No abstract

SUMMARYVariations in walking speed have a strong impact on gaitbased person identification. We propose a method that is robust against walking-speed variations. It is based on a combination of cubic higherorder local auto-correlation (CHLAC), gait silhouette-based principal component analysis (GSP), and a statistical framework using hidden Markov models (HMMs). The CHLAC features capture the within-phase spatiotemporal characteristics of each individual, the GSP features retain more shape/phase information for better gait sequence alignment, and the HMMs classify the ID of each gait even when walking speed changes nonlinearly. We compared the performance of our method with other conventional methods using five different databases, SOTON, USF-NIST, CMU-MoBo, TokyoTech A and TokyoTech B. The proposed method was equal to or better than the others when the speed did not change greatly, and it was significantly better when the speed varied across and within a gait sequence.

We propose a method for phase estimation of a single non-parametric quasi-periodic signal. Assuming signal intensities should be equal among samples of the same phase, such corresponding samples are obtained by self-dynamic time warping between a quasi-periodic signal and a signal with multiple-period shifts applied. A phase sequence is then estimated in a sub-sampling order using an optimization framework incorporating 1) a data term derived from the correspondences and 2) a smoothness term of the local phase evolution under 3) a monotonic-increasing constraint on the phase. Such a phase estimation is, however, illposed because of combination ambiguity between the phase evolution and the normalized periodic signal, and hence can result in a biased solution. Therefore, we introduce into the optimization framework 4) a bias correction term, which imposes zero-bias from the linear phase evolution. Analysis of the quasi-periodic signals from both simulated and real data indicate the effectiveness and also potential applications of the proposed method.

This paper describes a method of gait recognition by suppressing and using gait fluctuations. Inconsistent phasing between a matching pair of gait image sequences because of temporal fluctuations degrades the performance of gait recognition. We remove the temporal fluctuations by generating a phase-normalized gait image sequence with equal phase intervals. If inter-period gait fluctuations within a gait image sequence are repeatedly observed for the same subject, they can be regarded as a useful distinguishing gait feature. We extract phase fluctuations as temporal fluctuations as well as gait fluctuation image and trajectory fluctuations as spatial fluctuations. We combine them with the matching score using the phase-normalized image sequence as additional matching scores in the score-level fusion framework or as quality measures in the score-normalization framework. We evaluated the methods in experiments using large-scale publicly available databases and showed the effectiveness of the proposed methods.

No abstract