基于最大熵二值化时频图和DL-YOLOv5s的跳周期估计和跳频频率估计

胡竹艳; 王首斌; 刘顺兰; 沈雷

doi:10.11959/j.issn.1000-0801.2025114

您当前的位置：

首页 >

文章列表页 >

基于最大熵二值化时频图和DL-YOLOv5s的跳周期估计和跳频频率估计

研究与开发 | 更新时间：2025-09-04

- 基于最大熵二值化时频图和DL-YOLOv5s的跳周期估计和跳频频率估计
- Estimation of hop period and frequency hopping based on maximum entropy binarization of time-frequency maps and DL-YOLOv5s
- 电信科学 2025年41卷第8期页码：115-126
- 作者机构：
  
  1.杭州电子科技大学电子信息学院，浙江杭州 310018
  2.中国电子科技集团公司第三十六研究所，浙江嘉兴 314033
  3.杭州电子科技大学通信工程学院，浙江杭州 310018
- 作者简介：
  
  [ "胡竹艳（2000- ），女，杭州电子科技大学电子信息学院硕士生，主要研究方向为数字信号处理。" ]
  [ "王首斌（1984- ），男，博士，中国电子科技集团公司第三十六研究所高级工程师，主要研究方向为电子战系统总体技术。" ]
  [ "刘顺兰（1965- ），女，杭州电子科技大学电子信息学院教授，主要研究方向为无线通信、通信信号处理。" ]
  [ "沈雷（1979- ），男，博士，杭州电子科技大学通信工程学院教授，主要研究方向为图像处理和信号处理。" ]
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2025114
  中图分类号： TN911.73
- 收稿：2024-12-16，
  
  修回：2025-03-27，
  
  纸质出版：2025-08-20
- 稿件说明：
移动端阅览
胡竹艳,王首斌,刘顺兰等.基于最大熵二值化时频图和DL-YOLOv5s的跳周期估计和跳频频率估计[J].电信科学,2025,41(08):115-126.

HU Zhuyan,WANG Shoubin,LIU Shunlan,et al.Estimation of hop period and frequency hopping based on maximum entropy binarization of time-frequency maps and DL-YOLOv5s[J].Telecommunications Science,2025,41(08):115-126.
胡竹艳,王首斌,刘顺兰等.基于最大熵二值化时频图和DL-YOLOv5s的跳周期估计和跳频频率估计[J].电信科学,2025,41(08):115-126. DOI： 10.11959/j.issn.1000-0801.2025114.

HU Zhuyan,WANG Shoubin,LIU Shunlan,et al.Estimation of hop period and frequency hopping based on maximum entropy binarization of time-frequency maps and DL-YOLOv5s[J].Telecommunications Science,2025,41(08):115-126. DOI： 10.11959/j.issn.1000-0801.2025114.

摘要

针对低信噪比（signal-to-noise ratio，SNR）下跳周期估计和跳频频率估计误差较大的情况，提出了一种基于最大熵二值化时频图以及检测和定位（detection and localization，DL）-YOLOv5s的跳周期估计和跳频频率估计方法。首先，利用最大熵阈值分割方法结合形态学滤波对时频图进行处理，获得清晰的最大熵二值化时频图，再通过提出的DL-YOLOv5s模型对最大熵二值化时频图中的跳频信号进行检测和定位，通过增加ASPP模块和BiFPN模块，提高跳频信号的边缘和角点检测精度，并通过BOT3模块引入多头自注意力机制，提高跳频信号的定位精度，最后得到跳频信号的坐标位置，通过坐标的对照关系完成跳周期估计和跳频频率估计。实验结果表明，相较于YOLOv5s模型，提出的DL-YOLOv5s模型精确率

提高了5%，召回率

提高了2.2%，平均精度mAP 0.5和mAP 0.5:0.9分别提高了5.1%和4.2%，相较于YOLOv7、YOLOv8等其他模型，提出的DL-YOLOv5s模型体积更小，更适用于跳频信号参数估计常用的嵌入式设备这类资源受限的环境，且相较于传统跳频信号参数估计方法，提出的方法可以有效降低低信噪比下跳周期估计和跳频频率估计的误差。

