区域建议网络快速目标检测中一种新的多尺度特征融合方法

IF 0.5 4区 计算机科学 Q4 COMPUTER SCIENCE, SOFTWARE ENGINEERING International Journal of Data Warehousing and Mining Pub Date : 2020-07-01 DOI:10.4018/ijdwm.2020070107
Gang Liu, Chuyi Wang
{"title":"区域建议网络快速目标检测中一种新的多尺度特征融合方法","authors":"Gang Liu, Chuyi Wang","doi":"10.4018/ijdwm.2020070107","DOIUrl":null,"url":null,"abstract":"Neuralnetworkmodelshavebeenwidelyusedinthefieldofobjectdetecting.Theregionproposal methodsarewidelyusedinthecurrentobjectdetectionnetworksandhaveachievedwellperformance. Thecommonregionproposalmethodshunttheobjectsbygeneratingthousandsofthecandidate boxes.Compared toother regionproposalmethods, the regionproposalnetwork (RPN)method improvestheaccuracyanddetectionspeedwithseveralhundredcandidateboxes.However,sincethe featuremapscontainsinsufficientinformation,theabilityofRPNtodetectandlocatesmall-sized objectsispoor.Anovelmulti-scalefeaturefusionmethodforregionproposalnetworktosolvethe aboveproblemsisproposedinthisarticle.Theproposedmethodiscalledmulti-scaleregionproposal network(MS-RPN)whichcangeneratesuitablefeaturemapsfortheregionproposalnetwork.In MS-RPN,theselectedfeaturemapsatmultiplescalesarefineturnedrespectivelyandcompressed intoauniformspace.Thegeneratedfusionfeaturemapsarecalledrefinedfusionfeatures(RFFs). RFFsincorporateabundantdetailinformationandcontextinformation.AndRFFsaresenttoRPN togeneratebetterregionproposals.TheproposedapproachisevaluatedonPASCALVOC2007 andMSCOCObenchmarktasks.MS-RPNobtainssignificantimprovementsoverthecomparable state-of-the-artdetectionmodels. KeyWORDS Fusion Feature, Multi-Scale, Object Detecting, Region Proposal Network","PeriodicalId":54963,"journal":{"name":"International Journal of Data Warehousing and Mining","volume":"23 1","pages":"132-145"},"PeriodicalIF":0.5000,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"A Novel Multi-Scale Feature Fusion Method for Region Proposal Network in Fast Object Detection\",\"authors\":\"Gang Liu, Chuyi Wang\",\"doi\":\"10.4018/ijdwm.2020070107\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Neuralnetworkmodelshavebeenwidelyusedinthefieldofobjectdetecting.Theregionproposal methodsarewidelyusedinthecurrentobjectdetectionnetworksandhaveachievedwellperformance. Thecommonregionproposalmethodshunttheobjectsbygeneratingthousandsofthecandidate boxes.Compared toother regionproposalmethods, the regionproposalnetwork (RPN)method improvestheaccuracyanddetectionspeedwithseveralhundredcandidateboxes.However,sincethe featuremapscontainsinsufficientinformation,theabilityofRPNtodetectandlocatesmall-sized objectsispoor.Anovelmulti-scalefeaturefusionmethodforregionproposalnetworktosolvethe aboveproblemsisproposedinthisarticle.Theproposedmethodiscalledmulti-scaleregionproposal network(MS-RPN)whichcangeneratesuitablefeaturemapsfortheregionproposalnetwork.In MS-RPN,theselectedfeaturemapsatmultiplescalesarefineturnedrespectivelyandcompressed intoauniformspace.Thegeneratedfusionfeaturemapsarecalledrefinedfusionfeatures(RFFs). RFFsincorporateabundantdetailinformationandcontextinformation.AndRFFsaresenttoRPN togeneratebetterregionproposals.TheproposedapproachisevaluatedonPASCALVOC2007 andMSCOCObenchmarktasks.MS-RPNobtainssignificantimprovementsoverthecomparable state-of-the-artdetectionmodels. KeyWORDS Fusion Feature, Multi-Scale, Object Detecting, Region Proposal Network\",\"PeriodicalId\":54963,\"journal\":{\"name\":\"International Journal of Data Warehousing and Mining\",\"volume\":\"23 1\",\"pages\":\"132-145\"},\"PeriodicalIF\":0.5000,\"publicationDate\":\"2020-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Data Warehousing and Mining\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.4018/ijdwm.2020070107\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"COMPUTER SCIENCE, SOFTWARE ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Data Warehousing and Mining","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.4018/ijdwm.2020070107","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
引用次数: 4

