Trajectory-aware three-stream CNN for video action recognition

Zhengkui Weng; Yepeng Guan

doi:10.1117/1.JEI.28.2.021004

31 December 2018 Trajectory-aware three-stream CNN for video action recognition

Zhengkui Weng, Yepeng Guan

Author Affiliations +

Journal of Electronic Imaging, Vol. 28, Issue 2, 021004 (December 2018). https://doi.org/10.1117/1.JEI.28.2.021004

Abstract

Video-based human action recognition is a challenging task in computer vision. In recent years, the convolution neural network (CNN) and its extended versions have shown promising results for video action recognition. However, most of the existing methods cannot deal with the global motion information effectively, especially for long-term motion which is crucial to represent complex none-periodic actions. To address this issue, a stacked trajectory energy image (STEI) is proposed by extracting trajectories from motion saliency regions and stacked them onto one grayscale image. This will result in an STEI with discriminative texture feature which can effectively characterize the global motion from multiple consecutive frames. Then, a three-stream CNN framework is proposed to simultaneously capture spatial, temporal, and global motion information of the action from RGB frames, optical flow, and STEI. Moreover, a trajectory-aware convolution strategy is introduced by incorporating local and long-term motion information so as to learn the motion features directly and effectively from three complementary action-related regions. Finally, the learned features are aggregated and categorized by a linear support vector machine. The experimental results on two challenging datasets (i.e., HMDB51 and UCF101) demonstrate that our approach statistically outperforms a number of state-of-the-art methods.

Citation Download Citation

Zhengkui Weng and Yepeng Guan "Trajectory-aware three-stream CNN for video action recognition," Journal of Electronic Imaging 28(2), 021004 (31 December 2018). https://doi.org/10.1117/1.JEI.28.2.021004

Received: 28 May 2018; Accepted: 15 November 2018; Published: 31 December 2018

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