Other version: ftp://cui.unige.ch/PUBLIC/vision/papers/milanese/92.07.spie92.ps.Z
Highlights
More informations
Chapitre d'actes
unige:47828 
 |
A relaxation network for a feature-driven visual attention system |
|
| Authors | ||
| Published in | Su-Shing Chen. Neural and Stochastic Methods in Image and Signal Processing. San Diego (USA). 1992, p. 542-552 | |
| Collection |
SPIE Proceedings; 1766 |
|
| Abstract | In this paper an attention module is described, which can be used by an active vision system to generate gaze changes. This module is based on a bottom-up, feature-driven analysis of the image. The results are regions of the input image which contain strange features, i.e., locations of the most `interesting' and `important' information. The method proposed for detecting such regions is based on the decomposition of the input image into a set of independent retinotopic feature maps. Each map represents the value of a certain attribute computed on a set of low-level primitives such as contours and regions. Relevant objects can be detected if the corresponding primitives have a feature value strongly different from the neighboring ones. Local comparisons of feature values are used to compute such measures of `difference' for each feature map and give rise to a corresponding set of conspicuity maps. In order to obtain a single measure of interest for each location and to make the process robust to noise, a relaxation algorithm is run on the set of conspicuity maps. A dozen iterations are sufficient to detect a binary mask identifying the attention regions. Results on real scenes are presented. | |
| Full text | ||
| Structures | ||
| Research group | Computer Vision and Multimedia Laboratory | |
| Citation (ISO format) | MILANESE, Ruggero, BOST, Jean Marc, PUN, Thierry. A relaxation network for a feature-driven visual attention system. In: Su-Shing Chen (Ed.). Neural and Stochastic Methods in Image and Signal Processing. San Diego (USA). [s.l.] : [s.n.], 1992. p. 542-552. (SPIE Proceedings; 1766) https://archive-ouverte.unige.ch/unige:47828 |
191 hits 
0 download 
Contact an author
Update