一种改进YOLOv8的跳频网台分选算法

朱政宇; 赵航冉; 王梓晅; 王忠勇; 巩克现; 梁静

doi:10.12263/DZXB.20240487

您当前的位置：

首页 >

文章列表页 >

一种改进YOLOv8的跳频网台分选算法

学术论文 | 更新时间：2025-12-08

- 一种改进YOLOv8的跳频网台分选算法
  增强出版
- A Frequency Hopping Network Station Sorting Algorithm Based on Improved YOLOv8
- 电子学报 2025年53卷第2期页码：385-394
- 作者机构：
  
  1.郑州电气与信息工程学院，河南郑州 450001
  2.东南大学移动通信国家重点实验室，江苏南京 210018
  3.河南省智能网络和数据分析国际联合实验室，河南郑州 450001
- 作者简介：
  
  [ "朱政宇男，1988年5月出生，河南周口人.郑州大学电气与信息工程学院副教授、硕士生导师.主要研究方向为无线通信和信号处理、B5G/6G、智能反射面、通感一体化、无线携能传输、毫米波通信、机器学习、物理层安全、凸优化技术和等. E-mail: iezyzhu@zzu.edu.cn" ]
  [ "赵航冉男，2000年1月出生，河南洛阳人.郑州大学研究生.主要研究方向为跳频信号检测与分选. E-mail: zhr000124@163.com" ]
  [ "王梓晅男，1998年1月出生，河南周口人.郑州大学博士研究生.主要研究方向为通信信号分析与智能处理. E-mail: wzx1356466179@163.com" ]
  [ "王忠勇男，1965年8月出生，江苏遂州人.郑州大学教师、博士生导师.主要研究方向为通信信号处理、嵌入式系统. E-mail: iezywang@zzu.edu.cn" ]
  [ "巩克现男，1976年8月出生，山东泰安人.郑州大学教授、博士生导师.主要研究方向为无线通信信号分析与处理、信道编码、无线接入、目标监测及电子对抗等. E-mail: ggkx@163.com" ]
  [ "梁静女，1981年6月出生，河南兰考人.郑州大学教授、博士生导师.主要研究方向为演化计算及应用等. E-mail: liangjing@zzu.edu.cn" ]
- 基金信息：
  
  国家重点研发计划(2022YFD2001200);国家自然科学基金(61922072);河南省高校科技创新人才支持计划(23HASTIT019);河南省自然科学基金(232300421097);东南大学移动通信国家重点实验室开放课题(2023D11);西安电子科技大学空天地一体化综合业务网全国重点实验室(ISN25-24)
- DOI：10.12263/DZXB.20240487
  中图分类号： TN91;
- 收稿：2024-05-27，
  
  修回：2024-10-28，
  
  纸质出版：2025-02-25
- 稿件说明：
移动端阅览
朱政宇, 赵航冉, 王梓晅, 等. 一种改进YOLOv8的跳频网台分选算法[J]. 电子学报, 2025, 53(02): 385-394.

ZHU Zheng-yu, ZHAO Hang-ran, WANG Zi-xuan, et al. A Frequency Hopping Network Station Sorting Algorithm Based on Improved YOLOv8[J]. Acta Electronica Sinica, 2025, 53(02): 385-394.
朱政宇, 赵航冉, 王梓晅, 等. 一种改进YOLOv8的跳频网台分选算法[J]. 电子学报, 2025, 53(02): 385-394. DOI：10.12263/DZXB.20240487

ZHU Zheng-yu, ZHAO Hang-ran, WANG Zi-xuan, et al. A Frequency Hopping Network Station Sorting Algorithm Based on Improved YOLOv8[J]. Acta Electronica Sinica, 2025, 53(02): 385-394. DOI：10.12263/DZXB.20240487

摘要

针对传统跳频网台分选技术在低信噪比条件下检测效果不佳且实时性差的问题，本文提出一种基于YOLOv8（You Only Look Once version 8）的跳频信号分选算法.首先，对接收到的混叠信号进行短时傅里叶变换生成灰度时频图作为YOLOv8网络模型的输入.其次，针对混叠信号中扫频、定频信号以及跳频信号之间发生频率碰撞对检测精度的影响，在C2f层中引入可变形卷积核（Deformable Convolutional Net-works v2，DCNv2）提高网络特征提取的泛化能力.再次，在Backbone层中加入SimAM注意力机制，解决低信噪比下背景噪声易与跳频信号混淆影响检测精度的问题.最后，将Detect检测头的卷积核替换为局部卷积核（Partial Convolution，PConv），在mAP@0.5精度损失不超过0.37%的情况下使网络计算复杂度降低32.18%，提高网络模型的推理速度.实验结果表明，本文所提算法在信噪比为-5 dB时分选率达到97.68%，且模型收敛快，鲁棒性强.

