Human action recognition using extreme learning machine via multiple types of features

Abstract

This paper introduces a human actions recognition framework based on multiple types of features. Taking the advantage of motion-selectivity property of 3D dual-tree complex wavelet transform (3D DT-CWT) and affine SIFT local image detector, firstly spatio-temporal and local static features are extracted. No assumptions of scene background, location, objects of interest, or point of view information are made whereas bidirectional two-dimensional PCA (2D-PCA) is employed for dimensionality reduction which offers enhanced capabilities to preserve structure and correlation amongst neighborhood pixels of a video frame. The proposed technique is significantly faster than traditional methods due to volumetric processing of input video, and offers a rich representation of human actions in terms of reduction in artifacts. Experimental examples are given to illustrate the effectiveness of the approach.