视觉注意模型中权值估计与特征整合

Weight Estimation and Feature Integration in Modeling of Visual Attention

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。

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.