›› 2015, Vol. 28 ›› Issue (3): 11-.

• 论文 • 上一篇    下一篇

一种基于三轴加速度的跌倒检测方法

李政   

  1. (西安电子科技大学 物理与光电工程学院,陕西 西安 710071)
  • 出版日期:2015-03-15 发布日期:2015-03-12
  • 作者简介:李政(1989—),男,硕士研究生。研究方向:嵌入式系统开发。E-mail:416124633@qq.com

Falling Detection Method Based on Axis Acceleration

LI Zheng   

  1. (School of Physics and Optoelectronic Engineering,Xidian University,Xi'an 710071,China)
  • Online:2015-03-15 Published:2015-03-12

摘要:

提出了一种新的跌倒检测方法,基于三轴加速度数据和模式识别。这种方法利用MMA7260Q加速度传感器来识别物体运动时的加速度变化。由于在跌倒的过程中,三轴信号包含于宽广的信号区域中,因而文中提出的方法利用加速度峰值和加速度能量曲线来产生三轴加速度信号。利用文中提出的方法可避免由于人体在跌倒时由角度变化而产生的误差。根据实验结果,该方法在检测跌倒发生时的准确率可达90%以上。

关键词: 跌倒检测, 三轴加速度, 模式识别

Abstract:

This paper presents a new falling detecting method based on three-axis acceleration signal and pattern recognition.This method uses an acceleration sensor named MMA7260Q.When falling happens,the three-axis signal is involved in a huge signal area,and therefore the method uses the peak value of acceleration and the curve of acceleration energy to generate three-axis acceleration signal.This method can avoid the error caused by the changes of angle when falling happens.According to the result of experiments,using the method presented in this paper,the accuracy of falling detection is up to more than 90%.

Key words: falling detection;three-axis acceleration;pattern recognition

中图分类号: 

  • TP277.1