加权视差能量模型

Weighted Disparity Energy Model

由于人左右眼间距的存在,使得同一空间物体在左右眼视网膜上的投影存在位置差异,称之为视差.左右眼视网膜获取的信息最初在初级视皮层(V1区)进行融合,该区域有大量对视差敏感的神经元.关于它们的视差选择特性,目前比较公认的计算模型是视差能量模型,然而该模型却无法解释V1区神经元对反相关随机点立体图(Anti-correlated random dot stereograms,aRDS)的响应要比对随机点立体图的响应弱这一神经生理学发现.为此,本文提出了一种加权视差能量模型:首先,利用左右眼感受野内的信号差异对神经元的响应能量进行调制,然后再结合神经元之间的相互作用来计算细胞群响应,从而得到图像视差.本文旨在探索基于神经生理学的视差计算方法,主要贡献有:1)加权视差能量模型能够很好地解释V1区神经元对反随机点立体图的响应比随机点立体图响应弱的生理特性;2)加权视差能量模型的视差计算结果精度比现有基于神经生理学的模型更高,甚至高于一些传统的计算机视觉方法.

Due to the position difference of the two eyes, there exists difference between the projections of an object on the two eyes. This is what we call disparity. The primary visual cortex （V1 area） is thought to be the origin area to deal with binocular information and it contains many neurons which are sensitive to binocular disparity. The disparity tuning responses of these neurons have been well described by the disparity energy model. However, this model fails to explain a physiological finding that these neurons should have weaker responses to binocularly anti-correlated random dot stereograms （aRDS） relative to random dot stereograms. A weighted disparity energy model is proposed in this paper to tackle this problem. The responses of the neurons are modulated by making use of the signal differences within the left and right receptive fields. Then the population responses are computed based on the responses of individual neurons and interaction between them for disparity computation. This paper is primarily focused on developing the disparity computation model based on neurophysiological findings. The main contributions are two-fold： 1） it can adequately describe that the responses of the neurons in V1 to anti-correlated stimuli are weaker than those to random dot stereograms; 2） the obtained disparities are more accurate than existing neurophysiological methods, and even better than some classical computer vision methods.