3D Features for human action recognition with semi-supervised learning

Abstract

Human action recognition (HAR) is a very challenging task because of intra-class variations and complex backgrounds. Here, a motion history image (MHI)-based interest point refinement is proposed to remove the noisy interest points. Histogram of oriented gradient (HOG) and histogram of optical flow (HOF) techniques are extended from spatial to spatio-temporal domain to preserve the temporal information. These local features are used to build the trees for the random forest technique. During tree building, a semi-supervised learning is proposed for better splitting of data points at each node. For recognition of an action, mutual information is estimated for all the extracted interest points to each of the trained class by passing them through the random forest. The proposed method is evaluated on KTH, Weizmann, and UCF Sports standard datasets. The experimental results indicate that the proposed technique provides better performance compared to earlier reported techniques.