Human Gait Recognition from Motion Capture Data in Signature
Poses

J 2017

Human Gait Recognition from Motion Capture Data in Signature Poses

BALÁŽIA, Michal a Konstantinos N. PLATANIOTIS

Základní údaje

Originální název

Human Gait Recognition from Motion Capture Data in Signature Poses

Autoři

BALÁŽIA, Michal a Konstantinos N. PLATANIOTIS

Vydání

IET Biometrics, London, UK, IET, 2017, 2047-4938

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Velká Británie a Severní Irsko

Utajení

není předmětem státního či obchodního tajemství

Odkazy

IET Digital Library, IET Biometrics Premium Award, IEEE Xplore DL

Impakt faktor

Impact factor: 1.836

Označené pro přenos do RIV

Ano

Kód RIV

RIV/00216224:14330/17:00095906

Organizační jednotka

Fakulta informatiky

Klíčová slova česky

rozpoznavani podle chuze

Klíčová slova anglicky

gait recognition

Štítky

best3

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 8. 8. 2018 16:26, RNDr. Michal Balážia, Ph.D.

Anotace

V originále

Most contribution to the field of structure-based human gait recognition has been done through design of extraordinary gait features. Many research groups that address this topic introduce a unique combination of gait features, select a couple of well-known object classiers, and test some variations of their methods on their custom Kinect databases. For a practical system, it is not necessary to invent an ideal gait feature -- there have been many good geometric features designed -- but to smartly process the data there are at our disposal. This work proposes a gait recognition method without design of novel gait features; instead, we suggest an effective and highly efficient way of processing known types of features. Our method extracts a couple of joint angles from two signature poses within a gait cycle to form a gait pattern descriptor, and classifies the query subject by the baseline 1-NN classier. Not only are these poses distinctive enough, they also rarely accommodate motion irregularities that would result in confusion of identities. We experimentally demonstrate that our gait recognition method outperforms other relevant methods in terms of recognition rate and computational complexity. Evaluations were performed on an experimental database that precisely simulates street-level video surveillance environment.

Návaznosti

MUNI/A/0915/2013, interní kód MU

Název: Výzkum FI ve vybraných oblastech aplikované informatiky (Akronym: FI_Apl_Inf_2014)

Investor: Masarykova univerzita, Výzkum FI ve vybraných oblastech aplikované informatiky, DO R. 2020_Kategorie A - Specifický výzkum - Studentské výzkumné projekty

MUNI/A/1213/2014, interní kód MU

Název: Výzkum FI v aplikované informatice

Investor: Masarykova univerzita, Výzkum FI v aplikované informatice, DO R. 2020_Kategorie A - Specifický výzkum - Studentské výzkumné projekty

Přiložené soubory

bmt-arxiv.pdf Verze souboru

premium-award.pdf

Citovat

BALÁŽIA, Michal a Konstantinos N. PLATANIOTIS. Human Gait Recognition from Motion Capture Data in Signature Poses. IET Biometrics. London, UK: IET, 2017, roč. 6, č. 2, s. 129-137. ISSN 2047-4938. Dostupné z: https://doi.org/10.1049/iet-bmt.2015.0072.

@article{1359621,
   author = {Balážia, Michal and Plataniotis, Konstantinos N.},
   article_location = {London, UK},
   article_number = {2},
   doi = {https://doi.org/10.1049/iet-bmt.2015.0072},
   keywords = {gait recognition},
   language = {eng},
   issn = {2047-4938},
   journal = {IET Biometrics},
   note = {IET Biometrics Premium Award 2018},
   title = {Human Gait Recognition from Motion Capture Data in Signature Poses},
   url = {http://digital-library.theiet.org/content/journals/10.1049/iet-bmt.2015.0072},
   volume = {6},
   year = {2017}
}

TY  - JOUR
ID  - 1359621
AU  - Balážia, Michal - Plataniotis, Konstantinos N.
PY  - 2017
TI  - Human Gait Recognition from Motion Capture Data in Signature Poses
JF  - IET Biometrics
VL  - 6
IS  - 2
SP  - 129-137
EP  - 129-137
PB  - IET
SN  - 20474938
N1  - IET Biometrics Premium Award 2018
KW  - gait recognition
UR  - http://digital-library.theiet.org/content/journals/10.1049/iet-bmt.2015.0072
L2  - http://ieeexplore.ieee.org/document/7847562/
N2  - Most contribution to the field of structure-based human gait recognition has been done through design of extraordinary gait features. Many research groups that address this topic introduce a unique combination of gait features, select a couple of well-known object classiers, and test some variations of their methods on their custom Kinect databases. For a practical system, it is not necessary to invent an ideal gait feature -- there have been many good geometric features designed -- but to smartly process the data there are at our disposal. This work proposes a gait recognition method without design of novel gait features; instead, we suggest an effective and highly efficient way of processing known types of features. Our method extracts a couple of joint angles from two signature poses within a gait cycle to form a gait pattern descriptor, and classifies the query subject by the baseline 1-NN classier. Not only are these poses distinctive enough, they also rarely accommodate motion irregularities that would result in confusion of identities. We experimentally demonstrate that our gait recognition method outperforms other relevant methods in terms of recognition rate and computational complexity. Evaluations were performed on an experimental database that precisely simulates street-level video surveillance environment.
ER  -

BALÁŽIA, Michal a Konstantinos N. PLATANIOTIS. Human Gait Recognition from Motion Capture Data in Signature Poses. \textit{IET Biometrics}. London, UK: IET, 2017, roč.~6, č.~2, s.~129-137. ISSN~2047-4938. Dostupné z: https://doi.org/10.1049/iet-bmt.2015.0072.

Přehled o publikaci