基于视皮层V1模型的随机点视频序列运动特征提取

针对复杂场景中视频序列目标运动特征提取困难的问题,借鉴生物视觉系统对视频动态目标的运动感知机制,改进初级视皮层(V1)细胞模型,提出一种基于生物视皮层机制的视频运动特征提取方法。采用时空滤波器与半平方加归一化分别模拟神经元感受野的线性与非线性特性,再通过在输出权值中加入方向选择性调节参数得到普适性的V1细胞模型,从而解决传统模型方向选择性单一、多方向选择能力偏弱的问题。仿真结果表明所提模型模拟输出与生物实验数据较为吻合,能够模拟不同方向选择性的V1细胞,对复杂运动形态的随机点视频序列具有良好的运动特征提取能力。依靠该方法可以为处理特征光流信息提供新的思路,进而实现对视频序列目标的运动特征提取和有效跟踪。     

基于结构相似度的稀疏编码模型

已有的稀疏编码模型采用误差的平方和作为信息保持的客观评价标准,但最近的研究表明,人眼视觉系统的主要功能是从视觉区域提取图像和视频中的结构化信息.引入结构相似度来衡量信息保持的程度,通过对改进的目标函数进行优化,获得与初级视皮层中具有局部性、朝向性和带通性的感受野相类似的基函数集.实验结果表明,改进后的稀疏编码模型更符合人眼视觉系统特性.     

利用多层视觉网络模型进行图像局部特征表征的方法

为了寻求代价更小、效率更高、适应性更强的图像局部特征表征方法,提出一种基于视觉机制的多层网络计算模型.首先对初级视皮层中的简单细胞和复杂细胞等神经元进行建模;然后对腹侧视通路上的V4区神经元和下颞叶皮层区神经元的响应模式进行研究,并利用该计算模型对输入图像进行局部特征的表征.实验结果表明,与传统的图像特征描述方法相比,该模型所提取的图像局部特征具有足够的区分度;此外,利用生物视觉模型提取出的图像局部特征在具有复杂背景的场景中显示出了更加优秀的泛化能力.     

分层视觉特征感知在目标识别中的应用

为了模拟视觉通路的特征抽象与自学习能力,在视神经信息分层处理机制的基础上提出一种特征感知模型.在改进卷积神经网络框架的基础上,首先依据视网膜中神经元的方向选择性、空间局部性以及神经元间的侧抑制性,在初级视觉特征处理中构建一种视网膜拓扑映射;然后在中级视觉特征处理中引入生物神经的稀疏表达法,构建神经突触激活函数,解决了神经计算中常见的过拟合问题;最后提出模拟腹部通路信息传递的具有计算感知不变性的分层视觉特征感知计算模型.应用不同规模数据集进行测试的结果表明,该模型对大规模的目标识别问题具有较好的识别效果,目标识别的平均准确率可达85%.     

织物纹理的简单视神经细胞感受野的选择特性

研究了织物纹理的简单视神经细胞感受野的选择特性。分别选择具有明显方向性和周期性以及周期性和方向性不显著的两类代表织物纹理为研究对象,采用基于独立分量分析的视觉模型估计出简单视觉细胞的感受野。通过对感受野兴奋区域重心、方向角和面积的分析,以有效表示感受野在位置、方向和空间频率的选择特性。基于织物纹理与自然纹理两类纹理的简单细胞感受野选择性比较实验显示,相比于自然纹理,织物纹理的简单细胞感受野单元中的兴奋区域在方向、位置和空间频率上具有更加显著的选择特性。实验结果表明,提出的简单视觉细胞感受野选择特性研究方法在一定程度上揭示了初级视皮层对织物纹理图像处理的神经机制,从视觉感知层面反映了织物纹理的视觉特性。     

