FENG‎ > ‎


 Kinect-based Human Gait Identification under Different Covariate Factors
Azhin Tahir Sabir
Department of Software Engineering, Faculty of Engineering, Koya University

Abstract: In this study we present Kinect-based gait recognition using non-standard gait sequences. This study examines different scenarios to highlight the challenges of non-standard gait sequences. Gait signatures are extracted from the 20 joint points of the human body using a Microsoft Kinect sensor. This feature is constructed by calculating the distances between each two joint points from the 20 joint points of the human body provided which is known as the Euclidean Distance Feature (EDF). The experiments are based on five scenarios, and a Linear Discriminant Classifier (LDC) is used to test the performance of the proposed method. The results of the experiments indicate that the proposed method outperforms previous work in all scenarios. 

Keywords: Neutral and non-neutral gait recognition; Kinect sensor; EDF; PCA; LDA; LDC.

Date: 08/05/2019
Place: Faculty of Engineering/ Nashmeil Hall
Caroline Yousif Daniel,
May 9, 2019, 8:39 AM