摘要
手势识别是人机接口应用的一个重要场景,当前的手势识别方法大多基于表面肌电信号(s EMG)。为了探索新的传感方式,设计了一种新颖的基于超声传感器的手势识别系统。系统利用多个布置在前臂的单振元超声传感器检测肌肉界面的回波信息,对其进行特征提取和模式识别,识别手腕和手指的动作。实验结果表明:系统对于手指精细动作有良好的识别效果,5个手指动作的平均识别率为(91.1±4.73)%。
Gesture recognition is one of the most important scenarios in human-machine interface application,and present methods are generally based on surface electro myogram（ s EMG） signals. In order to explore new sensing mode,a novel gesture recognition system based on ultrasonic sensor is designed. Sensors are placed on forearm to detect echo information of muscle interface,so as to carry out character exraction and pattern recognition and wrist and finger motions can be recognized. Experimental results show that the system has good recognition effect on fine motion of finger,average recognition rate of five fingers motion is（ 91. 1 ± 4. 73） %.
出处
《传感器与微系统》
CSCD
2018年第2期80-82,共3页
Transducer and Microsystem Technologies
基金
国家自然科学基金资助项目(51575338)
关键词
超声传感器
人机接口
手势识别
ultrasonic sensor
human-machine interface
gesture recognition
