+91 8617752708

British Journal of Applied Science & Technology, ISSN: 2231-0843,Vol.: 20, Issue.: 5

Original-research-article

Recognition of Human Actions Based on Temporal Motion Templates

 

Samy Bakheet1,2*, Ayoub Al-Hamadi2 and M. A. Mofaddel1
1Department of Mathematics and Computer Science, Faculty of Science, Sohag University, P.O.Box 82524 Sohag, Egypt.
2Institute for Information Technology and Communications, Otto-von-Guericke-University Magdeburg, P.O.Box 4120, 39016 Magdeburg, Germany.

Article Information
Editor(s):
(1) Vitaly Kober, Department of Computer Science, CICESE, Mexico.
Reviewers:
(1) G. Murugananth, Ahalia School of Engineering and Technology, Kerala, India.
(2) Ferda Ernawan, Universiti Malaysia Pahang, Malaysia.
Complete Peer review History: http://www.sciencedomain.org/review-history/18899

Abstracts

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.

Keywords :

Human action recognition; temporal motion templates; naïve Bayes; IIKT action dataset; video interpretation.

Full Article - PDF    Page 1-11 Article Metrics

DOI : 10.9734/BJAST/2017/28318

Review History    Comments

Our Contacts

Guest House Road, Street no - 1/6,
Hooghly, West Bengal,
India

+91 8617752708

 

Third Floor, 207 Regent Street
London, W1B 3HH,
UK

+44 20-3031-1429