DOE: a dynamic object elimination scheme based on geometric and semantic constraints

In this paper, we propose a dynamic object elimination algorithm that combines semantic and geometric constraints to address the problem of visual SLAM being easily affected by dynamic feature points in dynamic environments. This issue leads to the degradation of localisation accuracy and robustness...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanli Liu, Siyi Chen, Heng Zhang, Neal N. Xiong, Wei Liang
Format: Article
Language:English
Published: Taylor & Francis Group 2023-12-01
Series:Connection Science
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/09540091.2023.2293460
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849703557019729920
author Yanli Liu
Siyi Chen
Heng Zhang
Neal N. Xiong
Wei Liang
author_facet Yanli Liu
Siyi Chen
Heng Zhang
Neal N. Xiong
Wei Liang
author_sort Yanli Liu
collection DOAJ
description In this paper, we propose a dynamic object elimination algorithm that combines semantic and geometric constraints to address the problem of visual SLAM being easily affected by dynamic feature points in dynamic environments. This issue leads to the degradation of localisation accuracy and robustness. Firstly, we employ a lightweight YOLO-Tiny network to enhance both detection accuracy and system speed. Secondly, we integrate the YOLO-Tiny network into the ORB-SLAM3 system to extract semantic information from the images and initiate the elimination of dynamic feature points. Subsequently, we augment this approach by incorporating geometric constraints between neighbouring frames to further eliminate dynamic feature points. Then, the former is supplemented by combining the geometric constraints between neighbouring frames to further eliminate dynamic feature points. Experiments on the TUM dataset demonstrate that the algorithm in this paper can improve the Relative Pose Error (RPE) by up to 95.12% and the Absolute Trajectory Error (ATE) by up to 99.01% in high dynamic sequences compared to ORB-SLAM3. The effectiveness of dynamic feature point elimination is evident, leading to significantly improved localisation accuracy.
format Article
id doaj-art-0bb7a003263e43f2a2a6ede23bc0c99b
institution DOAJ
issn 0954-0091
1360-0494
language English
publishDate 2023-12-01
publisher Taylor & Francis Group
record_format Article
series Connection Science
spelling doaj-art-0bb7a003263e43f2a2a6ede23bc0c99b2025-08-20T03:17:13ZengTaylor & Francis GroupConnection Science0954-00911360-04942023-12-0135110.1080/09540091.2023.2293460DOE: a dynamic object elimination scheme based on geometric and semantic constraintsYanli Liu0Siyi Chen1Heng Zhang2Neal N. Xiong3Wei Liang4School of Electronic Information, Shanghai Dianji University, Shanghai, People's Republic of ChinaSchool of Electronic Information, Shanghai Dianji University, Shanghai, People's Republic of ChinaSchool of Electronic Information, Shanghai Dianji University, Shanghai, People's Republic of ChinaDepartment of Mathematics and Computer Science, Sul Ross State University, Alpine, TX, USASchool of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan, People's Republic of ChinaIn this paper, we propose a dynamic object elimination algorithm that combines semantic and geometric constraints to address the problem of visual SLAM being easily affected by dynamic feature points in dynamic environments. This issue leads to the degradation of localisation accuracy and robustness. Firstly, we employ a lightweight YOLO-Tiny network to enhance both detection accuracy and system speed. Secondly, we integrate the YOLO-Tiny network into the ORB-SLAM3 system to extract semantic information from the images and initiate the elimination of dynamic feature points. Subsequently, we augment this approach by incorporating geometric constraints between neighbouring frames to further eliminate dynamic feature points. Then, the former is supplemented by combining the geometric constraints between neighbouring frames to further eliminate dynamic feature points. Experiments on the TUM dataset demonstrate that the algorithm in this paper can improve the Relative Pose Error (RPE) by up to 95.12% and the Absolute Trajectory Error (ATE) by up to 99.01% in high dynamic sequences compared to ORB-SLAM3. The effectiveness of dynamic feature point elimination is evident, leading to significantly improved localisation accuracy.https://www.tandfonline.com/doi/10.1080/09540091.2023.2293460Simultaneous localisation and mappingfeature pointdynamic environmentsemantic segmmentationmobile robots
spellingShingle Yanli Liu
Siyi Chen
Heng Zhang
Neal N. Xiong
Wei Liang
DOE: a dynamic object elimination scheme based on geometric and semantic constraints
Connection Science
Simultaneous localisation and mapping
feature point
dynamic environment
semantic segmmentation
mobile robots
title DOE: a dynamic object elimination scheme based on geometric and semantic constraints
title_full DOE: a dynamic object elimination scheme based on geometric and semantic constraints
title_fullStr DOE: a dynamic object elimination scheme based on geometric and semantic constraints
title_full_unstemmed DOE: a dynamic object elimination scheme based on geometric and semantic constraints
title_short DOE: a dynamic object elimination scheme based on geometric and semantic constraints
title_sort doe a dynamic object elimination scheme based on geometric and semantic constraints
topic Simultaneous localisation and mapping
feature point
dynamic environment
semantic segmmentation
mobile robots
url https://www.tandfonline.com/doi/10.1080/09540091.2023.2293460
work_keys_str_mv AT yanliliu doeadynamicobjecteliminationschemebasedongeometricandsemanticconstraints
AT siyichen doeadynamicobjecteliminationschemebasedongeometricandsemanticconstraints
AT hengzhang doeadynamicobjecteliminationschemebasedongeometricandsemanticconstraints
AT nealnxiong doeadynamicobjecteliminationschemebasedongeometricandsemanticconstraints
AT weiliang doeadynamicobjecteliminationschemebasedongeometricandsemanticconstraints