Modelling the Time-Variant Covariates for Gait Recognition

Abstract

Abstract. This paper deals with a problem of recognition by gait when time-dependent covariates are added, i.e. when 6 months have passed between recording of the gallery and the probe sets. We show how recognition rates fall significantly when data is captured between lengthy time intevals, for static and dynamic gait features. Under the assumption that it is possible to have some subjects from the probe for training and that similar subjects have similar changes in gait over time, a predictive model of changes in gait is suggested in this paper, which can improve the recognition capability. A small number of subjects were used for training and a much large number for classification and the probe contains the covariate data for a smaller number of subjects. Our new predictive model derives high recognition rates for different features which is a considerable improvement on recognition capability without this new approach.

Exploratory factor analysis of gait recognition

“…In this way the overall CCR could be improved from 23 to 27% [20]. By modelling the change in feature space (by using linear interpolation) the recognition rate with variation in time was improved from 23% to 65% [19]. Both of these are considerably improved over the 3% achieved by Phillips et al [15].…”

“…Phillips reported a CCR of 57% for Data (I) with load carriage and footwear covariates whilst a CCR of 3% is achieved for Data (II) with the following covariates : time, footwear, and clothing. Time has been shown [15,19] to play a major part in reducing recognition capability by gait. Using a silhouette based approach Veres showed that this could be redressed by fusing those parts of the gait signature which are invariant with time.…”

Gait recognition by dynamic cues

“…This is mainly because static features are dependent on clothing, bags, and other factors [12,11] which would certainly affect the recognition performance. On the other hand, Cutting et al [4] argued that dynamic features contribute significantly more in human recognition than static cues such as height.…”

Multilinear Modeling for Robust Identity Recognition from Gait

“…Bouchrika and Nixon (2008) conducted a comparative study of their influence in gait analysis. Veres et al (2005) proposed a remarkable predictive model of the "time of execution" covariate to improve recognition performance. The issue has however been approached so far on an empirical basis, i.e.…”