Human action recognition based on two-stream Ind recurrent neural network

Penghua Ge; Min Zhi

doi:10.1117/12.2524322

6 May 2019 Human action recognition based on two-stream Ind recurrent neural network

Penghua Ge, Min Zhi

Proceedings Volume 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018); 110693C (2019) https://doi.org/10.1117/12.2524322
Event: Tenth International Conference on Graphic and Image Processing (ICGIP 2018), 2018, Chengdu, China

Abstract

In order to avoid the influence of external factors on the subsequent recognition of RGB video and improve the accuracy of human motion recognition, an algorithm of human action recognition based on Two-Stream Ind Recurrent Neural Network is proposed. In terms of extracting features, the temporal network extracts the information on the 3D coordinate of different joints at each time and classifies it by a softmax layer. The spatial network converts the spatial positional relationship of the joints at each moment into a skeleton sequence and inputs it into the softmax layer to classify. Finally, the results of the classification of the temporal network and the spatial network are weighted and summed to obtain the final classification result. Experiments verify the validity of the model on the largest 3D skeleton action recognition dataset NTU RGB + D and SBU interactive dataset.

Citation Download Citation

Penghua Ge and Min Zhi "Human action recognition based on two-stream Ind recurrent neural network", Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018), 110693C (6 May 2019); https://doi.org/10.1117/12.2524322

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Neural networks

Neurons

3D modeling

Motion models

Video

Data modeling

Data hiding

Show All Keywords

Keywords/Phrases

Search In:

Publication Years