基于柔性阵列压感坐垫的人体坐姿检测系统  

Human Sitting Posture Detection System Based on Flexible Array Pressure Sensing Cushion

作　　者：张美燕 徐祎楠 王露晗 陈校楠 康睿鑫 朱启蔚 ZHANG Mei-yan;XU Yi-nan;WANG Lu-han;CHEN Xiao-nan;KANG Rui-xing;ZHU Qi-wei(College of Electrical Engineering,Zhejiang University of Water Resources and Electric Power,Hangzhou 310018,China)

机构地区：[1]浙江水利水电学院电气工程学院,浙江杭州310018

出　　处：《浙江水利水电学院学报》2021年第6期66-69,80,共5页Journal of Zhejiang University of Water Resources and Electric Power

基　　金：国家级大学生创新创业训练计划项目(202011481014);浙江省新苗人才计划(2021R423005)。

摘　　要：正确的伏案工作姿态对于人体健康有着重要的作用。针对目前各种坐姿检测方法存在使用困难、实时性差、精度较低等缺陷,提出并实现了一种基于柔性压感坐垫的人体坐姿检测系统,该系统采用4路16路模拟开关和高速ADC并行采集了32×32和16×16分辨率的阵列压力传感数据,并基于SVM的坐姿聚类方法,实现了6种常见坐姿状态的自动判决。实验结果表明,此方法和系统对于6种坐姿的判决正确率能够达到95%,相比于图像等方法具有更高的精度和实时性。Correct posture at the desk plays an important role in human health.In view of the existing defects of various sitting posture detection methods such as difficulty in use,poor real-time performance and low accuracy,a human body sitting posture detection system based on flexible pressure sensing cushion was proposed and implemented,which adopts four 16-channel analog switches and one high-speed ADC to collect the array pressure sensor data with32×32 and 16×16 resolution in parallel and realizes the automatic judgement of six common sitting states based on SVM clustering method.Experimental results verify that the recognition accuracy of the proposed method and system for six sitting postures can reach 95%,with higher accuracy and real-time performance than image based recognition methods.

关 键 词：柔性压力传感器 坐姿检测 多路模拟开关 支持向量机(SVM) 

分 类 号：R381[医药卫生—医学寄生虫学]