Most of the work in hand gesture recognition (HGR) focuses on developing diverse classification algorithms based on micro-Doppler (mD) spectrogram, that is 1-D motion along the radial direction. In this work, we exert effort on the radar system and preprocessing methods to extract 2-D motions for HGR. Specifically, we utilize an interferometric radar with two widely spaced receivers to obtain both radial and transversal micromotion features of hand gestures. In the preprocessing stage, as pre-interferometry is nonlinear multiplication in time domain, both the increased noise level and unwanted cross-terms may reduce its usefulness for HGR. To solve these problems, we propose a post-interferometric preprocessing method in frequency domain, which is capable of reducing noise level of the obtained spectrogram and suppressing the nuisance cross-terms. We measure four pairs of symmetric hand gestures from three persons and compare the HGR accuracy using different preprocessing methods. Experimental results show that the mD processing combined with post-interferometry give the highest HGR accuracy of over 99%.

中文翻译：

---

使用径向和横向双微动特征进行手势识别


手势识别 (HGR) 领域的大部分工作重点是开发基于微多普勒 (mD) 频谱图（即沿径向的一维运动）的各种分类算法。在这项工作中，我们致力于雷达系统和预处理方法来提取 HGR 的二维运动。具体来说，我们利用具有两个间隔较远的接收器的干涉雷达来获得手势的径向和横向微运动特征。在预处理阶段，由于预干涉测量是时域中的非线性乘法，因此增加的噪声水平和不需要的交叉项可能会降低其对 HGR 的有用性。为了解决这些问题，我们提出了一种频域后干涉预处理方法，该方法能够降低所获得的频谱图的噪声水平并抑制有害的交叉项。我们测量了三个人的四对对称手势，并使用不同的预处理方法比较了 HGR 准确性。实验结果表明，mD 处理与后干涉测量相结合的 HGR 精度最高可达 99% 以上。