Informační systém Repo
BALÁŽIA, Michal and Petr SOJKA. Walker-Independent Features for Gait Recognition from Motion Capture Data. In 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. p. 310-321. ISBN 978-3-319-49054-0. 2016.
Other formats:   BibTeX LaTeX RIS
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
Original language English
Type of outcome Proceedings paper
Field of Study Informatics
Country of publisher Switzerland
Confidentiality degree is not subject to a state or trade secret
Publication form printed version "print"
WWW URL URL
RIV identification code RIV/00216224:14330/16:00090768
Organization Fakulta informatiky – Repository – Repository
ISBN 978-3-319-49054-0
ISSN 0302-9743
UT WoS 000389509300028
Keywords (in Czech) strojové učení; klasifikace; rozpoznávání podle chůze
Keywords in English machine learning; classification; gait recognition
Links MUNI/A/0892/2015, interní kód Repo. MUNI/A/0935/2015, interní kód Repo.
Changed by Changed by: RNDr. Daniel Jakubík, učo 139797. Changed: 3/9/2020 05:10.
Abstract
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.
Displayed: 28/3/2024 22:01