SUN: A Bayesian framework for saliency using natural statistics.

SUN: A Bayesian framework for saliency using natural statistics.
复制标题

DOI:
10.1167/8.7.32
复制
发表时间:
2008-12-16
期刊:
影响因子:
1.8
通讯作者:
Cottrell GW
Cottrell GW
中科院分区:
医学4区
文献类型:
--
作者:
Zhang L;Tong MH;Marks TK;Shan H;Cottrell GW

文献摘要

参考文献

被引文献

相似文献

我们提出了一个显着性的定义,考虑视觉系统试图优化时,引导注意力。由此产生的模型是一个贝叶斯框架,自下而上的显着性自然出现的视觉特征的自信息,和整体显着性(结合自上而下的信息与自下而上的显着性)出现的特征和目标之间的逐点互信息搜索目标时。我们框架的实现表明,我们模型的自下而上显着性地图在预测人们自由观看时的注视点方面的性能与现有算法一样好或更好。与现有的显着性措施,这取决于正在查看的特定图像的统计数据,我们的显着性措施是来自自然图像的统计数据,提前从自然图像的集合中获得。因此,我们将我们的模型称为SUN(使用自然统计的显着性)。基于自然图像统计的显着性度量,而不是基于单个测试图像,为在人类中观察到的许多搜索不对称提供了一个简单的解释;单个测试图像的统计数据导致与这些不对称不一致的预测。在我们的模型中,显着性是局部计算的,这与早期视觉系统的神经解剖学是一致的,并导致一个有效的算法,很少的自由参数。
We propose a definition of saliency by considering what the visual system is trying to optimize when directing attention. The resulting model is a Bayesian framework from which bottom-up saliency emerges naturally as the self-information of visual features, and overall saliency (incorporating top-down information with bottom-up saliency) emerges as the pointwise mutual information between the features and the target when searching for a target. An implementation of our framework demonstrates that our model’s bottom-up saliency maps perform as well as or better than existing algorithms in predicting people’s fixations in free viewing. Unlike existing saliency measures, which depend on the statistics of the particular image being viewed, our measure of saliency is derived from natural image statistics, obtained in advance from a collection of natural images. For this reason, we call our model SUN (Saliency Using Natural statistics). A measure of saliency based on natural image statistics, rather than based on a single test image, provides a straightforward explanation for many search asymmetries observed in humans; the statistics of a single test image lead to predictions that are not consistent with these asymmetries. In our model, saliency is computed locally, which is consistent with the neuroanatomy of the early visual system and results in an efficient algorithm with few free parameters.
DOI: 10.1016/j.visres.2005.08.032
发表时间: 2006-04-01
期刊: VISION RESEARCH
影响因子: 1.8
作者:
Einhäuser, W;Kruse, W;König, P
通讯作者: König, P
DOI: 10.1167/6.9.4
发表时间: 2006-01-01
期刊: JOURNAL OF VISION
影响因子: 1.8
作者:
Carmi, Ran;Itti, Laurent
通讯作者: Itti, Laurent
DOI: 10.1016/0022-0965(72)90095-1
发表时间: 1972-01-01
影响因子: 2.6
作者:
FRIEDMAN, S
通讯作者: FRIEDMAN, S
DOI: 10.1109/34.730558
发表时间: 1998-11-01
影响因子: 23.6
作者:
Itti, L;Koch, C;Niebur, E
通讯作者: Niebur, E
DOI: 10.1016/s0042-6989(97)00121-1
发表时间: 1997-12-01
期刊: VISION RESEARCH
影响因子: 1.8
作者:
Bell, AJ;Sejnowski, TJ
通讯作者: Sejnowski, TJ