Neural Network Based Data Fusion for Hand Pose Recognition with Multiple ToF Sensors

Abstract : We present a study on 3D based hand pose recognition us-ing a new generation of 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. We investigate the performance of different 3D descriptors, as well as the fusion of two ToF sensor streams. By basing a data fusion strategy on the fact that multilayer perceptrons can produce normalized confidences in-dividually for each class, and similarly by designing information-theoretic online measures for assessing confidences of decisions, we show that ap-propriately chosen fusion strategies can improve overall performance to a very satisfactory level. Real-time capability is retained as the used 3D descriptors, the fusion strategy as well as the online confidence measures are computationally efficient.
Type de document :
Communication dans un congrès
International Conference on Artificial Neural Networks (ICANN), Sep 2014, Hamburg, Germany. pp.233 - 240, 2014, 〈10.1007/978-3-319-11179-7_30〉
Liste complète des métadonnées

Littérature citée [15 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01098697
Contributeur : Alexander Gepperth <>
Soumis le : dimanche 28 décembre 2014 - 15:45:04
Dernière modification le : vendredi 8 décembre 2017 - 14:42:15
Document(s) archivé(s) le : lundi 30 mars 2015 - 16:11:09

Fichier

kopinski2014neural.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Thomas Kopinski, Alexander Gepperth, Stefan Geisler, Uwe Handmann. Neural Network Based Data Fusion for Hand Pose Recognition with Multiple ToF Sensors. International Conference on Artificial Neural Networks (ICANN), Sep 2014, Hamburg, Germany. pp.233 - 240, 2014, 〈10.1007/978-3-319-11179-7_30〉. 〈hal-01098697〉

Partager

Métriques

Consultations de la notice

232

Téléchargements de fichiers

230