Optimization of ORB-SLAM3 algorithm based on deep learning

Zhaolan He; Xingrong Zhu; Jinghai Ye

doi:10.1117/12.3040881

10 September 2024 Optimization of ORB-SLAM3 algorithm based on deep learning

Zhaolan He, Xingrong Zhu, Jinghai Ye

Proceedings Volume 13257, International Conference on Advanced Image Processing Technology (AIPT 2024); 132570U (2024) https://doi.org/10.1117/12.3040881
Event: International Conference on Advanced Image Processing Technology (AIPT 2024), 2024, Chongqing, China

Abstract

A dynamic feature removal method combining the deep learning network YOLOv5 (You Only Look Once Version 5) and geometric constraints was proposed to address the poor positioning accuracy and robustness of the current ORB-SLAM3 system in dynamic scenarios, which could not meet the positioning needs of mobile robots in such scenarios. A dynamic feature point detection and removal thread was embedded in the tracking thread to eliminate the impact of dynamic feature points on camera pose estimation, thereby improving the accuracy and robustness of the SLAM system. The experiment used publicly available TUM datasets to validate the improved algorithm, and the experimental results showed that the improved algorithm had significant improvements in localization accuracy and robustness.

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

Citation Download Citation

Zhaolan He, Xingrong Zhu, and Jinghai Ye "Optimization of ORB-SLAM3 algorithm based on deep learning", Proc. SPIE 13257, International Conference on Advanced Image Processing Technology (AIPT 2024), 132570U (10 September 2024); https://doi.org/10.1117/12.3040881

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