Hand Gesture Recognition Based on Trajectories Features and Computation-Efficient Reused LSTM Network
Hand Gesture Recognition Based on Trajectories Features and Computation-Efficient Reused LSTM Network
复制标题
基于轨迹特征和计算高效重用 LSTM 网络的手势识别
DOI：
10.1109/jsen.2021.3079564
复制
发表时间：
2021-08-01
影响因子：
4.3
通讯作者：
Zheng, Xinbo
中科院分区：
文献类型：
--
作者：
Yang, Zhaocheng;Zheng, Xinbo
基于雷达传感器的非接触式手势识别被认为是一种有效的人机交互技术。在本文中，我们提出了一种手势识别方法的基础上的距离-多普勒-角度轨迹和重用的长短期记忆（RLSTM）网络使用77 GHz的调频连续波（FMCW）多输入多输出（MIMO）雷达。为了克服大量的手势干扰，手势桌面的设计和潜在的手势检测方法来确定它是否是一个潜在的手势。如果手势发生在假设的手势桌面中，则利用离散傅立叶变换（DFT）、多信号分类（MUSIC）算法和卡尔曼滤波提取距离-多普勒-角度轨迹。这些特征不仅可以显着降低后续神经网络的维数，而且还可以利用MIMO雷达提供的三维信息。最后，提出了一种具有重用前向传播方法的LSTM网络，以利用空间，时间和多普勒信息并简化网络架构。实验结果表明，所提出的方法可以达到99.4%的平均准确率和识别一个新的人的手势与9个手势的平均准确率为98.0%。
Touchless hand gesture recognition using radar sensor is considered to be an attractive and effective technique for human-machine interaction. In this paper, we propose a hand gesture recognition approach based-on range-Doppler-angle trajectories and a reused long short-term memory (RLSTM) network using a 77GHz frequency modulated continuous wave (FMCW) multiple-input-multiple-output (MIMO) radar. To overcome amounts of gesture interferences, a gesture desktop is designed and a potential hand gesture detection approach is followed to determine whether it is a potential hand gesture. If the gesture happens in the assumed gesture desktop, the range-Doppler-angle trajectories are extracted by using the discretize Fourier transform (DFT), multiple signal classification (MUSIC) algorithm and the Kalman filtering. These signatures cannot only significantly reduce the dimension for the following neural network but also exploit the three dimensional information provided by the MIMO radar. Finally, a LSTM network with the reused forward propagation approach is proposed to exploit the spatial, temporal and Doppler information and simplify the network architecture. The experimental results show that the proposed approach can achieve an average accuracy of 99.4% and recognize a new person’s hand gestures with an average accuracy of 98.0% for 9 hand gestures.