基于仿射不变性特征的视点空间划分

为了简化三维物体的识别过程,提高三维物体识别的识别率,该文利用Multi-scale autoconvolution、Trace变换、Zernike矩3种仿射不变性特征,对飞机、汽车、人等三维物体进行视点空间划分,用尽可能少的不等间隔的三维物体的二维投影图像来表达三维物体,并以此为依据进行三维物体识别。在此基础上提出一种针对不同类型物体的仿射不变性特征提取策略,并建立一个实现三维物体任意姿态识别的软件系统平台,应用Princeton形状标准库中的部分模型对该平台进行测试。结果表明,该方法能够取得较好的识别效果,识别率在90%以上。     

基于仿射不变性特征的视点空间划分

为了简化三维物体的识别过程,提高三维物体识别的识别率,该文利用Multi-scale autoconvolution、Trace变换、Zernike矩3种仿射不变性特征,对飞机、汽车、人等三维物体进行视点空间划分,用尽可能少的不等间隔的三维物体的二维投影图像来表达三维物体,并以此为依据进行三维物体识别。在此基础上提出一种针对不同类型物体的仿射不变性特征提取策略,并建立一个实现三维物体任意姿态识别的软件系统平台,应用Princeton形状标准库中的部分模型对该平台进行测试。结果表明,该方法能够取得较好的识别效果,识别率在90%以上。     

Efficient View-Based 3-D Object Retrieval via Hypergraph Learning

View-based 3-D object retrieval has become an emerging topic in recent years,especially with the fast development of visual content acquisition devices,such as mobile phones with cameras.Extensive research efforts have been dedicated to this task,while it is still difficult to measure the relevance between two objects with multiple views.In recent years,learning-based methods have been investigated in view-based 3-D object retrieval,such as graph-based learning.It is noted that the graph-based methods suffer from the high computational cost from the graph construction and the corresponding learning process.In this paper,we introduce a general framework to accelerate the learning-based view-based 3-D object matching in large scale data.Given a query object Q and one object O from a 3-D dataset D,the first step is to extract a small set of candidate relevant 3-D objects for object O.Then multiple hypergraphs can be constructed based on this small set of 3-D objects and the learning on the fused hypergraph is conducted to generate the relevance between Q and O,which can be further used in the retrieval procedure.Experiments demonstrate the effectiveness of the proposed framework.     

Computation of Edge-Edge-Edge Events Based on Conicoid Theory for 3-D Object Recognition

The availability of a good viewpoint space partition is crucial in three dimensional(3-D)object recognition on the approach of aspect graph.There are two important events,depicted by the aspect graph approach, edge-edge-edge(EEE)events and edge-vertex(EV)events.This paper presents an algorithm to compute EEE events by characteristic analysis based on conicoid theory,in contrast to current algorithms that focus too much on EV events and often overlook the importance of EEE events.Also,the paper provides a...     

基于几何元素的城市三维地理信息系统空间数据模型

空间数据模型是建立城市三维地理信息系统的核心问题。基于不同的城市空间对象划分方法 ,提出了城市三维地理信息系统的 18个空间数据模型 :①把空间现象抽象为点对象、线对象、规则面对象、规则体对象、不规则对象和DTM等 6类对象 ,基于 6种几何元素 (点、直线段、多边形、函数构造面、TIN面片、规则体素 )的不同组合 ,提出了城市三维地理信息系统的 9个空间数据模型 ;②把空间现象抽象为 5类对象 ,分别为零维空间对象 (点对象 )、一维空间对象 (线对象 )、二维空间对象 (面对象 )、三维空间对象 (体对象 )和DTM ,基于 6种几何元素的不同组合提出了 8个空间数据模型 ;③把空间现象抽象为零维对象、一维对象、二维对象、三维对象和DTM ,基于点、直线段、TIN面片、多边形、规则面、不规则面等 6类几何元素提出了一个空间数据模型。通过对一个数据模型的实验验证和各模型的理论分析 ,说明了这些模型的特点及可行性。     

