Efficient dynamic texture classification with probabilistic motifs - Laboratoire d'Informatique Fondamentale et Appliquée de Tours Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Efficient dynamic texture classification with probabilistic motifs

Résumé

We propose to tackle dynamic texture video classification as a pattern mining problem. In a nutshell, videos are represented by frequent sequences of representative patches. Firstly, we use a Gaussian Mixture Model to make the clustering of patches from training videos. Secondly, a soft assignment is used as an encoding method to construct sequences of probability vectors (p-sequences) representing sequences of spatio-temporal patches. Thirdly, for each class, we mine meaningful motifs appearing inside the training p-sequences by means of an adapted data mining approach. Finally, feature vectors are constructed from the mined motifs, using the probabilistic support, which quantifies the match between the p-sequences, of the video to be classified, and the key-motifs of the classes. Experimental results and analysis for dynamic texture classification on benchmark datasets (i.e. UCLA, Traffic) show the interest of the proposed method.
Fichier principal
Vignette du fichier
Nguyen_Efficient_Dynamic_Texture_Classification_with_Probabilistic_Motifs_ICPR2022.pdf (343.51 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03700841 , version 1 (21-06-2022)

Identifiants

  • HAL Id : hal-03700841 , version 1

Citer

Luong Phat Nguyen, Julien Mille, Dominique H Li, Donatello Conte, Nicolas Ragot. Efficient dynamic texture classification with probabilistic motifs. International Conference on Pattern Recognition, Aug 2022, Montréal, Canada. ⟨hal-03700841⟩
79 Consultations
76 Téléchargements

Partager

Gmail Facebook X LinkedIn More