一种体制或工作模式受到干扰或受到欺骗时,另一种体制或工作模式可以接续探测,增强了目标探测的抗干扰能力。③具有较强的反隐身能力。目前的隐身目标基本上都是在典型波段上达到隐身效果,比如降低微波、毫米波的雷达截面积(Radar Cross Section, RCS)和发动机的红外辐射能量等,较难做到全波段隐身。因此,不同体制、不同波段的复合形式对于探测、跟踪隐身目标具有较大的优势。④具有较强的气候适应能力。红外成像探测能够在夜间工作,但在高温、高湿、能见度较差的天气中性能会急剧下降,而电视成像探测则在这方面具有优势。不同波长的电磁波大气穿透能力不同,不同波段的复合便能增强对恶劣气象条件的适应能力,尤其是微波与光波复合后优势更为突出。⑤具有更广泛目标类型探测能力。该技术能够适应多目标探测的需要,提高了应用的灵活性。与单一波段、体制相比,多波段复合探测技术更具优势,更能适应未来复杂多变的陆战场环境。
多波段复合探测技术有复合探测总体、多波段复合系统、小型化轻量化结构设计、多源异构信息融合处理等,其中多波段复合系统是多模复合探测的关键核心技术。复合探测的波段复合形式可以分为分口径和共口径两种,其中分口径复合方式可以共用同一平台,也可以不共用同一平台,共口径复合探测系统集成难度更高。多波段复合探测技术在弹载平台上的应用如精确制导,则更具有挑战性。弹载复合探测系统的设计,不仅要考虑不同波段的相容性,而且要考虑结构尺寸、体积、重量、功耗、散热、复杂电磁环境以及成本的约束,需要突破高效复合集能器、高性能透反材料等技术,以解决多波段口面竞争问题。激光/毫米波/红外三模复合制导是未来制导技术研究的重点方向,最具有代表性的就是美国的“联合通用导弹”(Joint Common Missile, JCM)及其后续研究成果“联合空地导弹”(Joint Air-to-Ground Missile, JAGM)。JAGM采用主动毫米波/红外成像/半主动激光三模复合导引头,如图1(a)所示。该导引头的复合探测系统(图1(b))采用双圆极化、双通道单脉冲天线,包括4个双极化缝隙波导子阵列,并围成1个孔径,天线中心的这个通孔作为激光和红外的通路,充分利用了有限空间,同时获得良好的多波段复合效果。
目标表征技术是目标探测识别技术的关键前提。目标表征技术完成对目标的局部或者全局特征的表示表达,从而实现目标检测识别。目标表征技术主要可分为传统目标表征技术和基于深度学习的目标表征技术。目标表征技术的发展里程碑如图2所示。
传统目标表征技术主要应用于基于机器学习分类器的目标识别方法,具体流程如图3所示。该技术利用人工设计的算法完成图像的特征提取,如Haar、LBP、HOG、尺度不变特征变换(Scale-invariant Feature Transform, SIFT)特征、DPM算法等,然后利用机器学习分类器对特征进行分类,如SVM、AdaBoost、决策树等,完成目标的识别。具有代表性的方法主要有:基于Haar特征和AdaBoost分类器的Viola-Jones人脸识别、基于HOG特征和SVM分类器的行人识别、基于DPM特征和SVM分类器的物体检测算法。典型的传统目标表征技术的优缺点如表1所示。
深度卷积神经网络(Convolutional Neural Network, CNN)被广泛应用于图像表征的学习。CNN是受仿生学中的视觉神经系统启发而设计的人工神经网络结构,其中的卷积核为神经网络的权值,通过对不同图像子区域(局部感受野)使用共享权值的策略进行线性加权,并使用非线性激活函数、池化(Pooling)与采样操作等多层次的处理实现非线性的函数映射。一般认为,一个足够复杂的神经网络可以模拟任意形式的函数映射,因此在有足够的观测样本情况下,可以预期实现对图像内容的良好表征。
