| Autor: |
Yan Tao Zhao, Xiaoli Li, Si Yuan Feng, Mei Ling Fu, Bo Zhang, Xu Guang Zhang |
| Rok vydání: |
2013 |
| Předmět: |
|
| Zdroj: |
Applied Mechanics and Materials. :675-679 |
| ISSN: |
1662-7482 |
| DOI: |
10.4028/www.scientific.net/amm.333-335.675 |
| Popis: |
This paper presents an efficient and novel framework for human action recognition based on representing the motion of human body-joints and the theory of nonlinear dynamical systems. Our work is motivated by the pictorial structures model and advances in human pose estimation. Intuitively, a collective understanding of human joints movements can lead to a better representation and understanding of any human action through quantization in the polar space. We use time-delay embedding on the time series resulting of the evolution of human body-joints variables along time to reconstruct phase portraits. Moreover, we train SVM models for action recognition by comparing the distances between trajectories of human body-joints variables within the reconstructed phase portraits. The proposed framework is evaluated on MSR-Action3D dataset and results compared against several state-of-the-art methods. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
