Gait Recognition for Human Identification using Kinect

Abstract

Gait is a pattern of biometric movement for human identification. Unlike other biometrics such as fingerprint, iris, face, and voice recognition, human gait can be captured with unobtrusive method. In this paper, several measurements are proposed which uses body frame information in 3D space. Body frame data is generated from depth images captured using Kinect camera. The generated body frames are used for human gait analysis. The angle of lower body parts is measured in a gait cycle. In addition, the length of body parts is measured as a feature for combination with the angle measurements. The measurements are compared to each other from 5 subjects who have similar body type. The difference from comparison of the measurements indicates that the human gait has a potential pattern for human identification.