Human identification based on gait analysis

Sungjun Hong, Heesung Lee, Imran Fareed Nizami, Sung Je An, Euntai Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

In this paper, we have proposed a new representation for human gait recognition which is called as mass vector. The mass vector along a given row is defined as the number of pixels with a nonzero value in a given row of the binarized silhouette of a walking person. Sequences of temporally ordered mass vector are used to represent a gait of an individual. Besides, different gait features are extracted from the mass vector such as the down-sampled mass vectors and the principal components of mass vectors. We use the dynamic time-warping (DTW) approach for matching so that non-linear time normalization may be used to deal with the naturally-occurring changes in walking speed. Experimental results show that mass vector has a higher discriminative power than previous works for gait recognition.

Original languageEnglish
Title of host publicationICCAS 2007 - International Conference on Control, Automation and Systems
Pages2234-2237
Number of pages4
DOIs
Publication statusPublished - 2007 Dec 1
EventInternational Conference on Control, Automation and Systems, ICCAS 2007 - Seoul, Korea, Republic of
Duration: 2007 Oct 172007 Oct 20

Publication series

NameICCAS 2007 - International Conference on Control, Automation and Systems

Other

OtherInternational Conference on Control, Automation and Systems, ICCAS 2007
CountryKorea, Republic of
CitySeoul
Period07/10/1707/10/20

Fingerprint

Gait analysis
Pixels

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Hong, S., Lee, H., Nizami, I. F., An, S. J., & Kim, E. (2007). Human identification based on gait analysis. In ICCAS 2007 - International Conference on Control, Automation and Systems (pp. 2234-2237). [4406714] (ICCAS 2007 - International Conference on Control, Automation and Systems). https://doi.org/10.1109/ICCAS.2007.4406714
Hong, Sungjun ; Lee, Heesung ; Nizami, Imran Fareed ; An, Sung Je ; Kim, Euntai. / Human identification based on gait analysis. ICCAS 2007 - International Conference on Control, Automation and Systems. 2007. pp. 2234-2237 (ICCAS 2007 - International Conference on Control, Automation and Systems).
@inproceedings{614ff3b2fbda49e8abc3047677c41749,
title = "Human identification based on gait analysis",
abstract = "In this paper, we have proposed a new representation for human gait recognition which is called as mass vector. The mass vector along a given row is defined as the number of pixels with a nonzero value in a given row of the binarized silhouette of a walking person. Sequences of temporally ordered mass vector are used to represent a gait of an individual. Besides, different gait features are extracted from the mass vector such as the down-sampled mass vectors and the principal components of mass vectors. We use the dynamic time-warping (DTW) approach for matching so that non-linear time normalization may be used to deal with the naturally-occurring changes in walking speed. Experimental results show that mass vector has a higher discriminative power than previous works for gait recognition.",
author = "Sungjun Hong and Heesung Lee and Nizami, {Imran Fareed} and An, {Sung Je} and Euntai Kim",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/ICCAS.2007.4406714",
language = "English",
isbn = "8995003871",
series = "ICCAS 2007 - International Conference on Control, Automation and Systems",
pages = "2234--2237",
booktitle = "ICCAS 2007 - International Conference on Control, Automation and Systems",

}

Hong, S, Lee, H, Nizami, IF, An, SJ & Kim, E 2007, Human identification based on gait analysis. in ICCAS 2007 - International Conference on Control, Automation and Systems., 4406714, ICCAS 2007 - International Conference on Control, Automation and Systems, pp. 2234-2237, International Conference on Control, Automation and Systems, ICCAS 2007, Seoul, Korea, Republic of, 07/10/17. https://doi.org/10.1109/ICCAS.2007.4406714

Human identification based on gait analysis. / Hong, Sungjun; Lee, Heesung; Nizami, Imran Fareed; An, Sung Je; Kim, Euntai.

ICCAS 2007 - International Conference on Control, Automation and Systems. 2007. p. 2234-2237 4406714 (ICCAS 2007 - International Conference on Control, Automation and Systems).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Human identification based on gait analysis

AU - Hong, Sungjun

AU - Lee, Heesung

AU - Nizami, Imran Fareed

AU - An, Sung Je

AU - Kim, Euntai

PY - 2007/12/1

Y1 - 2007/12/1

N2 - In this paper, we have proposed a new representation for human gait recognition which is called as mass vector. The mass vector along a given row is defined as the number of pixels with a nonzero value in a given row of the binarized silhouette of a walking person. Sequences of temporally ordered mass vector are used to represent a gait of an individual. Besides, different gait features are extracted from the mass vector such as the down-sampled mass vectors and the principal components of mass vectors. We use the dynamic time-warping (DTW) approach for matching so that non-linear time normalization may be used to deal with the naturally-occurring changes in walking speed. Experimental results show that mass vector has a higher discriminative power than previous works for gait recognition.

AB - In this paper, we have proposed a new representation for human gait recognition which is called as mass vector. The mass vector along a given row is defined as the number of pixels with a nonzero value in a given row of the binarized silhouette of a walking person. Sequences of temporally ordered mass vector are used to represent a gait of an individual. Besides, different gait features are extracted from the mass vector such as the down-sampled mass vectors and the principal components of mass vectors. We use the dynamic time-warping (DTW) approach for matching so that non-linear time normalization may be used to deal with the naturally-occurring changes in walking speed. Experimental results show that mass vector has a higher discriminative power than previous works for gait recognition.

UR - http://www.scopus.com/inward/record.url?scp=48349143999&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48349143999&partnerID=8YFLogxK

U2 - 10.1109/ICCAS.2007.4406714

DO - 10.1109/ICCAS.2007.4406714

M3 - Conference contribution

AN - SCOPUS:48349143999

SN - 8995003871

SN - 9788995003879

T3 - ICCAS 2007 - International Conference on Control, Automation and Systems

SP - 2234

EP - 2237

BT - ICCAS 2007 - International Conference on Control, Automation and Systems

ER -

Hong S, Lee H, Nizami IF, An SJ, Kim E. Human identification based on gait analysis. In ICCAS 2007 - International Conference on Control, Automation and Systems. 2007. p. 2234-2237. 4406714. (ICCAS 2007 - International Conference on Control, Automation and Systems). https://doi.org/10.1109/ICCAS.2007.4406714