Wireless Hand Gesture Recognition Based on Continuous-Wave Doppler Radar Sensors
Wireless Hand Gesture Recognition Based on Continuous-Wave Doppler Radar Sensors
复制标题
基于连续波多普勒雷达传感器的无线手势识别
DOI：
10.1109/tmtt.2016.2610427
复制
发表时间：
2016-11-01
影响因子：
4.3
通讯作者：
Ran, Lixin
中科院分区：
文献类型：
--
作者：
Fan, Tenglong;Ma, Chao;Ran, Lixin
短程连续波多普勒雷达传感器主要用于各种运动的非接触检测。在本文中，我们研究的可行性，实现远程鼠标，一个计算机的输入设备，通过识别人体手势的基础上，双通道多普勒雷达传感器的功能。直接转换架构，对称副载波调制和带通采样技术被用来获得一个具有成本效益的解决方案。反正弦算法和运动成像算法提出了线性重建的手和手指的运动在一个2-D平面从解调的多普勒相移。实验结果验证了所提出的结构和算法的有效性。与频域“微多普勒”方法不同，提出的基于线性运动重构的远程手势识别方法能够识别出相应运动的明确特征，在人机交互的实际应用中具有广阔的应用前景。
Short-range continuous-wave Doppler radar sensors have been mainly used for noncontact detection of various motions. In this paper, we investigate the feasibility to implement the function of a remote mouse, an input device of a computer, by recognizing human gestures based on a dual-channel Doppler radar sensor. Direct conversion architecture, symmetric subcarrier modulation, and bandpass sampling techniques are used to obtain a cost-effective solution. An arcsine algorithm and a motion imaging algorithm are proposed to linearly reconstruct the hand and finger motions in a 2-D plane from the demodulated Doppler phase shifts. Experimental results verified the effectiveness of the proposed architecture and algorithms. Different from the frequency-domain “micro-Doppler” approach, the proposed remote gesture recognition based on linear motion reconstruction is able to recognize definitive signatures for the corresponding motions, exhibiting promising potential in practical applications of human-computer interaction.