Revisiting LBP-Based Texture Models for Human Action Recognition - ENSTA Paris - École nationale supérieure de techniques avancées Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Revisiting LBP-Based Texture Models for Human Action Recognition

Thanh Phuong Nguyen
Antoine Manzanera
Ngoc-Son Vu
Matthieu Garrigues

Résumé

A new method for action recognition is proposed by revisit-ing LBP-based dynamic texture operators. It captures the similarity of motion around keypoints tracked by a realtime semi-dense point track-ing method. The use of self-similarity operator allows to highlight the geometric shape of rigid parts of foreground object in a video sequence. Inheriting from the efficient representation of LBP-based methods and the appearance invariance of patch matching method, the method is well designed for capturing action primitives in unconstrained videos. Action recognition experiments, made on several academic action datasets vali-date the interest of our approach.
Fichier principal
Vignette du fichier
DynamicTexture_CIARP.pdf (2.72 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01118271 , version 1 (18-02-2015)

Identifiants

Citer

Thanh Phuong Nguyen, Antoine Manzanera, Ngoc-Son Vu, Matthieu Garrigues. Revisiting LBP-Based Texture Models for Human Action Recognition. Iberoamerican Congress on Pattern Recognition (CIARP), Nov 2013, La Havane, Cuba. pp.286 - 293, ⟨10.1007/978-3-642-41827-3_36⟩. ⟨hal-01118271⟩
118 Consultations
97 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More