现代雷达2025，Vol.47Issue(10)：10-18,9.DOI:10.16592/j.cnki.1004-7859.2025080301
基于多元时序特征融合的雷达低小慢目标识别
Radar Recognition of LSS Targets Based on Multi-variate Temporal Feature Fusion
邓世民 1桂凌 1李东瀛 1魏飞鸣 1张乐锋 2郁文贤1
作者信息
- 1. 上海市北斗导航与位置服务重点实验室,上海 200240
- 2. 上海戎慧智能科技有限公司,上海 201702
- 折叠
摘要
Abstract
Radar target recognition is significantly challenged by low-slow-small(LSS)characteristics of UAV targets.To address the challenges of weak features and difficulties in temporal modeling of LSS target,a multivariate temporal feature fusion-based method is proposed in this study.First,the multivariate characteristics of targets are efficiently and robustly characterized by ex-tracting velocity,echo,and altitude features from pure temporal trajectory data.Then,the trajectories are converted into continu-ous temporal segments via sliding-window slicing,preserving both local motion details and global temporal correlations.In addi-tion,long-range dependencies are captured using temporal convolutional networks(TCN).In the experiments,an accuracy of 95.13%is achieved on the test set,with state-of-the-art methods surpassed by 1.95%.Strong generalization capability is demon-strated by a cross-dataset accuracy of 92.41%.The signal-to-noise ratio(SNR)feature is proved to be the most critical contributor in ablation studies.It is demonstrated in the sliding window size comparison experiment that the highest accuracy is achieved with an 8-point sliding window.关键词
雷达目标识别/低小慢目标/多元特征融合/时序卷积网络/泛化能力Key words
radar target recognition/LSS targets/multi-variate feature fusion/TCN/generalization capability分类
电子信息工程引用本文复制引用
邓世民,桂凌,李东瀛,魏飞鸣,张乐锋,郁文贤..基于多元时序特征融合的雷达低小慢目标识别[J].现代雷达,2025,47(10):10-18,9.
