Dynamic gesture recognition for natural human system interaction

Hajar Hiyadi 1, 2 Fakhr-Eddine Ababsa 2 Christophe Montagne 2 El Houssine Bouyakhf 1 Fakhita Regragui 1
1 LIMIARF - Laboratoire d'Informatique, Mathématiques appliquées, Intelligence Artificielle et Reconnaissance de Formes
2 IBISC - Informatique, Biologie Intégrative et Systèmes Complexes
Abstract : This paper addresses two problems: 3d dynamic gesture recognition and gesture misallocation. In order to solve these problems, we propose a new approach which combines Hidden Markov Models (HMM) and Dynamic Time Warping (DTW). The proposed approach has two main phases; first, recognizing gestures using a hidden Markov model. Second, avoiding misallocation by rejecting gestures based on a threshold computed using DTW. Our database includes many samples of five gestures obtained with a Kinect and described by depth information only. The results show that our approach yields good gesture classification without any misallocation and it is robust against environmental constraints.
Keywords : Depth image Dynamic gesture recognition Dynamic time warping Hidden markov model Kinect
Document type :
Journal articles
Complete list of metadatas
https://hal.archives-ouvertes.fr/hal-01380425
Contributor : Frédéric Davesne <>
Submitted on : Thursday, October 13, 2016 - 10:16:33 AM
Last modification on : Monday, October 28, 2019 - 10:50:22 AM

Identifiers

  • HAL Id : hal-01380425, version 1

Collections

IBISC | IBISC-IRA2 | UNIV-EVRY | UNIV-PARIS-SACLAY

Citation

Hajar Hiyadi, Fakhr-Eddine Ababsa, Christophe Montagne, El Houssine Bouyakhf, Fakhita Regragui. Dynamic gesture recognition for natural human system interaction. Journal of Theoretical and Applied Information Technology, JATIT, 2016, 91 (2), pp.374--383. ⟨hal-01380425⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

194

Contact

Informations

CCSD