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

Laurent Itti; Christof Koch; Ernst Niebur

doi:10.1109/34.730558

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

Laurent Itti, Christof Koch, Ernst Niebur

Research output: Contribution to journal › Article › peer-review

8313 Scopus citations

Abstract

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.

Original language	English (US)
Pages (from-to)	1254-1259
Number of pages	6
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume	20
Issue number	11
DOIs	https://doi.org/10.1109/34.730558
State	Published - 1998
Externally published	Yes

Keywords

Feature extraction
Scene analysis
Target detection
Visual attention
Visual search

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Computational Theory and Mathematics
Artificial Intelligence
Applied Mathematics

Access to Document

10.1109/34.730558

Cite this

@article{21f57010f4a5450cbd80578b38388057,

title = "A model of saliency-based visual attention for rapid scene analysis",

abstract = "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.",

keywords = "Feature extraction, Scene analysis, Target detection, Visual attention, Visual search",

author = "Laurent Itti and Christof Koch and Ernst Niebur",

note = "Funding Information: This research was supported by the U.S. National Science Foundation, the Center for Neuromorphic Engineering at Caltech, and the U.S. Office of Naval Research.",

year = "1998",

doi = "10.1109/34.730558",

language = "English (US)",

volume = "20",

pages = "1254--1259",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

issn = "0162-8828",

publisher = "IEEE Computer Society",

number = "11",

}

TY - JOUR

T1 - A model of saliency-based visual attention for rapid scene analysis

AU - Itti, Laurent

AU - Koch, Christof

AU - Niebur, Ernst

N1 - Funding Information: This research was supported by the U.S. National Science Foundation, the Center for Neuromorphic Engineering at Caltech, and the U.S. Office of Naval Research.

PY - 1998

Y1 - 1998

N2 - 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.

AB - 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.

KW - Feature extraction

KW - Scene analysis

KW - Target detection

KW - Visual attention

KW - Visual search

UR - http://www.scopus.com/inward/record.url?scp=0032204063&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032204063&partnerID=8YFLogxK

U2 - 10.1109/34.730558

DO - 10.1109/34.730558

M3 - Article

AN - SCOPUS:0032204063

SN - 0162-8828

VL - 20

SP - 1254

EP - 1259

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

IS - 11

ER -

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

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this