L. Itti et al., A MODEL OF SALIENCY-BASED VISUAL-ATTENTION FOR RAPID SCENE ANALYSIS, IEEE transactions on pattern analysis and machine intelligence, 20(11), 1998, pp. 1254-1259
A visual attention system, inspired by the behavior and the neuronal a
rchitecture of the early primate visual system, is presented. Multisca
le image features are combined into a single topographical saliency ma
p. A dynamical neural network then selects attended locations in order
of decreasing saliency. The system breaks down the complex problem of
scene understanding by rapidly selecting, in a computationally effici
ent manner, conspicuous locations to be analyzed in detail.