基于三轴加速度传感器的跌倒检测研究

本文基于MMA7260QT加速度传感器获取的人体运动加速度信号,采用人体加速度向量幅值(SVM)和人体加速度向量区域值(SMA)描述了老年人的运动状态,检测人体跌倒,具有良好的准确性和实时性。采用bior3.3小波分析,在轮廓的基础上,最大程度上保留了细节,有效的去除噪声对特征量的干扰。本文提出了人体跌倒检测算法,大大降低了误判率和漏判率。首先,检测人体SVM是否超过阈值进行第一级跌倒检测,区别出人体日常活动(ADL)和跌倒;其次在此基础上,检测第一级各个跌倒的SMA值,是否超过阈值,判断跌倒和疑似跌倒。当两次判断都检测到跌倒发生时,报警。

Triaxial Accelerometer-Based Fall Detection Research

This article is based on human movement acceleration signal of acceleration sensors MMA7260QT, describing the movement state of the old with the body acceleration vector amplitude value vectors (SVM) and the body acceleration area (SMA) to detect man''s fall, which has a good accuracy and real-time performance. Adopting the method of Bior3.3 wavelet analysis ,this paper effectively remove noise interference with characteristics and retained the maximum details of outline. Fall in the human body detection algorithmproposed in this paper greatly reduce the misjudgment rate and false negative rate. In order to distinguish human daily activities (ADL) and fall,the first level fall detection is to judge whether the SVM is more than the detection threshold. On this basis, this paper detected whether the SMA of the falls in the first level is more than threshold, to distinguish fall down and suspected. When the above two steps detection both judge that fall occurs, the systemalerts.