雷达科学与技术2025，Vol.23Issue(1)：39-47,9.DOI:10.3969/j.issn.1672-2337.2025.01.004
基于图神经网络的多尺度特征融合雷达目标检测方法
Graph Neural Network Based Radar Target Detection Method with Multi-Scale Feature Fusion
摘要
Abstract
Aiming at the problem of radar target detection in complex clutter environment,a graph neural network-based radar target detection method with multi-scale feature fusion is proposed in this paper,which uses the feature cor-relations among multiple pulse echoes for the detection.Firstly,the proposed method utilizes multiple cascaded feature extraction modules to extract multi-scale features.Subsequently,it constructs multiple directed complete graphs using muti-scale features,where a node in a graph corresponds to a pulse,and the node features of each graph are the features of the corresponding scale.Then,each node can aggregate the information of its neighbors using the graph neural net-work,and the proposed method can therefore learn the higher-order correlation among the pulse echoes.Further,the pro-posed method fuses multi-scale features to enrich the feature representation of the target and the clutter.Finally,the fused features are mapped nonlinearly,and the detection results are obtained in the form of binary classification.The effectiveness of the proposed method is verified using the public radar database.关键词
雷达目标检测/杂波环境/图神经网络/多尺度特征融合Key words
radar target detection/clutter environment/graph neural network/multi-scale feature fusion分类
电子信息工程引用本文复制引用
汪翔,王彦斌,汪育苗,崔国龙..基于图神经网络的多尺度特征融合雷达目标检测方法[J].雷达科学与技术,2025,23(1):39-47,9.基金项目
国家自然科学基金(No.62271126) （No.62271126）
