Improved gait recognition by gait dynamics normalization

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 28; no. 6; pp. 863 - 876
• Main Authors: Zongyi Liu, Sarkar, S.
• Format: Journal Article
• Language: English
• Published: Los Alamitos, CA IEEE 01.06.2006; IEEE Computer Society; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Applied sciences; Artificial Intelligence; Biometrics; Biometry - methods; Cluster Analysis; Computation; Computer displays; Computer science; control theory; systems; Computer Simulation; Computer vision; Decoding; Diagnosis, Computer-Assisted - methods; Discriminant analysis; Dynamics; Exact sciences and technology; Footwear; Gait; Gait - physiology; Gait recognition; gait shape; Hidden Markov models; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Information Storage and Retrieval - methods; LDA; Legged locomotion; Linear discriminant analysis; Markov Chains; Mathematical models; Models, Biological; Models, Statistical; Pattern Recognition, Automated - methods; Pattern recognition. Digital image processing. Computational geometry; Performance enhancement; Photography - methods; population HMM; Reproducibility of Results; Sensitivity and Specificity; Shape; Studies; Viterbi algorithm; Walking; Biometrics; Discriminant analysis; Gait; Imaging; Form defect; Hidden Markov model; LDA; population HMM; Pattern analysis; Viterbi decoding; Gait recognition; gait shape
• ISSN: 0162-8828; 1939-3539
• DOI: 10.1109/TPAMI.2006.122

Potential sources for gait biometrics can be seen to derive from two aspects: gait shape and gait dynamics. We show that improved gait recognition can be achieved after normalization of dynamics and focusing on the shape information. We normalize for gait dynamics using a generic walking model, as captured by a population hidden Markov model (pHMM) defined for a set of individuals. The states of this pHMM represent gait stances over one gait cycle and the observations are the silhouettes of the corresponding gait stances. For each sequence, we first use Viterbi decoding of the gait dynamics to arrive at one dynamics-normalized, averaged, gait cycle of fixed length. The distance between two sequences is the distance between the two corresponding dynamics-normalized gait cycles, which we quantify by the sum of the distances between the corresponding gait stances. Distances between two silhouettes from the same generic gait stance are computed in the linear discriminant analysis space so as to maximize the discrimination between persons, while minimizing the variations of the same subject under different conditions. The distance computation is constructed so that it is invariant to dilations and erosions of the silhouettes. This helps us handle variations in silhouette shape that can occur with changing imaging conditions. We present results on three different, publicly available, data sets. First, we consider the HumanID gait challenge data set, which is the largest gait benchmarking data set that is available (122 subjects), exercising five different factors, i.e., viewpoint, shoe, surface, carrying condition, and time. We significantly improve the performance across the hard experiments involving surface change and briefcase carrying conditions. Second, we also show improved performance on the UMD gait data set that exercises time variations for 55 subjects. Third, on the CMU Mobo data set, we show results for matching across different walking speeds. It is worth noting that there was no separate training for the UMD and CMU data sets.