Spatio-temporal saliency model to predict eye movements in video free viewing - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2008

Spatio-temporal saliency model to predict eye movements in video free viewing

Résumé

This paper presents a spatio-temporal saliency model that predicts eye movements. This biologically inspired model separated a video frame into two signals corresponding to the two main outputs of the retina (parvocellular and magnocellular outputs). Both signals are then decomposed into elementary feature maps by cortical-like filters. These feature maps are then used to form two saliency maps: a static one and a dynamic one. These maps are fused into a spatio-temporal saliency map. The model is evaluated by comparing the salient areas of each frame predicted by these saliency maps (static, dynamic, spatio-temporal) to the eye positions of different subjects during a video free viewing experiment with a large database (17000 frames).
Fichier principal
Vignette du fichier
2008_eusipco_marat.pdf (479.37 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00288966 , version 1 (25-06-2008)

Identifiants

  • HAL Id : hal-00288966 , version 1

Citer

Sophie Marat, Tien Ho Phuoc, Lionel Granjon, Nathalie Guyader, Denis Pellerin, et al.. Spatio-temporal saliency model to predict eye movements in video free viewing. EUSIPCO 2008 - 16th European Signal Processing Conference, Aug 2008, Lausanne, Switzerland. pp.1-5. ⟨hal-00288966⟩
442 Consultations
155 Téléchargements

Partager

Gmail Facebook X LinkedIn More