Interpretable Gait Recognition by Granger Causality
Identifikátory výsledku
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>
Alternativní jazyky
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.
Klasifikace
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)
Návaznosti výsledku
Projekt
—
Návaznosti
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Ostatní
Rok uplatnění
2022
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
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