基于Android的运动状态识别分析系统设计  

Design of sports state recognition and analysis system based on Android

作　　者：康立富 王威廉[1] 何冰冰 吴海龙[1] 刘翔 吴超 Kang Lifu;Wang Weilian;He Bingbing;Wu Hailong;Liu Xiang;Wu Chao(School of Information Science and Technology, Yunnan University, Kunming 650091, China)

机构地区：[1]云南大学信息学院,昆明650091

出　　处：《国外电子测量技术》2017年第11期43-47,共5页Foreign Electronic Measurement Technology

基　　金：国家自然科学基金(61261008)项目资助

摘　　要：从数据采集、运动状态识别及识别结果显示3个方面,设计基于Android的运动状态识别分析系统。在硬件电路方面,本系统使用MPU6050加速度传感器采集数据,并做预处理。在软件方面,运动状态识别算法在手机APP的后台实时处理数据。首先对接收的6组数据进行预处理,检测并统计识别步数;其次运动周期提取,计算挥拍次数及平均挥拍速度;然后对运动周期内的数据进行标准化处理,调用个人特征数据库进行运动识别,实现越用越准;最后将结果通过基于Android的手机APP界面进行显示。在系统测试中,能够计算出挥拍次数、平均挥拍速度、步数,同时能够识别出羽毛球、乒乓球两种运动模式和高远球、弧旋球等8种运动动作,识别率达到90%以上。The recognition system of motion＇s states based on the Android have three aspects which is data acquisition, motion status recognition and identification results. In the hardware circuit, the system uses the MPU6050 acceleration sensor to collect 6 sets of data and preprocess it. In the software, the motion state recognition algorithm is real-time pro- cessing data in the background of mobile APP. First, the received six groups of data pretreatment, detection and statisti- cal identification of the number of steps; next, followed by the movement cycle extraction, calculate the number of swing and the average swing speed; and then the data within the movement cycle of standardized processing, call the personal characteristics of the database to exercise Identify which to achieve the more prospective; Finally, the results through the Android-based mobile APP interface to display, the system test, it can calculate the number of swing, the average swing speed, the number of steps, to identify two sports modes of badminton and table tennis, to judge lofty ball, arc ball and others eight kinds of movement and the recognition rate is 90% or more.

关 键 词：MPU6050 周期提取 运动状态识别 基于Android的手机APP 

分 类 号：TN99[电子电信—信号与信息处理]