Scattering Features for Multimodal Gait Recognition - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Scattering Features for Multimodal Gait Recognition

Srđan Kitić
  • Fonction : Auteur
  • PersonId : 1004825
Gilles Puy
Patrick Pérez
  • Fonction : Auteur
  • PersonId : 1022281

Résumé

We consider the problem of identifying people on the basis of their walk (gait) pattern. Classical approaches to tackle this problem are based on, e.g., video recordings or piezoelec-tric sensors embedded in the floor. In this work, we rely on acoustic and vibration measurements, obtained from a microphone and a geophone sensor, respectively. The contribution of this work is twofold. First, we propose a feature extraction method based on an (untrained) shallow scattering network, specially tailored for the gait signals. Second, we demonstrate that fusing the two modalities improves identification in the practically relevant open set scenario.
Fichier principal
Vignette du fichier
Gait_multimodal.pdf (258.58 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01523115 , version 1 (16-05-2017)

Identifiants

  • HAL Id : hal-01523115 , version 1

Citer

Srđan Kitić, Gilles Puy, Patrick Pérez, Philippe Gilberton. Scattering Features for Multimodal Gait Recognition. GlobalSIP 2017 - 5th IEEE Global Conference on Signal and Information Processing, Nov 2017, Montreal, Canada. ⟨hal-01523115⟩
73 Consultations
162 Téléchargements

Partager

Gmail Facebook X LinkedIn More