A Vision Substitution Method Based on Visual Attention Models

TIAN Ya-nan; LEI Hong-wei; WANG Xu

doi:10.3969/j.issn.0372-2112.2014.05.009

您当前的位置：

首页 >

文章列表页 >

A Vision Substitution Method Based on Visual Attention Models

更新时间：2025-07-16

- A Vision Substitution Method Based on Visual Attention Models
- Acta Electronica Sinica Vol. 42, Issue 5, Pages: 890-895(2014)
- 作者机构：
  
  东北大学信息科学与工程学院,辽宁,沈阳,110819
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.50477015);Fundamental Research Fund Project of Ministry of Education - Young University Teachers Research Fund (No.N110304002)
- DOI：10.3969/j.issn.0372-2112.2014.05.009
  CLC： TP391.41
- Published：2014
- 稿件说明：
移动端阅览
TIAN Ya-nan, LEI Hong-wei, WANG Xu. A Vision Substitution Method Based on Visual Attention Models[J]. Acta Electronica Sinica, 2014, 42(5): 890-895.
DOI：

TIAN Ya-nan, LEI Hong-wei, WANG Xu. A Vision Substitution Method Based on Visual Attention Models[J]. Acta Electronica Sinica, 2014, 42(5): 890-895. DOI： 10.3969/j.issn.0372-2112.2014.05.009.

摘要

现有的视觉替代方法均是在特定环境中

通过目标识别获得映射特征

缺少普遍的适用性.针对这一问题

提出了一种基于注意模型的视觉替代方法.利用人眼的视觉特性

提取图像的感兴趣区域

并根据听觉显示的基本原理

提出了将感兴趣区域的位置、尺寸和颜色映射为音符响度、音长和音调的PSC映射方法.实验结果表明:将图像中引起视觉注意的区域映射为电子音符

符合人类视觉认知过程

有利于盲人获得外部环境的重要信息

降低了盲人训练和学习的难度

并且听感良好

不会造成听觉疲劳.

Abstract

The existing vision substitution methods are only used in special environments because their mapping features are obtained by object recognition.Aiming at this problem

a vision substitution method based on visual attention models is proposed.Firstly

regions of interest are extracted according to human visual properties.And on the basis of the auditory display theory

PSC mapping method is presented that the position

size and color of regions of interest are respectively mapped into note loudness

duration and pitch.Results show that this method corresponds with the cognitive processes of human vision.It is good at helping the blind to obtain the important information and reducing the difficulty of training and learning.Moreover

the mapped electronic music is pleasing to ear and enjoyable.

关键词

Keywords

references

Views

1657

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Extracting Attention Information Algorithm Based onContrast Sensitivity and Markov Chain

A Phase Field Variational Model Joint Sobolev Gradient for Saliency Detection

Related Author

FONT face

Verdana

ZHANG Xiao-lin

ZHAO Hong-wei

WANG Hui

DAI Jin-bo

FONT

LI Meng

Related Institution

1'吉林大学计算机科学与技术学院

'吉林大学符号计算与知识工程教育部重点实验室

'长春师范学院计算机科学与技术学院

College of Economics and Business Administration, Chongqing University

College of Mathematics and Statistics, Chongqing Technology and Business University

⁰