Human gait recognition using localized Grassmann mean representatives with partial least squares regression

Abstract

Gait recognition has become popular due to the rising demand for nonintrusive biometrics. At its nascent stage of development, gait recognition faces a number of challenges. The performance of a gait recognition system is sensitive towards factors like viewing angle, clothing, shoe type, load carriage and speed changes. In this paper, the problems of gait are formulated on the Grassmann manifold. It is not difficult to obtain multiple snapshots of a walking subjects with the wide availability of camera networks. These sets of images can be modelled as low-dimensional subspaces, which can be realized naturally as points on the Grassmann manifold. Modelling image sets as low-dimensional subspaces provides not only possible clue of one’s gait, but also the common patterns of variation in the set. We present a method called Localized Grassmann Mean Representatives with Partial Least Squares Regression (LoGPLS) to infer a low-dimensional Euclidean approximation of the manifold. The notion of local mean representatives is introduced to construct multiple tangent spaces to better approximate the topological structure of the manifold. As the properties of the tangent spaces allows the Grassmann points to be evaluated in the vector space, partial least squares is applied to allow a more accurate classification of the points in a reduced space. Experiments have been conducted on four different publicly available gait databases. Empirical evidences demonstrate the effectiveness of the proposed approach in solving the various covariates in gait recognition.