摘要
利用六轴传感器在手势识别和姿态识别上的优势和无线系统的便利性,设计了基于六轴传感器的无线爬行动作识别系统,实现爬行动作的识别和姿态检测。利用动态时间规整(DTW)算法匹配模板识别四肢动作判断爬行意图,再根据传感器数据检测当前姿态,判断爬行方向。实验表明:系统在3 s内根据动作发出正确指令的概率达到74.2%,4 s内完成识别给出指令的概率达到91.7%,满足实际需求。
Take advantages of six-axis sensor in gesture recognition and attitude recognition and the convenience of wireless system,a wireless crawling action recognition system based on six-axis sensor is designed to achieve crawling action recognition and attitude estimation. Determine the crawling intention by using dynamic time warping（ DTW） algorithm to match template and to recognize limbs gesture so as to determine crawing,and according to six-axis sensor data to estimate the attitude so as to determine the crawling direction. Experiments show that the probability of identifying the correct instruction within 3 s is 74. 2 %,and the probability of identifying the instruction is 91. 7 % within 4 s,which can meet the actual demand.
作者
曾亿山
刘睿
ZENG Yi-shan;LIU Rui(School of Mechanical Engineering,Hefei University of Technology,Hefei 230009,China)
出处
《传感器与微系统》
CSCD
2018年第10期98-101,共4页
Transducer and Microsystem Technologies
基金
中央高校基础研究基金资助项目(2011HGZ1004)
关键词
六轴传感器
动态时间规整
手势识别
姿态检测
six-axis sensor
dynamic time warping（DTW）
gesture recognition
attitude detection
