Goal-oriented top-down probabilistic visual attention model for recognition of manipulated objects in egocentric videos - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Signal Processing: Image Communication Année : 2015

Goal-oriented top-down probabilistic visual attention model for recognition of manipulated objects in egocentric videos

Résumé

We propose a new top down probabilistic saliency model for egocentric video content. It aims to predict top-down visual attention maps focused on manipulated objects, that are then used for psycho-visual weighting of features in the problem of manipulated object recognition. The model is probabilistically defined using both global and local appearance features extracted from automatically segmented arm areas and objects. A psycho-visual experiment has been conducted in a guided framework that compares our proposal and other popular state-of-the-art models with respect to human gaze fixations. The obtained results show that our approach outperforms several popular bottom-up saliency approaches in a well-known egocentric dataset. Furthermore, an additional task-driven assessment for object recognition in egocentric video reveals that the proposed method improves the performance of several state-of-the-art techniques for object detection.

Dates et versions

hal-01436904 , version 1 (16-01-2017)

Identifiants

Citer

Vincent Buso, Iván González-Díaz, Jenny Benois-Pineau. Goal-oriented top-down probabilistic visual attention model for recognition of manipulated objects in egocentric videos. Signal Processing: Image Communication, 2015, Signal Processing: Image Communication, 39, pp.418 - 431. ⟨10.1016/j.image.2015.05.006⟩. ⟨hal-01436904⟩

Collections

CNRS
40 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More