Multi-sensor fusion SLAM localization method based on multi-metric evaluation of visual environment degradation

Zheyu Hu; Lijie Zhang

doi:10.1117/12.3052360

30 December 2024 Multi-sensor fusion SLAM localization method based on multi-metric evaluation of visual environment degradation

Zheyu Hu, Lijie Zhang

Author Affiliations +

Proceedings Volume 13394, International Workshop on Automation, Control, and Communication Engineering (IWACCE 2024); 133940P (2024) https://doi.org/10.1117/12.3052360
Event: International Workshop on Automation, Control, and Communication Engineering (IWACCE 2024), 2024, Hohhot, China

Abstract

The multi-sensor fusion SLAM localisation method has been widely used in robot navigation and other fields. For the problem of SLAM localization accuracy and robustness reduction caused by environment degradation in practical applications, this paper proposes a multi-sensor fusion SLAM localization method based on multi-metric evaluation of environment degradation. The visual environment degradation evaluation function is constructed by three evaluation indicators: the number of feature points, the feature point tracking success rate, and the feature point distribution uniformity. The LVI-SAM multi-sensor fusion SLAM localisation algorithm is improved by taking the environmental degradation evaluation result as the independent variable of the robust kernel function, and the output of the robust kernel function is used to adjust the weight of the visual odometry factor in the LVI-SAM back-end optimisation of the multi-sensor fusion SLAM localisation algorithm, so that the SLAM localisation algorithm can better adapt to the environmental changes. Experiments on public datasets show that the multi-sensor fusion SLAM localisation method proposed in this paper, based on multi-metric evaluation of visual environment degradation, reduces the absolute position error root mean square error (APE RMSE) and relative position error root mean square error (RPE RMSE) by at least 7.6% and 16.9%, respectively, compared to the LVI-SAM algorithm without visual environment degradation judgement and the LVI-SAM algorithm using the number of feature points to judge the environment degradation, and effectively improves the localisation accuracy and robustness.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Zheyu Hu and Lijie Zhang "Multi-sensor fusion SLAM localization method based on multi-metric evaluation of visual environment degradation", Proc. SPIE 13394, International Workshop on Automation, Control, and Communication Engineering (IWACCE 2024), 133940P (30 December 2024); https://doi.org/10.1117/12.3052360

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Visualization

Environmental sensing

Mathematical optimization

Principal component analysis

Covariance matrices

Data modeling

Feature fusion

Show All Keywords

Keywords/Phrases

Search In:

Publication Years