Walker-Independent Features for Gait Recognition from Motion
Capture Data

D 2016

Walker-Independent Features for Gait Recognition from Motion Capture Data

BALÁŽIA, Michal and Petr SOJKA

Basic information

Original name

Walker-Independent Features for Gait Recognition from Motion Capture Data

Authors

BALÁŽIA, Michal (703 Slovakia, guarantor, belonging to the institution) and Petr SOJKA (203 Czech Republic, belonging to the institution)

Edition

LNCS 10029. Switzerland, Proceedings of the joint IAPR International Workshops on Structural and Syntactic Pattern Recognition (SSPR 2016) and Statistical Techniques in Pattern Recognition (SPR 2016), p. 310-321, 12 pp. 2016

Publisher

Springer International Publishing AG

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Switzerland

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

printed version "print"

References:

DOI conference web

Impact factor

Impact factor: 0.402 in 2005

RIV identification code

RIV/00216224:14330/16:00090768

Organization unit

Faculty of Informatics

ISBN

978-3-319-49054-0

ISSN

DOI

http://dx.doi.org/10.1007/978-3-319-49055-7_28

UT WoS

000389509300028

Keywords (in Czech)

strojové učení; klasifikace; rozpoznávání podle chůze

Keywords in English

machine learning; classification; gait recognition

Abstract

V originále

MoCap-based human identification, as a pattern recognition discipline, can be optimized using a machine learning approach. Yet in some applications such as video surveillance new identities can appear on the fly and labeled data for all encountered people may not always be available. This work introduces the concept of learning walker-independent gait features directly from raw joint coordinates by a modification of the Fisher’s Linear Discriminant Analysis with Maximum Margin Criterion. Our new approach shows not only that these features can discriminate different people than who they are learned on, but also that the number of learning identities can be much smaller than the number of walkers encountered in the real operation.

Links

MUNI/A/0892/2015, interní kód MU

Name: Výzkum v aplikované informatice na FI MU (Acronym: VAIFIMU)

Investor: Masaryk University, Category A

MUNI/A/0935/2015, interní kód MU

Name: Zapojení studentů Fakulty informatiky do mezinárodní vědecké komunity (Acronym: SKOMU)

Investor: Masaryk University, Category A

Files attached

sspr10arxiv.pdf

Find similar documents

Citovat

BALÁŽIA, Michal and Petr SOJKA. Walker-Independent Features for Gait Recognition from Motion Capture Data. In Antonio Robles-Kelly, Marco Loog, Battista Biggio, Francisco Escolano, Richard Wilson. Proceedings of the joint IAPR International Workshops on Structural and Syntactic Pattern Recognition (SSPR 2016) and Statistical Techniques in Pattern Recognition (SPR 2016). LNCS 10029. Switzerland: Springer International Publishing AG, 2016, p. 310-321. ISBN 978-3-319-49054-0. Available from: https://dx.doi.org/10.1007/978-3-319-49055-7_28.

@inproceedings{1353537,
   author = {Balážia, Michal and Sojka, Petr},
   address = {Switzerland},
   booktitle = {Proceedings of the joint IAPR International Workshops on Structural and Syntactic Pattern Recognition (SSPR 2016) and Statistical Techniques in Pattern Recognition (SPR 2016)},
   doi = {http://dx.doi.org/10.1007/978-3-319-49055-7_28},
   edition = {LNCS 10029},
   editor = {Antonio Robles-Kelly, Marco Loog, Battista Biggio, Francisco Escolano, Richard Wilson},
   keywords = {machine learning; classification; gait recognition},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Switzerland},
   isbn = {978-3-319-49054-0},
   pages = {310-321},
   publisher = {Springer International Publishing AG},
   title = {Walker-Independent Features for Gait Recognition from Motion Capture Data},
   url = {https://doi.org/10.1007/978-3-319-49055-7_28},
   year = {2016}
}

TY  - JOUR
ID  - 1353537
AU  - Balážia, Michal - Sojka, Petr
PY  - 2016
TI  - Walker-Independent Features for Gait Recognition from Motion Capture Data
PB  - Springer International Publishing AG
CY  - Switzerland
SN  - 9783319490540
KW  - machine learning
KW  - classification
KW  - gait recognition
UR  - https://doi.org/10.1007/978-3-319-49055-7_28
L2  - https://doi.org/10.1007/978-3-319-49055-7_28
N2  - MoCap-based human identification, as a pattern recognition discipline, can be optimized using a machine learning approach. Yet in some applications such as video surveillance new identities can appear on the fly and labeled data for all encountered people may not always be available. This work introduces the concept of learning walker-independent gait features directly from raw joint coordinates by a modification of the Fisher’s Linear Discriminant Analysis with Maximum Margin Criterion. Our new approach shows not only that these features can discriminate different people than who they are learned on, but also that the number of learning identities can be much smaller than the number of walkers encountered in the real operation.
ER  -

BALÁŽIA, Michal and Petr SOJKA. Walker-Independent Features for Gait Recognition from Motion Capture Data. In Antonio Robles-Kelly, Marco Loog, Battista Biggio, Francisco Escolano, Richard Wilson. \textit{Proceedings of the joint IAPR International Workshops on Structural and Syntactic Pattern Recognition (SSPR 2016) and Statistical Techniques in Pattern Recognition (SPR 2016)}. LNCS 10029. Switzerland: Springer International Publishing AG, 2016, p.~310-321. ISBN~978-3-319-49054-0. Available from: https://dx.doi.org/10.1007/978-3-319-49055-7\_{}28.

Detailed Information on Publication Record