Computer Science ›› 2018, Vol. 45 ›› Issue (2): 306-311.doi: 10.11896/j.issn.1002-137X.2018.02.053

Previous Articles     Next Articles

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

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!
Full text



No Suggested Reading articles found!