Human Action Recognition Based on Integrating Body Pose, Part Shape, and Motion

Human Action Recognition Based on Integrating Body Pose, Part Shape, and Motion

Human action recognition is a challenging problem, especially in the presence of multiple actors in the scene and/or viewpoint variations. In this paper, three modalities, namely, 3-D skeletons, body part images, and motion history image (MHI), are integrated into a hybrid deep learning architecture...

Full description

Bibliographic Details
Main Authors: Hany El-Ghaish, Mohamed E. Hussien, Amin Shoukry, Rikio Onai
Format: Article
Language:English
Published: IEEE 2018-01-01
Series:IEEE Access
Subjects:
Human action recognition
spatial and temporal features
convolution neural networks (CNN)
long short-term memory (LSTM)
CNN-LSTM
motion history images (MHI)
Online Access:https://ieeexplore.ieee.org/document/8453782/

Internet

https://ieeexplore.ieee.org/document/8453782/

Similar Items