A practical time series action detection algorithm

Tao Ling; Jing Ling

doi:10.1117/12.2655049

2 November 2022 A practical time series action detection algorithm

Tao Ling, Jing Ling

Proceedings Volume 12351, International Conference on Advanced Sensing and Smart Manufacturing (ASSM 2022); 123511I (2022) https://doi.org/10.1117/12.2655049
Event: International Conference on Advanced Sensing and Smart Manufacturing (ASSM 2022), 2022, Nanjing, China

Abstract

This paper proposes a time series action detection algorithm. Based on the classical SlowFast algorithm, the input image of the slow channel is determined according to the image stability index to improve the detection accuracy of the slow module. Mixed algorithm to reduce fast-channel computations by determining input video segments for fast-channel based on fast skeletal action detection. By preprocessing, it can greatly reduce the computational load of SlowFast algorithm and improve its accuracy.

Citation Download Citation

Tao Ling and Jing Ling "A practical time series action detection algorithm", Proc. SPIE 12351, International Conference on Advanced Sensing and Smart Manufacturing (ASSM 2022), 123511I (2 November 2022); https://doi.org/10.1117/12.2655049

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