Multi-dimensional human action recognition model based on image set and group sparisty

2016 ◽  
Vol 215 ◽  
pp. 138-149 ◽  
Author(s):  
Z. Gao ◽  
Y. Zhang ◽  
H. Zhang ◽  
Y.B. Xue ◽  
G.P. Xu
Keyword(s):  
Action Recognition ◽  
Human Action Recognition ◽  
Human Action ◽  
Recognition Model ◽  
Model Based ◽  
Image Set

3D human action recognition model based on image set and regularized multi-task leaning

2017 ◽  
Vol 252 ◽  
pp. 67-76 ◽  
Author(s):  
Z. Gao ◽  
G.T. Zhang ◽  
H. Zhang ◽  
Y.B. Xue ◽  
G.P. Xu
Keyword(s):  
Action Recognition ◽  
Human Action Recognition ◽  
Human Action ◽  
Recognition Model ◽  
Model Based ◽  
Image Set

scholarly journals Model-based human action recognition

2010 ◽  
Author(s):  
Nattapon Noorit ◽  
Nikom Suvonvorn ◽  
Montri Karnchanadecha
Keyword(s):  
Action Recognition ◽  
Human Action Recognition ◽  
Human Action ◽  
Model Based

scholarly journals Human action recognition based on mixed gaussian hidden markov model

2021 ◽  
Vol 336 ◽  
pp. 06004
Author(s):  
Jiawei Xu ◽  
Qian Luo
Keyword(s):  
Markov Model ◽  
Hidden Markov Model ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Action Recognition ◽  
Hidden Markov ◽  
Human Action Recognition ◽  
Gaussian Mixture ◽  
Human Action ◽  
Model Based

Human action recognition is a challenging field in recent years. Many traditional signal processing and machine learning methods are gradually trying to be applied in this field. This paper uses a hidden Markov model based on mixed Gaussian to solve the problem of human action recognition. The model treats the observed human actions as samples which conform to the Gaussian mixture model, and each Gaussian mixture model is determined by a state variable. The training of the model is the process that obtain the model parameters through the expectation maximization algorithm. The simulation results show that the Hidden Markov Model based on the mixed Gaussian distribution can perform well in human action recognition.

Sign in / Sign up

Export Citation Format

Share Document