Abstract

Aiming at the problem that traditional frequency hopping network station sorting technology is ineffective under low signal-to-noise ratio conditions and has poor real-time detection performance

this paper proposes a shortwave frequency hop-ping signal sorting algorithm based on the improved YOLOv8 (You Only Look Once version 8). First

the short-time Fourier transform is performed on the received aliasing signal to generate a grayscale time-frequency image as the input of the YOLOv8 network model. Secondly

in view of the impact of frequency collisions between aliasing signals such as sweep frequency signals

fixed frequency signals and frequency hopping signals on detection accuracy

the Deformable Convolutional Net-works v2 is introduced in the C2f layer to improve the generalization ability of network feature extraction. Thirdly

the Simam attention mechanism is added to the backbone layer to solve the problem that background noise is easily confused with frequency hopping signals and affects detection accuracy under low signal-to-noise ratio. Finally

the convolutional kernel of Detect module is replaced by Partial Convolution kernel

which reduces the computational complexity of the network by 32.18% without the accuracy loss of mAP@0.5 exceeding 0.37%

and improve the inference speed of the network model. Experimental results show that the improved YOLOv8 algorithm proposed in this paper has a separation rate of 97.68% at -5 dB signal-to-noise ratio

and the model has fast convergence and strong robustness.

关键词

Keywords

references

李青华 , 韩岱洪 , 唐柯 , 等 . 跳频网台分选方法概述 [J ] . 中国无线电 , 2022 ( 5 ): 87 - 90 .

LI Q H , HAN D H , TANG K , et al . Overview of sorting methods for frequency hopping network stations [J ] . China Radio , 2022 ( 5 ): 87 - 90 . (in Chinese)

王淼 , 蔡晓霞 , 雷迎科 . 一种基于独立分量分析的变速跳频信号盲分离方法 [J ] . 空军工程大学学报(自然科学版) , 2019 , 20 ( 5 ): 58 - 63 .

WANG M , CAI X X , LEI Y K . A blind separation of variable frequency hopping signals based on independent component analysis [J ] . Journal of Air Force Engineering University (Natural Science Edition) , 2019 , 20 ( 5 ): 58 - 63 . (in Chinese)

杨芸丞 , 孙雪丽 , 钟兆根 , 等 . 一种改进的独立分量分析跳频网台分选方法 [J ] . 中国电子科学研究院学报 , 2018 , 13 ( 4 ): 452 - 459 .

YANG Y C , SUN X L , ZHONG Z G , et al . An improved independent component analysis frequency-hopping network station sorting method [J ] . Journal of China Academy of Electronics and Information Technology , 2018 , 13 ( 4 ): 452 - 459 . (in Chinese)

郭凌飞 , 张林波 . 一种改进的FCM聚类算法的混合矩阵估计 [J ] . 应用科技 , 2019 , 46 ( 2 ): 47 - 52 .

GUO L F , ZHANG L B . Mixing matrix estimation based on an improved FCM clustering algorithm [J ] . Applied Science and Technology , 2019 , 46 ( 2 ): 47 - 52 . (in Chinese)

王少波 , 郭英 , 眭萍 , 等 . 欠定条件下同步组网跳频信号盲源分离方法 [J ] . 计算机工程 , 2020 , 46 ( 10 ): 166 - 172, 181 .

WANG S B , GUO Y , SUI P , et al . Blind source separation method for frequency-hopping signal in synchronous networking under underdetermined condition [J ] . Computer Engineering , 2020 , 46 ( 10 ): 166 - 172, 181 . (in Chinese)

于欣永 , 郭英 , 张坤峰 , 等 . 基于盲源分离的多跳频信号网台分选算法 [J ] . 信号处理 , 2017 , 33 ( 8 ): 1082 - 1089 .

YU X Y , GUO Y , ZHANG K F , et al . A network sorting algorithm based on blind source separation of multi-FH signal [J ] . Journal of Signal Processing , 2017 , 33 ( 8 ): 1082 - 1089 . (in Chinese)

LIU S H , ZHANG Y D , SHAN T , et al . Structure-aware Bayesian compressive sensing for frequency-hopping spectrum estimation with missing observations [J ] . IEEE Transactions on Signal Processing , 2018 , 66 ( 8 ): 2153 - 2166 .

FU W H , JIANG T . A parameter estimation algorithm for multiple frequency-hopping signals based on compressed sensing [J ] . Physical Communication , 2019 , 37 : 100892 .

王淼 , 蔡晓霞 , 雷迎科 . 基于帧重叠的变速跳频信号分选算法 [J ] . 探测与控制学报 , 2020 , 42 ( 4 ): 63 - 68 .

