Convolutional neural networks have often been proposed for processing radar
Micro-Doppler signatures, most commonly with the goal of classifying the
signals. The majority of works tend to disregard phase information from the
complex time-frequency representation. Here, the utility of the phase
information, as well as the optimal format of the Doppler-time input for a
convolutional neural network, is analysed. It is found that the performance
achieved by convolutional neural network classifiers is heavily influenced by
the type of input representation, even across formats with equivalent
information. Furthermore, it is demonstrated that the phase component of the
Doppler-time representation contains rich information useful for classification
and that unwrapping the phase in the temporal dimension can improve the results
compared to a magnitude-only solution, improving accuracy from 0.920 to 0.938
on the tested human activity dataset. Further improvement of 0.947 is achieved
by training a linear classifier on embeddings from multiple-formats.

对于处理雷达微多普勒迹象，研究中分析了卷积神经网络的相位信息的实用性以及多普勒 - 时间输入的最佳格式。研究发现，卷积神经网络分类器的性能受到输入表示类型的影响，即使在具有等效信息的不同格式之间也是如此。此外，研究证明了多普勒 - 时间表示的相位分量包含用于分类的丰富信息，并且在时间维度上进行相位解包能够改善结果，将在测试的人体活动数据集上的准确性从 0.920 提高到 0.938。通过在多种格式上嵌入进行线性分类器的训练，进一步改进，达到 0.947 的准确性。

卷积神经网络用于雷达微多普勒特征处理的输入格式

On Input Formats for Radar Micro-Doppler Signature Processing by  Convolutional Neural Networks

As a hot topic in recent years, the ability of pedestrians identification
based on radar micro-Doppler signatures is limited by the lack of adequate
training data. In this paper, we propose a data-enhanced multi-characteristic
learning (DEMCL) model with data enhancement (DE) module and
multi-characteristic learning (MCL) module to learn more complementary
pedestrian micro-Doppler (m-D) signatures. In DE module, a range-Doppler
generative adversarial network (RDGAN) is proposed to enhance free walking
datasets, and MCL module with multi-scale convolution neural network (MCNN) and
radial basis function neural network (RBFNN) is trained to learn m-D signatures
extracted from enhanced datasets. Experimental results show that our model is
3.33% to 10.24% more accurate than other studies and has a short run time of
0.9324 seconds on a 25-minute walking dataset.

本文提出了一种数据增强的多特征学习模型（DEMCL），通过数据增强模块和多特征学习模块学习更多互补的行人微多普勒（m-D）信号，并通过实验证明该模型比其他研究的准确率高 3.33% 至 10.24%，且其对于一套 25 分钟的步行数据的短时运行时间为 0.9324 秒。