Personalized Interaction Techniques of Vision-Based 3D Dynamic Gestures Based on Small Sample Learning

WU Hui-yue; WANG Jian-min; DAI Guo-zhong

doi:10.3969/j.issn.0372-2112.2013.11.018

您当前的位置：

首页 >

文章列表页 >

Personalized Interaction Techniques of Vision-Based 3D Dynamic Gestures Based on Small Sample Learning

更新时间：2025-07-16

- Personalized Interaction Techniques of Vision-Based 3D Dynamic Gestures Based on Small Sample Learning
- Acta Electronica Sinica Vol. 41, Issue 11, Pages: 2230-2236(2013)
- 作者机构：
  
  1. 中山大学传播与设计学院,广东,广州,510006
  2. 中国科学院软件研究所人机交互与智能信息处理实验室,北京,100190
  3. 中山大学传播与设计学院,广东,广州,510006
  4. 中国科学院软件研究所人机交互与智能信息处理实验室,北京,100190
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61202344, No.61073132);Fundamental Research Funds for Universities Young Teacher Training Project of Sun Yat-sen University (No.1209119-17000-3161120);958 Project News Communication Innovation Base in the All-Media Eraof Sun Yat-sen University (No.90027-3284200)
- DOI：10.3969/j.issn.0372-2112.2013.11.018
  CLC： TP391
- Published：2013
- 稿件说明：
移动端阅览
WU Hui-yue, WANG Jian-min, DAI Guo-zhong. Personalized Interaction Techniques of Vision-Based 3D Dynamic Gestures Based on Small Sample Learning[J]. Acta Electronica Sinica, 2013, 41(11): 2230-2236.
DOI：

WU Hui-yue, WANG Jian-min, DAI Guo-zhong. Personalized Interaction Techniques of Vision-Based 3D Dynamic Gestures Based on Small Sample Learning[J]. Acta Electronica Sinica, 2013, 41(11): 2230-2236. DOI： 10.3969/j.issn.0372-2112.2013.11.018.

摘要

传统的动态手势交互技术如隐马尔科夫模型、神经网络和统计分类器等都需要大量的训练样本，建模过程中需要领域专家的干预、对普通用户来说使用起来较为困难，并且它们针对的是特定的手势集合，很难对其进行扩展.本文通过WOZ实验，分析了用户的行为特征并给出了基于手势的数字电视交互任务模型；提出了3D动态手势状态转移模型，解决了Midas Touch问题；提出了一种基于小样本学习的动态手势识别方法，解决了传统手势识别方法的缺点；构建了个性化手势设计平台，满足了用户的个性化定制需求；实验评估结果验证了本文方法的有效性.

Abstract

There are some unresolved issues left behind for many traditional dynamic gesture recognition methods

such as Hidden Markov Model(HMM)

Neural Network(NN)

and statistical classifiers.For example

they require a large number of training examples and the involvement of expert users in the training process.Moreover

they are used for some specific gesture sets which are difficult to be extended.In this paper

we first build a task model and a state transition model for vision-based dynamic gestures.Then we propose a method for 3D dynamic gesture recognition based on small sample learning.Next we design a toolkit for development of user-defined gestures.Finally

we develop a gesture-based interactive television prototype.Experimental results verify the validity of our method.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on a Model Driven Development Framework for Pen-Based User Interface

A Vision-Based Method for Finger-Screen Interaction

Human Face Orientation Based Non-Wearable and Natural Human-Computer Interaction

Related Author

ZHANG Xiao-ping

LIN Xue-yin

XU Guang-you

ZHU Yuan-xin

REN Hai-bing

REN Lei

CHEN Ming-xuan

DENG Chang-zhi

Related Institution

Dept.of Computer Science and Technology,Tsinghua University

School of Automation Science and Electrical Engineering Beihang University Beijing China

Graduate University of Chinese Academy of Sciences Beijing China

Intelligence Engineering Laboratory Institute of Software Chinese Academy of Sciences Beijing China

School of Automation Science and Electrical Engineering, Beihang University

⁰