基于拓扑图及三维特征的三维物体识别方法

提出一种基于拓扑图及三维特征的三维物体识别方法.该方法在图象预处理阶段先检测物体可视表面的闭合边界,再依据闭合边界对物体进行表面分割,并用一个景物特征图对景物进行表达(SAGR).在建模阶段,先采用多视图表面模型方法建模,再依据表面分割,对模型用一个模型特征图进行表达(MAGR).在物体识别阶段,将景物与模型的匹配分3部分进行,即扫描部件、图的匹配部件及匹配检验部件.匹配首先是基于 SAGR 与 MAGR 图的拓扑性质的匹配,然后是基于三维特征的匹配.根据匹配结果,或对未知物体自动建模,或给出识别结果.     

基于Markov随机场的三维物体识别算法

为准确识别出三维物体,提出了一种新的物体特征框架,采用密集采样的多分辨率网格来描述物体观测图像的局部特征,引入Markov随机场模型对网格节点之间的几何关系进行建模。不同图像之间的匹配通过最高置信度优先算法实现,以获取两图像各个节点之间的准确匹配关系以及全局相似度。在Coil-100(columbiaobjectimagelibrary)图像数据库上,以100个物体的4、8、18、36个视角的样本为模板,用其他68、64、54和36个视角的样本进行测试,该算法识别率分别为95.75%、99.30%、100.0%和100.0%,识别准确率明显高于文献中的方法,这说明算法在基于观测图像的物体识别领域有着非常好的应用前景。     

基于多方法集成的目标跟踪算法

在线运动目标跟踪是目前模式识别领域的一个难点问题,目标物体角度、姿态、远近距离变化以及遮挡等给鲁棒在线跟踪算法提出了苛刻的要求,单一算法很难有效处理所有问题.多方法集成是实现鲁棒在线跟踪的一种有效手段,为此提出了一个集成on-line boosting、基于归一化互相关的模板匹配法和粒子群优化算法的自适应目标跟踪算法框架.其中,on-line boosting是基本的跟踪算法;基于归一化互相关的模板匹配法有效避免了on-line boosting过多的错误更新;而基于粒子群优化算法的跟踪策略提高了系统对快速运动、外观变化的适应能力,同时也为模板的更新提供了保障,三种算法形成了有效互补,在稳定性和可塑性之间达到了一种平衡.在不同视频测试序列上的实验结果表明,该算法有效地缓解了自适应性和漂移之间的矛盾,能够实时地完成复杂的跟踪任务.     

层状介质中三维物体重构的对比源反演算法

对比源反演（CSI）算法将反演问题转化为求解成本泛函的极小值问题,从而形成重构对比源和对比度的迭代序列。开发了一种三维CSI算法对层状介质中的三维物体进行重构,该算法是对二维对比源反演算法的推广。该算法无须正演计算,亦无须人为地选择正则化参数,反演过程更稳定。CSI的每一次迭代过程均采用快速Fourier变换技术计算并矢Green函数算子及其共轭算子,确保了该算法在三维层状介质情况下的高效率。复杂模型的反演结果说明,CSI算法对重构层状介质中的任意三维异常体是非常有效的。     

计算全息三维信息获取的研究

计算全息所用的目标数据一般是通过计算机三维软件模拟获得，这样对于计算全息的应用有一定的限制．提出利用三维激光扫描仪获取计算全息图三维数据的方法，研究了计算全息物光分布和扫描三维数据之间的关系，建立了依据三维物体扫描数据的模拟物光波前分布，并分析了立体数据计算全息消隐问题．     

Bottlenose dolphins perceive object features through echolocation

How organisms (including people) recognize distant objects is a fundamental question. The correspondence between object characteristics (distal stimuli), like visual shape, and sensory characteristics (proximal stimuli), like retinal projection, is ambiguous. The view that sensory systems are 'designed' to 'pick up' ecologically useful information is vague about how such mechanisms might work. In echolocating dolphins, which are studied as models for object recognition sonar systems, the correspondence between echo characteristics and object characteristics is less clear. Many cognitive scientists assume that object characteristics are extracted from proximal stimuli, but evidence for this remains ambiguous. For example, a dolphin may store 'sound templates' in its brain and identify whole objects by listening for a particular sound. Alternatively, a dolphin's brain may contain algorithms, derived through natural endowments or experience or both, which allow it to identify object characteristics based on sounds. The standard method used to address this question in many species is indirect and has led to equivocal results with dolphins. Here we outline an appropriate method and test it to show that dolphins extract object characteristics directly from echoes.     