模拟初级视皮层脉冲神经元的动作识别系统

大脑中致力于运动信息处理的区域是初级视皮层(V1)和中颞区(MT).目前有关运动模式是在哪个区域完成的,存在不同的推测.迄今大多数关于动作识别的研究都是围绕MT阶段展开的.本文针对V1阶段获得的信息能否进行动作识别的问题展开研究,提出了模拟初级视皮层(V1)脉冲神经元的动作识别系统.该系统首先采用3D Gabor滤波器及其组合分别模拟初级视觉皮层中简单、复杂细胞的感受野,以此对视频图像进行处理,从而获取对运动速度和方向敏感的运动能量,并通过V1阶段的环绕抑制来增强运动能量和降低噪声的影响.其次,采用Integrate-and-fire脉冲神经元模型模拟初级视觉皮层的神经元,将获取的运动信息转换为神经元响应的脉冲链.最后,根据脉冲链平均发放率的特性提取运动特征向量,采用支持向量机(Support vector machine, SVM)作为分类器.在Weiziman数据库下进行测试,实验结果表明, V1阶段获得的信息可以进行动作的识别.     

空间统一调制模型的轮廓检测

目的 在人类大脑初级视皮层上,神经元不仅受到位于经典感受野中刺激的影响,同样也受到周边环境相应非经典感受野中刺激的影响。这种上下文的调制是通过视皮层的水平连接来实现的。基于初级视皮层的视觉机制,本文提出了一个轮廓提取模型。方法 首先利用局部能量计算初级视皮层上单个神经元的响应;然后通过构建一个新颖的空间统一调制算子获得周边刺激对于中央神经元的增强和抑制影响(上下文调制);最后整合上下文调制影响和中央神经元本身的能量响应,获得完整输出。结果 本文所提模型,无需在非经典感受野中划分增强域和抑制域,同时能够有效抑制背景纹理,突出目标轮廓,保留交点和角点信息。结论 通过对合成图像和自然图像的测试表明了本文算法的准确性和优越性,能够极大地提高复杂背景中轮廓检测的性能。     

采用局部场电位小波包熵分析空间频率特性

空间频率是视觉刺激的基本特征之一,为了研究视觉皮层神经元对刺激空间频率的响应特性,提出了一种基于局部场电位小波包熵的分析方法。通过以Long Evans大鼠为模式动物进行电生理实验,分别采用神经元放电统计分析和局部场电位小波包熵分析,发现不同空间频率刺激下,小波包熵调谐曲线与全局神经元放电调谐曲线具有一致性,证明了局部场电位小波包熵可用于表征视皮层神经元对刺激空间频率的选择性。结果还表明采用基于局部场电位小波包熵分析时,各通道结果具有更好的一致性。     

生物视觉系统的神经网络编码模型综述

生物视觉系统的研究一直是计算机视觉算法的重要灵感来源。有许多计算机视觉算法与生物视觉研究具有不同程度的对应关系,包括从纯粹的功能启发到用于解释生物观察的物理模型的方法。从视觉神经科学向计算机视觉界传达的经典观点是视觉皮层分层层次处理的结构。而人工神经网络设计的灵感来源正是视觉系统中的分层结构设计。深度神经网络在计算机视觉和机器学习等领域都占据主导地位。许多神经科学领域的学者也开始将深度神经网络应用在生物视觉系统的计算建模中。深度神经网络多层的结构设计加上误差的反向传播训练,使得它可以拟合绝大多数函数。因此,深度神经网络在学习视觉刺激与神经元响应的映射关系并取得目前性能最好的模型同时,网络内部的单元甚至学习出生物视觉系统子单元的表达。本文将从视网膜等初级视觉皮层和高级视觉皮层(如,视觉皮层第4区(visual area 4,V4)和下颞叶皮层(inferior temporal,IT))分别介绍基于神经网络的视觉系统编码模型。主要内容包括:1)有关视觉系统模型的概念与定义;2)初级视觉系统的神经网络预测模型;3)任务驱动的高级视觉皮层编码模型。最后本文还将介绍最新有关无监督学习的神经编码...     

