摘要: 提出一种能够识别通过手机示意的自然手势、进而控制媒体播放的通用型人机界面。用户通过挥动个人的手机表达操作意图,由手机内置三轴加速度传感器获取相应的手势数据,采用动态时间弯曲等多种算法对用户的手势进行识别,实现对多媒体播放的通用控制。实验结果表明,该界面对手机的几种通用手势均能获得较高的识别率,能在实际应用中对媒体进行简单、方便的控制。
关键词:
动态时间弯曲,
隐马尔科夫模型,
支持向量机,
自然手势识别,
人机交互,
媒体播放界面
Abstract: This paper presents a novel control interface commonly used by medium, the interface can identify the natural gestures expressed by user's mobile phone. Users express their operational intention by waving the mobile phone, the builtin threeaxis acceleration sensor will collect corresponding gesture data. It uses various algorithms, such as Dynamic Time Warping(DTW) to recognize the user's gestures in order to control the multimedia playing. Experimental results show that to a few of common gestures,the interface has a higher recognition rate and it can meet the requirement of the practical application to control media simply and conveniently.
Key words:
Dynamic Time Warping(DTW),
Hidden Markov Model(HMM),
Support Vector Machine(SVM),
natural gesture recognition,
humancomputer interaction,
media playing interface
中图分类号:
丁跃, 刘军发, 陈益强, 周经野. 基于手机手势识别的媒体控制界面[J]. 计算机工程, 2010, 36(23): 152-154.
DING Ti, LIU Jun-Fa, CHEN Yi-Jiang, ZHOU Jing-Shu. Media Control Interface Based on
Gesture Recognition of Mobile Phone[J]. Computer Engineering, 2010, 36(23): 152-154.