计算机科学 ›› 2018, Vol. 45 ›› Issue (2): 306-311.doi: 10.11896/j.issn.1002-137X.2018.02.053

• 图形图像及模式识别 • 上一篇    下一篇

基于卷积神经网络的多人行为识别方法

龚安,费凡,郑君   

  1. 中国石油大学华东计算机与通信工程学院 山东 青岛266580,中国石油大学华东计算机与通信工程学院 山东 青岛266580,中国石油大学华东计算机与通信工程学院 山东 青岛266580
  • 出版日期:2018-02-15 发布日期:2018-11-13

Multi-person Behavior Recognition Method Based on Convolutional Neural Networks

GONG An, FEI Fan and ZHENG Jun   

  • Online:2018-02-15 Published:2018-11-13

摘要: 为了解决多人行为识别中人物角色多且难以区分、图片增加的特征维数难以表达和学习以及行为背景复杂且容易产生干扰等问题,提出了一种基于卷积神经网络的多人行为识别方法。考虑到多人行为识别的复杂性,选择较为容易的两人交互行为作为研究对象,对实验中需要的图像数据库进行了初步的收集与预处理;然后选用在特征提取中不受拍摄角度、光照强度影响的Dense-sift算法来对原始图像进行初步的特征提取。由于人体行为图片相对手写数字图片更为复杂,因此为了使该网络能够很好地 识别 人体行为,针对该网络在其输入、网络层数、滤波器核数、学习率、输出等方面进行了修改。实验结果表明,提出的方法对拳击、拥抱、接吻3类交互行为的识别是有效的。

关键词: 多人行为识别,卷积神经网络,Dense-sift特征提取

Abstract: In order to solve the problems in multi-person behavior recognition,for example,it is difficult to distinguish many characters,it is difficult to express and learn increased feature dimension of image,the behavior background is complex and it is easy to cause interference,this paper proposed a method of multiplayer behavior recognition based on convolutional neural network.At first,considering the complexity of multi-person behavior recognition,the simple two-person interactive behavior is choosen as the research object and the picture database is collected.Then,because multiplayer behavior recognition has complicated background and many features in the recognition progress,a method using the Dense-sift algorithm for feature pretreatment mode is proposed.Against the complexity of the multiplayer behavior recognition,this network makes various modifications,such as input dimensions which is expanded to include layer convolution,convolution kernel increasing,output reduction,etc.Experimental results show that the proposed method can recognize simple multi-person behavior recognition,such as boxing,hug and kissing effectively.

Key words: Multi-person behavior recognition,Convolutional neural network,Dense-sift feature extraction

[1] DU Y,CHEN F,XU W,et al.Activity recognition throughmulti-scale motion detail analysis[J].Neurocomputing,2008,71(16-18):3561-3574.
[2] HAN L,LI J F,JIA Y D.Human Interaction Recognition Using Spatio-Temproal Words[J].Chinese Journal of Computers,2010,33(4):776-784.(in Chinese) 韩磊,李君峰,贾云得.基于时空单词的两人交互行为识别方法[J].计算机学报,2010,33(4):776-784.
[3] PENG D,HUIJUN D,LIGEN D,et al.Group interaction analy-sis in dynamic context[J].IEEE Transactions on Systems Man &Cybernetics Part B Cybernetics A Publication of the IEEE Systems Man & Cybernetics Society,2009,39(1):275-282.
[4] RYOO M S,AGGARWAL J K.Recognition of High-level GroupActivities Based on Activities of Individual Members[C]∥IEEE Workshop on Motion and Video Computing.IEEE Computer Society,2008:1-8.
[5] JI S,YANG M,YU K.3D convolutional neural networks for human action recognition[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2013,35(1):221-231.
[6] KARPATHY A,TODERICI G,SHETTY S,et al.Large-Scale Video Classification with Convolutional Neural Networks[C]∥IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society,2014:1725-1732.
[7] DAS A,PAL U,FERRER B M A,et al.Sclera recognition using dense-SIFT[C]∥International Conference on Intelligent Systems Design and Applications.2013:74-79.
[8] GAO C,ZHANG X,WANG Y L,et al.Automatic stitching approach of aerial image sequence based on SIFT features[J].Computer Applications,2007,21(11):2789-2792.(in Chinese) 高超,张鑫,王云丽,等.一种基于SIFI特征的航拍图像序列自动拼接方法[J].计算机应用,2007,21(11):2789-2792.
[9] BROWN M,LOWE D G.Invariant Features from Interest Point Groups[C]∥British Machine Vision Conference.2002:656-665.
[10] LOWE D G.Distinctive Image Features from Scale-InvariantKeypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[11] ZHAO Z H,YANG S P,MA Z Q.License Plate Character Reco-gnition Based on Convolutional Neural Network LeNet-5 [J].Journal of System Simulation,2010,22(3):638-641.(in Chinese) 赵志宏,杨绍普,马增强.基于卷积神经网络LeNet-5的车牌字符识别研究[J].系统仿真学报,2010,22(3):638-641.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 雷丽晖,王静. 可能性测度下的LTL模型检测并行化研究[J]. 计算机科学, 2018, 45(4): 71 -75 .
[2] 孙启,金燕,何琨,徐凌轩. 用于求解混合车辆路径问题的混合进化算法[J]. 计算机科学, 2018, 45(4): 76 -82 .
[3] 张佳男,肖鸣宇. 带权混合支配问题的近似算法研究[J]. 计算机科学, 2018, 45(4): 83 -88 .
[4] 伍建辉,黄中祥,李武,吴健辉,彭鑫,张生. 城市道路建设时序决策的鲁棒优化[J]. 计算机科学, 2018, 45(4): 89 -93 .
[5] 史雯隽,武继刚,罗裕春. 针对移动云计算任务迁移的快速高效调度算法[J]. 计算机科学, 2018, 45(4): 94 -99 .
[6] 周燕萍,业巧林. 基于L1-范数距离的最小二乘对支持向量机[J]. 计算机科学, 2018, 45(4): 100 -105 .
[7] 刘博艺,唐湘滟,程杰仁. 基于多生长时期模板匹配的玉米螟识别方法[J]. 计算机科学, 2018, 45(4): 106 -111 .
[8] 耿海军,施新刚,王之梁,尹霞,尹少平. 基于有向无环图的互联网域内节能路由算法[J]. 计算机科学, 2018, 45(4): 112 -116 .
[9] 崔琼,李建华,王宏,南明莉. 基于节点修复的网络化指挥信息系统弹性分析模型[J]. 计算机科学, 2018, 45(4): 117 -121 .
[10] 王振朝,侯欢欢,连蕊. 抑制CMT中乱序程度的路径优化方案[J]. 计算机科学, 2018, 45(4): 122 -125 .