虚拟实景对象建模与表现

虚拟对象是指物体的数字化外观仿真模型,与基于图形的虚拟对象相比,基于图像的虚拟对象具有绘制速度与物体复杂度无关、实时性强、可轻易达到相片级的视觉表现效果以及建模简单等特点,在许多领域都具有广泛的应用前景.传统的基于图像的虚拟对象建模需已知相机参数或图像深度信息,建模繁琐复杂.针对该问题,提出一种可实用的基于图像的虚拟对象简化模型--虚拟实景对象,对该模型建模只需围绕待建模物体周围采集一圈实景图像,无需已知相机参数或图像深度信息,表现时则采用视图合成方法来合成未采集图像视点的虚拟视图,从而实现对物体的连续自由观察.实验结果表明,该方法不仅建模过程简单,而且可以实现对虚拟对象的360度连续自由操纵.     

基于编档的体系结构视图冲突检测方法

软件体系结构由不同的视图组成,每个视图包含不同的体系结构关注点.在软件工程领域中,如何对这些视图进行比对和合并是一项非常重要的研究工作.然而,目前视图比对的主要研究都着眼于视图元素之间的比对,因而并不能有效地发现视图之间的隐含冲突.主要原因是由于不同视图背后隐含着不同的关注点,而关注点之间的冲突并不能显式地在视图中表现出来,因此仅作视图元素比对不能发现这种隐含冲突.针对该问题,提出了一种基于编档的体系结构视图隐含冲突检测方法.在该方法中,通过对设计方法进行建模来捕获体系结构关注点和视图之间的关联关系;以软件体系结构文档作为通用平台,通过4个连续的活动来检测关注点之间的隐含关系;为了支持方法的自动化,就其中出现的关系给出了一套数学定义.     

结合公共视图和对象Petri网的跨组织流程建模

组织间协同的信息流以及每个参与组织的自治性是跨组织协同的两个要素。结合跨组织工作流建模与对象网之间的相似性,提出了一种基于公共视图和对象Petri网的跨组织工作流建模方法。组织的公共视图隐藏了内部流程细节,是原流程中仅与合作伙伴相关的活动在外部的投影。通过组合各参与组织的公共视图得到了跨组织协同的信息流网结构,利用对象网的交互集建立了组织内部流程与通信结构的同步关系。通过一个建模实例阐述了该方法的有效性。     

基于多尺度多模式图像的肺结节分类对比研究

基于深度卷积神经网络模型,讨论了不同尺度及不同模式肺结节图像对模型分类表现的影响,并提出了一种2D多视图融合的肺图像处理方法,该方法比传统的2D方式能获取更多的肺结节信息,同时又能比3D的方式引入更少的干扰组织。为了验证模型,对LIDC-IDRI和LUNA16数据集进行了预处理,得到了16、25、36三种尺度下2D、3D、2D全视图融合以及2D多视图融合四种不同模式的肺结节图像,然后构建了2D CNN、3D CNN、2D全视图融合卷积神经网络、2D多视图融合卷积神经网络四种模型。利用上述样本对模型进行训练和验证,最终结果表明,2D多视图融合模式下的肺结节图像相对于其他模式图像具有更佳的肺结节分类表现;对比多种尺度图像,小尺度下的分类表现相对更佳。     

基于随机传播图卷积模型的零样本图像分类

零样本图像分类旨在识别训练时从未出现过的全新类别(未见类别),为此需要利用辅助信息建模未见类和可见类之间的关系。利用图卷积网络(GCN)进行零样本分类的模型可以借助知识图显式地表达类别之间的关系,但 GCN 易受过平滑影响,导致模型性能下降。针对此问题提出了基于随机传播图卷积模型的零样本图像分类方法。该方法使用随机传播机制处理原始特征以达到特征扰动和数据扩增的目的;利用数据中类别层级生成的知识图建模类别之间的语义关系。其中,图中节点代表类别,节点间的边代表类别之间的关系。再构建 GCN对处理后的特征进行训练,从节点中输出包含未见类别的分类器参数,进而实现零样本图像分类。实验结果表明,该方法可以有效地改善零样本图像分类中的时间消耗、分类精度和泛化性能。     

面向软件密集型系统的体系结构可变性建模

软件体系结构提供了软件系统的高层抽象,对于软件密集型系统的开发具有重要意义,基于体系结构层次的可变性管理可以有效地实现软件的定制和演化。目前体系结构层次的可变性建模并没有得到足够的关注,在分析出领域体系结构后,无法很好地实现体系结构的建模,而且体系结构层次可变性建模方法并没有很好地对可变性的复杂依赖关系进行建模。提出了一种基于多视图的体系结构可变性建模方法,基于UML Profile扩展机制,定义了可变性的构造型、标记值和相关的约束,并利用基于分离的可变性建模方法,定义可变点交互视图对系统中存在的依赖进行建模。基于可变性视图和依赖视图分离的可变性建模方法,实现了复杂依赖关系的有效管理,提高了可变性建模的效果。以船舶故障预测与健康管理系统作为研究案例,对该方法进行了验证,结果表明该方法能够有效地实现软件密集型系统的建模。     

