A real-time applicable 3D gesture recognition system for automobile HMI - ENSTA Paris - École nationale supérieure de techniques avancées Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

A real-time applicable 3D gesture recognition system for automobile HMI

Résumé

We present a system for 3D hand gesture recog-nition based on low-cost time-of-flight(ToF) sensors intended for outdoor use in automotive human-machine interaction. As signal quality is impaired compared to Kinect-type sensors, we study several ways to improve performance when a large number of gesture classes is involved. Our system fuses data coming from two ToF sensors which is used to build up a large database and subsequently train a multilayer perceptron (MLP). We demonstrate that we are able to reliably classify a set of ten hand gestures in real-time and describe the setup of the system, the utilised methods as well as possible application scenarios.
Fichier principal
Vignette du fichier
kopinski2014real.pdf (1.15 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01098700 , version 1 (28-12-2014)

Identifiants

Citer

Thomas Kopinski, Stefan Geisler, Louis-Charles Caron, Alexander Gepperth, Uwe Handmann. A real-time applicable 3D gesture recognition system for automobile HMI. IEEE International Conference On Intelligent Transportation Systems (ITSC), Oct 2014, Qingdao, China. pp.2616 - 2622, ⟨10.1109/ITSC.2014.6958109⟩. ⟨hal-01098700⟩
103 Consultations
396 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More