| 摘要: |
| 随着自动驾驶技术的发展，毫米波雷达成为自动驾驶的一个关键传感器，由于汽车雷达数目增加，雷达与雷达间相互干扰是不可避免的问题，为了减轻雷达间的相互干扰，识别车辆中雷达发射的信号类型是很有必要的。针对不同干扰信号类型，本文提出了一种基于残差神经网络的车载雷达干扰分类的方法，首先建立不同类型的干扰数据模型，生成大量的干扰数据，然后应用残差神经网络对不同类型的干扰进行分类。结果显示，该网络不仅收敛速度快，而且在干扰分类方面取得了很好的效果。 |
| 关键词: 毫米波雷达 干扰分类 深度学习 残差网络 |
| DOI：DOI:10.3969/j.issn.1672-2337.2022.06.014 |
| 分类号:TN958.94 |
| 基金项目:国家自然科学基金(No.61561010); 广西创新驱动发展专项(No.桂科AA21077008); 广西重点研发计划项目(No.桂科AB18126003,AB18221016) |
|
| Research on Interference Classification of Automotive Radar Based on ResNet |
|
JIANG Liubing， SHEN Jieqi， CHE Li
|
|
1. School of Information and Communication, Guilin University of Electronic Technology, Guilin 541004, China;2. Guangxi Key Laboratory of Wireless Broadband Communication and Signal Processing, Guilin 541004, China;3. School of Computer and Information Security, Guilin University of Electronic Technology, Guilin 541004, China
|
| Abstract: |
| With the development of automatic driving technology, millimeter wave radar has become a key sensor of automatic driving. However, with the increase of the number of automotive radars, the mutual interference between radars is inevitable. In order to reduce the influence of radar mutual interference, it is necessary to identify the type of signal transmitted by radar in vehicles. For different interference types, this paper proposes an interference classification method based on residual neural network. Firstly, different types of interference models are established to generate a large number of interference data, and then the residual neural network is used to classify different types of interferences. The results show that the network not only converges fast, but also gets good results in interference classification. |
| Key words: millimeter wave radar interference classification deep learning residual neural network |
