Robust Visual SLAM in Dynamic Environment Based on Motion Detection and Segmentation
Journal of Autonomous Vehicles and Systems · 01.01.2024 · 4 (1)
DOI: 10.1115/1.4065873 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Autonomous Vehicles and Systems, online erschienen am 26.07.2024. Verfasst von Xin Yu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 44 Literaturangaben. Gefördert von: Hunan Provincial Science and Technology Department.
Abstract (Originalsprache)
In this study, we propose a robust and accurate simultaneous localization and mapping (SLAM) method for dynamic environments. Our approach combines sparse optical flow with epipolar geometric constraints to detect motion, determining whether a priori dynamic objects are moving. By integrating semantic segmentation with this motion detection, we can effectively remove dynamic keypoints, eliminating the influence of dynamic objects. This dynamic object removal technique is integrated into ORB-SLAM2, enhancing its robustness and accuracy for localization and mapping. Experimental results on the TUM dataset demonstrate that our proposed system significantly reduces pose estimation error compared to ORB-SLAM2. Specifically, the RMSE and standard deviation (S.D.) of ORB-SLAM2 are reduced by up to 97.78% and 97.91%, respectively, in highly dynamic sequences, markedly improving robustness in dynamic environments. Furthermore, compared to other similar SLAM methods, our method reduces RMSE and S.D. by up to 69.26% and 73.03%, respectively. Dense semantic maps generated by our method also closely align with the ground truth.
Förderung
- Hunan Provincial Science and Technology Department
Zitieren
APA
Yu, X., Shen, R., Wu, K., & Lin, Z. (2024). Robust Visual SLAM in Dynamic Environment Based on Motion Detection and Segmentation. Journal of Autonomous Vehicles and Systems, 4(1). https://doi.org/10.1115/1.4065873
Vancouver
Yu X, Shen R, Wu K, Lin Z. Robust Visual SLAM in Dynamic Environment Based on Motion Detection and Segmentation. Journal of Autonomous Vehicles and Systems. 2024;4(1). doi:10.1115/1.4065873
BibTeX
@article{Yu2024,
author = {Yu, Xin and Shen, Rulin and Wu, Kang and Lin, Zhi},
title = {Robust Visual SLAM in Dynamic Environment Based on Motion Detection and Segmentation},
journal = {Journal of Autonomous Vehicles and Systems},
year = {2024},
volume = {4},
number = {1},
doi = {10.1115/1.4065873}
}
EUVIMED