ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Human action recognition using a fast learning fully complex-valued classifier

Babu, Venkatesh R and Suresh, S and Savitha, R (2012) Human action recognition using a fast learning fully complex-valued classifier. In: NEUROCOMPUTING, 89 (15). pp. 202-212.

[img] PDF
neu_comp_89_15_202-212.pdf - Published Version
Restricted to Registered users only

Download (1MB) | Request a copy
Official URL: http://dx.doi.org/10.1016/j.neucom.2012.03.003

Abstract

In this paper, we use optical flow based complex-valued features extracted from video sequences to recognize human actions. The optical flow features between two image planes can be appropriately represented in the Complex plane. Therefore, we argue that motion information that is used to model the human actions should be represented as complex-valued features and propose a fast learning fully complex-valued neural classifier to solve the action recognition task. The classifier, termed as, ``fast learning fully complex-valued neural (FLFCN) classifier'' is a single hidden layer fully complex-valued neural network. The neurons in the hidden layer employ the fully complex-valued activation function of the type of a hyperbolic secant function. The parameters of the hidden layer are chosen randomly and the output weights are estimated as the minimum norm least square solution to a set of linear equations. The results indicate the superior performance of FLFCN classifier in recognizing the actions compared to real-valued support vector machines and other existing results in the literature. Complex valued representation of 2D motion and orthogonal decision boundaries boost the classification performance of FLFCN classifier. (c) 2012 Elsevier B.V. All rights reserved.

Item Type: Journal Article
Publication: NEUROCOMPUTING
Publisher: ELSEVIER SCIENCE BV
Additional Information: Copyright for this article belongs to Elseview Science
Keywords: Action recognition;Complex-valued neural networks;Optical flow;Human Action;Orthogonal decision boundaries
Department/Centre: Division of Interdisciplinary Sciences > Supercomputer Education & Research Centre
Date Deposited: 28 Jun 2012 07:36
Last Modified: 28 Jun 2012 07:36
URI: http://eprints.iisc.ac.in/id/eprint/44729

Actions (login required)

View Item View Item