Share Email Print
cover

Proceedings Paper

A fast human action recognition algorithm based on key frame pinning
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper proposed a fast human action recognition algorithm which utilized two features that can be described as iconic posture and fast moving. At first, a human detection algorithm is used to detect human object in every frame. Then regions marked as human are sent into a trained deep classification network to match trained iconic postures in key frame. Then several frames before key frame and after key frame are examined by frame differences, which are used to compensate background movement and perform human motion speed judgment. After the key frame pinning and speed judgment, the final recognition results are determined.

Paper Details

Date Published: 25 October 2018
PDF: 7 pages
Proc. SPIE 10822, Real-time Photonic Measurements, Data Management, and Processing III, 108220U (25 October 2018); doi: 10.1117/12.2502412
Show Author Affiliations
Hai Tan, Huazhong Institute of Electro-Optics (China)
Yin Xu, Huazhong Institute of Electro-Optics (China)
Gangbo Sun, Huazhong Institute of Electro-Optics (China)
Bo Lei, Huazhong Institute of Electro-Optics (China)


Published in SPIE Proceedings Vol. 10822:
Real-time Photonic Measurements, Data Management, and Processing III
Ming Li; Bahram Jalali; Keisuke Goda; Kevin K. Tsia, Editor(s)

© SPIE. Terms of Use
Back to Top