[1]苏子旸,张 策*,张 茹,等.视觉同步定位与建图系统中回环检测研究进展[J].计算机技术与发展,2023,33(04):1-8.[doi:10. 3969 / j. issn. 1673-629X. 2023. 04. 001]
　SU Zi-yang,ZHANG Ce*,ZHANG Ru,et al.Research Progress of Loop-closure Detection in Visual SLAM System[J].,2023,33(04):1-8.[doi:10. 3969 / j. issn. 1673-629X. 2023. 04. 001]
点击复制

视觉同步定位与建图系统中回环检测研究进展()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
33
期数:
2023年04期
页码:
1-8
栏目:
综述
出版日期:
2023-04-10

文章信息/Info

Title:
Research Progress of Loop-closure Detection in Visual SLAM System
文章编号:
1673-629X(2023)04-0001-08
作者:
苏子旸1 ; 张 策1* ; 张 茹2 ; 张 展3 ; 张 婧1 ; 吕为工1
1. 哈尔滨工业大学(威海) 计算机科学与技术学院,山东 威海 264209;
2. 哈尔滨商业大学 管理学院,黑龙江 哈尔滨 150076;
3. 哈尔滨工业大学 计算机科学与技术学院,黑龙江 哈尔滨 150001
Author(s):
SU Zi-yang1 ; ZHANG Ce1* ; ZHANG Ru2 ; ZHANG Zhan3 ; ZHANG Jing1 ; LYU Wei-gong1
1. School of Computer Science and Technology,Harbin Institute of Technology ( Weihai) ,Weihai 264209,China;
2. School of Management,Harbin University of Commerce,Harbin 150076,China;
3. School of Computer Science and Technology,Harbin Institute of Technology,Harbin 150001,China
关键词:
同步定位与建图; 回环检测; 位置识别; 词袋模型; 深度学习
Keywords:
Simultaneous Localization And Mapping; loop-closure detection; place recognition; bag-of-words model; deep learning
分类号:
TP311
DOI:
10. 3969 / j. issn. 1673-629X. 2023. 04. 001
摘要:
回环检测又被称为位置识别,是“ 同步定位与建图冶( Simultaneous Localization And Mapping,SLAM)系统中根据图像间的相似度判断运动轨迹是否经过重复地点(即存在回环)的功能,起到阶段性消除累积误差的作用。 聚焦于视觉 SLAM系统这一特定主题下的回环检测主题进行研究,概述了 SLAM 系统的基本功能与基本组成,分析了视觉 SLAM 系统中回环检测的原理与工作流程、前置问题、评测指标。 剖析了回环检测发展过程中产生的系列方法,归类了视觉 SLAM 系统中回环检测存在的两类算法——基于词袋模型的回环检测算法和基于深度学习的回环检测算法,并对这两类算法的原理及优缺点进行了深入分析与总结。 分析表明,基于词袋模型的回环检测算法因其在实时性上的优势仍处于主流,基于深度学习的回环检测算法具有较好的准确率和鲁棒性,但受限于设备对计算资源的分配,这一类做法如何应用于注重实时性的视觉 SLAM 系统仍是亟待解决的问题。 最后,对回环检测面临的挑战和存在的问题进行了分析与展望。
Abstract:
Loop-closure detection, also known as position recognition, is a function in the Simultaneous Localization And Mapping( SLAM) system to judge whether the motion track passes through repeated places ( i. e. there is loop - closure) according to thesimilarity between images,and plays a role in eliminating cumulative errors in stages. Focused on the research of loop-closure detectionunder the specific theme of visual SLAM system,we summarize the basic functions and basic components of SLAM system,analyze theprinciple and workflow of loop-closure detection,pre-problems and evaluation indicators. We analyze a series of methods generated inthe development of loop-closure detection,classify two types of loop - closure detection algorithms in SLAM system,which are loop -closure detection algorithm based on bag-of-words model and loop-closure detection algorithm based on deep learning,and focus on theprinciple,advantages and disadvantages of these two types of algorithms. The analysis shows that the loop-closure detection algorithmbased on bag-of-words model is still in the mainstream because of its real-time advantage. The loop-closure detection algorithm basedon deep learning has excellent accuracy and robustness,but limited by the allocation of computing resources by devices,how to apply thiskind of method to the visual SLAM system that pays attention to real-time is still an urgent problem to be solved. Finally,the challengesand problems of loop-closure detection are analyzed and prospected.

相似文献/References:

[1]荆树旭,卢鹏宇,翟晓惠,等.基于 BoW 模型的增强 RGB-D SLAM 算法[J].计算机技术与发展,2021,31(04):1.[doi:10. 3969 / j. issn. 1673-629X. 2021. 04. 001]
　JING Shu-xu,LU Peng-yu,ZHAI Xiao-hui,et al.Enhanced RGB-D SLAM Algorithm Based on BoW Model[J].,2021,31(04):1.[doi:10. 3969 / j. issn. 1673-629X. 2021. 04. 001]
[2]沈斯杰,田 昕,魏国亮,等.基于 2D 激光雷达的 SLAM 算法研究综述[J].计算机技术与发展,2022,32(01):13.[doi:10. 3969 / j. issn. 1673-629X. 2022. 01. 003]
　SHEN Si-jie,TIAN Xin,WEI Guo-liang,et al.Review of SLAM Algorithm Based on 2D Lidar[J].,2022,32(04):13.[doi:10. 3969 / j. issn. 1673-629X. 2022. 01. 003]

更新日期/Last Update: 2023-04-10