Action Recognition Based on 3D Skeleton

ZHANG You-mei; CHANG Fa-liang; LIU Hong-bin

doi:10.3969/j.issn.0372-2112.2017.04.020

您当前的位置：

首页 >

文章列表页 >

Action Recognition Based on 3D Skeleton

更新时间：2025-07-16

- Action Recognition Based on 3D Skeleton
- Acta Electronica Sinica Vol. 45, Issue 4, Pages: 906-911(2017)
- 作者机构：
  
  山东大学控制科学与工程学院,山东,济南,250061
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61273277, No.61673244);Research Fund for the Doctoral Program of Higher Education of China (No.20130131110038)
- DOI：10.3969/j.issn.0372-2112.2017.04.020
  CLC： TP391.4
- Published Online：25 April 2017，
  
  Published：2017
- 稿件说明：
移动端阅览
ZHANG You-mei, CHANG Fa-liang, LIU Hong-bin. Action Recognition Based on 3D Skeleton[J]. Acta Electronica Sinica, 2017, 45(4): 906-911.
DOI：

ZHANG You-mei, CHANG Fa-liang, LIU Hong-bin. Action Recognition Based on 3D Skeleton[J]. Acta Electronica Sinica, 2017, 45(4): 906-911. DOI： 10.3969/j.issn.0372-2112.2017.04.020.

摘要

本文提出了一种基于3D人体骨架的动作识别方法.该方法以3D人体骨架为基础，将骨架中关节点的位置重新定义，形成简化的立体骨架模型，进而采用改进的动态时间规整算法（Reformative Dynamic Time Warping，R-DTW）对齐动作序列并进行识别.由于人体大小、形状、动作方式等差异，任意两个人表达同一动作都不尽相同，简化的立体骨架模型能有效缓解这种类内差异性.传统的DTW算法存在计算复杂性高，效率低的问题，本文在传统算法的基础上设计了一次规划，二次细化的方法，有效降低计算量，提高计算效率.该算法在MSR 3D Action数据库上的实验验证了其有效性.

Abstract

This paper presents an action recognition method based on 3D skeleton.This method redefines the coordinates of the articulations which belong to the skeleton to form a simplistic skeleton model firstly.Then a reformative dynamic time warping (R-DTW) algorithm is applied to implement action recognition.There are no two persons identical in an action owing to the difference of body size

shape and action expression.The simplistic skeleton model could decrease this intra-class variability effectively.The drawbacks of conventional DTW algorithm lie in high computational complexity and low recognition efficiency.To solve this problem

we design a method named Planning Refining.We conduct this algorithm on MSR Action3D dataset and the results demonstrate its effectiveness.

关键词

Keywords

references

Views

795

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Multi-Dimensional Dynamic Topology Learning Graph Convolution for Skeleton-Based Action Recognition

Skeleton Action Recognition Based on Multi-Stream Spatial Attention Graph Convolutional SRU Network

A Dynamic Head Gesture Recognition Method Based on 3D Convolutional Two‑Stream Network Fusion

On-Line Recognition of Actions in Daily Living

Related Author

CAO Li-jing

LUO Hui-lan

ZHAO Jun-nan

SHE Qing-shan

MENG Ming

CHEN Yun

ZHANG Bo‑tao

LÜ Qiang

Related Institution

School of Information Engineering， Jiangxi University of Science and Technology

College of Automation, Hangzhou Dianzi University

School of Automation， Hangzhou Dianzi University

Key Laboratory of Pervasive Computing of Ministry of Education, Department of ComputerScience and Technology, Tsinghua University

Tencent Research

⁰