WANG M , CAI X X , LEI Y K . Variable speed hopping signal sorting algorithm based on frame overlap [J ] . Journal of Detection & Control , 2020 , 42 ( 4 ): 63 - 68 . (in Chinese)

王淼 , 蔡晓霞 , 雷迎科 . 基于改进时频检测的欠定变速跳频信号盲分离算法 [J ] . 计算机工程 , 2020 , 46 ( 8 ): 172 - 177, 183 .

WANG M , CAI X X , LEI Y K . Blind separation algorithm for underdetermined variable speed frequency hopping signals based on improved time frequency detection [J ] . Computer Engineering , 2020 , 46 ( 8 ): 172 - 177, 183 . (in Chinese)

任珂 . 跳频电台分选关键技术研究 [D ] . 成都 : 电子科技大学 , 2020 .

REN K . Research on Key Technology of Frequency Hopping Radio Sorting [D ] . Chengdu : University of Electronic Science and Technology of China , 2020 . (in Chinese)

郭海召 . 跳频信号的检测、参数估计与分选算法研究 [D ] . 成都 : 电子科技大学 , 2016 .

GUO H Z . Study on Detection, Parameters Estimation and Seperation Algorithm for Frequency-Hopping Signals [D ] . Chengdu : University of Electronic Science and Technology of China , 2016 . (in Chinese)

WANG Z Y , ZHANG B B , ZHU Z Y , et al . Signal sorting algorithm of hybrid frequency hopping network station based on neural network [J ] . IEEE Access , 2021 , 9 : 35924 - 35931 .

LEE K G , OH S J . Detection of frequency-hopping signals with deep learning [J ] . IEEE Communications Letters , 2020 , 24 ( 5 ): 1042 - 1046 .

CHEN Z Y , SHI Y W , WANG Y W , et al . Unlocking signal processing with image detection: A frequency hopping detection scheme for complex EMI environments using STFT and CenterNet [J ] . IEEE Access , 2023 , 11 : 46004 - 46014 .

张盛魁 , 姚志成 , 范志良 , 等 . 基于局部自适应阈值的跳频信号提取和检测 [J ] . 电光与控制 , 2020 , 27 ( 1 ): 68 - 72 .

ZHANG S K , YAO Z C , FAN Z L , et al . Frequency hopping signal extraction and detection based on local adaptive threshold [J ] . Electronics Optics & Control , 2020 , 27 ( 1 ): 68 - 72 . (in Chinese)

DAI J F , QI H Z , XIONG Y W , et al . Deformable convolutional networks [C ] // 2017 IEEE International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2017 : 764 - 773 .

ZHU X Z , HU H , LIN S , et al . Deformable ConvNets V2: More deformable, better results [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2019 : 9300 - 9308 .

YANG L X , ZHANG R Y , LI L D , et al . SimAM: A simple, parameter-free attention module for convolutional neural Networksp [C ] // 38th International Conference on Machine Learning , New York : PMLR , 2021 : 11863 - 11874 .

CHEN J R , KAO S H , HE H , et al . Run, don't walk: Chasing higher FLOPS for faster neural networks [C ] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2023 : 12021 - 12031 .

ZHOU X Y , WANG D Q , KRÄHENBÜHL P . Objects as points [EB/OL ] .( 2019-04-25 )[ 2024-05-27 ] . https://arxiv.org/abs/1904.07850v2 https://arxiv.org/abs/1904.07850v2 .

BOCHKOVSKIY A , WANG C Y , LIAO H Y M . YOLOv4: Optimal speed and accuracy of object detection [EB/OL ] . ( 2020-04-23 )[ 2024-05-27 ] . https://arxiv.org/abs/2004.109 https://arxiv.org/abs/2004.109

34 v 1 .

LI C Y , LI L , JIANG H L , et al . YOLOv6: A single-stage object detection framework for industrial applications [EB/OL ] . ( 2022-09-07 )[ 2024-05-27 ] . https://arxiv.org/abs/2209.02976 https://arxiv.org/abs/2209.02976 .

WANG C Y , BOCHKOVSKIY A , LIAO H Y M . YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors [C ] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2023 : 7464 - 7475 .

朱政宇 , 王家政 , 梁静 , 等 . 复杂环境下基于联合特征聚类的多跳频网台分选 [J ] . 通信学报 , 2023 , 44 ( 9 ): 218 - 227 .

ZHU Z Y , WANG J Z , LIANG J , et al . Multi frequency hopping network station sorting based on joint feature clustering in complex environment [J ] . Journal on Communications , 2023 , 44 ( 9 ): 218 - 227 . (in Chinese)

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

雷达有源电磁干扰视觉检测与参数估计方法

无人机视角多源目标检测数据集UAV-RGBT及算法基准