DocumentCode :
649974
Title :
Recognition of human walking/running actions based on neural network
Author :
Alvarez Valle, Eladio ; Starostenko, Oleg
Author_Institution :
Dept. of Comput., Electron. & Mechatron., Univ. de las Americas Puebla, Cholula, Mexico
fYear :
2013
fDate :
Sept. 30 2013-Oct. 4 2013
Firstpage :
239
Lastpage :
244
Abstract :
High precision recognition of human actions directly from video records is still open problem. In this paper an approach for human action recognition for full body analysis based on a novel configuration of convolutional neural network is presented. The proposed convolutional neural network approach is a variant of multilayer perceptron, which main advantage is its ability to learn the feature extraction layers during retropropagation of errors from the lower layers using as input an image without any pre-processing. It permits to introduce the human descriptive action extraction process directly to neural network for more fast recognition. In order to evaluate the proposed approach a framework for recognizing human walking/running actions has been designed and tested on developed dataset that consists of multiple video records providing 4000 images per activity used for motion detection and activity interpretation.
Keywords :
feature extraction; gait analysis; image motion analysis; multilayer perceptrons; neural nets; video signal processing; convolutional neural network approach; error retropropagation; feature extraction layers; full body analysis; high precision recognition; human action recognition; human descriptive action extraction process; human running action recognition; human walking action recognition; motion detection; multilayer perceptron; multiple video records; convolutional neural network; feature extraction; human action recognition; machine learning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Electrical Engineering, Computing Science and Automatic Control (CCE), 2013 10th International Conference on
Conference_Location :
Mexico City
Print_ISBN :
978-1-4799-1460-9
Type :
conf
DOI :
10.1109/ICEEE.2013.6676005
Filename :
6676005
Link To Document :
بازگشت