Research on Method of Human Gait Recognition Based on Deterministic Learning

YANG Fei-fei, TAO Yu-kun, SI Wen-jie

Control Engineering of China ›› 2018, Vol. 25 ›› Issue (2) : 259-266.

Control Engineering of China ›› 2018, Vol. 25 ›› Issue (2) : 259-266.

Research on Method of Human Gait Recognition Based on Deterministic Learning

Author information +
History +

Abstract

 In this paper, we investigate the problem of human gait recognition based on temporal data sequences by utilizing the deterministic learning theory. Firstly, discrete-time joint angle data obtained by the motion-capture equipment or image-processing algorithms forms the temporal data sequences, and locally-accurate approximation of the underlying gait system dynamics is achieved by using radial basis function (RBF) networks. We then prove the convergence of the approximation error and related parameters. Consequently, the joint angle data sequences can effectively represent human gait locomotion by using the knowledge of approximated gait dynamics which is kept in constant RBF networks. Finally, similarity definition for temporal gait data sequences generated from different persons or from different status of one person is given, and a method for recognition of gait temporal data sequences is proposed. We use less complicated simulation examples of compass-like biped robots gait recognition to demonstrate the effectiveness of our schemes.

Key words

Deterministic learning / temporal data sequence / joint angle / human gait recognition / similarity definition

Cite this article

Download Citations
YANG Fei-fei, TAO Yu-kun, SI Wen-jie. Research on Method of Human Gait Recognition Based on Deterministic Learning[J]. Control Engineering of China, 2018, 25(2): 259-266

3

Accesses

0

Citation

Detail

Sections
Recommended

/