基于视觉感知的运动目标跟踪算法

针对运动目标跟踪问题, 为解决跟踪过程中因遮挡、目标尺度变化等易造成跟踪失败的现象, 提出一种基于视觉感知的跟踪算法。该算法以神经元响应为视觉特征, 首先从自然图像中学习初级视皮层细胞感受野; 然后计算背景图像和视频序列图像的神经元响应并得出差值, 与动态阈值比较, 识别出运动目标, 通过迭代实现目标跟踪。多类别实验结果表明, 该算法实现了运动目标稳定跟踪, 目标跟踪准确率达93. 5%且鲁棒性增强, 与典型算法Camshift和SIFT相比, 提高了跟踪算法的准确性和鲁棒性。     

An improved selective attention model considering orientation preferences

An improved selective attention model is proposed in this paper, which is designed as a network of spiking neurons of Hodgkin--Huxley type with star-like connections between the central units and peripheral neurons. In this model, peripheral neurons represent the neurons located in the primary visual cortex. Since orientation preference is an important property of neurons in primary visual cortex, it should be considered except for external stimuli intensity. Simulation results show that the improved model can sequentially select objects with different orientation preferences and has a reliable shift of attention from one object to another, which are consistent with the experimental results that the neurons with different orientation preferences are laid out in pinwheel patterns.     

视觉选择性注意模型化计算中的特征整合权值估计与图像显著性区域提取

针对视觉选择性注意模型化计算过程中不同特征在整合阶段的权值判定,提出一种基于特征图分布的权值估计方法,并在静态图像显著性区域提取中取得了令人满意的应用效果。首先提取原始图像的颜色、方向和强度特征图像,然后计算各个特征图的广义高斯分布参数与方差,进而给出一种特征图权值估计算法,最后通过对特征图的加权整合与归一化实现对原始图像的显著性区域提取。实验结果表明,通过此方法计算的权值对特征进行加权调制所提取的显著性区域的效果更加符合人眼的观测结果。     

Tilt aftereffects in a self-organizing model of the primary visual cortex

RF-LISSOM, a self-organizing model of laterally connected orientation maps in the primary visual cortex, was used to study the psychological phenomenon known as the tilt aftereffect. The same self-organizing processes that are responsible for the long-term development of the map are shown to result in tilt aftereffects over short timescales in the adult. The model permits simultaneous observation of large numbers of neurons and connections, making it possible to relate high-level phenomena to low-level events, which is difficult to do experimentally. The results give detailed computational support for the long-standing conjecture that the direct tilt aftereffect arises from adaptive lateral interactions between feature detectors. They also make a new prediction that the indirect effect results from the normalization of synaptic efficacies during this process. The model thus provides a unified computational explanation of self-organization and both the direct and indirect tilt aftereffect in the primary visual cortex.     

Feedback and Surround Modulated Boundary Detection

Edges are key components of any visual scene to the extent that we can recognise objects merely by their silhouettes. The human visual system captures edge information through neurons in the visual cortex that are sensitive to both intensity discontinuities and particular orientations. The “classical approach” assumes that these cells are only responsive to the stimulus present within their receptive fields, however, recent studies demonstrate that surrounding regions and inter-areal feedback connections influence their responses significantly. In this work we propose a biologically-inspired edge detection model in which orientation selective neurons are represented through the first derivative of a Gaussian function resembling double-opponent cells in the primary visual cortex (V1). In our model we account for four kinds of receptive field surround, i.e. full, far, iso- and orthogonal-orientation, whose contributions are contrast-dependant. The output signal from V1 is pooled in its perpendicular direction by larger V2 neurons employing a contrast-variant centre-surround kernel. We further introduce a feedback connection from higher-level visual areas to the lower ones. The results of our model on three benchmark datasets show a big improvement compared to the current non-learning and biologically-inspired state-of-the-art algorithms while being competitive to the learning-based methods.     

