查询结果:   高明柯,陈一民,张典华,吕圣卿,黄晨.基于证据理论融合的手势识别方法研究[J].计算机应用与软件,2018,35(1):191 - 194,260.
中文标题
基于证据理论融合的手势识别方法研究
发表栏目
人工智能与识别
摘要点击数
947
英文标题
RESEARCH ON GESTURE RECOGNITION BASED ON EVIDENCE THEORY FUSION
作 者
高明柯 陈一民 张典华 吕圣卿 黄晨 Gao Mingke Chen Yimin Zhang Dianhua Lü Shengqing Huang Chen
作者单位
上海大学计算机工程与科学学院 上海 200444 上海大学数码艺术学院 上海 201800 中国电子科技集团公司第三十二研究所 上海 201808   
英文单位
School of Computer Engineering and Science,Shanghai University,Shanghai 200444,China College of Digital Arts,Shanghai University,Shanghai 201800,China The 32nd Research Institute of China Electronics Technology Group Corporation,Shanghai 201808,China   
关键词
证据理论 手势识别 手势交互 隐马尔科夫模型 支持向量机
Keywords
Evidence theory Gesture recognition Gesture interaction Hidden Markov model Support vector machine
基金项目
上海市科技创新行动计划项目(16511101200);上海市科委国际合作项目(12510708400);上海市自然科学基金项目(14ZR1419700)
作者资料
高明柯,讲师,主研领域:增强现实,手势交互,数据可视化。陈一民,教授。张典华,讲师。吕圣卿,硕士生。黄晨,博士生。 。
文章摘要
针对证据理论能将多源数据有机合成为具有更高可信度结果的特点,提出基于证据理论融合的手势识别方法。方法先采用Leap Motion采集手势视频序列,提取手势运动轨迹的方向角作为特征;采用隐马尔科夫模型和支持向量机分别对手势进行训练,进而在识别中通过证据理论将两种方法所计算的手势基本概率分配进行决策融合,实现最终的手势识别;将该方法应用于医疗可视化系统中,实现了自然直观的手势交互。实验结果表明,该方法结合了隐马尔科夫模型和支持向量机的优点,可有效提高手势识别率和交互准确性。
Abstract
Based on the evidence theory that the multi-source data can be organically synthesis to the higher and more reliable results, the gesture recognition method based on evidence theory fusion is proposed. Firstly, gesture video sequences are captured by Leap Motion and the direction angle of gesture trajectory is extracted as the feature. Secondly, Hidden Markov Model and Support Vector Machine are used for gesture training, and then the basic probability assignment of gesture of the two methods are fused based on decision by evidence theory in recognition processing to realize the final gesture recognition. Finally, this method is applied into medical visualization system to realize the natural and intuitive gesture interaction. The experimental results show that this method combines the advantages of Hidden Markov Model and Support Vector Machine that can effectively improve the gesture recognition rate and the interactive accuracy.
下载PDF全文