You Are How You Walk: Uncooperative MoCap Gait Identification
for Video Surveillance with Incomplete and Noisy Data

D 2017

You Are How You Walk: Uncooperative MoCap Gait Identification for Video Surveillance with Incomplete and Noisy Data

BALÁŽIA, Michal a Petr SOJKA

Základní údaje

Originální název

You Are How You Walk: Uncooperative MoCap Gait Identification for Video Surveillance with Incomplete and Noisy Data

Autoři

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

Vydání

USA, Proceedings of the 3rd IEEE/IAPR International Joint Conference on Biometrics (IJCB 2017), od s. 208-215, 8 s. 2017

Nakladatel

IEEE

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Odkazy

IEEE Xplore DL conference web

Kód RIV

RIV/00216224:14330/17:00097675

Organizační jednotka

Fakulta informatiky

ISBN

978-1-5386-1124-1

DOI

http://dx.doi.org/10.1109/BTAS.2017.8272700

UT WoS

000426973200026

Klíčová slova česky

rozpoznávání podle chůze

Klíčová slova anglicky

gait recognition

Štítky

best1, IJCB

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 18. 5. 2018 12:03, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

This work offers a design of a video surveillance system based on a soft biometric -- gait identification from MoCap data. The main focus is on two substantial issues of the video surveillance scenario: (1) the walkers do not cooperate in providing learning data to establish their identities and (2) the data are often noisy or incomplete. We show that only a few examples of human gait cycles are required to learn a projection of raw MoCap data onto a low-dimensional sub-space where the identities are well separable. Latent features learned by Maximum Margin Criterion (MMC) method discriminate better than any collection of geometric features. The MMC method is also highly robust to noisy data and works properly even with only a fraction of joints tracked. The overall workflow of the design is directly applicable for a day-to-day operation based on the available MoCap technology and algorithms for gait analysis. In the concept we introduce, a walker's identity is represented by a cluster of gait data collected at their incidents within the surveillance system: They are how they walk.

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

ijcb61arxiv.pdf

Vyhledat podobné dokumenty

Citovat

BALÁŽIA, Michal a Petr SOJKA. You Are How You Walk: Uncooperative MoCap Gait Identification for Video Surveillance with Incomplete and Noisy Data. Online. In Ross Beveridge, Liang Wang, Mark Nixon. Proceedings of the 3rd IEEE/IAPR International Joint Conference on Biometrics (IJCB 2017). USA: IEEE, 2017, s. 208-215. ISBN 978-1-5386-1124-1. Dostupné z: https://dx.doi.org/10.1109/BTAS.2017.8272700.

@inproceedings{1390687,
   author = {Balážia, Michal and Sojka, Petr},
   address = {USA},
   booktitle = {Proceedings of the 3rd IEEE/IAPR International Joint Conference on Biometrics (IJCB 2017)},
   doi = {http://dx.doi.org/10.1109/BTAS.2017.8272700},
   editor = {Ross Beveridge, Liang Wang, Mark Nixon},
   keywords = {gait recognition},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {USA},
   isbn = {978-1-5386-1124-1},
   pages = {208-215},
   publisher = {IEEE},
   title = {You Are How You Walk: Uncooperative MoCap Gait Identification for Video Surveillance with Incomplete and Noisy Data},
   url = {http://ieeexplore.ieee.org/document/8272700/},
   year = {2017}
}

TY  - JOUR
ID  - 1390687
AU  - Balážia, Michal - Sojka, Petr
PY  - 2017
TI  - You Are How You Walk: Uncooperative MoCap Gait Identification for Video Surveillance with Incomplete and Noisy Data
PB  - IEEE
CY  - USA
SN  - 9781538611241
KW  - gait recognition
UR  - http://ieeexplore.ieee.org/document/8272700/
L2  - http://ieeexplore.ieee.org/document/8272700/
N2  - This work offers a design of a video surveillance system based on a soft biometric -- gait identification from MoCap data. The main focus is on two substantial issues of the video surveillance scenario: (1) the walkers do not cooperate in providing learning data to establish their identities and (2) the data are often noisy or incomplete. We show that only a few examples of human gait cycles are required to learn a projection of raw MoCap data onto a low-dimensional sub-space where the identities are well separable. Latent features learned by Maximum Margin Criterion (MMC) method discriminate better than any collection of geometric features. The MMC method is also highly robust to noisy data and works properly even with only a fraction of joints tracked. The overall workflow of the design is directly applicable for a day-to-day operation based on the available MoCap technology and algorithms for gait analysis. In the concept we introduce, a walker's identity is represented by a cluster of gait data collected at their incidents within the surveillance system: They are how they walk.
ER  -

BALÁŽIA, Michal a Petr SOJKA. You Are How You Walk: Uncooperative MoCap Gait Identification for Video Surveillance with Incomplete and Noisy Data. Online. In Ross Beveridge, Liang Wang, Mark Nixon. \textit{Proceedings of the 3rd IEEE/IAPR International Joint Conference on Biometrics (IJCB 2017)}. USA: IEEE, 2017, s.~208-215. ISBN~978-1-5386-1124-1. Dostupné z: https://dx.doi.org/10.1109/BTAS.2017.8272700.

Podrobný výpis o publikaci