Hand gesture recognition for driver vehicle interaction

Yannick Jacob 1 Sotiris Manitsaris 1 Fabien Moutarde 1 Gautam Lele 2 Laetitia Pradere 2
1 CAOR - Centre de Robotique
2 PSA - PSA Peugeot Citroën
Abstract : In this paper, we present a new driver vehicle interface based on hand gestures that uses a hierarchical model to minimize resources requirements. Depth information is provided by time of flight sensor with automotive certification. In particular, we develop our implementation of a Random Forest based posture classification in two subcases: micro gestures at the wheel and macro gestures in front of the touch screen.
Keywords : hand gesture recognition human computer interaction micro gestures automotive sensing
Type de document :
Communication dans un congrès
IEEE Computer Society Workshop on Observing and understanding hands in action (Hands 2015) of 28th IEEE conf. on Computer Vision and Pattern Recognition (CVPR'2015), Jun 2015, Boston, United States
Liste complète des métadonnées

Littérature citée [8 références]  Voir  Masquer  Télécharger
https://hal-mines-paristech.archives-ouvertes.fr/hal-01256263
Contributeur : Fabien Moutarde <>
Soumis le : jeudi 14 janvier 2016 - 15:37:11
Dernière modification le : lundi 12 novembre 2018 - 10:56:41
Document(s) archivé(s) le : samedi 16 avril 2016 - 11:01:27

Fichier

Hand-Gesture_Recognition_for_D...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01256263, version 1

Collections

ENSMP | ENSMP_CAOR | PARISTECH | PSL

Citation

Yannick Jacob, Sotiris Manitsaris, Fabien Moutarde, Gautam Lele, Laetitia Pradere. Hand gesture recognition for driver vehicle interaction. IEEE Computer Society Workshop on Observing and understanding hands in action (Hands 2015) of 28th IEEE conf. on Computer Vision and Pattern Recognition (CVPR'2015), Jun 2015, Boston, United States. 〈hal-01256263〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

260

Téléchargements de fichiers

670

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD