现代雷达2025，Vol.47Issue(10)：85-91,7.DOI:10.16592/j.cnki.1004-7859.2025070401
基于端到端实例分割的雷达目标检测关联
An End-to-end Instance Segmentation Network for Radar Target Detection and Association
申伦豪 1余继周 1叶春茂 1胡鹏飞 1王洪淼1
作者信息
- 1. 北京无线电测量研究所,北京 100854
- 折叠
摘要
Abstract
Radar systems operating in complex environments face challenges such as dense target distribution,trajectory overlap,and fluctuating scattering intensity.Traditional threshold and filter-based methods often fail to achieve both high detection accuracy and reliable target association.An end-to-end instance segmentation network is proposed to jointly address target detection and as-sociation.Pulse-compressed signals are converted into time-range images,and an encoder-decoder network is employed to perform pixel-level detection and feature embedding.Background constraints and embedding losses are incorporated during training to im-prove feature separability,while unsupervised clustering in the embedding space enables automatic target distinction and associa-tion during inference.Experimental results show that the proposed method achieves superior accuracy,robustness,and efficiency compared with conventional approaches,providing a practical framework for intelligent radar detection and track initiation.关键词
脉压图像/端到端实例分割/多目标检测/目标关联/嵌入特征/检测与关联一体化Key words
pulse-compressed image/end-to-end instance segmentation/multi-target detection/target association/embedding fea-tures/joint detection and association分类
电子信息工程引用本文复制引用
申伦豪,余继周,叶春茂,胡鹏飞,王洪淼..基于端到端实例分割的雷达目标检测关联[J].现代雷达,2025,47(10):85-91,7.
