老人跌倒姿态实时识别系统硬件设计
|
摘要
针对老人跌倒姿态识别的需求,设计了一套基于石墨烯/橡胶传感器与MPU6050的老人跌倒姿态实时识别系统。石墨烯/橡胶传感器位于膝盖处,传感器的电阻会随着腿部运动而发生变化,从而实现对腿部运动状态检测;MPU6050安装在人体上身,用来监测人体正常状态和意外跌倒时加速度水平。系统硬件设计以MSP430F149单片机为核心,设计了传感器信号调理模块、主控电路模块、电源模块、MPU6050接口模块、报警模块、蓝牙模块。系统分别采集石墨烯/橡胶传感器与MPU6050的输出信号,并且通过跌倒监测算法判断是否出现跌倒,通过报警模块将老人的位置信息连同跌倒姿态以短信的形式发送至监护人手机上,构建完整的监测网络。实验结果表明系统监测跌倒的准确率达95.84%,跌倒姿态的准确率达90..84%,能够实现对老人跌倒姿态的实时识别。
In order to meet the needs of elderly fall posture recognition,a real-time system based on graphene/rubber sensor and MPU6050 is designed.The graphene/rubber sensor is placed at the knee and the resistance of the sensor changes as the leg moves,to achieve the detection of leg movement.The MPU6050 is placed on the upper body to monitor the normal state of the human body and the acceleration level when accidentally falls.As the kennel component,MSP430 F149 is used to propose the hardware system,which includes sensor monitoring module,kennel controlling module,power module,MPU6050 interface module,alerting module and blue teeth module.The proposed system collects the output signals of the graphene/rubber sensor and the MPU6050 respectively,and judges whether there is a fall from a monitoring algorithm.When the fall information or the alarm information was detected,the system remind the danger through the alarm module.At the same time,the falling information and location are sent to the specified mobile phone by short message so as to establish a monitoring network.Experimental results show that the accuracy rate of monitoring falls and falling posture are 95.84% and 90.84%,respectively,which can realize the real-time recognition of the fall posture of the elderly.
In order to meet the needs of elderly fall posture recognition,a real-time system based on graphene/rubber sensor and MPU6050 is designed.The graphene/rubber sensor is placed at the knee and the resistance of the sensor changes as the leg moves,to achieve the detection of leg movement.The MPU6050 is placed on the upper body to monitor the normal state of the human body and the acceleration level when accidentally falls.As the kennel component,MSP430 F149 is used to propose the hardware system,which includes sensor monitoring module,kennel controlling module,power module,MPU6050 interface module,alerting module and blue teeth module.The proposed system collects the output signals of the graphene/rubber sensor and the MPU6050 respectively,and judges whether there is a fall from a monitoring algorithm.When the fall information or the alarm information was detected,the system remind the danger through the alarm module.At the same time,the falling information and location are sent to the specified mobile phone by short message so as to establish a monitoring network.Experimental results show that the accuracy rate of monitoring falls and falling posture are 95.84% and 90.84%,respectively,which can realize the real-time recognition of the fall posture of the elderly.
引文
[1] 罗媛媛.浅谈老年人跌倒问题的相关因素研究与预防护理[J].临床医药文献电子杂志,2017(47):9230-9231.
[2] 张怡然.浅析老年人跌倒的原因及防治措施[J].家庭医药.就医选药,2018(10):36-327.
[3] W WIBISONO,DN ARIFIN,BA PRATOMO,et al.Falls detection and notification system using tri-axial accelerometer and gyroscope sensors of a smartphone[C].2013 Conference on Technologies and Applications of Artificial Intelligence.TAAI:IEEE Computer Society,2014:382-385.
[4] 杨任兵,程文播,钱庆,等.红外图像中基于多特征提取的跌倒检测算法研究[J].红外技术,2017,39(12):1131-1138.
[5] 汪大峰,刘勇奎,刘爽,等.视频监控中跌倒行为识别[J].电子设计工程,2016,24(22):1222-1226.
[6] YANG LEI,REN YANYUN,ZHANG WENQIANG.3D Depth image analysis for indoor fall detection of elderly people[J].数字通信,2016,2(1):24-34.
[7] ISMAIL MOHAMED.MAHER.BEN,BCHIR OUIEM..Automatic fall detection using membership based histogram descriptors[J].Journal of Computer Science and Technology,2017,33(2):237.
[8] TOREYIN,DEDEOGLU,CETIN.HMM based falling person detection using both audio and video[C].The Workshop on Computer Vision in Human-Computer Interaction.Graz,2006:211-220.
[9] 鲍楠,姜博文,李永泽,等.基于Kinect传感器的摔倒检测研究[J].电子设计工程,2017,25(12):149-152.
[10] KHAN M S,YU M,FENG P,et al.An unsupervised acoustic fall detection system using source separation for sound interference suppression[J].Signal Processing,2015,110:199-210.
[11] 李仲年,臧春华,杨刚,等.基于噪声嵌入的跌倒检测系统设计[J].微处理机,2017,38(2):74-76.
[12] CHEFFENA M.Fall detection using smartphone audio features[J].IEEE J Biomed Health Inform,2016,20(4):1073-1080.
[13] TUAN NGUYEN GIA,VICTOR KATHAN SARKER,LGOR TCARENKO,et al.Energy efficient wearable sensor node for IoT-based fall detection systems[J].Microprocessors & Microsystems,2018,56:34-46.
