Identification of people walking along curved trajectories

Yumi Iwashita, Koichi Ogawara, Ryo Kurazume

Research output: Contribution to journalArticle

25 Citations (Scopus)

Abstract

Conventional methods of gait analysis for person identification use features extracted from a sequence of camera images taken during one or more gait cycles. The walking direction is implicitly assumed not to change. However, with the exception of very particular cases, such as walking on a circle centered on the camera, or along a line passing through the camera, there is always some degree of orientation change, most pronounced when the person is closer to the camera. This change in the angle between the velocity vector and the position vector in respect to the camera causes a decrease in performance for conventional methods. To address this issue we propose in this paper a new method, which provides improved identification in this context of orientation change. The proposed method uses a 4D gait database consisting of multiple 3D shape models of walking people and adaptive virtual image synthesis with high accuracy. Each frame, for the duration of a gait cycle, is used to estimate the walking direction of the subject, and a virtual image corresponding to the estimated direction is synthesized from the 4D gait database. The identification uses affine moment invariants as gait features. The efficiency of the proposed method is demonstrated through experiments using a database that includes 42 subjects.

Original languageEnglish
Pages (from-to)60-69
Number of pages10
JournalPattern Recognition Letters
Volume48
DOIs
Publication statusPublished - Oct 15 2014

Fingerprint

Cameras
Trajectories
Gait analysis
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Identification of people walking along curved trajectories. / Iwashita, Yumi; Ogawara, Koichi; Kurazume, Ryo.

In: Pattern Recognition Letters, Vol. 48, 15.10.2014, p. 60-69.

Research output: Contribution to journalArticle

Iwashita, Yumi ; Ogawara, Koichi ; Kurazume, Ryo. / Identification of people walking along curved trajectories. In: Pattern Recognition Letters. 2014 ; Vol. 48. pp. 60-69.
@article{d304b5d441aa4bb1aee4a186895b3c67,
title = "Identification of people walking along curved trajectories",
abstract = "Conventional methods of gait analysis for person identification use features extracted from a sequence of camera images taken during one or more gait cycles. The walking direction is implicitly assumed not to change. However, with the exception of very particular cases, such as walking on a circle centered on the camera, or along a line passing through the camera, there is always some degree of orientation change, most pronounced when the person is closer to the camera. This change in the angle between the velocity vector and the position vector in respect to the camera causes a decrease in performance for conventional methods. To address this issue we propose in this paper a new method, which provides improved identification in this context of orientation change. The proposed method uses a 4D gait database consisting of multiple 3D shape models of walking people and adaptive virtual image synthesis with high accuracy. Each frame, for the duration of a gait cycle, is used to estimate the walking direction of the subject, and a virtual image corresponding to the estimated direction is synthesized from the 4D gait database. The identification uses affine moment invariants as gait features. The efficiency of the proposed method is demonstrated through experiments using a database that includes 42 subjects.",
author = "Yumi Iwashita and Koichi Ogawara and Ryo Kurazume",
year = "2014",
month = "10",
day = "15",
doi = "10.1016/j.patrec.2014.04.004",
language = "English",
volume = "48",
pages = "60--69",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",

}

TY - JOUR

T1 - Identification of people walking along curved trajectories

AU - Iwashita, Yumi

AU - Ogawara, Koichi

AU - Kurazume, Ryo

PY - 2014/10/15

Y1 - 2014/10/15

N2 - Conventional methods of gait analysis for person identification use features extracted from a sequence of camera images taken during one or more gait cycles. The walking direction is implicitly assumed not to change. However, with the exception of very particular cases, such as walking on a circle centered on the camera, or along a line passing through the camera, there is always some degree of orientation change, most pronounced when the person is closer to the camera. This change in the angle between the velocity vector and the position vector in respect to the camera causes a decrease in performance for conventional methods. To address this issue we propose in this paper a new method, which provides improved identification in this context of orientation change. The proposed method uses a 4D gait database consisting of multiple 3D shape models of walking people and adaptive virtual image synthesis with high accuracy. Each frame, for the duration of a gait cycle, is used to estimate the walking direction of the subject, and a virtual image corresponding to the estimated direction is synthesized from the 4D gait database. The identification uses affine moment invariants as gait features. The efficiency of the proposed method is demonstrated through experiments using a database that includes 42 subjects.

AB - Conventional methods of gait analysis for person identification use features extracted from a sequence of camera images taken during one or more gait cycles. The walking direction is implicitly assumed not to change. However, with the exception of very particular cases, such as walking on a circle centered on the camera, or along a line passing through the camera, there is always some degree of orientation change, most pronounced when the person is closer to the camera. This change in the angle between the velocity vector and the position vector in respect to the camera causes a decrease in performance for conventional methods. To address this issue we propose in this paper a new method, which provides improved identification in this context of orientation change. The proposed method uses a 4D gait database consisting of multiple 3D shape models of walking people and adaptive virtual image synthesis with high accuracy. Each frame, for the duration of a gait cycle, is used to estimate the walking direction of the subject, and a virtual image corresponding to the estimated direction is synthesized from the 4D gait database. The identification uses affine moment invariants as gait features. The efficiency of the proposed method is demonstrated through experiments using a database that includes 42 subjects.

UR - http://www.scopus.com/inward/record.url?scp=84906778800&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906778800&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2014.04.004

DO - 10.1016/j.patrec.2014.04.004

M3 - Article

AN - SCOPUS:84906778800

VL - 48

SP - 60

EP - 69

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

ER -