Understanding the cortical specialization for horizontal disparity

Because the eyes are displaced horizontally, binocular vision is inherently anisotropic. Recent experimental work has uncovered evidence of this anisotropy in primary visual cortex (V1): neurons respond over a wider range of horizontal than vertical disparity, regardless of their orientation tuning. This probably reflects the horizontally elongated distribution of two-dimensional disparity experienced by the visual system, but it conflicts with all existing models of disparity selectivity, in which the relative response range to vertical and horizontal disparities is determined by the preferred orientation. Potentially, this discrepancy could require us to abandon the widely held view that processing in V1 neurons is initially linear. Here, we show that these new experimental data can be reconciled with an initial linear stage; we present two physiologically plausible ways of extending existing models to achieve this. First, we allow neurons to receive input from multiple binocular subunits with different position disparities (previous models have assumed all subunits have identical position and phase disparity). Then we incorporate a form of divisive normalization, which has successfully explained many response properties of V1 neurons but has not previously been incorporated into a model of disparity selectivity. We show that either of these mechanisms decouples disparity tuning from orientation tuning and discuss how the models could be tested experimentally. This represents the first explanation of how the cortical specialization for horizontal disparity may be achieved.     

An amplitude equation approach to contextual effects in visual cortex

A mathematical theory of interacting hypercolumns in primary visual cortex (V1) is presented that incorporates details concerning the anisotropic nature of long-range lateral connections. Each hypercolumn is modeled as a ring of interacting excitatory and inhibitory neural populations with orientation preferences over the range 0 to 180 degrees. Analytical methods from bifurcation theory are used to derive nonlinear equations for the amplitude and phase of the population tuning curves in which the effective lateral interactions are linear in the amplitudes. These amplitude equations describe how mutual interactions between hypercolumns via lateral connections modify the response of each hypercolumn to modulated inputs from the lateral geniculate nucleus; such interactions form the basis of contextual effects. The coupled ring model is shown to reproduce a number of orientation-dependent and contrast-dependent features observed in center-surround experiments. A major prediction of the model is that the anisotropy in lateral connections results in a nonuniform modulatory effect of the surround that is correlated with the orientation of the center.     

多水平外区抑制的轮廓检测

提取自然图像中的物体轮廓是机器视觉研究的重要问题,主要困难在于自然图像中的纹理性边缘严重干扰了物体轮廓的提取。研究表明视皮层方位选择性神经元的非经典感受野机制使得人类视觉系统在处理自然图像时不仅能够抑制纹理性边缘,而且能够增强物体的轮廓。基于此人们提出多种仿生轮廓检测算法,但算法中被称为抑制水平的参量在取值较高时会漏检部分轮廓,而在其取值较低时又会引入过多的纹理性边缘。针对这一问题,提出多水平外区抑制轮廓检测算法,通过整合各级单水平外区抑制的检测信息,有效抑制了纹理性边缘和降低了漏检轮廓的可能性。实验结果表明,相对于传统算法,新算法在轮廓检测性能上提高了10%左右,并具有更好的稳健性。     

考虑微动机制与感受野特性的轮廓检测模型

轮廓检测是目标识别中关键的步骤之一。人类视觉系统具有快速和有效地从复杂场景中提取轮廓特征的能力,初级视觉皮层（V1区）的非经典感受野对中心神经元刺激具有抑制特性。传统模型利用该感受野特性,采用圆环形的非经典感受野模板模拟纹理抑制的距离权重,在传统模型的基础上,提出一种引入人眼微动机制的轮廓检测新模型,该模型将圆环形模板按等间隔角度生成八个子模板,由子模板中的相应角度方位区域置换数值模拟眼动机制,通过竞争获得最终抑制权重。实验结果表明,该模型较传统模型具有较高的性能评测指标,在最大程度抑制背景纹理的同时,保留了更多的真实轮廓。     

Contour detection based on a non-classical receptive field model with butterfly-shaped inhibition subregions

Physiological studies show that the response of classical receptive field (CRF) to visual stimulus could be suppressed by non-classical receptive field (NCRF) inhibition of the neurons in primary visual cortex (V1) and most of CRFs and NCRFs in V1 are orientation-selective. In addition, surround inhibition is normally spatially asymmetric. Inspired by these visual mechanisms, we proposed a feasible contour detection method based on an improved orientation-selective inhibition model in this paper. A butterfly-formed surrounding area is employed for the computation of inhibition term, and only one side subregion that produces less inhibition contributes to cell's response, which could provide a flexible inhibitory effect for the NCRF modulation on CRF. Comparisons with other visual contour detection models show that the proposed model can suppress texture effectively while retaining contours as much as possible.