Gaussian Mixture Models and Principal Component Analysis Based Human Trajectory Behavior Recognition

TIAN Guo-hui; YIN Jian-qin; YAN Yun-zhang; LI Guo-dong

doi:10.3969/j.issn.0372-2112.2016.01.021

您当前的位置：

首页 >

文章列表页 >

Gaussian Mixture Models and Principal Component Analysis Based Human Trajectory Behavior Recognition

更新时间：2025-07-16

- Gaussian Mixture Models and Principal Component Analysis Based Human Trajectory Behavior Recognition
- Acta Electronica Sinica Vol. 44, Issue 1, Pages: 143-149(2016)
- 作者机构：
  
  1. 山东大学控制科学与工程学院,山东,济南,250061
  2. 济南大学信息科学与工程学院山东省网络环境智能计算技术重点实验室,山东,济南,250022
  3. 山东大学控制科学与工程学院,山东,济南,250061
  4. 济南大学信息科学与工程学院山东省网络环境智能计算技术重点实验室,山东,济南,250022
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0372-2112.2016.01.021
  CLC： TP391
- Published：2016
- 稿件说明：
移动端阅览
TIAN Guo-hui, YIN Jian-qin, YAN Yun-zhang, et al. Gaussian Mixture Models and Principal Component Analysis Based Human Trajectory Behavior Recognition[J]. Acta Electronica Sinica, 2016, 44(1): 143-149.
DOI：

TIAN Guo-hui, YIN Jian-qin, YAN Yun-zhang, et al. Gaussian Mixture Models and Principal Component Analysis Based Human Trajectory Behavior Recognition[J]. Acta Electronica Sinica, 2016, 44(1): 143-149. DOI： 10.3969/j.issn.0372-2112.2016.01.021.

摘要

针对家庭辅助生活应用场景下的目标意图识别和异常行为判别问题

提出了一种基于目标轨迹的行为分析方法.首先

提出了关键点和关键区域的概念

将家庭环境划分为不同的关键点和关键区域

并以此来描述和区分不同轨迹;然后

提出了利用混合高斯模型的关键点及关键区域获取算法

将轨迹转化为关键点及关键区域表示

并以此为基础进行了行为意图的识别和部分异常轨迹的判断;最后

借助主成分分析的方法弥补混合高斯聚类在异常轨迹识别方面的缺陷

提高了识别准确率.实验表明

该方法能够有效的对行为意图和异常行为进行识别.

Abstract

In order to solve the problems of human motion intention recognition and abnormal behavior detection in home environment

a trajectory analysis based algorithm is discussed in this paper.Firstly

the home environment is divided into different key points and areas

so that the motion trajectory can be described by them.Moreover

based on mixture Gaussian model

the problems of motion intention recognition and abnormal behavior detection are analyzed.Finally

the PCA algorithm is applied to improve the accuracy of abnormal behavior detection.The experimental results show the effectiveness and reliability of the above conclusions.

关键词

Keywords

references

Views

2068

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Empirical Mode Decomposition De-noising Method Based on Principal Component Analysis

Poison Attack and Defense Strategies on PCA-Based Anomaly Detector

Medical Image Registration Based on Principal Phase Congruency

A Method for Texture Classification by Integrating Gabor Filters and ICA

Element Recovery from Counting Bloom Filters' Hash Space

Related Author

WANG Xiang-li

ZHANG Xiao-dong

WANG Wen-bo

CHEN Ming

QIAN Ye-kui

LU Zhen-tai

FENG Yan-qiu

FENG Qian-jin

Related Institution

School of Computer Science and Technology Wuhan University of Technology Wuhan Hubei China

State key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan Hubei China

State Key Laboratory of Remote Sensing Science Beijing China

School of Science Wuhan University of Science and Technology Wuhan Hubei China

School of Computer Science and Technology, Wuhan University of Technology

⁰