卷积神经网络在人工神经网络的基础上引入了卷积运算和采样操作,使得所提取的特征具有某种程度的空间不变性,因此具有更好的识别性能。卷积神经网络模型主要由输入层、卷积层、采样层、全连接层和输出层等构成,其本质上与传统目标检测模型相似,通过大数据学习样本对网络参数进行训练。卷积神经网络的参数更新过程可被看作表征学习与任务学习联合优化的过程。在网络训练过程中,参数更新的范围不仅包括最后的感知机参数,也包括往前直到第1层的所有网络参数,从而实现表征与目标分类的联合优化。
在陆战场弹载化应用中,目标自主识别技术需要解决两方面的问题:一是基于深度学习的目标自主识别算法相较于传统算法需要消耗较高的计算资源,需将现有深度学习模型实时高效地部署在对功耗和体积都有严格要求的弹载制导平台上;二是由于军事需求应用的特殊性,研究人员难以获取大量、准确的训练数据用于目标模型学习,在实际应用中通常采用模型微调、数据增强和迁移学习3种方式对样本数据进行增广。
随着网络模型压缩技术和人工智能(Artificial Intelligence, AI)芯片计算平台的快速革新,在轻量化网络模型和AI芯片的助力下,目标自主识别技术弹载化得以高速发展,精确性、实时性、功耗、体积和成本等制导武器指标需求均能得到满足。
基于模型微调的方法首先在含有大量数据的原数据集上训练一个分类模型,然后在含有少量数据的目标数据集上对模型进行微调。由于少量数据并不能很好地反映大量数据的真实分布情况,因此这种做法可能导致模型过拟合。基于数据增强的方法是利用辅助数据集或者辅助信息,增强目标数据集中样本的特征或扩充目标数据集,使模型能更好地提取特征。根据学习方法的不同,可将基于数据增强的小样本学习方法进一步细分为基于无标签数据、基于数据合成、基于特征增强3类方法。基于迁移学习的方法是目前比较前沿的方法,该方法是指将已经学会的知识迁移到一个新的领域中。基于迁移学习的方法细分为基于度量学习、基于元学习和基于图神经网络(Graph Neural Network, GNN)的方法。在度量学习的框架下,目前已有许多性能较好的小样本学习模型,例如比较著名的原型网络(Prototypical Network)和匹配网络(Matching Network)等。基于元学习的方法不仅在目标任务上训练模型,并且从许多不同的任务中学习元知识,当一个新的任务到来时,利用元知识调整模型参数,使模型能够快速收敛。近年来,随着图神经网络的兴起,图神经网络也被广泛应用到小样本学习中。
陆战场目标检测识别需尽量在较远的距离下完成,以保证自身平台的安全。因此,高性能的远距离弱小目标检测识别需求是相对于其他应用差异较大的地方。对于典型分辨率为640×512像素的探测系统来讲,当目标小于7×7像素时,就可认为是小目标;目标在图像中信噪比低于4时,即可认为是弱目标。这两个主要特性导致算法无法有效利用目标形状、尺寸、纹理等特征进行目标检测识别。针对陆战场弱小目标检测识别的技术难点,通常采用特征增强、引入上下文信息、锚点框设计、数据扩充、提高定位精度、尺度自适应检测等一系列措施对深度学习网络进行修正。
由于自然环境或人为干扰的影响,仅依靠单一波段的成像技术往往不足以获得目标的全面信息。目前主要依靠多通道多波段信息融合技术采集更高维度的目标特征信息,通过对高维数据进行融合处理,解决人工干扰或恶劣天候干扰对目标检测识别性能的影响。
像素级融合是在直接采集数据的层面上进行信息融合,其特点是融合后的图像可给予观察者更快捷、直观和全面的认识,也更适合机器进一步处理和分析;特征级融合是对边缘、纹理等信息进行综合处理,其特点是可对信息进行压缩处理,便于实时化处理;决策级融合利用对信息的处理结果进行数据集成,以一定准则及信息处理结果的可信度做出最优决策,其特点是实时性高、容错能力强。为保证全部图像信息在深度学习网络中的无损传递,减少人工设计特征提取算法和融合策略对数据的损耗,需采用像素级融合的思路设计深度学习模型,实现多波段、多通道信息的融合。
