Experimental Investigation of Human Gait Recognition Database using Wearable Sensors

Abstract

In this research human gait database is collected using different possible methods such as Wearable sensors, Smartphone and Cameras. For a gait recognition accelerometer data from wearable shimmer modules and smartphone are used. Data from different sensors location is compared to know which sensor location have better recognition rate. Different walking scenarios like slow, normal and fast walk were investigated. Wearable sensors and smartphone data are compared to know whether mobile phones can be used for gait recognition or not. Also effects of age, height, weight on gait recognition are also studied. The obtained results of gait biometric matrices like Genuine Recognition Rate (GRR), Total Recognition Rate (TRR) and Equal Error Rate (EER) showed better results. EER in different walking scenarios ranged from 0.17% to 2.27% for the five wearable sensors at different locations, whereas EER results of smartphone data ranged from 1.23% to 4.07%. For sensors located at leg, pocket and hand the average GRR value falls with increase in age group, while for sensors located at upper pocket and bag, the GRR value doesn't follow any trend. Moreover GRR results on all sensors show no significance regarding height or weight variations.

A New Post-Processing Proposal for Improving Biometric Gait Recognition Using Wearable Devices

“… Filtering to soften the signal. Here, one of the most commonly employed algorithms [ 13 , 45 , 53 ], the Weighted Moving Average (WMA), has been used. This algorithm is defined as: , with being the data at the instant t , the instant before and the instant after, respectively.…”

“…Problem 3 can be solved by detecting negative accumulated timestamp values and correcting them. The elimination of the zones with the problems 1 and 2, walking detection , has been addressed in previous works (e.g., in [ 45 ] with real devices or in [ 47 , 53 ] with simulated ones), but with solutions based on a prior exact gait cycle detection. As our approach is different, we propose our own alternative, based on using the following measures: Autocorrelation, R. The autocorrelation of the signal or a portion of it is defined as (Equation ( A1 )).…”