吉林大学学报(信息科学版) ›› 2016, Vol. 34 ›› Issue (1): 1-7.

• 论文 •    下一篇

基于无线体域网的人体姿态多级分层识别算法

胡封晔1, 王璐1, 王珊珊1, 郭纲2   

  1. 1. 吉林大学通信工程学院, 长春130012; 2. 空军航空大学飞行器控制系, 长春130022
  • 收稿日期:2015-05-05 出版日期:2016-01-25 发布日期:2016-05-10
  • 作者简介:胡封晔(1974—), 男, 河南原阳人, 吉林大学教授, 硕士生导师, 博士, 主要从事无线体域网、移动通信中的信号处理、认知无线电研究, (Tel)86-18643119191(E-mail)hufy@jlu. edu. cn。
  • 基金资助:

    国家自然科学基金资助项目(61074165; 61273064)

Hierarchical Recognition Algorithm of Body Posture Based on Wireless Body Area Network

HU Fengye1, WANG Lu1, WANG Shanshan1, GUO Gang2   

  1. 1. College of Communication Engineering, Jilin University, Changchun 130012, China;2. Department of Flight Vehicle Control, Air Force Aviation University, Changchun 130022, China
  • Received:2015-05-05 Online:2016-01-25 Published:2016-05-10

摘要:

为解决无线体域网WBAN(Wireless Body Area Network)中人体姿态识别率低、算法复杂的问题, 设计了一种以多层分级理论为基础的人体姿态多级分层识别算法。考虑到使用者的舒适度, 将九轴加速度陀螺仪传感器(VG350) 做成腰带佩戴在腰部实时采集数据。运用加速度向量幅值(SVM: Signal Vector Magnitude)、角度、角加速度和位移等参量, 通过对实际测量数据的分析, 将坐、蹲、弯腰、慢走和跑等姿态进行识别。实验结果表明, 该算法简单, 姿态识别率高达96. 5%。

关键词: 人体姿态多级分层识别算法, 加速度陀螺仪传感器, 信息处理技术, 加速度向量幅值

Abstract:

To solve the low recognition rate and complex algorithm of human body posture in WBAN(Wireless Body Area Network), a hierarchical theory is employed to design a human body posture hierarchical recognition algorithm. Considering the comfort level of the user, the nine axis acceleration gyroscope sensor (VG350) is placed into a belt worn at the waist to collect real-time data. Use of acceleration SVM ( Signal Vector Magnitude), angle, angular acceleration and displacement recognized five gestures (sit, squat, stoop, walk and run) by analyzing collected data. The experimental results show that the algorithm is simple and posture recognition rate is up to 96. 5%.

Key words: information processing technology, acceleration signal vector magnitude, body posture hierarchical recognition algorithm, acceleration gyroscope sensor

中图分类号: 

  • TN911. 7