Action Recognition by Multiple Features and Hyper-sphere Multi-class SVM

Abstract

In this paper we propose a novel framework for action recognition based on multiple features for improve action recognition in videos. The fusion of multiple features is important for recognizing actions as often a single features based representation is not enough to capture the imaging variations (view-point, illumination etc.) and attributes of individuals (size, age, gender etc). Hence, we use two kinds of features: i) a quantized vocabulary of local spatio-temporal (ST) volumes (cuboids and 2-D SIFT), and ii) the higher order statistical models of interest points, which aims to capture the global information of the actor. We construct video presentation in terms of local space time features and global features and integrate such representations with hper-sphere multi-class SVM. Experiments on publicly available datasets show that our proposed approach is effective. An additional experiment shows that using both local and global features provides a richer representation of human action when compared to the use of a single feature type.