Loop Closure Detection With Reweighting Net VLAD and Local Motion and Structure Consensus
Loop Closure Detection With Reweighting Net VLAD and Local Motion and Structure Consensus作者机构:Electronic Information SchoolWuhan UniversityWuhan 430072China IEEE School of Computer Science and TechnologyHarbin Institute of TechnologyHarbin 150001China
出 版 物:《IEEE/CAA Journal of Automatica Sinica》 (自动化学报(英文版))
年 卷 期:2022年第9卷第6期
页 面:1087-1090页
核心收录:
学科分类:08[工学] 081104[工学-模式识别与智能系统] 080203[工学-机械设计及理论] 0802[工学-机械工程] 0811[工学-控制科学与工程]
基 金:supported by Key Research and Development Program of Hubei Province(2020BAB113) the Natural Science Fund of Hubei Province(2019CFA037)。
主 题:Net hierarchical arrangement
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 arrangement of visual elements is lost.