Communication Dans Un Congrès Année : 2013

Local polynomial space-time descriptors for actions classification

Résumé

In this paper we propose to tackle human actions indexing by introducing a new local motion descriptor. Our proposed descriptor is based on two modeling, a spatial model and a temporal model. The spatial model is computed by projection of optical flow onto bivari- ate orthogonal polynomials. Then, the time evolution of spatial coefficients is modeled with a one dimension polynomial basis. To perform the action classification, we extend recent still image signatures using local de- scriptors to our proposal and combine them with linear SVM classifiers. The experiments are carried out on the well known KTH dataset and on the more challeng- ing Hollywood2 action classification dataset and show promising results.

Fichier principal
Vignette du fichier
kihl13icmva.pdf (227.01 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Loading...

Dates et versions

hal-00807493 , version 1 (03-04-2013)

Licence

Identifiants

  • HAL Id : hal-00807493 , version 1

Citer

Olivier Kihl, David Picard, Philippe-Henri Gosselin. Local polynomial space-time descriptors for actions classification. International Conference on Machine Vision Applications, May 2013, Kyoto, Japan. ⟨hal-00807493⟩
374 Consultations
280 Téléchargements

Partager

  • More