[1]陈昌红,刘 园.基于改进和积网络的双人交互行为识别[J].计算机技术与发展,2019,29(10):157-163.[doi:10. 3969 / j. issn. 1673-629X. 2019. 10. 031]
　CHEN Chang-hong,LIU Yuan.Human Interaction Recognition Based on Improved Sum Product Networks[J].,2019,29(10):157-163.[doi:10. 3969 / j. issn. 1673-629X. 2019. 10. 031]
点击复制

基于改进和积网络的双人交互行为识别()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
29
期数:
2019年10期
页码:
157-163
栏目:
智能、算法、系统工程
出版日期:
2019-10-10

文章信息/Info

Title:
Human Interaction Recognition Based on Improved Sum Product Networks
文章编号:
1673-629X(2019)10-0157-07
作者:
陈昌红; 刘 园
南京邮电大学 通信与信息工程学院,江苏 南京 210003
Author(s):
CHEN Chang-hong; LIU Yuan
School of Communication and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China
关键词:
双人交互行为识别; 神经网络; 独立子空间分析; 和积网咯; 结构学习算法
Keywords:
human interaction recognition; neural network; independent subspace analysis; sum product networks; structure learning algorithm
分类号:
TN911.73
DOI:
10. 3969 / j. issn. 1673-629X. 2019. 10. 031
摘要:
受到视角变化、相机移动、尺度、光线、遮挡等因素的影响,双人交互行为识别的效果往往不太理想。 有效地提取特征和合理地建立交互模型是双人交互行为识别与理解的两个重要研究内容。 基于深度学习的思想,直接在三维空间中构建多层神经网络,使用两层卷积叠加独立子空间分析网络提取视频的时空特征。 在此基础上,提出了一种基于改进和积网络(sum product networks, SPNs)的双人行为识别算法。 通过改进后的 LearnSPN 结构学习算法学习和积网络的结构和权重,在训练过程中对数据集进行实例划分或者变量划分直至满足划分结束条件,从而实现对双人交互行为的分类。该方法在 UT、BIT-Interaction 和 TV-human 交互数据库上进行测试,实验结果证明了该方法对双人交互行为识别的有效性,尤其对背景复杂的 TV-human 交互数据库效果更好。
Abstract:
Due to the influence of visual angle change,camera movement,scale,light and occlusion,the effect of human interaction recognition is always unsatisfactory. The most important research contents of human interaction recognition are effective feature extraction and reasonable interaction model establishment. Based on the idea of deep learning,multi-layer neural network is constructed in the three-dimensional space directly,and the spatial-temporal features of video are extracted by using two-layered convolution superimposed independent subspace analysis (ISA). Human interaction recognition algorithm is proposed based on improved sum product networks(SPNs). The improved LearnSPN structure learning algorithm is used to learn the structure and weight of SPNs. Instance partition or variable partition is implemented on the database in the training process until satisfying the ending condition. Therefore the human interaction recognition is realized. The method is tested on UT-Interaction, BIT-Interaction and TV-human Interaction database,and the results show its effectiveness,especially for the TV-human Interaction database with complex background.

相似文献/References:

[1]路川 胡欣杰.区域航空市场航线客流量预测研究[J].计算机技术与发展,2010,(04):84.
　LU Chuan,HU Xin-jie.Analysis of Regional Airline Passenger Forecast Title[J].,2010,(10):84.
[2]高峥 陈蜀宇 李国勇.混合入侵检测系统的研究[J].计算机技术与发展,2010,(06):148.
　GAO Zheng,CHEN Shu-yu,LI Guo-yong.Research of a Hybrid Intrusion Detection System[J].,2010,(10):148.
[3]包力伟 周俊.铸锻企业生产质量控制系统的开发[J].计算机技术与发展,2008,(04):174.
　BAO Li-wei,ZHOU Jun.Development of a Manufacture Quality Control System in Casting Company[J].,2008,(10):174.
[4]李志俊 程家兴 金奎 饶玉佳.基于样本期望训练数的BP神经网络改进研究[J].计算机技术与发展,2009,(05):103.
　LI Zhi-jun,CHENG Jia-xing,JIN Kui,et al.BP Algorithm Improvement Based on Sample Expected Training Number[J].,2009,(10):103.
[5]李龙澍 葛瑞峰 王慧萍.基于神经网络的批强化学习在Robocup中的应用[J].计算机技术与发展,2009,(07):98.
　LI Long-shu,GE Rui-feng,WANG Hui-ping.Application of Batch Reinforcement Learning Based on NN to Robocup[J].,2009,(10):98.
[6]贾志先.神经网络在空白试卷识别中的应用[J].计算机技术与发展,2009,(08):208.
　JIA Zhi-xian.Application of Neural Network in Recognization Blank Examination Paper[J].,2009,(10):208.
[7]肖宜龙 路游 亓永刚.基于神经网络的NURBS曲面重建[J].计算机技术与发展,2009,(09):65.
　XIAO Yi-long,LU You,QI Yong-gang.NURBS Surface Reconstruction Based on Neural Network[J].,2009,(10):65.
[8]蔡秋茹 罗烨 柳益君 叶飞跃.企业资信的BP神经网络评估模型研究[J].计算机技术与发展,2009,(10):117.
　CAI Qiu-ru,LUO Ye,LIU Yi-jun,et al.Research on BP Neural Network Model for Corporation Credit Rating[J].,2009,(10):117.
[9]王晓敏 刘希玉 戴芬.BP神经网络预测算法的改进及应用[J].计算机技术与发展,2009,(11):64.
　WANG Xiao-min,LIU Xi-yu,DAI Fen.Improvement and Application of BP Neural Network Forecasting Algorithm[J].,2009,(10):64.
[10]崔海青 刘希玉.基于粒子群算法的RBF网络参数优化算法[J].计算机技术与发展,2009,(12):117.
　CUI Hai-qing,LIU Xi-yu.Parameter Optimization Algorithm of RBF Neural Network Based on PSO Algorithm[J].,2009,(10):117.

更新日期/Last Update: 2019-10-10