基于運(yùn)動(dòng)分割的動(dòng)態(tài)SLAM聯(lián)合優(yōu)化算法

打開文本圖片集

Dynamic SLAM joint optimization algorithm based on motion segmentation

ZhangYutong，F(xiàn)an Xinyue，Zhou Zhiyuan，Xie Yuanyuan （ScholofCommicatio&IfoatioEnginering，CongqingUniesityofosts&Telecomnitios，ChongingChina）

Abstract：InordertoaddressthechallngeoftraditionalSLAMbeingeasilydisruptedbydynamicobjectsinthescene，this paper proposedavisual SLAMalgorithmsuitable fordynamicenvironments，referrdtoas GMS-SLAM.Inthisapproach，itreplacedsemanticsegmentation withageometric methodbasedonepipolarconstraints，andemployedopticaldilation to further eliminatepotentialcoplanarambiguities.Itmodeleddynamicobjectsusing motionconstraintsandrigidityconstraints.Thisaproachutilizedthegraphoptimizationmodule tooptimizethecamerapose information，andtransformedhumanskeletalmodelingintorigidojects tobeincorporatedintothegraphoptimizationprocess.Aditionally，byexploitingthestrongcorelation betweencameraself-motionandepipolarconstraints，itintegratedthesegmentationnetworkandoptimizationmoduleintoa unifiedframework forjointrefinement.ExperimentalvalidationontheKITTIandhighlydynamicShibuyadatasetsdemonstratesthat GMS-SLAMachievessubstantialimprovements inacuracycompared tostate-of-the-artdynamicvisualalgoritms， suchas DytanVO，and clasical dynamic algorithms ike DynaSLAM，exhibiting superiorlocalization performance in dynamic environments.

Key Words：dynamic SLAM；graph optimization；motion segmentation；rigid constrains

0 引言

SLAM系統(tǒng)幫助機(jī)器人在未知環(huán)境中尋找自身位置，構(gòu)建軌跡地圖以達(dá)到識(shí)別整個(gè)環(huán)境的目的。（剩余12666字）