Stacked sparse autoencoder and history of binary motion image for human activity recognition

Abstract

The recognition of human actions in a video sequence still remains a challenging task in the computer vision community. Several techniques have been proposed until today such as silhouette detection, local space-time features and optical flow techniques. In this paper, a supervised way followed by an unsupervised learning using the principle of the auto-encoder is proposed to address the problem. We introduce a new foreground detection architecture based on information extracted from the Gaussian mixture model (GMM) incorporating with the uniform motion of Magnitude of Optical Flow (MOF). Thus, we use a fast dynamic frame skipping technique to avoid frames that contain irrelevant motion, making it possible to decrease the computational complexity of silhouette extraction. Furthermore a new technique of representations to construct an informative concept for human action recognition based on the superposition of human silhouettes is presented. We called this approach history of binary motion image (HBMI).Our method has been evaluated by a classification on the Ixmas, Weizmann, and KTH datasets, the Sparce Stacked Auto-encoder (SSAE), an instance of a deep learning strategy, is presented for efficient human activities detection and the Softmax (SMC) for the classification. The objective of this classifier in deep learning is the learning of function hierarchies with higher-level functions at lower-level functions of the hierarchy to provide an agile, robust and simple method. The results prove the efficiency of our proposed approach with respect to the irregularity in the performance of an action shape distortion, change of point of view as well as significant changes of scale.