• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Applied Computational Electromagnetics Society journal >Micro-motion Forms Classification of Space Cone-shaped Target Based on Convolution Neural Network
【24h】

Micro-motion Forms Classification of Space Cone-shaped Target Based on Convolution Neural Network

机译：基于卷积神经网络的空间锥形目标微运动形式分类

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this paper, the echo models with different micro-motion forms (spin, tumbling, precession, and nutation) of space cone-shaped target are built. Different from the ideal point scatterers model, the radar echo contains the contribution from the complex radar cross section (RCS) of point scatterer vs aspect angle. And a convolution neural network (CNN) model for micro-motion forms classification based on the micro-Doppler characteristics in spectrograms is presented. The simulation results show that our method can discriminate different micro-motion forms effectively and the overall accuracy is 97.24%. Different levels of additive white Gaussian noise are added to simulate noise-contaminated radar echo. It has been found that the presented method has a stronger anti-noise ability than support vector machine (SVM). When the Signal-to-Noise Ratio (SNR) of Gaussian white noise is 10 dB, the overall accuracy of our algorithm is 29.79% higher than that of SVM.
机译：本文建立了具有不同微运动形式（旋转，翻滚，进动和章动）的空间锥形目标回波模型。与理想的点散射体模型不同，雷达回波包含点散射体的复杂雷达横截面（RCS）对纵横角的贡献。提出了基于频谱图中微多普勒特征的微运动形式分类的卷积神经网络模型。仿真结果表明，该方法可以有效地区分不同的微动形式，总体精度为97.24％。添加了不同级别的加性高斯白噪声，以模拟受噪声污染的雷达回波。已经发现，所提出的方法具有比支持向量机（SVM）更强的抗噪声能力。当高斯白噪声的信噪比（SNR）为10 dB时，我们算法的整体精度比SVM高29.79％。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号