MULTIMODAL CLASSIFICATION OF DANCE MOVEMENTS USING BODY JOINT TRAJECTORIES AND STEP SOUNDS

Abstract : We present a multimodal approach to recognize isolated complex human body movements, namely Salsa dance steps. Our system exploits motion features extracted from 3D sub-trajec-tories of dancers' body-joints (deduced from Kinect depth-map sequences) using principal component analysis (PCA). These sub-trajectories are obtained thanks to a footstep impact detection module (from recordings of piezoelectric sensors installed on the dance floor). Two alternative classifiers are tested with the resulting PCA features, namely Gaussian mixture models and hidden Markov models (HMM). Our experiments on a multimodal Salsa dataset show that our approach is superior to a more traditionnal method. Using HMM classifiers with three hidden states, our system achieves a classification performance of 74% in F-measure when recognizing gestures among six possible classes, which outperforms the reference method by 11 percentage points.
Type de document :
Communication dans un congrès
International Workshop on Image and Audio Analysis for Multimedia Interactive Services WIAMIS, Nov 2013, Paris, France. pp.1-4, 2013, 〈10.1109/WIAMIS.2013.6616151〉
Liste complète des métadonnées

Littérature citée [7 références]  Voir  Masquer  Télécharger

https://hal-imt.archives-ouvertes.fr/hal-00904461
Contributeur : Admin Télécom Paristech <>
Soumis le : jeudi 14 novembre 2013 - 15:21:25
Dernière modification le : jeudi 11 janvier 2018 - 06:23:38
Document(s) archivé(s) le : samedi 15 février 2014 - 04:35:13

Fichier

WIAMIS13_AM_MultimodalClassifi...
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Aymeric Masurelle, Slim Essid, Gaël Richard. MULTIMODAL CLASSIFICATION OF DANCE MOVEMENTS USING BODY JOINT TRAJECTORIES AND STEP SOUNDS. International Workshop on Image and Audio Analysis for Multimedia Interactive Services WIAMIS, Nov 2013, Paris, France. pp.1-4, 2013, 〈10.1109/WIAMIS.2013.6616151〉. 〈hal-00904461〉

Partager

Métriques

Consultations de la notice

276

Téléchargements de fichiers

253