| 摘要: |
| 飞机机身的非刚性振动、航行姿态的改变以及机上旋转部件的转动等均会引发对其雷达回波的非线性调制，采用多重分形测度可以对飞机回波的此类调制特征进行细致的刻画。文中引入方差分形维轨迹（VFDT）这一种新的多重分形算法对飞机回波进行特性分析和特征提取，基于提出的VFDT特征并结合支持向量机（SVM），对实际录取的多种类型飞机回波进行了目标分类识别实验。实验结果表明，VFDT特征可以较好地对多种不同类型的飞机目标进行分类辨识，并具有较小的计算量。 |
| 关键词: 特征提取 方差分形维轨迹 目标分类 低分辨雷达 |
| DOI：DOI:10.3969/j.issn.1672-2337.2020.04.014 |
| 分类号:TN957.51 |
| 基金项目:国家自然科学基金 （No.61561004） |
|
| VFDT Features Based Classification Method for Aircraft |
|
LI Qiusheng， ZHANG Huaxia
|
|
1. Research Center of Intelligent Control Engineering Technology， Gannan Normal University, Ganzhou 341000, China;2. School of Physics and Electronic Information， Gannan Normal University， Ganzhou 341000， China
|
| Abstract: |
| The non-rigid vibration of the fuselage，the change of flying attitude and the rotation of the rotating parts of the aircraft will produce nonlinear modulation on the aircraft target radar echo. The multifractal measure can be used to describe the modulation features of the aircraft echo in detail. In this paper，a new multifractal algorithm，variance fractal dimension trajectory (VFDT)，is introduced to analyze and extract the features of aircraft echoes，and the target classification experiments of various types of aircraft echoes are carried out based on the extracted VFDT features combined with support vector machine (SVM). The experimental results show that the VFDT features can effectively classify different types of experimental targets，and the computational cost is small. |
| Key words: feature extraction variance fractal dimension trajectory (VFDT) target classification low-resolution radar |
