Suppr超能文献

立体知觉对视注意力选择的基于原型对象模型中视觉显著性的影响。

The influence of stereopsis on visual saliency in a proto-object based model of selective attention.

机构信息

The Department of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD, USA.

The Department of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD, USA.

出版信息

Vision Res. 2023 Nov;212:108304. doi: 10.1016/j.visres.2023.108304. Epub 2023 Aug 3.

Abstract

Some animals including humans use stereoscopic vision which reconstructs spatial information about the environment from the disparity between images captured by eyes in two separate adjacent locations. Like other sensory information, such stereoscopic information is expected to influence attentional selection. We develop a biologically plausible model of binocular vision to study its effect on bottom-up visual attention, i.e., visual saliency. In our model, the scene is organized in terms of proto-objects on which attention acts, rather than on unbound sets of elementary features. We show that taking into account the stereoscopic information improves the performance of the model in the prediction of human eye movements with statistically significant differences.

摘要

有些动物(包括人类)使用立体视觉,这种视觉通过双眼在两个相邻位置捕获的图像之间的视差来重建关于环境的空间信息。与其他感觉信息一样,这种立体信息预计会影响注意力的选择。我们开发了一种基于生物学的双目视觉模型来研究其对自下而上的视觉注意力(即视觉显著性)的影响。在我们的模型中,场景是根据注意力作用的原对象组织的,而不是根据无界的基本特征集组织的。我们表明,考虑到立体信息可以显著提高模型在预测人类眼球运动方面的性能。

相似文献

2
A proto-object based saliency model in three-dimensional space.一种基于原物体的三维空间显著模型。
Vision Res. 2016 Feb;119:42-9. doi: 10.1016/j.visres.2015.12.004. Epub 2016 Jan 19.
5
Mice Discriminate Stereoscopic Surfaces Without Fixating in Depth.老鼠无需注视深度即可辨别立体表面。
J Neurosci. 2019 Oct 9;39(41):8024-8037. doi: 10.1523/JNEUROSCI.0895-19.2019. Epub 2019 Aug 28.
6
Human stereopsis.人类立体视觉。
Hum Factors. 1992 Dec;34(6):669-92. doi: 10.1177/001872089203400603.
8
Task demands and binocular eye movements.任务要求与双眼眼动
J Vis. 2003 Dec 17;3(11):817-30. doi: 10.1167/3.11.15.

本文引用的文献

3
Proto-Object Based Saliency Model With Texture Detection Channel.具有纹理检测通道的基于原型对象的显著性模型
Front Comput Neurosci. 2020 Sep 24;14:541581. doi: 10.3389/fncom.2020.541581. eCollection 2020.
6
Disruptive coloration and binocular disparity: breaking camouflage.扰乱色和双目视差:打破伪装。
Proc Biol Sci. 2019 Feb 13;286(1896):20182045. doi: 10.1098/rspb.2018.2045.
8
What Do Different Evaluation Metrics Tell Us About Saliency Models?不同的评估指标能告诉我们关于显著性模型的哪些信息?
IEEE Trans Pattern Anal Mach Intell. 2019 Mar;41(3):740-757. doi: 10.1109/TPAMI.2018.2815601. Epub 2018 Mar 13.
9

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验