基于判别稀疏性表示的不完整多视图分类

传统多视图学习通常假设样本在每个视图都是完整的,但是由于数据难以获取、设备故障、遮挡等因素,这一假设并不总能成立,而传统的多视图学习方法很难有效处理不完整多视图数据.目前,研究者们已经提出了一些不完整多视图学习的方法,但是这些方法没有充分利用样本类别信息,从而影响恢复后样本的判别性.因此,提出基于判别稀疏性表示的不完整多视图分类方法(IMVC-DSR).具体地,该方法假设缺失样本可用少量观测样本稀疏线性表示.同时,为了充分利用类别先验信息,增加恢复后样本的判别性,该方法鼓励相同类别样本之间相互表示,降低不同类别样本之间的相互表达.此外,该方法考虑到视图之间的相关关系,引入选择算子选出不同视图的相同样本,并约束相同样本在不同视图的线性表达具有一致性.最后,在公开的五组数据集上验证了所提方法IMVC-DSR的有效性.     

多视图主动学习的多样性样本选择方法研究

为了去除高光谱图像多视图主动学习分类中的所选样本的冗余,降低人工标记成本,本文提出了两种用于多视图主动学习分类中的多样性样本选择方法。将高光谱图像进行超像素分割,将所选样本中属于不同的超像素的样本加入训练集,其余样本加入候选集;比较各视图对样本的预测标签,将所选样本中预测标签不完全相同的样本加入训练集,其余样本加入候选集。本文分别用这两种方法对传统多视图主动学习的样本选择方法进行改进,并用两组高光谱图像数据进行实验。实验结果表明:使用这两种方法改进后,所得分类精度不变,使用的训练样本数量大幅减少。     

基于序列图像建模的多视图模型合并策略

通过基于单幅图像的建模方法或者基于立体像对的建模方法，可以恢复图像序列中每一幅图像或者立体图像对对应的模型．但所得的是局部模型，并非物体的完整模型．针对这一问题，提出了一种基于图像建模的多视图模型合并策略．根据建筑物模型的规整性，在从单幅图像恢复出建筑物模型的基础上，给出了一种简单灵活、易于实现的针对建筑物的多视图合并方法，从而得到完整的场景模型．该方法大致分为建立视图公共坐标系链表、坐标转换、顶点合并、模型合拢等几部分．从整个过程来看，该方法系统、完善，实验结果显示每一步的操作都是可行的，并且是有效的．     

煤炭战略联盟集成模型研究

在CIMS企业集成理念思想指导下，提出煤炭企业基于战略联盟的企业集成理念．在详细分析战略联盟集成关系特点、信息需求和功能需求基础上，提出从关系视图、信息视图和过程视图的角度，对煤矿战略联盟进行建模的方法，揭示煤炭战略联盟关系的内涵．在战略联盟模型中提出反映成员企业之间关联关系的核心能力约束网络，有利于动态表示联盟关系．     

基于多视角距离图象的三维物体建模及其在识别中的应用

模型的表示和构建是基于距离图象三维物体识别技术中的关键模块之一.针对已有方法 存在的若干问题,提出一个新的综合多个视角距离图象的三维物体模型表示策略和增量式的 模型习得算法,并将该模型表示用于三维物体识别中.实验结果验证了算法的有效性.     

图像中物体空间关系的表示及在检索中的应用

基于图像中物体之间的空间关系的图像检索往往受困于待处理的图像中物体种类和空间位置难以自动准确地获取。文中基于物体识别算法的输出,提出一种对物体空间关系的三元组表示法,给出基于这种表示方法对图像索引、相似度计算和检索排序的方法及允许用户使用查询词和空间关系表达查询需求的二维输入界面,并实现原型系统。这种表示法具有良好的鲁棒性,可容忍物体识别算法一定程度的误差,将物体识别得到的置信度加入三元组表示法置信度计算和排序算法中,减少物体识别结果误差对检索性能的影响。在原型系统上的实验表明,该系统在实验中对包含物体位置关系的检索给出更准确的结果,在NDCG@m、MAP、F@m上均优于现有系统。     

一种基于联合表示的图像分类方法

在图像分类识别中,对于同一目标的不同图像,其训练样本和测试样本在同一位置的像素强度通常不同,这不利于提取目标图像的显著特征。这里给出一种基于稀疏表示的联合表示的图像分类方法,此方法首先利用相邻列之间的关系得到原始图像对应的虚拟图像,利用虚拟图像提高图像中中等强度像素的作用,降低过大或过小强度像素对图像分类的影响;然后用同一个目标的原始图像和虚拟图像一起表示目标,得到目标图像的联合表示;最后利用联合表示方法对目标分类。针对不同目标图像库的实验研究表明,给出的联合方法优于利用单一图像进行分类的方法,而且本方法能联合不同的表示方法来提高图像分类正确率。     

Learning to detect objects in images via a sparse, part-based representation

We study the problem of detecting objects in still, gray-scale images. Our primary focus is the development of a learning-based approach to the problem that makes use of a sparse, part-based representation. A vocabulary of distinctive object parts is automatically constructed from a set of sample images of the object class of interest; images are then represented using parts from this vocabulary, together with spatial relations observed among the parts. Based on this representation, a learning algorithm is used to automatically learn to detect instances of the object class in new images. The approach can be applied to any object with distinguishable parts in a relatively fixed spatial configuration; it is evaluated here on difficult sets of real-world images containing side views of cars, and is seen to successfully detect objects in varying conditions amidst background clutter and mild occlusion. In evaluating object detection approaches, several important methodological issues arise that have not been satisfactorily addressed in the previous work. A secondary focus of this paper is to highlight these issues, and to develop rigorous evaluation standards for the object detection problem. A critical evaluation of our approach under the proposed standards is presented.     

