Item request has been placed! ×
Item request cannot be made. ×
loading  Processing Request

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

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
اقرأ أكثر حفظ في قائمتي
  • معلومة اضافية
    • Contributors:
      Digital image processing, modeling and communication (TEMICS); Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA); Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes); Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes); Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Rennes – Bretagne Atlantique; Institut National de Recherche en Informatique et en Automatique (Inria)
    • بيانات النشر:
      HAL CCSD
    • الموضوع:
      2011
    • Collection:
      École Centrale Paris: HAL-ECP
    • الموضوع:
      Spain
    • الموضوع:
      Barcelona, Spain
    • نبذة مختصرة :
      International audience ; 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.
    • Relation:
      inria-00628076; https://inria.hal.science/inria-00628076; https://inria.hal.science/inria-00628076/document; https://inria.hal.science/inria-00628076/file/LeMeur_ICME_2011.pdf
    • الدخول الالكتروني :
      https://inria.hal.science/inria-00628076
      https://inria.hal.science/inria-00628076/document
      https://inria.hal.science/inria-00628076/file/LeMeur_ICME_2011.pdf
    • Rights:
      info:eu-repo/semantics/OpenAccess
    • الرقم المعرف:
      edsbas.4087F049