Numerical simulation of tomographic-SAR imaging and object reconstruction using compressive sensing with L 1/2-norm regularization

By making use of multiple acquisitions of synthetic aperture radar （SAR） observations over the same area, tomographic-SAR （tomo-SAR） technology can achieve three-dimensional （3-D） imaging of the objects of interest. The compressive sensing （CS） approach has been applied to deal with the sparseness of the elevation signals. Due to its sparsity and convexity, the L1-norm regulariza- tion, as an approximated Lo-norm with an exact solution, has been employed in CS to reconstruct the reflectivity profile of the objects. In this paper, based on our studies on polarimetric scattering and SAR imaging simulations, we produce numerical multi-pass tomo-SAR observations of the terrain object. Then, we present the CS with novel L1/2- norm regularization to realize 3-D reconstruction. As a non-convex optimization problem, the L1/2-norm regularization is solved by an iterative algorithm. This numerical simulation of tomo-SAR imaging and 3-D reconstruction of the object modeling can be of great help for parameterized analysis of tomo-SAR imagery. As an example, a tomo-SAR image and 3-D reconstruction of the Beijing National Stadium model are presented.     

投影距离的概率峰值效应及其在三维目标识别中的应用

在计算机视觉中，由于物体的几何特性随视线的变化而变化，从而给三维目标识别带来了困难．在设计识别算法时，关键是理解目标重要特征的变化，如角度、距离等的变化．在视线方向各向同性条件下，投影角度和距离的概率密度在其原值附近具有峰值效应，即投影角度及距离接近于原角度及距离．利用投影角度的联合概率函数可识别多面体．在已知距离时，为了便于识别目标，导出了投影距离的密度函数．实验结果证明了该方法的有效性．     

基于核心密度估计的动态目标分割改进模型

数字视频中的动态目标分割是基于计算机视觉技术的分析、识别系统中关键的处理步骤,分割结果的正确率决定了后期分析或识别过程的质量.在数字视频中存在各种有害动态像素,它们会降低分割过程的正确率.动态目标的阴影是这些有害像素的一种,因为它们本身不属于动态目标形状信息的范畴,但分割过程却能很容易将它们作为有效的动态目标像素分割出来.最近有关动态目标分割的研究提出了基于核心密度估计模型的分割方法.基于RGB颜色空间的核心密度估计模型能够在彩色视频中抑制阴影,但是对于灰度视频这种模型是无法抑制阴影的.作者针对上述局限提出了一种基于像素边缘测量的核心密度估计模型,用于动态目标分割,能够在彩色和灰度视频中抑制阴影.实验结果证明,这种新模型在通常的应用条件下是有效的.     

全球战场环境实时仿真系统研究

为了对全球范围内的战场作战情况进行实时模拟,文章提出了一种构建战场环境仿真系统的解决方案,分别以基于视点的LOD和地形预读方法解决大规模地形的可视化问题,以基于模板的动态场景元素管理解决大量运动物体的组织、管理问题,以基于经纬度的运动物体位姿变换解决物体运动姿态的模拟问题。实验结果表明,该方法能够实现大规模地形的实时可视化,能够对物体运动姿态进行有效的模拟,满足全球范围内战场环境实时仿真的需要。     