Abstract

In response to the significant estimation errors in hop period and hop frequency under low signal-to-noise ratio (SNR) conditions

a method for hop period and hop frequency estimation based on maximum entropy binarization of time-frequency maps and a detection and localization (DL)-YOLOv5s model was proposed. Firstly

the maximum entropy thresholding method combined with morphological filtering was utilized to process the time-frequency map

resulting in a clear maximum entropy binarized time-frequency map. Then

the proposed DL-YOLOv5s model was appllied to detect and localize the hop frequency signals within the maximum entropy binarized time-frequency map. By incorporating the ASPP module and BiFPN module

the precision of edge and corner detection for hop frequency signals was enhanced. Additionally

a multi-head self-attention mechanism was introduced to improve the localization accuracy of hop frequency signals by the BOT3 module. Ultimately

the coordinates of the hop frequency signals were obtained

and through the correlation of these coordinates

the estimation of hop period and frequency was completed. The experimental results show that compared to the YOLOv5s model

the proposed DL-YOLOv5s model improves precision (

) by 5%

recall (

) by 2.2%

and the mean average precision (mAP) at 0.5 and

mAP at 0.5:0.9 by 5.1% and 4.2% respectively. In comparison to other models such as YOLOv7 and YOLOv8

the proposed DL-YOLOv5s model is smaller in size

making it more suitable for resource-constrained environments like embedded devices commonly used for frequency-hopping signal parameter estimation. Additionally

compared to traditional methods for frequency-hopping signal parameter estimation

the proposed method effectively reduces the estimation errors of hopping period and hopping frequency under low signal-to-noise ratio conditions.

关键词

Keywords

references

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 . Research on detection, parameter estimation and sorting algorithm of frequency hopping signal [D ] . Chengdu : University of Electronic Science and Technology of China , 2016 .

沙志超 , 黄知涛 , 周一宇 , 等 . 基于稀疏重构的跳频信号时频分析方法 [J ] . 通信学报 , 2013 , 34 ( 5 ): 107 - 112 .

SHA Z C , HUANG Z T , ZHOU Y Y , et al . Time-frequency analysis of freqency-hopping signals based on sparse recovery [J ] . Journal on Communications , 2013 , 34 ( 5 ): 107 - 112 .

周磊 . 复杂噪声中跳频信号参数估计研究 [D ] . 西安 : 西安电子科技大学 , 2018 .

ZHOU L . Research on parameter estimation of frequency hopping signal in complex noise [D ] . Xi’an : Xidian University , 2018 .

YU L . Research on parameter blind estimation algorithm of Costas frequency hopping signals [J ] . Systems Engineering and Electronics , 2012 , 3 : 444 - 450 .

MA Y K , YAN Y C . Blind detection and parameter estimation of single frequency-hopping signal in complex electromagnetic environment [C ] // Proceedings of the 2016 Sixth International Conference on Instrumentation & Measurement , Computer, Communication and Control (IMCCC) . Piscataway : IEEE Press , 2016 : 370 - 374 .

王忠仁 , 林君 , 李文伟 . 基于Wigner-Ville分布的复杂时变信号的时频分析 [J ] . 电子学报 , 2005 , 33 ( 12 ): 2239 - 2241 .

WANG Z R , LIN J , LI W W . Time-frequency analysis for complex time-varying signals based on Wigner-Ville distribution [J ] . Acta Electronica Sinica , 2005 , 33 ( 12 ): 2239 - 2241 .

CHEN T C . Joint signal parameter estimation of frequency-hopping communications [J ] . IET Communications , 2012 , 6 ( 4 ): 381 - 389 .

付卫红 , 王璐 , 贾坤 , 等 . 基于STFT与SPWVD的跳频参数盲估计算法 [J ] . 华中科技大学学报(自然科学版) , 2014 , 42 ( 9 ): 59 - 63 .

FU W H , WANG L , JIA K , et al . Blind parameter estimation algorithm for frequency hopping signals based on STFT and SPWVD [J ] . Journal of Huazhong University of Science and Technology (Natural Science Edition) , 2014 , 42 ( 9 ): 59 - 63 .

钱怡 , 马庆力 , 路后兵 . 基于改进SPWVD的DS/FH信号跳频参数估计方法 [J ] . 舰船电子对抗 , 2015 , 38 ( 1 ): 50 - 53, 79 .

QIAN Y , MA Q L , LU H B . Estimation method of frequency hopping parameter of DS/FH signal based on improved SPWVD [J ] . Shipboard Electronic Countermeasure , 2015 , 38 ( 1 ): 50 - 53, 79 .

申艳妮 . 非平稳信号的频谱感知方法研究 [D ] . 成都 : 电子科技大学 , 2018 .

