Research of Unsupervised Posture Modeling and Action Recognition Based on Spatial-Temporal Interesting Points

WANG Chuan-xu; LIU Yun; LI Wan-qing

您当前的位置：

首页 >

文章列表页 >

Research of Unsupervised Posture Modeling and Action Recognition Based on Spatial-Temporal Interesting Points

更新时间：2025-07-16

- Research of Unsupervised Posture Modeling and Action Recognition Based on Spatial-Temporal Interesting Points
- Acta Electronica Sinica Vol. 39, Issue 8, Pages: 1751-1756(2011)
- 作者机构：
  
  1. 青岛科技大学信息学院,山东,青岛,266061
  2. School of Computer Science and Software Engineering,University of Wollongong,NSW,Australia,2522
  3. 青岛科技大学信息学院山东青岛,266061
  4. School of Computer Science and Software EngineeringUniversity of WollongongNSWAustralia,2522
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP301.6
- Published：2011
- 稿件说明：
移动端阅览
WANG Chuan-xu, LIU Yun, LI Wan-qing. Research of Unsupervised Posture Modeling and Action Recognition Based on Spatial-Temporal Interesting Points[J]. Acta Electronica Sinica, 2011, 39(8): 1751-1756.
DOI：

WANG Chuan-xu, LIU Yun, LI Wan-qing. Research of Unsupervised Posture Modeling and Action Recognition Based on Spatial-Temporal Interesting Points[J]. Acta Electronica Sinica, 2011, 39(8): 1751-1756. DOI：

摘要

姿态建模是行为描述和识别的关键环节

提出了基于时空特征点的姿态建模方法.提取样本库中姿态的时空特征点作为底层特征

一个姿态对应一个时空特征点集合;采用非监督分类方法对姿态样本归类

获得典型姿态的聚类结果

每个典型姿态类别采用基于EM的高斯混合模型进行建模.计算各典型姿态间的转移概率

建立状态已知的描述人类多种行为的VMM模型

实现对行为的描述.针对行为识别问题

提出将汉字分词的二元语法模型应用于行为识别.实验证明该算法具有计算复杂度低、鲁棒性强等优点.

Abstract

Posture modeling is critical for action description and recognition

a posture modeling and action recognition method is proposed in this paper.Spatial Temporal Interesting Points (STIPs) are extracted from learning samples

in fact

one posture consists of a set of STIPs;a unsupervised clustering method is adopted to classify salient postures from these posture samples

then a GMM model is established for each clustering result;transitional probability among salient postures are calculated

and a Visible state Markov Model(VMM) is learnt to describe various actions.Bi

gram method is put forward for action recognition

Extensive experiments are conducted and the results prove its robustness and validity.

关键词

Keywords

references

Views

1719

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Enhanced Spatial-Temporal Graph Convolutional Network for Skeleton-Based Action Recognition

Research on 3D Multi-Branch Aggregated Lightweight Network Video Action Recognition Algorithm

An Improved VLAD Coding Method Based on Fusion Feature in Action Recognition

Action Recognition Based on Deep Learning and Artificial Intelligence Planning

Recurrent Region Attention and Video Frame Attention Based Video Action Recognition Network Design

Related Author

WU Hui-xin

MENG Yao

SUN Hao-chen

WEI Fu-peng

GUAN Meng-yi

JIANG Wei

HU Zheng-ping

ZHAO Meng-yao

Related Institution

School of Information Engineering, North China University of Water Resources and Electric Power

School of Information Science and Engineering, Yanshan University

Hebei Key Laboratory of Information Transmission and Signal Processing, Yanshan University

School of Information Science and Engineering Yanshan University Qinhuangdao Hebei China

Hebei Key Laboratory of Information Transmission and Signal Processing Yanshan University Qinhuangdao Hebei China

⁰