GA-STIP: Action Recognition in Multi-Channel Videos With Geometric Algebra Based Spatio-Temporal Interest Points

Rui Wang; Zhongzheng Cao; Xiangyang Wang; Weici Xue; Wenming Cao

doi:10.1109/ACCESS.2018.2872321

IEEE Access (Jan 2018)

GA-STIP: Action Recognition in Multi-Channel Videos With Geometric Algebra Based Spatio-Temporal Interest Points

Rui Wang,
Zhongzheng Cao,
Xiangyang Wang,
Weici Xue,
Wenming Cao

Affiliations

Rui Wang: ORCiD; Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, School of Communication and Information Engineering, Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai, China
Zhongzheng Cao: Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, School of Communication and Information Engineering, Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai, China
Xiangyang Wang: Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, School of Communication and Information Engineering, Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai, China
Weici Xue: Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, School of Communication and Information Engineering, Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai, China
Wenming Cao: ORCiD; College of Information Engineering, Shenzhen University, Shenzhen, China

DOI: https://doi.org/10.1109/ACCESS.2018.2872321
Journal volume & issue: Vol. 6
pp. 56575 – 56586

Abstract

Read online

Spatiotemporal interest points (STIPs) are often extracted for action recognition in videos. But most of the current interest point detection methods are not suitable for multi-channel videos. In this paper, a new geometric algebra (GA)-based STIP detection method is proposed for action recognition in multi-channel videos. Specifically, we take the advantage of GA to represent multi-channel videos and develop a new method to obtain multi-scale space, and then GA-based difference of Gaussian is computed to detect STIPs. Experimental results show that GA-STIP method can achieve better performance for multi-channel video action recognition.

Published in IEEE Access

ISSN: 2169-3536 (Online)
Publisher: IEEE
Country of publisher: United States
LCC subjects: Technology: Electrical engineering. Electronics. Nuclear engineering
Website: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6287639

About the journal

Abstract

Keywords