SHEN Y N . Research on spectrum sensing method of non-stationary signal [D ] . Chengdu : University of Electronic Science and Technology of China , 2018 .

席有猷 , 李志刚 , 王苗 . 结合图像处理与时频分析的直扩/跳频信号参数估计 [J ] . 电讯技术 , 2014 , 54 ( 8 ): 1071 - 1076 .

XI Y Y , LI Z G , WANG M . Parameters estimation of DS/FH signal based on image processing and time-frequency analysis [J ] . Telecommunication Engineering , 2014 , 54 ( 8 ): 1071 - 1076 .

王宇阳 , 黄浩 , 陶建军 . 基于图像处理的跳频信号参数估计和双网台分选 [J ] . 通信技术 , 2023 , 56 ( 5 ): 604 - 610 .

WANG Y Y , HUANG H , TAO J J . Parameter estimation and dual-network station sorting of frequency hopping signal based on image processing [J ] . Communications Technology , 2023 , 56 ( 5 ): 604 - 610 .

刘佳敏 , 赵知劲 , 尚俊娜 , 等 . 基于时频矩阵局部对比度的跳频信号参数估计 [J ] . 电信科学 , 2021 , 37 ( 10 ): 126 - 135 .

LIU J M , ZHAO Z J , SHANG J N , et al . Parameter estimation of frequency hopping signal based on time-frequency matrix LCM [J ] . Telecommunications Science , 2021 , 37 ( 10 ): 126 - 135 .

曾诚 , 宋燕 . 改进的OTSU和最大熵结合的迭代图像分割算法 [J ] . 智能计算机与应用 , 2020 , 10 ( 12 ): 121 - 125 .

ZENG C , SONG Y . An improved image segmentation algorithm based on OTSU and maximum entropy [J ] . Intelligent Computer and Applications , 2020 , 10 ( 12 ): 121 - 125 .

李卫 . 视觉Transformer模型设计及其轻量化研究 [D ] . 成都 : 电子科技大学 , 2023 .

LI W . Design of visual Transformer model and its lightweight research [D ] . Chengdu : University of Electronic Science and Technology of China , 2023 .

黄文才 . 复杂环境下跳频信号的提取与参数估计 [D ] . 成都 : 电子科技大学 , 2021 .

HUANG W C . Extraction and parameter estimation of frequency hopping signal in complex environment [D ] . Chengdu : University of Electronic Science and Technology of China , 2021 .

侯公羽 , 陈钦煌 , 杨振华 , 等 . 基于改进YOLOv5的安全帽检测算法 [J ] . 工程科学学报 , 2024 , 46 ( 2 ): 329 - 342 .

HOU G Y , CHEN Q H , YANG Z H , et al . Helmet detection method based on improved YOLOv5 [J ] . Chinese Journal of Engineering , 2024 , 46 ( 2 ): 329 - 342 .

王川川 , 张宽桥 , 王满喜 . 基于时频变换和波形整形的跳频信号参数估计方法 [J ] . 强激光与粒子束 , 2024 , 36 ( 9 ): 157 - 163 .

WANG C C , ZHANG K Q , WANG M X . Parameter estimation method for frequency hopping signal based on time-frequency transform and waveform shaping [J ] . High Power Laser and Particle Beams , 2024 , 36 ( 9 ): 157 - 163 .

崔昊杨 , 杨可欣 , 葛海华 , 等 . 面向电力开关柜的轻量型GB-YOLOv5m状态检测方法 [J ] . 电子与信息学报 , 2022 , 44 ( 11 ): 3777 - 3787 .

CUI H Y , YANG K X , GE H H , et al . Lightweight GB-YOLOv5m state detection method for power switchgear [J ] . Journal of Electronics & Information Technology , 2022 , 44 ( 11 ): 3777 - 3787 .

王硕凡 . 复杂场景下多视角行人重识别与跟踪研究 [D ] . 南京 : 东南大学 , 2023 .

WANG S F . Research on pedestrian re-recognition and tracking from multiple perspectives in complex scenes [D ] . Nanjing : Southeast University , 2023 .

浏览量

182

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于深度可分离卷积的MambaUNet的语音增强方法

LEO卫星扩频信号的高精度参数估计方法

基于时频矩阵局部对比度的跳频信号参数估计

非理想信道下的传感器网络一比特最大似然算法

正弦调频连续波信号参数估计新方法