基于肌电信号的嵌入式手势识别系统设计  

Design of Gesture Recognition Experiment System Based on Electromyographic Signal

作　　者：杨建华[1] 李正 赵妤 王少文 YANG Jian-hua;LI Zheng;ZHAO Yu;WANG Shao-wen(College of Electronic Information Engineering,Xi'an Technological University,Xi'an 710021,China)

机构地区：[1]西安工业大学电子信息工程学院,西安710021

出　　处：《自动化与仪表》2021年第12期62-66,共5页Automation & Instrumentation

摘　　要：针对传统手势识别系统基于PC机运行,无法进行便携式应用的问题,该文设计了基于肌电信号的嵌入式手势识别系统。系统硬件主要包含肌电传感器、肌电信号调理电路、STM32嵌入式处理器。系统软件主要完成了肌电信号手势识别的特征提取、参数训练、贝叶斯分类器算法,同时增加了FreeRTOS操作系统实现多任务处理。实验测试结果表明,该嵌入式系统能够较为准确地实时完成简单手势识别,识别准确率可以达到87.6%。该系统的研制为可穿戴式生理信号智能感知系统研究提供一定的研究开发基础。Aiming at the problem that the traditional gesture recognition system is based on PC and can not be used in portable applications,this paper designs an embedded gesture recognition system based on EMG signal.The system hardware mainly includes EMG sensor,EMG signal conditioning circuit,STM32 embedded processor.The system software includes feature extraction and training for EMG gesture recognition,Bayesian classifier algorithm design and embedded multi task software implementation based on FreeRTOS operating system.The experimental results show that the embedded system can complete the accurate recognition of simple gestures in real time,and the recognition accuracy can reach 87.6%.The development of the system can provide a certain research and development basis for the wearable physiological signal intelligent sensing system.

关 键 词：肌电采集电路 STM32处理器 贝叶斯分类器 FREERTOS 

分 类 号：TN815[电子电信—信息与通信工程]