Recognition of Human Actions Based on Temporal Motion Templates
Samy Bakheet, Ayoub Al-Hamadi, M. A. Mofaddel
Current Journal of Applied Science and Technology · pp. 1–11 · Published 3 May 2017
10.9734/BJAST/2017/28318Abstract
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.
Cited by 4
Samy Bakheet, Ayoub Al-Hamadi · Heliyon · 2022
Samy Bakheet, Shtwai Alsubai, Abdullah Alqahtani · Applied Sciences · 2022
Junkai Yin, Shanhai Pan, Xiaohua Li · 2023 3rd International Conference on Electronic Information Engineering and Computer (EIECT) · 2023
Showing 3 of 4 known citations — external sources report more than can currently be individually listed.
Related research
- Hypertension Prediction System Using Naive Bayes Classifier — shares topic coverage
- Feature-based Model for Extraction and Classification of High Quality Questions in Online Forum — shares topic coverage
- A Model for Coronary Heart Disease Prediction Using Data Mining Classification Techniques — shares topic coverage
- Plant Leaf Disease Detection by Using Different Classification Techniques: Comparative — shares topic coverage
- Predicting Weather Forecasting State Based on Data Mining Classification Algorithms — shares topic coverage
Article metrics
Real usage data collected on this platform.
5
Page views
0
PDF downloads
0
Outbound clicks
4
Citations
Views over time
Views by country
Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".
Traffic sources
Referring site, by host.
Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.