A Novel Motion Recognition Method Based on Improved Two-stream Convolutional Neural Network and Sparse Feature Fusion

Chen Chen1

  1. Sports Institute, Henan University of Technology
    Zhengzhou City, 470001 China
    byoungholee@qq.com

Abstract

Motion recognition is a hot topic in the field of computer vision. It is a challenging task. Motion recognition analysis is closely related to the network input, network structure and feature fusion. Due to the noise in the video, traditional methods cannot better obtain the feature information resulting in the problem of inaccurate motion recognition. Feature selection directly affects the efficiency of recognition, and there are still many problems to be solved in the multi-level feature fusion process. In this paper, we propose a novel motion recognition method based on an improved two-stream convolutional neural network and sparse feature fusion. In the low-rank space, because sparse features can effectively capture the information of motion objects in the video, meanwhile, we supplement the network input data, in view of the lack of information interaction in the network, we fuse the high-level semantic information and low-level detail information to recognize the motions by introducing attention mechanism, which makes the performance of the two-stream convolutional neural network have more advantages. Experimental results on UCF101 and HMDB51 data sets show that the proposed method can effectively improve the performance of motion recognition.

Key words

motion recognition, two-stream convolutional neural network, attention mechanism, sparse feature fusion, low-rank space

Digital Object Identifier (DOI)

https://doi.org/10.2298/CSIS220105043C

Publication information

Volume 19, Issue 3 (September 2022)
Year of Publication: 2022
ISSN: 1820-0214 (Print) 2406-1018 (Online)
Publisher: ComSIS Consortium

Full text

DownloadAvailable in PDF
Portable Document Format

How to cite

Chen, C.: A Novel Motion Recognition Method Based on Improved Two-stream Convolutional Neural Network and Sparse Feature Fusion. Computer Science and Information Systems, Vol. 19, No. 3, 1329-1348. (2022), https://doi.org/10.2298/CSIS220105043C