View-independent person identification from human gait

Zonghua Zhang; Nikolaus F. Troje

doi:10.1016/j.neucom.2005.06.002

View-independent person identification from human gait

Zonghua Zhang, Nikolaus F. Troje

School of Engineering & Physical Sciences

Research output: Contribution to journal › Article › peer-review

60 Citations (Scopus)

Abstract

Based on a three-dimensional (3D) linear model and the Bayesian rule, a method is explored to identify human walkers from two-dimensional (2D) motion sequences taken from different viewpoints. Principal component analysis constructs the 3D linear model from a set of Fourier represented examples. The sets of coefficients derived from projecting 2D motion sequences onto the 3D model by means of a maximum a posterior estimate is used as a signature of a walker. Simulating an identification experiment on a set of walking data we show that these signatures show invariance across viewpoints and can be used for viewpoint-independent person identification. © 2005 Elsevier B.V. All rights reserved.

Original language	English
Pages (from-to)	250-256
Number of pages	7
Journal	Neurocomputing
Volume	69
Issue number	1-3
DOIs	https://doi.org/10.1016/j.neucom.2005.06.002
Publication status	Published - Dec 2005

Keywords

Linear model
Principal component analysis (PCA)
View-independent gait identification

Access to Document

10.1016/j.neucom.2005.06.002

Cite this

@article{17e378e0724441d9a5c2d7814a44f442,

title = "View-independent person identification from human gait",

abstract = "Based on a three-dimensional (3D) linear model and the Bayesian rule, a method is explored to identify human walkers from two-dimensional (2D) motion sequences taken from different viewpoints. Principal component analysis constructs the 3D linear model from a set of Fourier represented examples. The sets of coefficients derived from projecting 2D motion sequences onto the 3D model by means of a maximum a posterior estimate is used as a signature of a walker. Simulating an identification experiment on a set of walking data we show that these signatures show invariance across viewpoints and can be used for viewpoint-independent person identification. {\textcopyright} 2005 Elsevier B.V. All rights reserved.",

keywords = "Linear model, Principal component analysis (PCA), View-independent gait identification",

author = "Zonghua Zhang and Troje, {Nikolaus F.}",

year = "2005",

month = dec,

doi = "10.1016/j.neucom.2005.06.002",

language = "English",

volume = "69",

pages = "250--256",

journal = "Neurocomputing",

issn = "0925-2312",

publisher = "Elsevier",

number = "1-3",

}

TY - JOUR

T1 - View-independent person identification from human gait

AU - Zhang, Zonghua

AU - Troje, Nikolaus F.

PY - 2005/12

Y1 - 2005/12

N2 - Based on a three-dimensional (3D) linear model and the Bayesian rule, a method is explored to identify human walkers from two-dimensional (2D) motion sequences taken from different viewpoints. Principal component analysis constructs the 3D linear model from a set of Fourier represented examples. The sets of coefficients derived from projecting 2D motion sequences onto the 3D model by means of a maximum a posterior estimate is used as a signature of a walker. Simulating an identification experiment on a set of walking data we show that these signatures show invariance across viewpoints and can be used for viewpoint-independent person identification. © 2005 Elsevier B.V. All rights reserved.

AB - Based on a three-dimensional (3D) linear model and the Bayesian rule, a method is explored to identify human walkers from two-dimensional (2D) motion sequences taken from different viewpoints. Principal component analysis constructs the 3D linear model from a set of Fourier represented examples. The sets of coefficients derived from projecting 2D motion sequences onto the 3D model by means of a maximum a posterior estimate is used as a signature of a walker. Simulating an identification experiment on a set of walking data we show that these signatures show invariance across viewpoints and can be used for viewpoint-independent person identification. © 2005 Elsevier B.V. All rights reserved.

KW - Linear model

KW - Principal component analysis (PCA)

KW - View-independent gait identification

UR - http://www.scopus.com/inward/record.url?scp=27844507504&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2005.06.002

DO - 10.1016/j.neucom.2005.06.002

M3 - Article

SN - 0925-2312

VL - 69

SP - 250

EP - 256

JO - Neurocomputing

JF - Neurocomputing

IS - 1-3

ER -

View-independent person identification from human gait

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this