A model of saliency-based visual attention for rapid scene analysis

被引:7980
作者
Itti, L [1 ]
Koch, C
Niebur, E
机构
[1] CALTECH 139 74, Computat & Neural Syst Program, Pasadena, CA 91125 USA
[2] Johns Hopkins Univ, Krieger Mind Brain Inst, Baltimore, MD 21218 USA
基金
美国国家科学基金会;
关键词
visual attention; scene analysis; feature extraction; target detection; visual search;
D O I
10.1109/34.730558
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A visual attention system, inspired by the behavior and the neuronal architecture of the early primate visual system, is presented. Multiscale image features are combined into a single topographical saliency map. 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 efficient manner, conspicuous locations to be analyzed in detail.
引用
收藏
页码:1254 / 1259
页数:6
相关论文
共 18 条