Recognizing Gestures by Learning Local Motion Signatures of HOG Descriptors

Abstract : We introduce a new gesture recognition framework based on learning local motion signatures (LMSs) of HOG descriptors . Our main contribution is to propose a new probabilistic learning-classification scheme based on a reliable tracking of local features. After the generation of these LMSs computed on one individual by tracking Histograms of Oriented Gradient (HOG) descriptor, we learn a code-book of video-words (i.e. clusters of LMSs) using kmeans algorithm on a learning gesture video database. Then the video-words are compacted to a code-book of code-words by the Maximization of Mutual Information (MMI) algorithm. At the final step, we compare the LMSs generated for a new gesture w.r.t. the learned code-book via the k-nearest neighbors (k-NN) algorithm and a novel voting strategy. Our main contribution is the handling of the N to N mapping between code-words and gesture labels within the proposed voting strategy. Experiments have been carried out on two public gesture databases: KTH and IXMAS . Results show that the proposed method outperforms recent state-of-the-art methods
Type de document :
Article dans une revue
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2012
Liste complète des métadonnées

Littérature citée [31 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00696371
Contributeur : Francois Bremond <>
Soumis le : vendredi 11 mai 2012 - 15:22:24
Dernière modification le : jeudi 11 janvier 2018 - 16:37:23
Document(s) archivé(s) le : dimanche 12 août 2012 - 02:38:50

Fichier

Becha-Pami2011.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00696371, version 1

Collections

Citation

Mohamed Kaâniche, Francois Bremond. Recognizing Gestures by Learning Local Motion Signatures of HOG Descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2012. 〈hal-00696371〉

Partager

Métriques

Consultations de la notice

335

Téléchargements de fichiers

279