Research on gesture recognition algorithm based on depth information

HUA Xu-fen; SUN Jun

doi:10.13873/J.1000-9787(2017)12-0122-04

Chinese

您当前的位置：

首页 >

文章列表页 >

Research on gesture recognition algorithm based on depth information

更新时间：2025-09-11

- Research on gesture recognition algorithm based on depth information
- Vol. 36, Issue 12, Pages: 122-125(2017)
- 作者机构：
  
  1. 江南大学物联网工程学院
  2. 无锡职业技术学院
- 作者简介：
- 基金信息：
- DOI：10.13873/J.1000-9787(2017)12-0122-04
  CLC： TP391.41
- Published：2017
- 稿件说明：
移动端阅览
[1]华旭奋,孙俊.基于深度信息的手势识别算法研究[J].传感器与微系统,2017,36(12):122-125.

HUA Xu-fen, SUN Jun. Research on gesture recognition algorithm based on depth information[J]. 2017, 36(12): 122-125.
[1]华旭奋,孙俊.基于深度信息的手势识别算法研究[J].传感器与微系统,2017,36(12):122-125. DOI： 10.13873/J.1000-9787(2017)12-0122-04.

HUA Xu-fen, SUN Jun. Research on gesture recognition algorithm based on depth information[J]. 2017, 36(12): 122-125. DOI： 10.13873/J.1000-9787(2017)12-0122-04.

摘要

针对在复杂背景中传统手势识别算法的识别率低问题

利用Kinect的深度摄像头获取深度图像

分割出手势区域后进行预处理;提取手势的几何特征

并提出深度信息的同心圆分布直方图特征

融合手势的几何特征和深度信息的同心圆分布直方图特征;学习训练随机森林分类器进行手势识别。文中通过在复杂背景条件下对常见的"石头"、"剪刀"、"布"3种手势进行测试

实验结果表明:文中所提方法具有很好的平移

旋转和缩放不变性

能适应复杂环境的变化。

Abstract

In order to deal with the problem of low recognition rate of traditional hand gesture recognition algorithm with complex background

a gesture recognition algorithm based on depth information is proposed. Depth image is obtained by the depth camera of Kinect

pre-processing is performed after dividing the gesture area.Geometric features of hand gesture are extracted

character of concentric distribution histogram of depth information is presented. Learn and train random forest classifier for gesture recognition

the geometric features of the hand gestures and the histograms of the concentric circles of the depth information are used to recognize the tested hand gesture via random forest classifier. Three kinds of gestures

such as stone

scissors and cloth

are tested under complex background. The experimental results show that the proposed method has better translation

rotation and scaling invariance

and can adapt to the change of complex environment.

关键词

Keywords

references

基于Kinect和变形雅可比-傅里叶矩的手势识别 [J]. 刘亚瑞,杨文璐. 传感器与微系统 . 2016(07)

一种基于手机加速度传感器的三维手势身份认证方法 [J]. 王尧,孙子文,周治平. 传感器与微系统 . 2014(08)

基于深度图像技术的手势识别方法 [J]. 曹雏清,李瑞峰,赵立军. 计算机工程 . 2012(08)

Feature learning based on SAE-PCA network for Human gesture recognition in RGBD images [J] . Shao-Zi Li,Bin Yu,Wei Wu,Song-Zhi Su,Rong-Rong Ji. Neurocomputing . 2014

Continuous body and hand gesture recognition for natural human-computer interaction [J] . Yale Song,David Demirdjian,Randall Davis. ACM Transactions on Interactive Intelligent Systems （TiiS） . 2012 (1)

Views

223

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Hand gestures interactive hexapod robot based on Raspberry Pi

Prior direction angle estimation in 3D object detection

Online gesture recognition based on B-mode ultrasound

Hand gesture recognition based on Leap Motion and SVM

Hand gesture recognition based on Kinect and Pseudo-Jacobi-Fourier moments

Related Author

XUE Zhifeng

JIANG Gang

LIU Canghai

WANG Yitian

ZHAO Huaqing

FANG Zhijun

GAO Yongbin

HUANG You-jia

Related Institution

School of Manufacturing Science and Engineering,Southwest University of Science and Technology

College of Nuclear Technology and Automation Engineering,Chengdu University of Technology

School of Electronic and Electrical Engineering,Shanghai University of Engineering Science

State Key Laboratory of Mechanical System and Vibration,Shanghai Jiao Tong University

College of Information Engineering, Shanghai Maritime University

⁰