图4为典型的基于深度学习的多波段图像融合模型结构。密集连接卷积神经网络(Densely Connected Convolutional Networks, DenseNet)用于融合不同波段的图像,特征提取器用于提取图像的浅层、深层特征。特征提取器使用预训练的VGG-16网络模型,如图5所示。VGG-16的输入被统一为单通道,然后复制为三通道并送入网络。网络中每个池化层的前一卷积层输出的特征图作为后续信息度量的输入。前两层的输出特征图是浅层特征,只突出了纹理和形状细节。第4、5层特征图保留了更多的深层特征。因此,结合浅层信息和深层信息可以更有效地表示人类视觉不容易感知的有效信息。信息度量利用特征的梯度来度量信息。信息保护度代表保留源图像中的信息的程度,为信息保护度分配两个自适应权重,其定义融合图像与源图像之间相似性的权重,更高的权重代表更高的相似性,即源图像更多信息被保留。损失函数主要用于度量融合后图像与各波段图像的相似性损失。
随着大规模集成电路的不断发展和目标识别跟踪算法性能的稳固提升,目标探测识别跟踪一体化技术已成为行业发展方向。目标探测识别一体化技术是指图像传感器和目标识别算法的硬件平台共用,其优势是弹载图像探测识别跟踪系统体积更小、功耗更低、成本更低、可靠性更高。由于探测端和信息处理端耦合更加紧密,可以最大限度地保持有效信息,提高目标识别跟踪能力。此外,目标探测识别一体化技术可以有效去除探测系统和信息处理系统的硬件资源冗余,实现武器系统低成本设计和小型化设计,能够更好应用于微型武器系统和蜂群作战平台。
近年来,在大数据、高性能计算等技术支撑下,以深度学习为代表的目标识别方法很好地解决了“目标在图像什么位置”和“目标是什么”等感知智能问题。而对于“目标在干什么”“目标的关键重点部位在哪里”“目标对我方的威胁度如何”等认知智能的需求,即更进一步的逻辑及认知推理,却还远远无法满足。2015年以来,美国军方陆续提出了“多域战”“全域战”的概念,其核心为“跨域协同增效”,强调多域作战能力的一体化。而全域战场态势感知,则是实现“一体化”的基础,也是支撑作战人员把握全局、破网断链、体系对抗及联合制胜的重要保证。态势感知是指对一定时间和空间内的态势要素进行感知,并对获得的信息进行理解,进而形成对这些态势要素下一时刻状态的预测。态势感知可分为察觉、理解、预测3个层次,如图6所示。
目标识别,作为一项面向探测预警、情报侦察、态势感知、精确制导等多个军事应用领域的关键使能技术,以人工智能为技术手段,能够解决战场自动目标识别的关键问题,是打赢未来智能化战争的重要手段之一。目标识别主要应用于察觉层次,用于获取环境中的态势要素,包括相关态势要素的状态、属性及动向。例如,区域内所有关于敌我双方位置、类型、数量、作战能力及动态方面的精确信息,并掌握各方之间的关系。智能目标识别可将人从生理极限中解放出来,基于自主学习、智能推理、在线升级等技术优势,综合不同数据来源,提升数据处理和数据挖掘效率,缩短观察、判断、决策、行动环的反应时间,减少战场态势感知的不确定性,在智能决策、指挥协同、情报分析以及电磁网络攻防等关键作战领域发挥作用。
群体智能感知和协同智能感知也是一个重要的研究方向。实战环境下敌方高价值目标通常以编队形式出现,具备较强的体系化综合防御、攻击能力。在“弹群”攻击模式下,开展多弹间智能交互与协同智能感知处理技术研究,实现群体的分布式智能化协作,以及“弹群集体智慧决策”,是目标智能化识别与检测的重要方向。目前美国在研的“主宰者”(Dominator)和“洛卡斯”(Low Cost Autonomous Attack System, LOCAAS)巡飞弹装配低性能传感器和简易程序,通过多批次、大规模巡飞弹协同,完成目标侦察和攻击。虽然武器单体不具备较强的探测能力,但若群体最前端的巡飞弹实现近距离探测目标,便可立刻将探测到的信息数据传递给身后的巡飞弹,巡飞弹就会对目标实行群组攻击。这些巡飞弹组成的探测网络构成立体的战场态势感知系统,实现目标的自主探测,支撑指挥、控制、通信、计算机、杀伤、情报、监视侦察(Command, Control, Communications, Computer, Kill, Intelligence, Surveillance, Reconnaissance, C4KISR)系统架构,可以提高弹药整体的作战效能。
