CoFormerNet: A Transformer-Based Fusion Approach for Enhanced Vehicle-Infrastructure Cooperative Perception
Sensors · 24.06.2024 · 24 (13) · 4101
DOI: 10.3390/s24134101 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 24.06.2024. Verfasst von Bin Li und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Transportation, Southeast University, Nanjing 211189, China. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, Shenzhen Longhua District Digital Intelligent Forming System Equipment Collaborative Innovation Platform.
Abstract (Originalsprache)
Vehicle–infrastructure cooperative perception is becoming increasingly crucial for autonomous driving systems and involves leveraging infrastructure’s broader spatial perspective and computational resources. This paper introduces CoFormerNet, which is a novel framework for improving cooperative perception. CoFormerNet employs a consistent structure for both vehicle and infrastructure branches, integrating the temporal aggregation module and spatial-modulated cross-attention to fuse intermediate features at two distinct stages. This design effectively handles communication delays and spatial misalignment. Experimental results using the DAIR-V2X and V2XSet datasets demonstrated that CoFormerNet significantly outperformed the existing methods, achieving state-of-the-art performance in 3D object detection.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Transportation, Southeast University, Nanjing 211189, China.
- School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, China.
- Department of Transportation Engineering, Beijing Institute of Technology, Zhuhai 519088, China.
- ShenSi Lab, Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen 518110, China.
ORCID-Profile: Bin Li, Yanan Zhao
Förderung
- National Key Research and Development Program of China
- Shenzhen Longhua District Digital Intelligent Forming System Equipment Collaborative Innovation Platform
Zitieren
APA
Li, B., Zhao, Y., & Tan, H. (2024). CoFormerNet: A Transformer-Based Fusion Approach for Enhanced Vehicle-Infrastructure Cooperative Perception. Sensors, 24(13), 4101. https://doi.org/10.3390/s24134101
Vancouver
Li B, Zhao Y, Tan H. CoFormerNet: A Transformer-Based Fusion Approach for Enhanced Vehicle-Infrastructure Cooperative Perception. Sensors. 2024;24(13):4101. doi:10.3390/s24134101
BibTeX
@article{Li2024,
author = {Li, Bin and Zhao, Yanan and Tan, Huachun},
title = {CoFormerNet: A Transformer-Based Fusion Approach for Enhanced Vehicle-Infrastructure Cooperative Perception},
journal = {Sensors},
year = {2024},
volume = {24},
number = {13},
pages = {4101},
doi = {10.3390/s24134101}
}
EUVIMED