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

被引:8137
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
[1]  
[Anonymous], [No title captured]
[2]   Expectation-based selective attention for visual monitoring and control of a robot vehicle [J].
Baluja, S ;
Pomerleau, DA .
ROBOTICS AND AUTONOMOUS SYSTEMS, 1997, 22 (3-4) :329-344
[3]   A model for inhibitory lateral interaction effects in perceived contrast [J].
Cannon, MW ;
Fullenkamp, SC .
VISION RESEARCH, 1996, 36 (08) :1115-1125
[4]   Colour tuning in human visual cortex measured with functional magnetic resonance imaging [J].
Engel, S ;
Zhang, XM ;
Wandell, B .
NATURE, 1997, 388 (6637) :68-71
[5]   The representation of visual salience in monkey parietal cortex [J].
Gottlieb, JP ;
Kusunoki, M ;
Goldberg, ME .
NATURE, 1998, 391 (6666) :481-484
[6]  
GREENSPAN H, 1994, 1994 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, P222, DOI 10.1109/CVPR.1994.323833
[7]  
KOCH C, 1985, HUM NEUROBIOL, V4, P219
[8]   A CLOSED CURVE IS MUCH MORE THAN AN INCOMPLETE ONE - EFFECT OF CLOSURE IN FIGURE GROUND SEGMENTATION [J].
KOVACS, I ;
JULESZ, B .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 1993, 90 (16) :7495-7497
[9]  
Leventhal A., 1991, NEURAL BASIS VISUAL, V4
[10]   ATTENTIVE MECHANISMS FOR DYNAMIC AND STATIC SCENE ANALYSIS [J].
MILANESE, R ;
GIL, S ;
PUN, T .
OPTICAL ENGINEERING, 1995, 34 (08) :2428-2434