Human Gait Database for Normal Walk Collected by Smartphone Accelerometer

Abstract

Gait recognition is the characterization of unique biometric patterns associated with each individual which can be utilized to identify a person without direct contact. A public gait database with a relatively large number of subjects can provide a great opportunity for future studies to build and validate gait authentication models. The goal of this study is to introduce a comprehensive gait database of 93 human subjects who walked between two endpoints (320 meters) during two different sessions and record their gait data using two smartphones, one attached to the right thigh and another one on the left side of the waist. This data is collected to be utilized by a deep learning-based method that requires enough time points. The metadata including age, gender, smoking, daily exercise time, height, and weight of an individual is recorded. this data set is publicly available.