伴随着高性能计算机的快速发展和各种识别算法的工程化应用,目标识别算法正在民用和军用的各个领域呈现规模化的发展态势。虽然陆战场的环境条件非常复杂,但是在大数据和人工智能技术的加持下,复杂背景条件下的目标识别技术终究会取得重大突破。弹群协同、集群式联合探测、复合探测、仿生探测、自动感知、信息融合、自主识别、分布式计算等技术将会是目标探测识别的主要发展趋势,未来陆战场的作战装备自动化、智能化、无人化的进度也会大幅加速,更多、更先进的智能陆战武器系统也会逐渐加速实战化。
参考文献 引证文献
排序方式:
[1]
陈健, 王永明, 赵革, 等. 舰船目标特性研究综述[J]. 舰船电子工程, 2008, 28(5): 17-21.
[2]
刘进, 张天序. 不变矩构造方法的研究[J]. 华中科技大学学报(自然科学版), 2003, 31(3): 1-3.
[3]
张天序, 刘进. 不变矩稳定性及基于多级特征模型的目标识别研究[J]. 计算机学报, 2004, 27(10): 1335-1340.
[4]
张天序, 曹杨, 刘进, 等. 基于不变矩的前视红外图像机场目标识别[J]. 华中科技大学学报(自然科学版), 2007, 35(1): 17-19.
[5]
孙红辉, 王红霞, 田涛. 一种基于不变矩和BP网络的目标识别方法[J]. 微电子学与计算机, 2011, 28(3): 63-65.
[6]
Tabb K, Davey N, Adams R, et al. The recognition and analysis of animate objects using neural networks and active contour models[J]. Neurocomputing, 2002, 43(1-4): 145-172.
[7]
桑农, 唐红卫, 曹治国, 等. 基于Gabor滤波器组和特征分组神经网络目标识别[J]. 华中科技大学学报(自然科学版), 2003, 31(11): 47-49.
[8]
杨福平, 白振兴. BP神经网络和D-S证据理论的目标识别[J]. 火力与指挥控制, 2006, 31(10): 88-90.
[9]
Bobick A F, Davis J W. The recognition of human movement using temporal templates[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(3): 257-267.
[10]
牛照东, 许旻, 王卫华, 等. 一种利用层次化模板匹配的地面建筑红外图像自动识别方法[C]// 第十三届全国信号处理学术年会(CCSP-2007)论文集. 北京: 中国仪器仪表学会, 中国电子学会, 2007: 179-182.
[11]
张义广, 冯志高, 张天序, 等. 基于可见光图像模板匹配的目标识别算法[J]. 激光与红外, 2007, 37(12): 1322-1324.
[12]
Han F, Shan Y, Cekander R, et al. A two-stage approach to people and vehicle detection with HOG-based SVM[C]// Performance Metrics for Intelligent Systems 2006 Workshop. 2006: 133-140.
