Identifying Walk Cycles for Human Recognition

D 2012

Identifying Walk Cycles for Human Recognition

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

Basic information

Original name

Identifying Walk Cycles for Human Recognition

Authors

VALČÍK, Jakub (203 Czech Republic, guarantor, belonging to the institution), Jan SEDMIDUBSKÝ (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 7299. Berlin, Proceedings of Pacific Asia Workshop on Intelligence and Security Informatics (PAISI 2012), p. 127-135, 9 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

Malaysia

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

printed version "print"

Impact factor

Impact factor: 0.402 in 2005

RIV identification code

RIV/00216224:14330/12:00057307

Organization unit

Faculty of Informatics

ISBN

978-3-642-30427-9

ISSN

DOI

http://dx.doi.org/10.1007/978-3-642-30428-6_10

Keywords in English

gait recognition; walk cycle identification; time normalization; similarity distance

Abstract

V originále

We concentrate on recognizing persons according to the way they walk. Our approach considers a human movement as a set of trajectories of hips, knees, and feet captured as the person walks. The trajectories are used for the extraction of viewpoint invariant planar signals that express how a distance between a pair of specific points on the human body changes in time. We solely focus on analysis and normalization of extracted signals to simplify their similarity comparison, without presenting any specific gait recognition method. In particular, we propose a novel method for automatic determination of walk cycles within extracted signals and evaluate its importance on a real-life human motion database.

Links

GBP103/12/G084, research and development project

Name: Centrum pro multi-modální interpretaci dat velkého rozsahu

Investor: Czech Science Foundation

VG20122015073, research and development project

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

Investor: Ministry of the Interior of the CR

Citovat

VALČÍK, Jakub, Jan SEDMIDUBSKÝ, Michal BALÁŽIA and Pavel ZEZULA. Identifying Walk Cycles for Human Recognition. In M. Chau, G. Alan Wang, Wei Thoo Yue, Hsinchun Chen. Proceedings of Pacific Asia Workshop on Intelligence and Security Informatics (PAISI 2012). LNCS 7299. Berlin: Springer-Verlag, 2012, p. 127-135. ISBN 978-3-642-30427-9. Available from: https://dx.doi.org/10.1007/978-3-642-30428-6_10.

@inproceedings{976628,
   author = {Valčík, Jakub and Sedmidubský, Jan and Balážia, Michal and Zezula, Pavel},
   address = {Berlin},
   booktitle = {Proceedings of Pacific Asia Workshop on Intelligence and Security Informatics (PAISI 2012)},
   doi = {http://dx.doi.org/10.1007/978-3-642-30428-6_10},
   edition = {LNCS 7299},
   editor = {M. Chau, G. Alan Wang, Wei Thoo Yue, Hsinchun Chen},
   keywords = {gait recognition; walk cycle identification; time normalization; similarity distance},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Berlin},
   isbn = {978-3-642-30427-9},
   pages = {127-135},
   publisher = {Springer-Verlag},
   title = {Identifying Walk Cycles for Human Recognition},
   year = {2012}
}

TY  - JOUR
ID  - 976628
AU  - Valčík, Jakub - Sedmidubský, Jan - Balážia, Michal - Zezula, Pavel
PY  - 2012
TI  - Identifying Walk Cycles for Human Recognition
PB  - Springer-Verlag
CY  - Berlin
SN  - 9783642304279
KW  - gait recognition
KW  - walk cycle identification
KW  - time normalization
KW  - similarity distance
N2  - We concentrate on recognizing persons according to the way they walk. Our approach considers a human movement as a set of trajectories of hips, knees, and feet captured as the person walks. The trajectories are used for the extraction of viewpoint invariant planar signals that express how a distance between a pair of specific points on the human body changes in time. We solely focus on analysis and normalization of extracted signals to simplify their similarity comparison, without presenting any specific gait recognition method. In particular, we propose a novel method for automatic determination of walk cycles within extracted signals and evaluate its importance on a real-life human motion database.
ER  -

VALČÍK, Jakub, Jan SEDMIDUBSKÝ, Michal BALÁŽIA and Pavel ZEZULA. Identifying Walk Cycles for Human Recognition. In M. Chau, G. Alan Wang, Wei Thoo Yue, Hsinchun Chen. \textit{Proceedings of Pacific Asia Workshop on Intelligence and Security Informatics (PAISI 2012)}. LNCS 7299. Berlin: Springer-Verlag, 2012, p.~127-135. ISBN~978-3-642-30427-9. Available from: https://dx.doi.org/10.1007/978-3-642-30428-6\_{}10.

Detailed Information on Publication Record