Volumes of Blurred-Invariant Gaussians for Dynamic Texture Classification - ETIS, équipe MIDI Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Volumes of Blurred-Invariant Gaussians for Dynamic Texture Classification

Thanh Tuan Nguyen
  • Fonction : Auteur
  • PersonId : 1035759
Thanh Phuong Nguyen
Ngoc-Son Vu

Résumé

An effective model, which jointly captures shape and motion cues, for dynamic texture (DT) description is introduced by taking into account advantages of volumes of blurred-invariant features in three main following stages. First, a 3-dimensional Gaussian kernel is used to form smoothed sequences that allow to deal with well-known limitations of local encoding such as near uniform regions and sensitivity to noise. Second , a receptive volume of the Difference of Gaussians (DoG) is figured out to mitigate the negative impacts of environmental and illumination changes which are major challenges in DT understanding. Finally, a local encoding operator is addressed to construct a discriminative descriptor of enhancing patterns extracted from the filtered volumes. Evaluations on benchmark datasets (i.e., UCLA, DynTex, and DynTex++) for issue of DT classification have positively validated our crucial contributions.
Fichier principal
Vignette du fichier
CAIP-34.pdf (2.78 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02160704 , version 1 (19-06-2019)

Identifiants

  • HAL Id : hal-02160704 , version 1

Citer

Thanh Tuan Nguyen, Thanh Phuong Nguyen, Frédéric Bouchara, Ngoc-Son Vu. Volumes of Blurred-Invariant Gaussians for Dynamic Texture Classification. Computer Analysis of Images and Patterns (CAIP), Sep 2019, Salerno, Italy. ⟨hal-02160704⟩
142 Consultations
96 Téléchargements

Partager

Gmail Facebook X LinkedIn More