'Big Bang' tomography as a new route to atomic-resolution electron tomography

Until now it has not been possible to image at atomic resolution using classical electron tomographic methods, except when the target is a perfectly crystalline nano-object imaged along a few zone axes. The main reasons are that mechanical tilting in an electron microscope with sub-?ngstr?m precision over a very large angular range is difficult, that many real-life objects such as dielectric layers in microelectronic devices impose geometrical constraints and that many radiation-sensitive objects such as proteins limit the total electron dose. Hence, there is a need for a new tomographic scheme that is able to deduce three-dimensional information from only one or a few projections. Here we present an electron tomographic method that can be used to determine, from only one viewing direction and with sub-?ngstr?m precision, both the position of individual atoms in the plane of observation and their vertical position. The concept is based on the fact that an experimentally reconstructed exit wave consists of the superposition of the spherical waves that have been scattered by the individual atoms of the object. Furthermore, the phase of a Fourier component of a spherical wave increases with the distance of propagation at a known 'phase speed'. If we assume that an atom is a point-like object, the relationship between the phase and the phase speed of each Fourier component is linear, and the distance between the atom and the plane of observation can therefore be determined by linear fitting. This picture has similarities with Big Bang cosmology, in which the Universe expands from a point-like origin such that the distance of any galaxy from the origin is linearly proportional to the speed at which it moves away from the origin (Hubble expansion). The proof of concept of the method has been demonstrated experimentally for graphene with a two-layer structure and it will work optimally for similar layered materials, such as boron nitride and molybdenum disulphide.     

混合交通场景中的车辆检测和识别

介绍了一种城市交通流量视频检测系统及其车辆识别新算法。通过检测道路上的运动目标并利用目标的运动信息和外形特征进行车辆识别。考虑到目标的阴影会影响目标的形状特征 ,导致目标识别错误 ,提出了一种新的阴影检测算法———利用目标的灰度特征对运动目标进行阴影检测和分离。实验结果表明该系统在模拟城市混合交通环境下 ,能够克服目标阴影的影响 ,准确检测和识别车辆 ,同时能够满足实时性的要求     

复杂对象模式的规范化设计

该文给出了复杂对象模式的规范化设计。复杂对象模式的规范化设计不仅是将对象组合到相关联的关系中，而且要选择一个能很好地表示对象间的语义关系的结构。首先，基于对象间的语间关系，定义对象依赖；然后定义对象范式－－规范化对象模式树和规范化对象模式森林，并且讨论对象范式的特性，指出规范化对象模式森林是所要求的复杂对象模式的结构；最后给出了导出规范化对象模式森林的MIMI算法。     

三维图像中物体体素重建的新方法

在三维图像，例如LSCM，CT和MRI图像的处理、识别、可视化和计算机绘图中，三维物体的重建是必不可少的．已有的三维物体重建方法是基于二维物体重建的连通模拟法，因此重建速度慢．为此，我们提出一种新的快速的三维物体体素重建方法．在这种方法中，首先采用边沿跟踪和水平扫描的区域标号法重建三维图像的每个平面中的二维物体切片，然后采用伪OR运算和链接表的叠片法重建三维图像中的三维物体实体．作者首先介绍边沿跟踪和水平扫描方法，然后介绍伪OR运算和链接表，最后给出采用这种方法的实验结果的一个例子。     

2-D shape completion with shape priors

We propose new techniques for 2-D shape/contour completion, which is one of the important research topics related to shape analysis and computer vision, e.g. the detection of incomplete objects due to occlusion and noises. The purpose of shape completion is to find the optimal curve segments that fill the missing contour parts, so as to acquire the best estimation of the original complete object shapes. Unlike the previous work using local smoothness or minimum curvature priors, we solve the problem under a Bayesian formulation taking advantage of global shape prior knowledge. With the priors, our methods are expert in recovering significant shape structures and dealing with large occlusion cases. There are two different priors adopted in this paper: (i) A generic prior model that prefers minimal global shape transformation (including non-rigid deformation and affine transformation with respect to a reference object shape) of the recovered complete shape; and (ii) a class-specific shape prior model learned from training examples of an object category, which prefers the reconstructed shape to follow the learned shape variation models of the category. Efficient contour completion algorithms are suggested corresponding to the two types of priors. Our experimental results demonstrate the advantage of the proposed shape completion approaches compared to the existing techniques, especially for objects with complex structure under severe occlusion.