Gait Recognition Based on Normalized Walk Cycles

D 2012

Gait Recognition Based on Normalized Walk Cycles

SEDMIDUBSKÝ, Jan, Jakub VALČÍK, Michal BALÁŽIA and Pavel ZEZULA

Basic information

Original name

Gait Recognition Based on Normalized Walk Cycles

Name in Czech

Rozpoznávání chůze na základě normalizovaných kroků

Authors

SEDMIDUBSKÝ, Jan (203 Czech Republic, guarantor, belonging to the institution), Jakub VALČÍK (203 Czech Republic, belonging to the institution), Michal BALÁŽIA (703 Slovakia, belonging to the institution) and Pavel ZEZULA (203 Czech Republic, belonging to the institution)

Edition

LNCS 7432. Heidelberg, Proceedings of 8th International Symposium on Visual Computing (ISVC 2012), p. 11-20, 10 pp. 2012

Publisher

Springer-Verlag

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Germany

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

printed version "print"

References:

conference web

Impact factor

Impact factor: 0.402 in 2005

RIV identification code

RIV/00216224:14330/12:00057394

Organization unit

Faculty of Informatics

ISBN

978-3-642-33190-9

ISSN

DOI

http://dx.doi.org/10.1007/978-3-642-33191-6_2

UT WoS

000363265800002

Keywords in English

gait recognition; gait pattern; similarity of gait patterns

Abstract

V originále

We focus on recognizing persons according to the way they walk. Our approach considers a human movement as a set of trajectories formed by specific anatomical landmarks, such as hips, feet, shoulders, or hands. The trajectories are used for the extraction of distance-time dependency signals that express how a distance between a pair of specific landmarks on the human body changes in time as the person walks. The collection of such signals characterizes a gait pattern of person's walk. To determine the similarity of gait patterns, we propose several functions that compare various combinations of extracted signals. The gait patterns are compared on the level of individual walk cycles in order to increase the recognition effectiveness. The results evaluated on a 3D database of walking humans achieved the recognition rate up to 96%.

Links

GAP103/10/0886, research and development project

Name: Vizuální vyhledávání obrázků na Webu (Acronym: VisualWeb)

Investor: Czech Science Foundation, Content-based Image Retrieval on the Web Scale

VG20122015073, research and development project

Name: Efektivní vyhledávání v rozsáhlých biometrických datech (Acronym: EFBIO)

Investor: Ministry of the Interior of the CR

Citovat

SEDMIDUBSKÝ, Jan, Jakub VALČÍK, Michal BALÁŽIA and Pavel ZEZULA. Gait Recognition Based on Normalized Walk Cycles. In George Bebis, Richard Boyle, Bahram Parvin, Darko Koracin, Charless Fowlkes, Sen Wang, Min-Hyung Choi, Stephan Mantler, Jürgen Schulze, Daniel Acevedo, Klaus Mueller, Michael Papka. Proceedings of 8th International Symposium on Visual Computing (ISVC 2012). LNCS 7432. Heidelberg: Springer-Verlag, 2012, p. 11-20. ISBN 978-3-642-33190-9. Available from: https://dx.doi.org/10.1007/978-3-642-33191-6_2.

@inproceedings{982503,
   author = {Sedmidubský, Jan and Valčík, Jakub and Balážia, Michal and Zezula, Pavel},
   address = {Heidelberg},
   booktitle = {Proceedings of 8th International Symposium on Visual Computing (ISVC 2012)},
   doi = {http://dx.doi.org/10.1007/978-3-642-33191-6_2},
   edition = {LNCS 7432},
   editor = {George Bebis, Richard Boyle, Bahram Parvin, Darko Koracin, Charless Fowlkes, Sen Wang, Min-Hyung Choi, Stephan Mantler, Jürgen Schulze, Daniel Acevedo, Klaus Mueller, Michael Papka},
   keywords = {gait recognition; gait pattern; similarity of gait patterns},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Heidelberg},
   isbn = {978-3-642-33190-9},
   pages = {11-20},
   publisher = {Springer-Verlag},
   title = {Gait Recognition Based on Normalized Walk Cycles},
   url = {http://www.isvc.net/12/},
   year = {2012}
}

TY  - JOUR
ID  - 982503
AU  - Sedmidubský, Jan - Valčík, Jakub - Balážia, Michal - Zezula, Pavel
PY  - 2012
TI  - Gait Recognition Based on Normalized Walk Cycles
PB  - Springer-Verlag
CY  - Heidelberg
SN  - 9783642331909
KW  - gait recognition
KW  - gait pattern
KW  - similarity of gait patterns
UR  - http://www.isvc.net/12/
L2  - http://www.isvc.net/12/
N2  - We focus on recognizing persons according to the way they walk. Our approach considers a human movement as a set of trajectories formed by specific anatomical landmarks, such as hips, feet, shoulders, or hands. The trajectories are used for the extraction of distance-time dependency signals that express how a distance between a pair of specific landmarks on the human body changes in time as the person walks. The collection of such signals characterizes a gait pattern of person's walk. To determine the similarity of gait patterns, we propose several functions that compare various combinations of extracted signals. The gait patterns are compared on the level of individual walk cycles in order to increase the recognition effectiveness. The results evaluated on a 3D database of walking humans achieved the recognition rate up to 96%.
ER  -

SEDMIDUBSKÝ, Jan, Jakub VALČÍK, Michal BALÁŽIA and Pavel ZEZULA. Gait Recognition Based on Normalized Walk Cycles. In George Bebis, Richard Boyle, Bahram Parvin, Darko Koracin, Charless Fowlkes, Sen Wang, Min-Hyung Choi, Stephan Mantler, Jürgen Schulze, Daniel Acevedo, Klaus Mueller, Michael Papka. \textit{Proceedings of 8th International Symposium on Visual Computing (ISVC 2012)}. LNCS 7432. Heidelberg: Springer-Verlag, 2012, p.~11-20. ISBN~978-3-642-33190-9. Available from: https://dx.doi.org/10.1007/978-3-642-33191-6\_{}2.

Detailed Information on Publication Record