DMCA
On the plausibility of the discriminant centersurround hypothesis for visual saliency (2008)
| Venue: | Journal of Vision |
| Citations: | 96 - 11 self |
BibTeX
@ARTICLE{Gao08onthe,
author = {Dashan Gao and Vijay Mahadevan and Nuno Vasconcelos},
title = {On the plausibility of the discriminant centersurround hypothesis for visual saliency},
journal = {Journal of Vision},
year = {2008},
pages = {1--18}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
The classical hypothesis, that bottom-up saliency is a center-surround process, is combined with a more recent hypothesis that all saliency decisions are optimal in a decision-theoretic sense. The combined hypothesis is denoted as discriminant center-surround saliency, and the corresponding optimal saliency architecture is derived. This architecture equates the saliency of each image location to the discriminant power of a set of features with respect to the classification problem that opposes stimuli at center and surround, at that location. It is shown that the resulting saliency detector makes accurate quantitative predictions for various aspects of the psychophysics of human saliency, including non-linear properties beyond the reach of previous saliency models. Furthermore, it is shown that discriminant center-surround saliency can be easily generalized to various stimulus modalities (such as color, orientation and motion), and provides optimal solutions for many other saliency problems of interest for computer vision. Optimal solutions, under this hypothesis, are derived for a number of the former (including static natural images, dense motion fields, and even dynamic textures), and applied to a number of the latter (the prediction of human eye fixations, motion-based saliency in the presence of ego-motion, and motion-based saliency in the presence of highly dynamic backgrounds). In result, discriminant saliency is shown to predict eye fixations better than previous models, and produces background subtraction algorithms that outperform the state-of-the-art in computer vision. 1
Keyphrases
visual saliency discriminant centersurround hypothesis optimal solution discriminant center-surround saliency motion-based saliency computer vision center-surround process dense motion field human eye fixation various aspect dynamic texture human saliency accurate quantitative prediction discriminant saliency corresponding optimal saliency architecture image location eye fixation many saliency problem decision-theoretic sense previous model recent hypothesis discriminant power classification problem previous saliency model classical hypothesis bottom-up saliency saliency detector non-linear property static natural image combined hypothesis saliency decision background subtraction dynamic background various stimulus modality