[13]
Li X, Guo X S. A HOG feature and SVM based method for forward vehicle detection with single camera[C]// 2013 5th International Conference on Intelligent Human-Machine Systems and Cybernetics. Piscataway: IEEE Press, 2013: 263-266.
[14]
Pang Y W, Yuan Y, Li X L, et al. Efficient HOG human detection[J]. Signal Processing, 2011, 91(4): 773-781.
[15]
Viola P, Jones M. Rapid object detection using a boosted cascade of simple features[C]// Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2001, 1: 511-518.
[16]
Yang M, Crenshaw J, Augustine B, et al. AdaBoost-based face detection for embedded systems[J]. Computer Vision and Image Understanding, 2010, 114(11): 1116-1125.
[17]
Padilla R, Filho Costa C F F, Costa M G F. Evaluation of haar cascade classifiers designed for face detection[J]. International Journal of Computer, Electrical, Automation, Control and Information Engineering, 2012, 6(4): 466-469.
[18]
Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]// 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2014: 580-587.
[19]
Sultana F, Sufian A, Dutta P. A review of object detection models based on convolutional neural network[M]// Advances in Intelligent Systems and Computing. Singapore: Springer Singapore, 2020: 1-16.
[20]
Girshick R. Fast R-CNN[C]// 2015 IEEE International Conference on Computer Vision. Piscataway: IEEE Press, 2005: 1440-1448.
[21]
Ren S Q, He K M, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[22]
Purkait P, Zhao C, Zach C. SPP-net: Deep absolute pose regression with synthetic views[DB/OL]. arXiv Preprint: 1712.03452, 2017.
[23]
Liu W, Anguelov D, Erhan D, et al. SSD: Single shot MultiBox detector[C]// Computer Vision-ECCV 2016. Cham: Springer International Publishing, 2016: 21-37.
[24]
Arya M C, Rawat A. A review on YOLO (You Look Only One): An algorithm for real time object detection[J]. International Journal of Engineering Science 2020, 11: 554-557.
[25]
Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detection[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2016: 779-788.
[26]
Redmon J, Farhadi A. YOLO9000: Better, faster, stronger[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2017: 6517-6525.
[27]
Redmon J, Farhadi A. YOLOv3: An incremental improvement[DB/OL]. arXiv Preprint: 1804.02767, 2018.
[28]
Bochkovskiy A, Wang C Y, Liao H Y M. YOLOv4: Optimal speed and accuracy of object detection[DB/OL]. arXiv Preprint: 2004.10934, 2004.
[29]
Adarsh P, Rathi P, Kumar M. YOLOv3-tiny: Object Detection and Recognition using one stage improved model[C]// 2020 6th International Conference on Advanced Computing and Communication Systems (ICACCS). Piscataway:IEEE Press, 2020: 687-694.
[30]
Carion N, Massa F, Synnaeve G, et al. End-to-end object detection with transformers[C]// Computer Vision-ECCV 2020. Cham: Springer International Publishing, 2020: 213-229.
[31]
Stewart R, Andriluka M, Ng A Y. End-to-end people detection in crowded scenes[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2016: 2325-2333.
[32]
Hosang J, Benenson R, Schiele B. Learning non-maximum suppression[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2017: 6469-6477.
2022年第1卷第4期
PDF下载
3016
1564
引用本文
BibTeX
文章信息
doi: 10.3981/j.issn.2097-0781.2022.04.005
  • 接收时间:2022-10-24
  • 出版时间:2022-12-20
  • 发布时间:2023-01-17
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2022-10-24
  • 修回日期:2022-11-03
基金
作者信息
    1.西安现代控制技术研究所,西安 710065
    2.西安导引科技有限责任公司,西安 710065

通讯作者:

参考文献
分享链接
https://castjournals.cast.org.cn/joweb/qzkj/CN/10.3981/j.issn.2097-0781.2022.04.005
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
表12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