模式识别与人工智能
Friday, Apr. 4, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2021, Vol. 34 Issue (9): 863-870    DOI: 10.16451/j.cnki.issn1003-6059.202109009
Deep Learning Algorithms and the Applications in Image and Vision Current Issue| Next Issue| Archive| Adv Search |
Human Action Recognition Fusing Two-Stream Networks and SVM
TONG Anyang1,2, TANG Chao1,2, WANG Wenjian3
1. School of Artificial Intelligence and Big Data, Hefei University, Hefei 230601
2. Anhui Provincial Key Laboratory of Multimodal Cognitive Com-putation, Anhui University, Hefei 230601
3. School of Computer and Information Technology, Shanxi University, Taiyuan 030006

Download: PDF (671 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  It is difficult for the traditional two-stream convolutional neural network to understand the long-motion information, and when the long-time stream information is lost, the generalization ability of the model decreases. Therefore, a method for human action recognition fusing two-stream network and support vector machine is proposed. Firstly, RGB images of each frame in the video and their corresponding dense optical flow sequence diagrams in the vertical direction are extracted, and the spatial information and time information of actions in the video are obtained. The information is input into the spatial domain and time domain networks for pre-training, and feature extraction is carried out after pre-training. Secondly, the feature vectors with the same dimension extracted from the two-stream network are fused in parallel to improve the representation ability of feature vectors. Finally, the fused feature vectors are input into the linear support vector machine for training and classification. The experimental results based on the standard open database proves that the classification effect of the proposed method is good.
Key wordsTwo-Stream Network      Support Vector Machine      Feature Fusion      Optical Flow     
Received: 28 April 2021     
ZTFLH: TP 391.41  
Fund:Natural Science Foundation of Anhui Province(No.2008085MF202), University Natural Sciences Research Project of Anhui Province(No.KJ2020A0660), Open Project of Key Laboratory of Multimodal Cognitive Computation of Anhui University(No.MMC202003)
Corresponding Authors: TANG Chao, Ph.D., associate professor. His research interests include machine learning and computer vision.   
About author:: TONG Anyang, master student. His research interests include deep learning and computer vision.
WANG Wenjian, Ph.D., professor. Her research interests include machine learning and computing intelligence.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
TONG Anyang
TANG Chao
WANG Wenjian
Cite this article:   
TONG Anyang,TANG Chao,WANG Wenjian. Human Action Recognition Fusing Two-Stream Networks and SVM[J]. , 2021, 34(9): 863-870.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202109009      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2021/V34/I9/863
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn