DMCA
Integration of Bottom--Up and Top--Down Cues for Visual Attention Using Non--Linear Relaxation (1994)
BibTeX
@MISC{Bost94integrationof,
author = {Jean--marc Bost and Thierry Pun and Ruggero Milanese Harry and Ruggero Milanese and Harry Wechsler and Harry Wechsler and Sylvia Gil and Sylvia Gil},
title = {Integration of Bottom--Up and Top--Down Cues for Visual Attention Using Non--Linear Relaxation},
year = {1994}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Active and selective perception seeks regions of interest in an image in order to reduce the computational complexity associated with time--consuming processes such as object recognition. We describe in this paper a visual attention system that extracts regions of interest by integrating multiple image cues. Bottom--up cues are detected by decomposing the image into a number of feature and conspicuity maps, while a--priori knowledge (i.e. models) about objects is used to generate top--down attention cues. Bottom--up and top--down information is combined through a non--linear relaxation process using energy minimization--like procedures. The functionality of the attention system is expanded by the introduction of an alerting (motion--based) system able to explore and avoid obstacles. Experimental results are reported, using cluttered and noisy scenes. E-mail: milanese@icsi.berkeley.edu. H.W. is with the George Mason University, Fairfax, VA. SG, JMB, and T.P. are with the Uni...
Keyphrases
top cue priori knowledge object recognition selective perception noisy scene computational complexity non linear relaxation process multiple image cue milanese icsi visual attention system energy minimization attention system experimental result george mason university attention cue conspicuity map
