基于倾角的跌倒检测方法与系统研究  

Study on the Method and System for Falling Detection Based on the Inclinometer

作　　者：朱勇[1] 张研[1] 宋佳[1] 邱天爽[1] 

机构地区：[1]大连理工大学电子信息与电气工程学部生物医学工程系,大连116024

出　　处：《生物医学工程学杂志》2013年第1期95-99,共5页Journal of Biomedical Engineering

基　　金：国家自然科学基金资助项目(60940023;60872122)

摘　　要：跌倒作为一种伤害性动作,威胁着人的安全与健康,特别是对于老年人,跌倒往往造成损伤甚至因伤死亡的严重后果。本文提出一种基于角度的跌倒检测方法。首先,利用安装在腰部的便携式角度传感装置,采集人体运动时的角度信息,并通过无线数据传输装置发送到计算机。然后,将跌倒过程分为3个检测阶段(跌倒初期、跌倒碰撞、倒后姿势),通过对每个阶段的角度数据进行短时特征提取与分析,做出基于阈值的判决。最终,综合3个阶段的判决结果给出较为稳健的跌倒检测结果。实验结果表明,本文采用的基于角度的跌倒检测方法较为有效,跌倒检测正确率达到97.23%,且同时漏检率为0。A falling is a risky incident of safety and health of human. It may cause serious injuries, such as bone frac- ture, and even death. A falling detection method based on inclinometer is described. At first, we collect angle data recorded by a wearable inclinometer placed at subject＇s waist. The angular data are transmitted to PC through a wireless data transmission device. Then, the falling duration is divided into three phases： the state of fall, the impact phase, and the posture phase. We make threshold-based fall-detection decisions in every phase after feature extrac- tion and analysis of the short-time angle data. Finally, a robust falling detection result is given by comprehensive considerations of the three phases decisions. The experiment results proved that the accuracy of our falling detection method was up to 97.23% without undetected falls.

关 键 词：跌倒检测 角度传感器 动作识别 加速度传感器 

分 类 号：R318.0[医药卫生—生物医学工程]