| 引用本文: | 孙延鹏， 李思锐， 屈乐乐. 基于多域特征融合的旋翼无人机分类识别[J]. 雷达科学与技术, 2023, 21(4): 447-453.[点击复制] |
| SUN Yanpeng, LI Sirui, QU Lele. Rotorcraft UAV Classification and Recognition Based on Multi⁃Domain Feature Fusion[J]. Radar Science and Technology, 2023, 21(4): 447-453.[点击复制] |
|
| 摘要: |
| 为提高雷达旋翼无人机的识别效果，本文提出一种基于多域特征融合的旋翼无人机分类方法。首先利用K波段连续波（Continuous Wave，CW）雷达观测多旋翼无人机，对采集到的雷达回波信号进行信号处理依次得到时频图、节奏速度图（Cadence?Velocity Diagram, CVD）和节奏频谱图（Cadence Frequency Spectrum，CFS），然后将时频图和CVD图分别输入SqueezeNet网络，CFS数据输入一维卷积神经网络（1?D?CNN）提取回波信号在时频域、节奏速度域和节奏频率域的特征，最后将特征融合输入支持向量机（Support Vector Machine, SVM）进行分类。实测雷达数据处理的结果表明基于多域特征融合的旋翼无人机分类识别方法对三类旋翼无人机的分类准确率达到99.14%。 |
| 关键词: 旋翼无人机分类 多域特征融合 SqueezeNet网络 支持向量机 |
| DOI：DOI:10.3969/j.issn.1672-2337.2023.04.012 |
| 分类号:TN957.5 |
| 基金项目:国家自然科学基金（No.61671310）；航空科学基金（No.2019ZC054004）；辽宁省兴辽英才计划项目基金（No.XLYC1907134）；辽宁省百千万人才工程项目基金（No.2018B21） |
|
| Rotorcraft UAV Classification and Recognition Based on Multi⁃Domain Feature Fusion |
|
SUN Yanpeng, LI Sirui, QU Lele
|
|
College of Electronic Information Engineering, Shenyang Aerospace University, Shenyang 110136, China
|
| Abstract: |
| In order to improve the recognition effect of rotorcraft UAV based on radar, this paper proposes a rotorcraft UAV classification method based on multi?domain feature fusion. Firstly, the K?band continuous wave （CW） radar is used to observe the multi?rotor UAV. The collected radar echo signals are processed to obtain the time?frequency diagram, cadence?velocity diagram （CVD） and cadence?frequency spectrum （CFS） successively. Then the time?frequency map and CVD are respectively input into SqueezeNet network, and the CFS data are input into one?dimensional convolutional neural network （1?D?CNN） to extract the features of echo signal in time?frequency domain, rhythm?velocity domain and rhythm?frequency domain. Finally, the features are fused into support vector machine （SVM） for classification. The results of radar data processing show that the classification accuracy of three types of rotorcraft UAV based on multi?domain feature fusion is 99.14%. |
| Key words: rotorcraft UAV classification multi⁃domain feature fusion SqueezeNet network support vector machine |
