Interpretable Gait Recognition by Granger Causality

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F22%3A00125672" target="_blank" >RIV/00216224:14330/22:00125672 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/ICPR56361.2022.9956624" target="_blank" >https://doi.org/10.1109/ICPR56361.2022.9956624</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICPR56361.2022.9956624" target="_blank" >10.1109/ICPR56361.2022.9956624</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Interpretable Gait Recognition by Granger Causality

Popis výsledku v původním jazyce

Which joint interactions in the human gait cycle can be used as biometric characteristics? Most current methods on gait recognition suffer from a lack of interpretability. We propose an interpretable feature representation of gait sequences by the graphical Granger causal inference. The gait sequence of a person in the standardized motion capture format, constituting a set of 3D joint spatial trajectories, is envisaged as a causal system of joints interacting in time. We apply the graphical Granger model (GGM) to obtain the so-called Granger causal graph among joints as a discriminative and visually interpretable representation of a person's gait. We evaluate eleven distance functions in the GGM feature space by established classification and class-separability evaluation metrics. Our experiments indicate that, depending on the metric, the most appropriate distance functions for the GGM are the total norm distance and the Ky-Fan 1-norm distance. Experiments also show that the GGM is able to detect the most discriminative joint interactions and that it outperforms five related interpretable models in correct classification rate and in the Davies-Bouldin index. The proposed GGM model can serve as a complementary tool for gait analysis in kinesiology or for gait recognition in video surveillance.

Název v anglickém jazyce

Interpretable Gait Recognition by Granger Causality

Popis výsledku anglicky

Which joint interactions in the human gait cycle can be used as biometric characteristics? Most current methods on gait recognition suffer from a lack of interpretability. We propose an interpretable feature representation of gait sequences by the graphical Granger causal inference. The gait sequence of a person in the standardized motion capture format, constituting a set of 3D joint spatial trajectories, is envisaged as a causal system of joints interacting in time. We apply the graphical Granger model (GGM) to obtain the so-called Granger causal graph among joints as a discriminative and visually interpretable representation of a person's gait. We evaluate eleven distance functions in the GGM feature space by established classification and class-separability evaluation metrics. Our experiments indicate that, depending on the metric, the most appropriate distance functions for the GGM are the total norm distance and the Ky-Fan 1-norm distance. Experiments also show that the GGM is able to detect the most discriminative joint interactions and that it outperforms five related interpretable models in correct classification rate and in the Davies-Bouldin index. The proposed GGM model can serve as a complementary tool for gait analysis in kinesiology or for gait recognition in video surveillance.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of 26th International Conference on Pattern Recognition, ICPR 2022

ISBN

9781665490627

ISSN

1051-4651

e-ISSN

—

Počet stran výsledku

7

Strana od-do

1069-1075

Název nakladatele

IEEE

Místo vydání

Los Alamitos, CA, USA

Místo konání akce

Montréal, Québec, Canada

Datum konání akce

21. 8. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000897707601011