摘要
复杂电磁环境中干扰信号会严重恶化跳频信号检测和识别性能,为了解决传统的检测方法在实际应用中存在错检、漏检、误检、多检等问题,通过对YOLOv5s网络进行改进,提出一种基于时频图的信号检测和识别算法。首先,构建了跳频信号+干扰信号组合模式的数据集,包含4种不同跳频信号调制类型和6种不同干扰类型,每个组合生成300个高分辨率时频图样本,总计构建7200组数据;其次,考虑到干扰和信号在时频图上拥有相似的特征,而跳频信号频率会随时间不断跳变,这使得信号附近的背景信息成为区分信号与干扰的关键特征,提出利用语境分层模块对背景信息进行分级,采用深度可分离卷积模块提取信号附近的背景信息,利用门控聚合机制加权聚合背景信息和信号特征,输出更具判别力的复合特征;最后,利用语境分层模块与门控聚合机制对YOLOv5s网络的主干网络部分进行改造,得到改进的跳频信号检测器。仿真结果表明:较传统YOLOv5s网络,所提算法的召回率R提升15.9百分点,均值平均精度mAP@0.5∶0.95提升8.9百分点,F 1提升9百分点,错检、漏检等情况显著减少。
In complex electromagnetic environments,interference signals can severely degrade the detection and recognition performance of frequency-hopping signals.To address issues of false detection,missed detection,and over-detection in traditional methods,in this study an improved time-frequency diagram-based signal detection and recognition algorithm was proposed by modifying the YOLOv5s network.Firstly,a composite dataset containing frequency hopping signals+interference signals was constructed,comprising 4 modulation types of frequency hopping signals and 6 interference types,with 300 high-resolution time-frequency diagram samples generated for each combination(totaling 7200 groups).Secondly,considering the similar features between interference and signals in time-frequency diagrams,and recognizing that the frequency variation pattern of hopping signals could make background information around signals crucial for differentiation,a context hierarchy module was proposed to hierarchically process background information.This module employed depthwise separable convolution to extract surrounding background features and utilized a gated aggregation mechanism to perform weighted fusion of background information and signal features,thereby generating more discriminative composite features.Finally,the backbone network of YOLOv5s was modified by integrating the context hierarchy module and gated aggregation mechanism to develop an improved frequency hopping signal detector.Simulation results showed that compared with the original YOLOv5s network,the proposed method achieved 15.9 percentage points improvement in recall rate R,8.9 percentage points enhancement in mean average precision mAP@0.5∶0.95,and 9 percentage points increase in F 1,while significantly reducing false and missed detection occurrences.
作者
张海宾
魏洪基
王超
向长波
杨明洋
李晓龙
ZHANG Haibin;WEI Hongji;WANG Chao;XIANG Changbo;YANG Mingyang;LI Xiaolong(Hangzhou Research Institute,Xidian University,Hangzhou 311200,China;School of Telecommunications Engineering,Xidian University,Xi’an 710126,China;Ceyear Technologies Co.,Ltd.,Qingdao 266555,China;Beijing Institute of Control and Electronic Technology,Beijing 100038,China)
出处
《郑州大学学报(工学版)》
北大核心
2025年第5期43-50,共8页
Journal of Zhengzhou University(Engineering Science)
基金
国防基础科研计划资助(JCKY2021608B001)。
关键词
跳频信号
信号检测
信号识别
干扰信号
YOLOv5s
frequency hopping signal
signal detection
signal recognition
interference signal
YOLOv5s
作者简介
张海宾(1981-),男,山东菏泽人,西安电子科技大学教授,博士,博士生导师,主要从事人工智能安全、工业互联网安全方面的研究,E-mail:hbzhang@mail.xidian.edu.cn;通信作者:王超(1985-),男,江苏徐州人,西安电子科技大学副教授,博士,博士生导师,主要从事5G&6G无线网络及关键技术、物理层安全、隐蔽通信、深度学习及其在无线通信优化中的应用方面的研究,E-mail:chaowang@xidian.edu.cn。
