摘要
为准确识别军校学员便步、齐步、正步、跑步、仰卧起坐、俯卧撑、折返跑等七类日常运动状态,提出了一种基于可穿戴设备的军校学员运动状态识别方法。该方法首先利用穿戴式加速度数据采集设备采集并分析学员运动数据,并根据预先设定的特征,对运动数据进行特征提取;然后,利用设置的相应阈值对数据特征值进行识别,判断出相应的运动状态;最后,对军校学员日常运动中的七类运动状态进行了实验验证。结果表明:所提出的方法可有效识别学员运动状态,具有较高的识别率。
In an effort to accurately distinguish and test cadets′ daily motion states such as route step, quick march, goose step, running, sit-up, push-up, shuttle run etc., a motion state recognition method is proposed based on wearable device for cadets in military academy. First of all, a wearable acceleration data acquisition device is used to collect and analyze the trainees' movement data and extract the features of the data according to the predefined features. And then, the characteristic values are identified through the corresponding threshold to get the corresponding motion state. Finally, the seven kinds of daily motion state of cadets are tested and verified by experiments. The results show that the method proposed in this paper works effectively with a high rate of recognition.
作者
刘林锋
涂亚庆
赵运勇
陈鹏
LIU Lin-feng;TU Ya-qing;ZHAO Yun-yong;CHEN Peng(Dept. of Military Logistics, Army Logistics Univ. of PLA, Chongqing 401311, China;Chongqing Ruanhui Technology Co. Ltd., Chongqing 400039, China)
出处
《海军工程大学学报》
CAS
北大核心
2019年第2期49-53,112,共6页
Journal of Naval University of Engineering
基金
国家自然科学基金资助项目(61871402)
重庆市自然科学重点基金资助项目(CSTC2015jcyjBX0017)