Kalman Filter-Based Fusion of LiDAR and Camera Data in Bird’s Eye View for Multi-Object Tracking in Autonomous Vehicles
Sensors · 03.12.2024 · 24 (23) · 7718
DOI: 10.3390/s24237718 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 03.12.2024. Verfasst von Loay Alfeqy und 3 weiteren Autor:innen. Beteiligte Einrichtung: Mechatronics Engineering Department, Faculty of Engineering, Ain Shams University, Cairo 11535, Egypt. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Accurate multi-object tracking (MOT) is essential for autonomous vehicles, enabling them to perceive and interact with dynamic environments effectively. Single-modality 3D MOT algorithms often face limitations due to sensor constraints, resulting in unreliable tracking. Recent multi-modal approaches have improved performance but rely heavily on complex, deep-learning-based fusion techniques. In this work, we present CLF-BEVSORT, a camera-LiDAR fusion model operating in the bird’s eye view (BEV) space using the SORT tracking framework. The proposed method introduces a novel association strategy that incorporates structural similarity into the cost function, enabling effective data fusion between 2D camera detections and 3D LiDAR detections for robust track recovery during short occlusions by leveraging LiDAR depth. Evaluated on the KITTI dataset, CLF-BEVSORT achieves state-of-the-art performance with a HOTA score of 77.26% for the Car class, surpassing StrongFusionMOT and DeepFusionMOT by 2.13%, with high precision (85.13%) and recall (80.45%). For the Pedestrian class, it achieves a HOTA score of 46.03%, outperforming Be-Track and StrongFusionMOT by (6.16%). Additionally, CLF-BEVSORT reduces identity switches (IDSW) by over 45% for cars compared to baselines AB3DMOT and BEVSORT, demonstrating robust, consistent tracking and setting a new benchmark for 3DMOT in autonomous driving.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Mechatronics Engineering Department, Faculty of Engineering, Ain Shams University, Cairo 11535, Egypt.
ORCID-Profile: Loay Alfeqy, Hossam E Hassan Abdelmunim, Shady A Maged, Diaa Emad
Zitieren
APA
Alfeqy, L., Abdelmunim, H. E. H., Maged, S. A., & Emad, D. (2024). Kalman Filter-Based Fusion of LiDAR and Camera Data in Bird’s Eye View for Multi-Object Tracking in Autonomous Vehicles. Sensors, 24(23), 7718. https://doi.org/10.3390/s24237718
Vancouver
Alfeqy L, Abdelmunim HEH, Maged SA, Emad D. Kalman Filter-Based Fusion of LiDAR and Camera Data in Bird’s Eye View for Multi-Object Tracking in Autonomous Vehicles. Sensors. 2024;24(23):7718. doi:10.3390/s24237718
BibTeX
@article{Alfeqy2024,
author = {Alfeqy, Loay and Abdelmunim, Hossam E Hassan and Maged, Shady A and Emad, Diaa},
title = {Kalman Filter-Based Fusion of LiDAR and Camera Data in Bird’s Eye View for Multi-Object Tracking in Autonomous Vehicles},
journal = {Sensors},
year = {2024},
volume = {24},
number = {23},
pages = {7718},
doi = {10.3390/s24237718}
}
EUVIMED