摘要

Neuralnetworkmodelshavebeenwidelyusedinthefieldofobjectdetecting。Theregionproposal methodsarewidelyusedinthecurrentobjectdetectionnetworksandhaveachievedwellperformance。Thecommonregionproposalmethodshunttheobjectsbygeneratingthousandsofthecandidate盒子。Compared toother regionproposalmethods, regionproposalnetwork (RPN)method improvestheaccuracyanddetectionspeedwithseveralhundredcandidateboxes。However，sincethe featuremapscontainsinsufficientinformation，theabilityofRPNtodetectandlocatesmall-sized objectsispoor。Anovelmulti-scalefeaturefusionmethodforregionproposalnetworktosolvethe aboveproblemsisproposedinthisarticle。Theproposedmethodiscalledmulti-scaleregionproposal network_ (MS-RPN)whichcangeneratesuitablefeaturemapsfortheregionproposalnetwork。In MS-RPN，theselectedfeaturemapsatmultiplescalesarefineturnedrespectivelyandcompressed intoauniformspace.Thegeneratedfusionfeaturemapsarecalledrefinedfusionfeatures(RFFs)。RFFsincorporateabundantdetailinformationandcontextinformation。AndRFFsaresenttoRPN togeneratebetterregionproposals。TheproposedapproachisevaluatedonPASCALVOC2007 andMSCOCObenchmarktasks。MS-RPNobtainssignificantimprovementsoverthecomparable state-of-the-artdetectionmodels。关键词融合特征，多尺度，目标检测，区域建议网络
本文章由计算机程序翻译，如有差异，请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
A Novel Multi-Scale Feature Fusion Method for Region Proposal Network in Fast Object Detection
Neuralnetworkmodelshavebeenwidelyusedinthefieldofobjectdetecting.Theregionproposal methodsarewidelyusedinthecurrentobjectdetectionnetworksandhaveachievedwellperformance. Thecommonregionproposalmethodshunttheobjectsbygeneratingthousandsofthecandidate boxes.Compared toother regionproposalmethods, the regionproposalnetwork (RPN)method improvestheaccuracyanddetectionspeedwithseveralhundredcandidateboxes.However,sincethe featuremapscontainsinsufficientinformation,theabilityofRPNtodetectandlocatesmall-sized objectsispoor.Anovelmulti-scalefeaturefusionmethodforregionproposalnetworktosolvethe aboveproblemsisproposedinthisarticle.Theproposedmethodiscalledmulti-scaleregionproposal network(MS-RPN)whichcangeneratesuitablefeaturemapsfortheregionproposalnetwork.In MS-RPN,theselectedfeaturemapsatmultiplescalesarefineturnedrespectivelyandcompressed intoauniformspace.Thegeneratedfusionfeaturemapsarecalledrefinedfusionfeatures(RFFs). RFFsincorporateabundantdetailinformationandcontextinformation.AndRFFsaresenttoRPN togeneratebetterregionproposals.TheproposedapproachisevaluatedonPASCALVOC2007 andMSCOCObenchmarktasks.MS-RPNobtainssignificantimprovementsoverthecomparable state-of-the-artdetectionmodels. KeyWORDS Fusion Feature, Multi-Scale, Object Detecting, Region Proposal Network
求助全文
通过发布文献求助，成功后即可免费获取论文全文。 去求助
来源期刊
International Journal of Data Warehousing and Mining
International Journal of Data Warehousing and Mining COMPUTER SCIENCE, SOFTWARE ENGINEERING-
CiteScore
2.40
自引率
0.00%
发文量
20
审稿时长
>12 weeks
期刊介绍： The International Journal of Data Warehousing and Mining (IJDWM) disseminates the latest international research findings in the areas of data management and analyzation. IJDWM provides a forum for state-of-the-art developments and research, as well as current innovative activities focusing on the integration between the fields of data warehousing and data mining. Emphasizing applicability to real world problems, this journal meets the needs of both academic researchers and practicing IT professionals.The journal is devoted to the publications of high quality papers on theoretical developments and practical applications in data warehousing and data mining. Original research papers, state-of-the-art reviews, and technical notes are invited for publications. The journal accepts paper submission of any work relevant to data warehousing and data mining. Special attention will be given to papers focusing on mining of data from data warehouses; integration of databases, data warehousing, and data mining; and holistic approaches to mining and archiving
期刊最新文献
Research on Multi-Parameter Prediction of Rabbit Housing Environment Based on Transformer Analyzing AI-Generated Packaging's Impact on Consumer Satisfaction With Three Types of Datasets A Cross-Domain Recommender System for Literary Books Using Multi-Head Self-Attention Interaction and Knowledge Transfer Learning An Outlier Detection Algorithm Based on Probability Density Clustering An Intelligent Heart Disease Prediction Framework Using Machine Learning and Deep Learning Techniques
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们：info@booksci.cn
Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1