Title: A pyramidal deep learning architecture for human action recognition

Authors: Lidong Xie; Wei Pan; Chao Tang; Huosheng Hu

Addresses: Cognitive Science Department, Fujian Key Laboratory of the Brain-like Intelligent Systems, Xiamen University, Xiamen 361005, China ' Cognitive Science Department, Fujian Key Laboratory of the Brain-like Intelligent Systems, Xiamen University, Xiamen 361005, China ' Cognitive Science Department, Fujian Key Laboratory of the Brain-like Intelligent Systems, Xiamen University, Xiamen 361005, China ' School of Computer Science and Electronic Engineering, University of Essex, Colchester CO4 3SQ, UK

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.

Keywords: deep learning; stacked de-noising auto-encoder; Kinect; human action recognition; depth images; 3D vision sensors; neural networks; pattern recognition; human actions.

DOI: 10.1504/IJMIC.2014.060007

International Journal of Modelling, Identification and Control, 2014 Vol.21 No.2, pp.139 - 146

Published online: 07 Jun 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article