Skip to Main content Skip to Navigation
Conference papers

PREDICTING SALIENCY USING TWO CONTEXTUAL PRIORS: THE DOMINANT DEPTH AND THE HORIZON LINE

Olivier Le Meur 1 
1 TEMICS - Digital image processing, modeling and communication
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : A computational model of visual attention using visual inferences is proposed. The dominant depth and the horizon line position are inferred from low-level visual features. This prior knowledge helps to find salient areas on still color pictures. Regarding the dominant depth, the idea is to favor the lowest spatial frequencies on close-up scenes whereas the highest spatial frequencies are used to predict salient areas on panoramic view. Some studies showed that the horizon line is a natural attractor of our gaze. Horizon detection is then used to improve the saliency prediction. Results show that the proposed model outperforms existing approaches. However, the dominant depth does not bring any gain in the saliency prediction.
Document type :
Conference papers
Complete list of metadata

https://hal.inria.fr/inria-00628076
Contributor : Olivier Le Meur Connect in order to contact the contributor
Submitted on : Friday, September 30, 2011 - 1:21:45 PM
Last modification on : Friday, February 4, 2022 - 3:15:17 AM
Long-term archiving on: : Saturday, December 31, 2011 - 2:30:25 AM

Files

Identifiers

  • HAL Id : inria-00628076, version 1

Citation

Olivier Le Meur. PREDICTING SALIENCY USING TWO CONTEXTUAL PRIORS: THE DOMINANT DEPTH AND THE HORIZON LINE. ICME, Jul 2011, Barcelona, Spain. ⟨inria-00628076⟩

Share

Metrics

Record views

156

Files downloads

105