«上一篇
 文章快速检索 高级检索

 雷达学报  2018, Vol. 7 Issue (5): 557-564  DOI: 10.12000/JR18061 0

### 引用本文

Zhang Pengfei, Li Gang, Huo Chaoying, et al.. Classification of drones based on micro-doppler radar signatures using dual radar sensors[J]. Journal of Radars, 2018, 7(5): 557-564. DOI: 10.12000/JR18061.

### 文章历史

(清华大学电子系   北京   100084)
(北京环境特性研究所   北京   100854)

Classification of Drones Based on Micro-Doppler Radar Signatures Using Dual Radar Sensors
Zhang Pengfei, Li Gang, Huo Chaoying, Yin Hongcheng
(Department of Electronic Engineering, Tsinghua University, Beijing 100084, China)
(Beijing Institute of Environmental Features, Beijing 100854, China)
Foundation Item: Ministry Research Foundation, Ministry Key Laboratory Research Foundation
Abstract: Classification of drones is important due to their increasing popularity and potential threats. The micro-Doppler signatures that depend on the rotation of rotor blades facilitate the classification of drones. To enhance the robustness of micro-Doppler based classification of drones, dual radar sensing classification scheme is proposed in this paper. First, time-frequency spectrograms are obtained by performing a short-time Fourier transform on the radar data collected by two radar sensors that have similar angular diversity. Then, principal components analysis is utilized to extract the features from the time-frequency spectrograms and the features obtained by the two radar sensors are fused together. Finally, the classification results are obtained by using the support vector machine. The experimental results show that the classification accuracy obtained by the fusion of dual radar sensors is 5% higher than that obtained by only using a single radar sensor.
Key words: Micro-Doppler    Drones    Target classification    Multi-angle and multi-band observation
1 引言

2 实验数据采集

 图 1 实验场景几何示意图 Fig.1 The experimental geometry

 图 2 3类无人机示意图 Fig.2 Appearance of the drones
3 基于微动特征的无人机分类

 图 3 典型识别流程 Fig.3 Typical flow chart of radar recognition
 图 4 特征提取与融合流程示意图 Fig.4 The flow chart of feature extraction and fusion with dual radar sensors
3.1 时频分析

 图 5 3种无人机的时频图 Fig.5 Spectrograms of three types of drones

3.2 特征提取

PCA是一种基于目标统计特性的最佳正交变换。由于它能够有效地消除冗余数据并且本身的计算量小，能很好地用于实时处理，本文采用PCA进行特性提取。首先将2维时频图进行向量化操作，排列为1维向量 ${{x}}$ ，则可以得到训练样本集 ${{X}} = \{ {{{x}}_1}$ ${{x}}_2\; ·\!·\!·\; {{{x}}_n}\}$ 。利用PCA求特征向量：

 图 6 实验数据的特征分布 Fig.6 Feature distribution of the experimental data
3.3 SVM分类器

4 实测数据结果分析

4.1 不同训练样本比例下的识别率分析

 图 7 识别率随训练样本比例变化情况 Fig.7 Recognition accuracy under different sizes of training set

4.2 不同噪声水平下的识别率分析

 图 8 识别率随加性噪声强度变化情况 Fig.8 Recognition accuracies under different levels of additive Gaussian white noise

5 结论