Skip to Main Content
This paper presents a novel multi-view gait recognition method which combines the Enhanced Gabor (EG) representation of the Gait Energy Image (GEI) and Regularized Locally Tensor Discriminant Analysis (RLTDA) method. EG first derives desirable gait features characterized by spatial frequency, spatial locality, and orientation selectivity to cope with the variations due to surface, shoe types, clothing, carrying conditions, etc. Different from traditional Gabor transformation, which does not consider the structural characteristics of the gait features, our representation method not only considers the statistical property of the input features but also adopts a nonlinear mapping to emphasize those important feature points. The dimensionality of the derivation of EG gait feature is further reduced by using RLTDA, which directly obtain a set of locally optimal tensor eigenvectors and can capture nonlinear manifolds of gait features that exhibit appearance changes due to variable viewing angles. An aggregation scheme is adopted to combine the complementary information from differently RLTDA recognizers at the matching score level. The proposed method achieves the best average Rank-1 recognition rates for multi-view gait recognition based on image sequences from the USF HumanID gait challenge database and CASIA gait database.
Circuits and Systems for Video Technology, IEEE Transactions on (Volume:PP , Issue: 99 )