A Three-Level Computational Attention Model

Autor/innen

  • Matei Mancas
  • Bernard Gosselin
  • Benoît Macq

DOI:

https://doi.org/10.2390/biecoll-icvs2007-153

Schlagworte:

computational attention, visual importance, saliency, rarity, DDC: 004 (Data processing, computer science, computer systems)

Abstract

This article deals with a biologically-motivated three-level computational attention model architecture based on the rarity and the information theory framework. It mainly focuses on a low-level step which aims in fastly highlighting important areas and a middle-level step which analyses the behaviour of the detected areas. Their application on both still images and videos provide results to be used by the third high-level step.

Downloads

Veröffentlicht

2007-12-31

Ausgabe

Rubrik

ICVS Workshop on Computational Attention & Applications - WCAA 2007