Video action recognition based on improved 3D convolutional network and sparse representation classification

Wang Liu; Qi Fu; Yuqiu Lu; Jinyu Sun; Shiwei Ma

doi:10.1117/12.2542195

27 November 2019 Video action recognition based on improved 3D convolutional network and sparse representation classification

Wang Liu, Qi Fu, Yuqiu Lu, Jinyu Sun, Shiwei Ma

Author Affiliations +

Proceedings Volume 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence; 1132115 (2019) https://doi.org/10.1117/12.2542195
Event: The Second International Conference on Image, Video Processing and Artifical Intelligence, 2019, Shanghai, China

Abstract

In view of the problem that the typical convolutional neural networks fail to model actions at their full temporal extent, a novel video action recognition algorithm, which is based on improved 3D Convolutional Network (iC3D) architecture with K-means keyframes extraction and sparse representation classification (SRC), is proposed in this study. During the feature extraction process, the K-means keyframes extraction is constrained to reduce redundant information generated by continuous video frames and increase the temporal acceptance region. Meanwhile, to improve the noise immunity, sparse coding and its reconstruction errors are used for classification. The proposed method has 96.5% recognition accuracy on the typical video action classification dataset UCF101 that outperforms other competing methods. In addition, we built a wild test dataset to verify the generalization performance of the proposed model.

Citation Download Citation

Wang Liu, Qi Fu, Yuqiu Lu, Jinyu Sun, and Shiwei Ma "Video action recognition based on improved 3D convolutional network and sparse representation classification", Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 1132115 (27 November 2019); https://doi.org/10.1117/12.2542195

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available