Recognition of Human Actions Based on Temporal Motion Templates

Bakheet, Samy and Al-Hamadi, Ayoub and Mofaddel, M (2017) Recognition of Human Actions Based on Temporal Motion Templates. British Journal of Applied Science & Technology, 20 (5). pp. 1-11. ISSN 22310843

[thumbnail of Bakheet2052016BJAST28318.pdf] Text
Bakheet2052016BJAST28318.pdf - Published Version

Download (1MB)

Abstract

Despite their attractive properties of invariance, robustness and reliability, statistical motion descriptions from temporal templates have not apparently received the amount of attention they might deserve in the human action recognition literature. In this paper, we propose an innovative approach for action recognition, where a novel fuzzy representation based on temporal motion templates is developed to model human actions as time series of low-dimensional descriptors. An NB (Naïve Bayes) classifier is trained on these features for action classification. When tested on a realistic action dataset incorporating a large collection of video data, the results demonstrate that the approach is able to achieve a recognition rate of as high as 93.7%, while remaining tractable for real-time operation.

Item Type: Article
Subjects: East India Archive > Multidisciplinary
Depositing User: Unnamed user with email support@eastindiaarchive.com
Date Deposited: 22 May 2023 06:13
Last Modified: 21 Sep 2024 04:37
URI: http://ebooks.keeplibrary.com/id/eprint/1091

Actions (login required)

View Item
View Item