基于BP神经网络的人体行为识别

邹建

doi:10.11959/j.issn.2096-109x.2017.00196

您当前的位置：

首页 >

文章列表页 >

基于BP神经网络的人体行为识别

学术论文 | 更新时间：2024-06-03

- 基于BP神经网络的人体行为识别
- Human action recognition based on back propagation neural network
- 网络与信息安全学报 2017年3卷第9期页码：55-60
- 作者机构：
- 作者简介：
  
  [ "邹建（1980-），男，贵州毕节人，贵州省通信管理局网维中心工程师，主要研究方向为网络安全。" ]
- 基金信息：
- DOI：10.11959/j.issn.2096-109x.2017.00196
  中图分类号： TP391.41
- 网络首发：2017-09，
  
  纸质出版：2017-09-15
- 稿件说明：
移动端阅览
邹建. 基于BP神经网络的人体行为识别[J]. 网络与信息安全学报, 2017,3(9):55-60.

Jian ZOU. Human action recognition based on back propagation neural network[J]. Chinese Journal of Network and Information Security, 2017, 3(9): 55-60.
邹建. 基于BP神经网络的人体行为识别[J]. 网络与信息安全学报, 2017,3(9):55-60. DOI： 10.11959/j.issn.2096-109x.2017.00196.

Jian ZOU. Human action recognition based on back propagation neural network[J]. Chinese Journal of Network and Information Security, 2017, 3(9): 55-60. DOI： 10.11959/j.issn.2096-109x.2017.00196.

摘要

针对人体行为识别问题，提出一种基于径向基函数（BP）神经网络的人体行为分类算法。首先，利用奇异值分解（SVD）算法提取视频每一帧的奇异值，将每一帧的奇异值按照行拼接起来即为一个视频的样本，样本按照行排成样本矩阵；然后，利用主成分分析（PCA）对得到的矩阵进行去相关并且降低维数，降低维数的矩阵再进行线性鉴别分析（LDA），使样本变得线性可分；最后，利用BP神经网络对样本进行分类；实验结果表明，与采用最近邻分类和K近邻分类（kNN）相比，所提算法具有更高的识别率。

Abstract

For human action recognition

an algorithm for classifying human action based on back propagation (BP) neural network was proposed.Firstly

singular value decomposition (SVD) was used to extract the singular value of each frame of the video.Then each row of a matrix was composed of the singular value of each video.Every single row of the matrix is a sample of human action.Secondly

the principle component analysis (PCA) algorithm was proposed to remove correlation and reduce dimension.Then the linear discriminant analysis (LDA) algorithm was applied to matrix processed by PCA to make samples linearly separable.Finally

the back propagation neural network was used as a classifier.The experimental results show that the proposed method

compared with nearest neighbor classifier and K-nearest neighbor (kNN) classifier

has a higher recognition rate.

关键词

Keywords

references

ADAM N R , ATLURI V , HUANG W K . Modeling and analysis of workflows using Petri nets [J ] . Journal of Intelligent Information Systems , 1998 , 10 ( 2 ): 131 - 158 .

TU T Y , SHI Y X . Image capture and efficient storing in monitor system [J ] . Application Research of Computers , 2005 , 22 ( 8 ): 241 - 242 .

李妍婷 , 罗予频 , 唐光荣 . 单目视频中的多视角行为识别方法 [J ] . 计算机应用 , 2006 , 26 ( 7 ): 1592 - 1594 .

LI Y T , LUO Y P , TANG G R . Activity recognition method of multiple view angles from monocular videos [J ] . Journal of Computer Applications , 2006 , 26 ( 7 ): 1592 - 1594 .

SCHULDT C , LAPTEV I , CAPUTO B . Recognizing human actions:a local SVM approach [C ] // The 17th International Conference on Pattern Recognition . 2004 : 32 - 36 .

许伟坚 , 冯超 , 李进锦 , 等 . 一种新的视频质量评价中帧对齐算法 [J ] . 厦门大学学报(自然版) , 2012 , 51 ( 2 ): 185 - 188 .

XU W J , FENG C . A new frame alignment algorithm in video quality evaluation [J ] . Journal of Xiamen University (Natural Science) , 2012 , 51 ( 2 ): 185 - 188 .

KIM T K , WONG S F , CIPOLLA R . Tensor canonical correlation analysis for action classification [C ] // IEEE Conference on Computer Vision and Pattern Recognition . 2007 : 1 - 8 .

WANG Y , CHUA C S . Face recognition from 2D and 3D images using 3D Gabor filters [J ] . Image and Vision Computing , 2005 , 23 ( 11 ): 1018 - 1028 .

CAI D , HE X , WEN J R , et al . Support tensor machines for text categorization [J ] .2006. 2005 .

JI S , XU W , YANG M , et al . 3D convolutional neural networks for human action recognition [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2013 , 35 ( 1 ): 221 - 231 .

浏览量

2539

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据