表面肌电信号的多流卷积网络融合手势识别方法  

GESTURE RECOGNITION BASED ON MULTI-STREAM CONVOLUTION NETWORK FOR SURFACE EMG SIGNAL

作　　者：谷学静 沈攀 刘海望 郭俊 位占锋 Gu Xuejing;Shen Pan;Liu Haiwang;Guo Jun;Wei Zhanfeng(School of Electrical Engineering,North China University of Technology,Tangshan 063210,Hebei,China;Tangshan Digital Media Engineering Technology Research Center,Tangshan 063000,Hebei,China;School of Electrical Information,Qing Gong College,North China University of Technology,Tangshan 063000,Hebei,China)

机构地区：[1]华北理工大学电气工程学院,河北唐山063210 [2]唐山市数字媒体工程技术研究中心,河北唐山063000 [3]华北理工大学轻工学院电气信息学院,河北唐山063000

出　　处：《计算机应用与软件》2022年第8期220-225,共6页Computer Applications and Software

基　　金：河北省自然科学基金高端钢铁冶金联合研究基金专项(F2017209120)。

摘　　要：为了提高基于表面肌电信号的手势动作识别的准确率,提出一种多流卷积融合的深度学习方法,通过对手臂肌肉区域间所产生的肌电信号图像进行多流表征,将表征所产生的多个肌电信号的子图像分别输入到构建的多流卷积网络中,由多流卷积网络分支对这些不同的肌电子图像进行特征提取和建模;通过融合网络层进行特征融合,将融合后的特征输入Softmax层进行手势动作的分类,输出得到概率最大的动作类型的标签,从而达到提升手势识别准确率的效果。实验结果表明用多流卷积的方法处理肌电信号的手势识别准确率比传统机器学方法高出17百分点。In order to improve the accuracy of gesture recognition based on surface EMG signals,we propose a multi-stream convolution fusion deep learning.We performed the multi-stream characterization of the EMG signals generated between different muscle regions of the arm.The sub-images of multiple EMG signals were input into the constructed multi-stream convolutional network.The multi-stream convolutional network branches performed feature extraction and modeling of those different sub-images.Through the feature fusion in the fusion network layer,we input the fused features into the Softmax layer for the classification of gesture actions,and output the label of the action type with the greatest probability,so as to improve the accuracy of gesture recognition.The experimental result shows that the gesture recognition accuracy of EMG signal processed by multi stream convolution method is 17 percentage points higher than that of traditional machine methods.

关 键 词：手势识别 肌电信号 多流表征 多流卷积 深度学习 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]