Automotive Radar Ghost Target Detection With Physics‐Aware Graph Neural Network
Electronics Letters · 2026-01 · 62 (1)
DOI: 10.1049/ell2.70684 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics Letters, online erschienen am 02.08.2026. Verfasst von Guanhua Ding und 3 weiteren Autor:innen. Die Arbeit nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Multipath propagation in automotive radar produces ghost targets that can mislead perception systems in autonomous driving. This letter proposes a physics‐aware graph neural network (PAGNN) that exploits multipath propagation geometry for radar ghost detection. PAGNN operates in two stages: a GNN‐based affinity clustering stage that groups radar points into target‐level clusters, and a classification stage that identifies ghosts through graph convolution and physics‐informed attention modules. Experiments on real‐world automotive radar data demonstrate that PAGNN outperforms existing methods, improving mean average precision by 15.83 percentage points over the PointNet++ baseline. These results highlight the effectiveness of embedding physical models into graph‐based learning for radar perception.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Ding, G., Zhang, S., Liu, R., & Sun, J. (2026). Automotive Radar Ghost Target Detection With Physics‐Aware Graph Neural Network. Electronics Letters, 62(1). https://doi.org/10.1049/ell2.70684
Vancouver
Ding G, Zhang S, Liu R, Sun J. Automotive Radar Ghost Target Detection With Physics‐Aware Graph Neural Network. Electronics Letters. 2026;62(1). doi:10.1049/ell2.70684
BibTeX
@article{Ding2026,
author = {Ding, Guanhua and Zhang, Shuo and Liu, Ran and Sun, Jinping},
title = {Automotive Radar Ghost Target Detection With Physics‐Aware Graph Neural Network},
journal = {Electronics Letters},
year = {2026},
volume = {62},
number = {1},
doi = {10.1049/ell2.70684}
}
EUVIMED