ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Real-time motion removal based on point correlations for RGB-D SLAM in indoor dynamic environments

Wang, Kesai; Yao, Xifan*; Ma, Nanfeng; Jing, Xuan
NEURAL COMPUTING & APPLICATIONS2023-4DOI: 10.1007/s00521-022-07879-x
1被引4阅读
引用收藏
分享

摘要

The traditional visual simultaneous localization and mapping (SLAM) systems have a high dependence on static world assumption, which makes them easy to fail to track in dynamic environments. In this paper, we propose a real-time dynamic visual SLAM system (RTDSLAM) based on ORB-SLAM3 to realize accurate pose estimation of the camera in indoor dynamic environments. We regard the static objects in the environments as a complete virtual rigid body and add two motion removal modules to handle the dynamic feature points without the aid of the camera's ego motion. The geometry-based motion removal module utilizes the point correlations and the structural invariance of rigid body to detect sparse dynamic feature points between two keyframes, and the clustering of depth images helps find the complete dynamic regions. Meanwhile, the template-based motion removal module uses template matching to fast track the known moving objects between ordinary frames. The dynamic feature points located on moving objects are removed and only static feature points are reserved for pose estimation. We evaluate our system on public TUM and Bonn datasets, and the comparison with state-of-the-art dynamic visual SLAM systems shows our advantages both in runtime and the accuracy of pose estimation. Besides, the test in real-world scenes shows the effectiveness of our system in dynamic environments.

学科与关键词

关键词
Simultaneous localization and mapping (SLAM)Dynamic environmentsEgo-motionPose estimation
相关
加载中…
  • Dynamic visual simultaneous localization and mapping based on semantic segmentation module
    Jin, Jing*; Jiang, Xufeng; Yu, Chenhui; Zhao, Lingna; Tang, ZhenApplied Intelligence, 2023, 53(16): 19418-19432.被引 1
  • Dynamic RGB-D SLAM Based on Static Probability and Observation Number
    Liu, Yu; Wu, Yilin*; Pan, WenzhaoIEEE Transactions on Instrumentation and Measurement, 2021, 70: 8503411.被引 5
  • Robust RGB: D-SLAM in highly dynamic environments based on probability observations and clustering optimization
    Liu, Hailin; Tian, Liangfang*; Du, Qiliang; Xu, WenjieMeasurement Science and Technology, 2024, 35(3): 035405.
查看全部 →

发表信息

论文状态
公开发表
期刊
NEURAL COMPUTING & APPLICATIONS
发表日期
2023-04
卷期
第 35 卷, 第 12 期
页码
8707-8722
DOI
10.1007/s00521-022-07879-x
语言
ENGLISH
成果收录
SCIE
资助标注
Guangdong Basic and Applied Basic Research Foundation [2022A1515010095, 2021A1515010506]; National Natural Science Foundation of China [51675186]; Royal Society of Edinburgh [51911530245]

作者

  • W

    Wang, Kesai (第一作者)

  • Y

    Yao, Xifan (通讯)

查看全部 4 位作者收起作者
  • M

    Ma, Nanfeng

  • J

    Jing, Xuan

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417