[14] 陈鹏,涂亚庆,童俊平,等.可穿戴式跌倒检测智能系统设计[J].传感器与微系统:2017,36(2):114-116.
[15] HSIEH CHIA-YEH,HUANG CHIH-NING,LIU KAI-CHUN,et al.A machine learning approach to fall detection algorithm using wearable sensor[C].Proceedings of the IEEE International Conference on Advanced Materials for Science and Engineering.Tainan:Institute of Electrical and Electronics Engineers Inc,2017:707-710.
[16] 贾震宇,王维,王琛,等.可穿戴设备在医疗领域中的应用发展[J].中国医疗设备,2017,32(2):96-99.
[17] 任玉兰,宋航,姜兆宇,等.石墨烯性能及研究进展[J].牡丹江师范学院学报(自然科学版),2017,100(3):43-46.
[18] 唐征海,郭春宝,张立群,等.石墨烯/橡胶纳米复合材料[J].高分子学报,2014(7):865-877.
[19] 王鹏,苏正涛,王珊,等.国内外石墨烯/橡胶复合材料研究进展[J].新材料产业,2015(6):58-66.
[20] TIANYI ZHEN,LILEI MAO,JIAWEI WANG,et al.Wearable preimpact fall detector using SVM[C].Proceedings of the International Conference on Sensing Technology.Nanjing:IEEE Computer Society,2016:1-6.
[21] 马琼华,王忠,郑晓彬.基于Android的老年人跌倒检测系统研究[J].数字技术与应用,2017(2):105-106.
[2] 张怡然.浅析老年人跌倒的原因及防治措施[J].家庭医药.就医选药,2018(10):36-327.
[3] W WIBISONO,DN ARIFIN,BA PRATOMO,et al.Falls detection and notification system using tri-axial accelerometer and gyroscope sensors of a smartphone[C].2013 Conference on Technologies and Applications of Artificial Intelligence.TAAI:IEEE Computer Society,2014:382-385.
[4] 杨任兵,程文播,钱庆,等.红外图像中基于多特征提取的跌倒检测算法研究[J].红外技术,2017,39(12):1131-1138.
[5] 汪大峰,刘勇奎,刘爽,等.视频监控中跌倒行为识别[J].电子设计工程,2016,24(22):1222-1226.
[6] YANG LEI,REN YANYUN,ZHANG WENQIANG.3D Depth image analysis for indoor fall detection of elderly people[J].数字通信,2016,2(1):24-34.
[7] ISMAIL MOHAMED.MAHER.BEN,BCHIR OUIEM..Automatic fall detection using membership based histogram descriptors[J].Journal of Computer Science and Technology,2017,33(2):237.
[8] TOREYIN,DEDEOGLU,CETIN.HMM based falling person detection using both audio and video[C].The Workshop on Computer Vision in Human-Computer Interaction.Graz,2006:211-220.
[9] 鲍楠,姜博文,李永泽,等.基于Kinect传感器的摔倒检测研究[J].电子设计工程,2017,25(12):149-152.
[10] KHAN M S,YU M,FENG P,et al.An unsupervised acoustic fall detection system using source separation for sound interference suppression[J].Signal Processing,2015,110:199-210.
[11] 李仲年,臧春华,杨刚,等.基于噪声嵌入的跌倒检测系统设计[J].微处理机,2017,38(2):74-76.
[12] CHEFFENA M.Fall detection using smartphone audio features[J].IEEE J Biomed Health Inform,2016,20(4):1073-1080.
[13] TUAN NGUYEN GIA,VICTOR KATHAN SARKER,LGOR TCARENKO,et al.Energy efficient wearable sensor node for IoT-based fall detection systems[J].Microprocessors & Microsystems,2018,56:34-46.
[14] 陈鹏,涂亚庆,童俊平,等.可穿戴式跌倒检测智能系统设计[J].传感器与微系统:2017,36(2):114-116.
[15] HSIEH CHIA-YEH,HUANG CHIH-NING,LIU KAI-CHUN,et al.A machine learning approach to fall detection algorithm using wearable sensor[C].Proceedings of the IEEE International Conference on Advanced Materials for Science and Engineering.Tainan:Institute of Electrical and Electronics Engineers Inc,2017:707-710.
[16] 贾震宇,王维,王琛,等.可穿戴设备在医疗领域中的应用发展[J].中国医疗设备,2017,32(2):96-99.
[17] 任玉兰,宋航,姜兆宇,等.石墨烯性能及研究进展[J].牡丹江师范学院学报(自然科学版),2017,100(3):43-46.
[18] 唐征海,郭春宝,张立群,等.石墨烯/橡胶纳米复合材料[J].高分子学报,2014(7):865-877.
[19] 王鹏,苏正涛,王珊,等.国内外石墨烯/橡胶复合材料研究进展[J].新材料产业,2015(6):58-66.
[20] TIANYI ZHEN,LILEI MAO,JIAWEI WANG,et al.Wearable preimpact fall detector using SVM[C].Proceedings of the International Conference on Sensing Technology.Nanjing:IEEE Computer Society,2016:1-6.
[21] 马琼华,王忠,郑晓彬.基于Android的老年人跌倒检测系统研究[J].数字技术与应用,2017(2):105-106.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |