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

Laurent Itti, Christof Koch, Ernst Niebur

Research output: Contribution to journalArticle

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 languageEnglish (US)
Pages (from-to)1254-1259
Number of pages6
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume20
Issue number11
DOIs
StatePublished - Dec 1 1998
Externally publishedYes

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

Fingerprint Dive into the research topics of 'A model of saliency-based visual attention for rapid scene analysis'. Together they form a unique fingerprint.

  • Cite this