| 视觉注意模型中权值估计与特征整合 |
| |
| 引用本文： | 李净净,张基宏,梁永生.视觉注意模型中权值估计与特征整合[J].深圳信息职业技术学院学报,2012,10(3):42-45. |
| |
| 作者姓名： | 李净净 张基宏 梁永生 |
| |
| 作者单位： | 1. 深圳大学信息工程学院,广东深圳,518060
2. 深圳信息职业技术学院信息技术研究所,广东深圳,518172 |
| |
| 基金项目： | 广东省自然科学基金项目 |
| |
| 摘 要： | 针对视觉注意模型中不同特征在特征整合阶段的权值判定,提出了一种基于显著区域分布的权值估计方法。在Itti-Koch视觉注意计算模型的基础上,不同于平均权值的方法,通过计算各个特征图显著区域的分布、位置、个数,计算权值整合特征图。实验结果表明,该方法得到的显著图能更好地模拟人眼的观测结果。
|
| 关 键 词： | 视觉注意模型 特征整合 权值估计 显著图 |
Weight Estimation and Feature Integration in Modeling of Visual Attention |
| |
| Li Jingjing,ZHANG Jihong,LIANG Yongsheng.Weight Estimation and Feature Integration in Modeling of Visual Attention[J].Journal of Shenzhen Institute of Information Technology,2012,10(3):42-45. |
| |
| Authors: | Li Jingjing ZHANG Jihong LIANG Yongsheng |
| |
| Institution: | 1.School of Information Engineering,Shenzhen University,Guangdong Shenzhen 518060,P.R.China;2.Institute of Information Technology,Shenzhen Institute of Information Technology,Guangdong Shenzhen 518172,P.R.China) |
| |
| Abstract: | According to the different of features during feature integration process in modeling of visual attention,a method of weight estimation for different features is presented .Unlike the average weighted method in Itti-Koch model.Weight estimation and feature integration is estimated according to the number, the position, the distribution of each saliency area.The experimental results demonstrate that the processed method outperforms traditional method to meet the requirement of observers. |
| |
| Keywords: | visual attention model feature integration weight estimation saliency map |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
