Robust gait recognition via discriminative set matching

• Published in: Journal of visual communication and image representation Vol. 24; no. 4; pp. 439 - 447
• Main Authors: Liu, Nini, Lu, Jiwen, Yang, Gao, Tan, Yap-Peng
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Inc 01.05.2013; Elsevier
• Subjects: Applied sciences; Artificial intelligence; Computer science; control theory; systems; Exact sciences and technology; Gait; Gait recognition; Multiview gait recognition; Pattern recognition. Digital image processing. Computational geometry; Recognition; Representations; Set-to-set matching; Subspace distance; Subspaces; Visual; Set-to-set matching; Subspace distance; Multiview gait recognition; Legged locomotion; Computer vision; Discriminant analysis; Image recognition; Gait; Subspace method; Canonical correlation; Variance; Posture; Multiple view; Walking; Experimental result; Vector space; Efficiency; Distance; Pattern extraction
• ISSN: 1047-3203; 1095-9076
• DOI: 10.1016/j.jvcir.2013.02.002

► We propose a framework for multiview gait recognition across varying views and walking conditions. ► Our approach is computationally inexpensive and suitable for real applications. ► Our method can perform robust even with limited number of training samples of each subject. ► Extensive experimental results are presented to demonstrate the effectiveness of the proposed framework. In this paper, we propose a framework for gait recognition across varying views and walking conditions based on gait sequences collected from multiple viewpoints. Different from most existing view-dependent gait recognition systems, we devise a new Multiview Subspace Representation (MSR) method which considers gait sequences collected from different views of the same subject as a feature set and extracts a linear subspace to describe the feature set. Subspace-based feature representation methods measure the variances among samples, and can handle certain intra-subject variations. To better exploit the discriminative information from these subspaces for recognition, we further propose a marginal canonical correlation analysis (MCCA) method which maximizes the margins of interclass subspaces within a neighborhood. Experimental results on a widely used multiview gait database are presented to demonstrate the effectiveness of the proposed framework.