A pyramidal deep learning architecture for human action recognition

Abstract

This paper proposes a pyramidal deep learning architecture for human action recognition based on depth images from a 3D vision sensor. This method consists of three steps: 1) pre-processing depth image; 2) building a hidden deep neural network; 3) pattern recognition. A novel pyramidal stacked de-noising auto-encoder (pSDAE) is proposed to build a deep neural network so that its weights can be learnt layer by layer. A feed-forward neural network based on the deep learned weights is trained to classify each action pattern. Based on the experimental results from the Kinect dataset of human actions sampled in experiments, it is clear that the proposed approach outperforms the existing classical classify method. The robust experiment results on the Weizmann dataset show the good expansibility of the proposed method.