Recognition of human actions using moment based features and artificial neural networks

Author

Sharma, Arun ; Kumar, Dinesh K. ; Kumar, Sanjay ; McLachlan, Neil

Author_Institution

Sch. of Electr. & Comput. Eng., RMIT Univ., Melbourne, Vic., Australia

fYear

2004

fDate

5-7 Jan. 2004

Firstpage

368

Abstract

This paper presents performance of view-based approach in automated recognition of predefined hand and gross body actions using artificial neural network. This approach represents motion by a static grey scale image template computed by collapsing the temporal components into the cumulative image-difference of frames. The seven invariant Hu moments are used as the feature vectors. The performance of the system is tested in real time using feed forward multilayer perceptron (MLP) based on back propagation.

Keywords

backpropagation; feature extraction; feedforward neural nets; gesture recognition; multilayer perceptrons; object recognition; Hu moments; artificial neural networks; automated recognition; back propagation; cumulative frame image-difference; feature vectors; feed forward multilayer perceptron; grey scale image template; human actions recognition; moment based features; static image template; Application software; Artificial neural networks; Australia; Computer applications; Feeds; Humans; Multilayer perceptrons; Real time systems; Surveillance; System testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia Modelling Conference, 2004. Proceedings. 10th International

Print_ISBN

0-7695-2084-7

Type

conf

DOI

10.1109/MULMM.2004.1265015

Filename

1265015