Gait Recognition from Motion Capture Data

J 2018

Gait Recognition from Motion Capture Data

BALÁŽIA, Michal a Petr SOJKA

Základní údaje

Originální název

Gait Recognition from Motion Capture Data

Autoři

BALÁŽIA, Michal (703 Slovensko, garant, domácí) a Petr SOJKA (203 Česká republika, domácí)

Vydání

ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), special issue on Representation, Analysis and Recognition of 3D Humans, New York, USA, ACM, 2018, 1551-6857

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Odkazy

DOI software, developed framework and database for reproducibility

Impakt faktor

Impact factor: 2.870

Kód RIV

RIV/00216224:14330/18:00102051

Organizační jednotka

Fakulta informatiky

DOI

http://dx.doi.org/10.1145/3152124

UT WoS

000433517100008

Klíčová slova česky

rozpoznávání podle chůze

Klíčová slova anglicky

gait recognition

Štítky

best2, gait recognition

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 30. 9. 2020 23:11, doc. RNDr. Petr Sojka, Ph.D.

Anotace

V originále

Gait recognition from motion capture data, as a pattern classification discipline, can be improved by the use of machine learning. This paper contributes to the state-of-the-art with a statistical approach for extracting robust gait features directly from raw data by a modification of Linear Discriminant Analysis with Maximum Margin Criterion. Experiments on the CMU MoCap database show that the suggested method outperforms thirteen relevant methods based on geometric features and a method to learn the features by a combination of Principal Component Analysis and Linear Discriminant Analysis. The methods are evaluated in terms of the distribution of biometric templates in respective feature spaces expressed in a number of class separability coefficients and classification metrics. Results also indicate a high portability of learned features, that means, we can learn what aspects of walk people generally differ in and extract those as general gait features. Recognizing people without needing group-specific features is convenient as particular people might not always provide annotated learning data. As a contribution to reproducible research, our evaluation framework and database have been made publicly available. This research makes motion capture technology directly applicable for human recognition.

Návaznosti

MUNI/A/0992/2016, interní kód MU

Název: Zapojení studentů Fakulty informatiky do mezinárodní vědecké komunity (Akronym: SKOMU)

Investor: Masarykova univerzita, Zapojení studentů Fakulty informatiky do mezinárodní vědecké komunity, DO R. 2020_Kategorie A - Specifický výzkum - Studentské výzkumné projekty

MUNI/A/0997/2016, interní kód MU

Název: Aplikovaný výzkum na FI: vyhledávacích systémy, bezpečnost, vizualizace dat a virtuální realita.

Investor: Masarykova univerzita, Aplikovaný výzkum na FI: vyhledávacích systémy, bezpečnost, vizualizace dat a virtuální realita., DO R. 2020_Kategorie A - Specifický výzkum - Studentské výzkumné projekty

Přiložené soubory

tomm22final.pdf

Požádat o autorskou verzi souboru

Citovat

BALÁŽIA, Michal a Petr SOJKA. Gait Recognition from Motion Capture Data. ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), special issue on Representation, Analysis and Recognition of 3D Humans. New York, USA: ACM, 2018, roč. 14, 1s, s. 1-18. ISSN 1551-6857. Dostupné z: https://dx.doi.org/10.1145/3152124.

@article{1390685,
   author = {Balážia, Michal and Sojka, Petr},
   article_location = {New York, USA},
   article_number = {1s},
   doi = {http://dx.doi.org/10.1145/3152124},
   keywords = {gait recognition},
   language = {eng},
   issn = {1551-6857},
   journal = {ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), special issue on Representation, Analysis and Recognition of 3D Humans},
   note = {ACM TOMM},
   title = {Gait Recognition from Motion Capture Data},
   url = {https://doi.org/10.1145/3152124},
   volume = {14},
   year = {2018}
}

TY  - JOUR
ID  - 1390685
AU  - Balážia, Michal - Sojka, Petr
PY  - 2018
TI  - Gait Recognition from Motion Capture Data
JF  - ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), special issue on Representation, Analysis and Recognition of 3D Humans
VL  - 14
IS  - 1s
SP  - 1-18
EP  - 1-18
PB  - ACM
SN  - 15516857
N1  - ACM TOMM
KW  - gait recognition
UR  - https://doi.org/10.1145/3152124
L2  - https://doi.org/10.1145/3152124
N2  - Gait recognition from motion capture data, as a pattern classification discipline, can be improved by the use of machine learning. This paper contributes to the state-of-the-art with a statistical approach for extracting robust gait features directly from raw data by a modification of Linear Discriminant Analysis with Maximum Margin Criterion. Experiments on the CMU MoCap database show that the suggested method outperforms thirteen relevant methods based on geometric features and a method to learn the features by a combination of Principal Component Analysis and Linear Discriminant Analysis. The methods are evaluated in terms of the distribution of biometric templates in respective feature spaces expressed in a number of class separability coefficients and classification metrics. Results also indicate a high portability of learned features, that means, we can learn what aspects of walk people generally differ in and extract those as general gait features. Recognizing people without needing group-specific features is convenient as particular people might not always provide annotated learning data. As a contribution to reproducible research, our evaluation framework and database have been made publicly available. This research makes motion capture technology directly applicable for human recognition.
ER  -

BALÁŽIA, Michal a Petr SOJKA. Gait Recognition from Motion Capture Data. \textit{ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), special issue on Representation, Analysis and Recognition of 3D Humans}. New York, USA: ACM, 2018, roč.~14, 1s, s.~1-18. ISSN~1551-6857. Dostupné z: https://dx.doi.org/10.1145/3152124.

Podrobný výpis o publikaci