Color Information in a Model of Saliency - Archive ouverte HAL Access content directly
Conference Papers Year : 2014

Color Information in a Model of Saliency

(1) , (2) , (1) , (1)


Bottom-up saliency models have been developed to predict the location of gaze according to the low level features of visual scenes, such as intensity, color, frequency and motion. We investigate in this paper the contribution of color features in computing the bottom-up saliency. We incorporated a chrominance pathway to a luminance-based model (Marat et al.). We evaluated the performance of the model with and without chrominance pathway. We added an efficient multi-GPU implementation of the chrominance pathway to the parallel implementation of the luminance-based model proposed by Rahman et al., preserving real time solution. Results show that color information improves the performance of the saliency model in predicting eye positions.
Fichier principal
Vignette du fichier
hamel_eusipco2014.pdf (3.42 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01068276 , version 1 (26-09-2014)


  • HAL Id : hal-01068276 , version 1


Shahrbanoo Hamel, Nathalie Guyader, Denis Pellerin, Dominique Houzet. Color Information in a Model of Saliency. EUSIPCO 2014 - 22th European Signal Processing Conference, Sep 2014, Lisbonne, Portugal. pp.1-5. ⟨hal-01068276⟩
205 View
129 Download


Gmail Facebook Twitter LinkedIn More