Neural model of visual stereomatching : slant , transparency and clouds
Neural model of visual stereomatching : slant , transparency and clouds
复制标题
视觉立体匹配的神经模型：倾斜、透明度和云彩
DOI：
10.1088/0954-898x/7/4/003
复制
发表时间：
1996
期刊：
影响因子：
64.8
通讯作者：
E. Graves
中科院分区：
文献类型：
--
作者：
J. Marshall;G. J. Kalarickal;E. Graves
描述了倾斜和透明表面的立体匹配，该模型使用大脑皮层双目调节的神经元对单个视觉特征的差异进行选择，而神经元对局部表面片的位置、深度和3D方向进行选择。该模型基于一套简单的学习规则。在该模型中，单眼神经元以适当的差值将兴奋性连接通路投射到双眼神经元。双眼神经元将兴奋性连接通路投射到适当调节的“表面贴片”神经元。表面贴片神经元向双眼神经元投射出相互兴奋的联系通路。各向异性的层内抑制性连接通路在具有重叠感受野的神经元之间投射。给出了该模型对描述各种倾斜表面和透明覆盖表面的模拟立体图像对的响应。对于所有的表面，该模型(I)基于全局表面的连贯性和唯一性来分配视差匹配和表面片表示，(Ii)允许代表同一图像位置内的多个视差的神经元的共同激活，(Iii)直接表示倾斜和倾斜的表面，而不是用一系列正面平行的步骤来近似它们，(Iv)将视差分配给随机深度的点云，如人类观察者和不同于Prazdny(1985)的方法，以及(V)导致全局一致的匹配覆盖贪婪的局部匹配。与Marr和Poggio(1976)的模型不同，该模型表示透明度；与Prazdny的模型不同，该模型分配了独特的差异。
Stereomatching of oblique and transparent surfaces is described using a model of cortical binocular ‘tuned’ neurons selective for disparities of individual visual features and neurons selective for the position, depth and 3D orientation of local surface patches. The model is based on a simple set of learning rules. In the model, monocular neurons project excitatory connection pathways to binocular neurons at appropriate disparities. Binocular neurons project excitatory connection pathways to appropriately tuned ‘surface patch’ neurons. The surface patch neurons project reciprocal excitatory connection pathways to the binocular neurons. Anisotropic intralayer inhibitory connection pathways project between neurons with overlapping receptive fields. The model’s responses to simulated stereo image pairs depicting a variety of oblique surfaces and transparently overlaid surfaces are presented. For all the surfaces, the model (i) assigns disparity matches and surface patch representations based on global surface coherence and uniqueness, (ii) permits coactivation of neurons representing multiple disparities within the same image location, (iii) represents oblique slanted and tilted surfaces directly, rather than approximating them with a series of frontoparallel steps, (iv) assigns disparities to a cloud of points at random depths, like human observers and unlike Prazdny’s (1985) method, and (v) causes globally consistent matches to override greedy local matches. The model represents transparency, unlike the model of Marr and Poggio (1976), and it assigns unique disparities, unlike the model of Prazdny.