典型文献
Loop Closure Detection With Reweighting Net VLAD and Local Motion and Structure Consensus
文献摘要：
Dear Editor,
Loop closure detection(LCD)is an important module in simultaneous localization and mapping(SLAM).In this letter,we address the LCD task from the semantic aspect to the geometric one.To this end,a network termed as AttentionNetVLAD which can simultaneously extract global and local features is proposed.It leverages attentive selection for local features,coupling with reweighting the soft assignment in NetVLAD via the attention map for global features.Given a query image,candidate frames are first identified coarsely by retrieving similar global features in the database via hierarchical navigable small world(HNSW).As global features mainly summarize the semantic information of images and lead to compact representation,information about spatial arrange-ment of visual elements is lost.To provide fine results,we further propose a feature matching method termed as local motion and structure consensus(LMSC)to conduct geometric verification between candidate pairs.It constructs local neighborhood structures of local features through motion consistency and manifold representation,and formulates the matching problem into an optimization model,enabling linearithmic time complexity via a closed-form solution.Experiments on several public datasets demonstrate that LMSC performs well in feature matching,and the proposed LCD system can yield satisfying results.
文献关键词：
中图分类号：
作者姓名：
Kaining Zhang;Jiayi Ma;Junjun Jiang
作者机构：
Electronic Information School,Wuhan University,Wuhan 430072,China;School of Computer Science and Technology,Harbin Institute of Technology,Harbin 150001,China
文献出处：
引用格式：
[1]Kaining Zhang;Jiayi Ma;Junjun Jiang-.Loop Closure Detection With Reweighting Net VLAD and Local Motion and Structure Consensus)[J].自动化学报（英文版）,2022(06):1087-1090
A类：
Reweighting,
Loop,AttentionNetVLAD,reweighting,navigable,HNSW,LMSC,linearithmic
B类：
Closure,Detection,With,Local,Motion,Structure,Consensus,Dear,Editor,closure,detection,LCD,important,module,localization,mapping,SLAM,In,this,letter,address,task,from,semantic,aspect,geometric,one,To,end,network,termed,which,simultaneously,extract,global,features,proposed,It,leverages,attentive,selection,coupling,soft,assignment,via,attention,Given,query,candidate,frames,are,first,identified,coarsely,by,retrieving,similar,database,hierarchical,small,world,mainly,summarize,information,images,lead,compact,representation,about,spatial,arrange,visual,elements,lost,provide,fine,results,further,matching,method,motion,consensus,conduct,verification,between,pairs,constructs,neighborhood,structures,through,consistency,manifold,formulates,problem,into,optimization,model,enabling,complexity,closed,solution,Experiments,several,public,datasets,demonstrate,that,performs,well,system,yield,satisfying
AB值：
0.575327
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
