Clothing-invariant gait identification using part-based clothing categorization and adaptive weight control

• Published in: Pattern recognition Vol. 43; no. 6; pp. 2281 - 2291
• Main Authors: Altab Hossain, Md, Makihara, Yasushi, Wang, Junqiu, Yagi, Yasushi
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01.06.2010; Elsevier
• Subjects: Adaptive weight control; Applied sciences; Biometrics; Clothing-invariant; Exact sciences and technology; Gait identification; Information, signal and communications theory; Part-based; Pattern recognition; Signal processing; Telecommunications and information theory; Biometrics; Part-based; Clothing-invariant; Adaptive weight control; Gait identification; Performance evaluation; Clothing; Pattern recognition; Adaptive control; Adaptive method; Discrimination; Human body model; Automatic recognition; Categorization
• ISSN: 0031-3203; 1873-5142
• DOI: 10.1016/j.patcog.2009.12.020

Variations in clothing alter an individual's appearance, making the problem of gait identification much more difficult. If the type of clothing differs between the gallery and a probe, certain parts of the silhouettes are likely to change and the ability to discriminate subjects decreases with respect to these parts. A part-based approach, therefore, has the potential of selecting the appropriate parts. This paper proposes a method for part-based gait identification in the light of substantial clothing variations. We divide the human body into eight sections, including four overlapping ones, since the larger parts have a higher discrimination capability, while the smaller parts are more likely to be unaffected by clothing variations. Furthermore, as there are certain clothes that are common to different parts, we present a categorization for items of clothing that groups similar clothes. Next, we exploit the discrimination capability as a matching weight for each part and control the weights adaptively based on the distribution of distances between the probe and all the galleries. The results of the experiments using our large-scale gait dataset with clothing variations show that the proposed method achieves far better performance than other approaches.