基于阈值与PSO-SVM的人体跌倒检测研究  

Research on Human Fall Detection Based on Threshold and PSO-SVM

作　　者：孙晓雯[1] 孙子文[1] 秦昉[1] 

机构地区：[1]江南大学物联网工程学院,江苏无锡214122

出　　处：《计算机工程》2016年第5期317-321,共5页Computer Engineering

基　　金：国家自然科学基金资助项目(61373126);江苏省自然科学基金资助项目(BK20131107)

摘　　要：为提高人体跌倒检测精确度,提出一种基于智能手机加速度传感器的人体跌倒检测算法。通过智能手机获取人体运动加速度信息,采用阈值分类与模式识别分类相结合的算法进行跌倒检测。通过阈值检测实现人体行为跌倒状态的初步判定,判断是否为疑似跌倒行为。由模式识别方法进一步实现对疑似跌倒行为的精确分类,提取倾角和斜率作为人体跌倒分类特征,利用粒子群优化参数的支持向量机分类器从疑似跌倒行为中识别跌倒行为。仿真实验结果显示,与未优化的支持向量机方法以及加速度阈值方法相比,该算法能有效提高人体跌倒检测准确率。To improve the accuracy in human fall detection, a fall detection algorithm based on acceleration sensor in a smart phone is proposed. The acceleration information of human movement is collected by a smart phone, and a mixed method is utilized by combining threshold classification with pattern recognition classification to detect falls. Threshold classification is used to realize preliminary determination of human behavior. The accurate determination of human behavior is realized by using pattern recognition classification, which includes extracting inclination and slope as classification feature through Support Vector Machine （SVM） whose parameters are optimized by Particle Swarm Optimization（PSO） algorithm to detect falls. In the comparison with SVM whose parameters are not optimized and the acceleration threshold algorithm, the simulation experimental results show that the human fall detection accuracy of the proposed fall detection algorithm is higher than the comparison algorithms.

关 键 词：跌倒检测 加速度传感器 阈值检测 模式识别 粒子群优化 支持向量机 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]