EUVIMEDScopri EUVIMED
Open access · CC BY 4.0

DOE-LVI: Tightly Coupled LiDAR-Visual-Inertial SLAM System with Dynamic Object Elimination

Tuanjie Li iD, Shichao Yang, Xu Li, Junjie Wang

Sensors · 2026-06-11 · 26 (12) · 3717

DOI: 10.3390/s26123717 ↗

At a glance

Journal article in Sensors, published online on 2026-06-11. Written by Tuanjie Li and 3 co-authors. Institution: College of Information Engineering, Tarim University, Alar City 843300, China. 22 references. The full text is freely available (open access, CC BY 4.0). Funded by: Shaanxi Province Natural Science Basic Research Program.

AbstractSubjectsDati bibliograficiCiteRelated studies

Abstract (original language)

In dynamic environments, Simultaneous Localization and Mapping (SLAM) systems often struggle with the challenges posed by moving objects. To address these issues, we propose Dynamic-Object-Elimination LiDAR-Visual-Inertial SLAM (DOE-LVI), an advanced tightly coupled LiDAR-Visual-Inertial SLAM system. DOE-LVI integrates two primary subsystems: the Visual-Inertial System (VIS) and the LiDAR-Inertial System (LIS). The VIS component extracts depth information from LiDAR scans and correlates it with visual features, providing accurate pose estimation by minimizing both visual and IMU residuals. The LIS uses this initial estimate to generate range images and perform preliminary removal of dynamic points. Misclassified points are then corrected through ground fitting and precise scan matching with the submap. For enhanced loop closure detection, DOE-LVI employs global LiDAR descriptors, which significantly improve both localization robustness and accuracy. Experimental evaluations on the KITTI and UrbanNav datasets demonstrate that DOE-LVI achieves robust localization and mapping performance, particularly in highly dynamic environments.

Subjects

Author keywords

LiDAR-visual-inertial odometrydynamic environmentplace recognitionsimultaneous localization and mapping

Authors and institutions

  • College of Information Engineering, Tarim University, Alar City 843300, China.
  • School of Mechano-Electronic Engineering, Xidian University, Xi'an 710071, China.
  • Baidu Inc., Beijing 100193, China.

ORCID profiles: Tuanjie Li

Funding

  • Shaanxi Province Natural Science Basic Research Program

Cite

APA

Li, T., Yang, S., Li, X., & Wang, J. (2026). DOE-LVI: Tightly Coupled LiDAR-Visual-Inertial SLAM System with Dynamic Object Elimination. Sensors, 26(12), 3717. https://doi.org/10.3390/s26123717

Vancouver

Li T, Yang S, Li X, Wang J. DOE-LVI: Tightly Coupled LiDAR-Visual-Inertial SLAM System with Dynamic Object Elimination. Sensors. 2026;26(12):3717. doi:10.3390/s26123717

BibTeX
@article{Li2026,
  author = {Li, Tuanjie and Yang, Shichao and Li, Xu and Wang, Junjie},
  title = {DOE-LVI: Tightly Coupled LiDAR-Visual-Inertial SLAM System with Dynamic Object Elimination},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {12},
  pages = {3717},
  doi = {10.3390/s26123717}
}
Start for free →