A Robust and Lightweight Loop Closure Detection Approach for Challenging Environments
Drones · 12.07.2024 · 8 (7) · 322
DOI: 10.3390/drones8070322 ↗Kurz gefasst
Fachartikel in der Zeitschrift Drones, online erschienen am 12.07.2024. Verfasst von Yuan Shi und 3 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Sichuan Province of China.
Abstract (Originalsprache)
Loop closure detection is crucial for simultaneous localization and mapping (SLAM), as it can effectively correct the accumulated errors. Complex scenarios put forward high requirements on the robustness of loop closure detection. Traditional feature-based loop closure detection methods often fail to meet these challenges. To solve this problem, this paper proposes a robust and efficient deep-learning-based loop closure detection approach. We employ MixVPR to extract global descriptors from keyframes and construct a global descriptor database. For local feature extraction, SuperPoint is utilized. Then, the constructed global descriptor database is used to find the loop frame candidates, and LightGlue is subsequently used to match the most similar loop frame and current keyframe with the local features. After matching, the relative pose can be computed. Our approach is first evaluated on several public datasets, and the results prove that our approach is highly robust to complex environments. The proposed approach is further validated on a real-world dataset collected by a drone and achieves accurate performance and shows good robustness in challenging conditions. Additionally, an analysis of time and memory costs is also conducted and proves that our approach can maintain accuracy and have satisfactory real-time performance as well.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Sichuan Province of China
Zitieren
APA
Shi, Y., Li, R., Shi, Y., & Liang, S. (2024). A Robust and Lightweight Loop Closure Detection Approach for Challenging Environments. Drones, 8(7), 322. https://doi.org/10.3390/drones8070322
Vancouver
Shi Y, Li R, Shi Y, Liang S. A Robust and Lightweight Loop Closure Detection Approach for Challenging Environments. Drones. 2024;8(7):322. doi:10.3390/drones8070322
BibTeX
@article{Shi2024,
author = {Shi, Yuan and Li, Rui and Shi, Yingjing and Liang, Shaofeng},
title = {A Robust and Lightweight Loop Closure Detection Approach for Challenging Environments},
journal = {Drones},
year = {2024},
volume = {8},
number = {7},
pages = {322},
doi = {10.3390/drones8070322}
}
EUVIMED