Representation and shape matching of 3-d objects

A three-dimensional scene analysis system for the shape matching of real world 3-D objects is presented. Various issues related to representation and modeling of 3-D objects are addressed. A new method for the approximation of 3-D objects by a set of planar faces is discussed. The major advantage of this method is that it is applicable to a complete object and not restricted to single range view which was the limitation of the previous work in 3-D scene analysis. The method is a sequential region growing algorithm. It is not applied to range images, but rather to a set of 3-D points. The 3-D model of an object is obtained by combining the object points from a sequence of range data images corresponding to various views of the object, applying the necessary transformations and then approximating the surface by polygons. A stochastic labeling technique is used to do the shape matching of 3-D objects. The technique matches the faces of an unknown view against the faces of the model. It explicitly maximizes a criterion function based on the ambiguity and inconsistency of classification. It is hierarchical and uses results obtained at low levels to speed up and improve the accuracy of results at higher levels. The objective here is to match the individual views of the object taken from any vantage point. Details of the algorithm are presented and the results are shown on several unknown views of a complicated automobile casting.     

Alias-free voxelization of geometric objects

Introduces a new concept for alias-free voxelization of geometric objects based on a voxelization model (V-model). The V-model of an object is its representation in 3D continuous space by a trivariate density function. This function is sampled during the voxelization and the resulting values are stored in a volume buffer. This concept enables us to study general issues of sampling and rendering separately from object-specific design issues. It provides us with a possibility to design such V-models, which are correct from the point of view of both the sampling and rendering, thus leading to both alias-free volumetric representation and alias-free rendered images. We performed numerous experiments with different combinations of V-models and reconstruction techniques. We have shown that the V-model with a Gaussian surface density profile combined with tricubic interpolation and Gabor derivative reconstruction outperforms the previously published technique with a linear density profile. This enables higher fidelity of images rendered from volume data due to increased sharpness of edges and thinner surface patches     

基于小波表征的遥感影像的目标检测

指出了基于像素灰度值的影像表征方法在表达检测目标信息上的不足,提出了运用小波变换的方法对遥感影像进行信息提取和表达。为了增强表达检测目标信息的能力,采用H aar母小波作为影像小波变换的小波基。实验表明:基于小波变换的表征方法在遥感影像目标检测的诸多性能指标上都优于基于影像像素灰度值的表征方法。     

Implicit Surface-Based Geometric Fusion

This paper introduces a general purpose algorithm for reliable integration of sets of surface measurements into a single 3D model. The new algorithm constructs a single continuous implicit surface representation which is the zero-set of a scalar field function. An explicit object model is obtained using any implicit surface polygonization algorithm. Object models are reconstructed from both multiple view conventional 2.5D range images and hand-held sensor range data. To our knowledge this is the first geometric fusion algorithm capable of reconstructing 3D object models from noisy hand-held sensor range data.This approach has several important advantages over existing techniques. The implicit surface representation allows reconstruction of unknown objects of arbitrary topology and geometry. A continuous implicit surface representation enables reliable reconstruction of complex geometry. Correct integration of overlapping surface measurements in the presence of noise is achieved using geometric constraints based on measurement uncertainty. The use of measurement uncertainty ensures that the algorithm is robust to significant levels of measurement noise. Previous implicit surface-based approaches use discrete representations resulting in unreliable reconstruction for regions of high curvature or thin surface sections. Direct representation of the implicit surface boundary ensures correct reconstruction of arbitrary topology object surfaces. Fusion of overlapping measurements is performed using operations in 3D space only. This avoids the local 2D projection required for many previous methods which results in limitations on the object surface geometry that is reliably reconstructed. All previous geometric fusion algorithms developed for conventional range sensor data are based on the 2.5D image structure preventing their use for hand-held sensor data. Performance evaluation of the new integration algorithm against existing techniques demonstrates improved reconstruction of complex geometry.     

The Space of All Stereo Images

A theory of stereo image formation is presented that enables a complete classification of all possible stereo views, including non-perspective varieties. Towards this end, the notion of epipolar geometry is generalized to apply to multiperspective images. It is shown that any stereo pair must consist of rays lying on one of three varieties of quadric surfaces. A unified representation is developed to model all classes of stereo views, based on the concept of a quadric view. The benefits include a unified treatment of projection and triangulation operations for all stereo views. The framework is applied to derive new types of stereo image representations with unusual and useful properties. Experimental examples of these images are constructed and used to obtain 3D binocular object reconstructions.