穿戴式运动姿态检测方法研究与实现
发布时间：2018-09-06 18:22
【摘要】：人体运动姿态检测技术是获取人体运动信息的重要手段,在体育训练、步态识别、动作识别、医疗康复、运动和健康管理以及生物认证等领域都有着广泛的应用。目前基于MEMS传感器的姿态检测方法大多都是利用加速度传感器来采集人体姿态信息的,优点是体积小、功耗低,但是单独的加速度传感器不能快速响应人体运动姿态变化,故测量准确度不高。本文在分析人体甩臂步行、俯卧撑和仰卧起坐运动姿态特点的基础上,确定了运动姿态的特征参数,设计并实现了运动姿态的检测算法。论文研究内容主要体现在以下三个方面：一、设计了一个穿戴式运动姿态参数采集模块,该模块采用MPU9250九轴运动传感器采集人体运动姿态信息,并利用BLE4.0蓝牙无线通信功能将特征参数发送至上位机；二、采用matlab自主设计了一款基于GUI图像界面的仿真软件,并利用该软件对本文研究的运动姿态检测算法进行了仿真验证；三、采用Eclipse自主设计了基于安卓平台的APP软件,实现了参数采集模块测试、运动姿态检测以及心率测量功能。大量的测试统计结果表明,本文研究的姿态检测方法具有较高的稳定性和准确度：计步准确率大于87.7%；俯卧撑运动和仰卧起坐运动计数准确率大于86.3%；心率测量准确率高于90%。
[Abstract]:Human motion attitude detection technology is an important means to obtain human motion information. It is widely used in sports training, gait recognition, movement recognition, medical rehabilitation, sports and health management and biological certification. At present, most of the attitude detection methods based on MEMS sensor use acceleration sensor to collect human body attitude information, which has the advantages of small size and low power consumption, but the single acceleration sensor can not quickly respond to the change of human motion attitude. Therefore, the accuracy of measurement is not high. On the basis of analyzing the characteristics of human swinging arm walking, push-ups and sit-ups, the characteristic parameters of motion attitude are determined, and the algorithm of motion attitude detection is designed and implemented. The main contents of this paper are as follows: first, a wearable motion attitude parameter acquisition module is designed, which uses MPU9250 nine-axis motion sensor to collect human motion attitude information. The BLE4.0 Bluetooth wireless communication function is used to send the feature parameters to the upper computer. Secondly, a simulation software based on GUI image interface is designed by using matlab, and the motion attitude detection algorithm is simulated and verified by the software. Thirdly, the APP software based on Android platform is designed by Eclipse, which realizes the function of parameter acquisition module test, motion posture detection and heart rate measurement. A large number of test results show that the attitude detection method studied in this paper has high stability and accuracy: the accuracy of step counting is greater than 87.7, the accuracy of counting push-ups and sit-ups is more than 86.3, and the accuracy of heart rate measurement is more than 90.
【学位授予单位】：华中师范大学
【学位级别】：硕士
【学位授予年份】：2016
【分类号】：TP391.41;TP212.9
本文编号：2227149
[Abstract]:Human motion attitude detection technology is an important means to obtain human motion information. It is widely used in sports training, gait recognition, movement recognition, medical rehabilitation, sports and health management and biological certification. At present, most of the attitude detection methods based on MEMS sensor use acceleration sensor to collect human body attitude information, which has the advantages of small size and low power consumption, but the single acceleration sensor can not quickly respond to the change of human motion attitude. Therefore, the accuracy of measurement is not high. On the basis of analyzing the characteristics of human swinging arm walking, push-ups and sit-ups, the characteristic parameters of motion attitude are determined, and the algorithm of motion attitude detection is designed and implemented. The main contents of this paper are as follows: first, a wearable motion attitude parameter acquisition module is designed, which uses MPU9250 nine-axis motion sensor to collect human motion attitude information. The BLE4.0 Bluetooth wireless communication function is used to send the feature parameters to the upper computer. Secondly, a simulation software based on GUI image interface is designed by using matlab, and the motion attitude detection algorithm is simulated and verified by the software. Thirdly, the APP software based on Android platform is designed by Eclipse, which realizes the function of parameter acquisition module test, motion posture detection and heart rate measurement. A large number of test results show that the attitude detection method studied in this paper has high stability and accuracy: the accuracy of step counting is greater than 87.7, the accuracy of counting push-ups and sit-ups is more than 86.3, and the accuracy of heart rate measurement is more than 90.
【学位授予单位】：华中师范大学
【学位级别】：硕士
【学位授予年份】：2016
【分类号】：TP391.41;TP212.9
【相似文献】
相关期刊论文 前2条
1 杨继锋;刘勇志;黄路炜;李科;;潜射导弹出筒过程运动姿态分析与建模仿真[J];计算机仿真;2014年06期
2 ;[J];;年期
相关会议论文 前1条
1 秦兴春;茅坪;卢惠民;;某型舰船主要运动姿态的模拟仿真[A];1998年上海市系统仿真学会学术年会论文专辑[C];1998年
相关硕士学位论文 前3条
1 陈亚芹;穿戴式运动姿态检测方法研究与实现[D];华中师范大学;2016年
2 李明;大型船舶直航运动视景仿真及姿态预报研究[D];哈尔滨工程大学;2012年
3 冯文武;运动姿态检测系统的设计与实现[D];重庆大学;2008年
，本文编号：2227149
本文链接：https://www.wllwen.com/kejilunwen/ruanjiangongchenglunwen/2227149.html
