信息与控制2024，Vol.53Issue(4)：487-498,12.DOI:10.13976/j.cnki.xk.2024.3169
基于三类对象投票和语义回环的动态SLAM算法
Dynamic SLAM Algorithm Based on Voting of Three Objects and Semantic Loop Closure
摘要
Abstract
We introduce a dynamic simultaneous localization and mapping(SLAM)algorithm,combi-ning deep learning-based semantic segmentation with visual SLAM.As a conclusion,this algo-rithm utilizes voting based on three categories of objects and semantic loop closures to effectively mitigate the impact of dynamic objects on SLAM system performance,while enhancing localization and mapping accuracy.Firstly,the semantic objects are classified into three categories:static,potentially dynamic,and certainly dynamic.Then voting method is employed based on reprojection depth error to identify the motion states of these semantic objects,thereby negating the influence of moving targets.Additionally,we employ a semantic similarity loop closure optimization method to enhance loop closure detection robustness.Experimental results on the TUM RGB-D dynamic data-set and the KITTI dataset demonstrate that our algorithm reduces the average absolute trajectory er-ror by 57.13％and 23.39％compared to the ORB-SLAM3 algorithm,respectively,confirming its robustness in dynamic scenes.关键词
动态同步定位与地图构建/语义分割/回环检测Key words
dynamic SLAM(simultaneous localization and mapping)/semantic segmentation/loop closure detection分类
信息技术与安全科学引用本文复制引用
诸葛玥,罗海勇,陈润泽,周姿能,林长海..基于三类对象投票和语义回环的动态SLAM算法[J].信息与控制,2024,53(4):487-498,12.基金项目
中国科学院战略性先导科技专项项目(XDA28040000) （XDA28040000）
国家自然科学基金项目(62261042,62002026) （62261042,62002026）
北京市自然科学基金项目(L221003) （L221003）
宜宾市高层次人才项目(2022YG03) （2022YG03）
