作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2010, Vol. 36 ›› Issue (23): 152-154. doi: 10.3969/j.issn.1000-3428.2010.23.050

• 人工智能及识别技术 • 上一篇    下一篇

基于手机手势识别的媒体控制界面

丁跃1,2,刘军发2,陈益强2,周经野1   

  1. (1. 湘潭大学信息工程学院,湖南 湘潭 411105; 2. 中国科学院计算技术研究所,北京 100080)
  • 出版日期:2010-12-05 发布日期:2010-12-14
  • 作者简介:丁跃(1980-),男,硕士研究生,主研方向:普适计算,机器学习;刘军发,助理研究员、博士;陈益强,研究员;周经野,教授
  • 基金资助:
    国家自然科学基金资助项目(90820303, 60775027);国家“863”计划基金资助项目(2009AA01Z320)

Media Control Interface Based on Gesture Recognition of Mobile Phone

DING Yue1,2,LIU Junfa2,CHEN Yiqiang2,ZHOU Jingye1   

  1. (1.College of Information Engineering, Xiangtan University, Xiangtan 411105, China; 2.Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100080, China)
  • Online:2010-12-05 Published:2010-12-14

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 builtin threeaxis 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, humancomputer interaction, media playing interface

中图分类号: