真实感虚拟人脸的实现和应用

实现了一个交互式人脸建膜和动画的工具，用户可以很容易从一个人的正面和侧面的照片构造出头部的三维模型，并在这个模型上实现特定人脸的表情和动画，同时可以进行口型和声音的同步。基于以上技术，实现了一个虚拟人脸的动画组件，可以应用于WINDOWS应用系统中，给用户提供更加新颖和友好的局面。     

三维脸部网格模型的交互式调整

脸部网络模型的建立是基于模型的人脸合成技术的关键步骤。提出了一种结合自动和交互方式，利用正交图象的三维人脸模型调整算法，首先利用区域增长法和矩形模板匹配确定正面图象中人脸及各特征区域的位置，利用变形模板自动提取人脸完整特征；然后交互地修正人脸特点的准确正面位置，并从侧面图象提取特征点的深度；最后算法自动确定脸部姿态和利用反向距离内插调整模型非特征点，获得输和人脸模型。实验结果表明，该算法简便实用，费时较少，具有一定的实用价值。     

基于Kinect与网格几何变形的人脸表情动画

面部表情重建的实时性与重建效果的真实性是人脸表情动画的关键问题,提出一种基于Kinect人脸追踪和几何变形技术的面部表情快速重建新方法。使用微软的Kinect设备识别出表演者面部并记录其特征点数据,并利用捕捉到的特征点建立覆盖人脸的网格模型,从中选取变形使用的控制点数据,由于Kinect可以实时地自动追踪表演者面部,由此实现了利用三种不同变形算法对目标模型实时快速重建。实验结果表明,该方法简单易实施,不用在表演者面部做任何标定,可以自动地将人脸表情动作迁移到目标模型上,实现人脸表情快速重建,并且保证目标模型表情真实自然。     

全自动的基于MPEG-4的任意拓扑结构人脸动画

构造任意拓扑结构人脸网格的人脸动画定义表是基于MPEG-4的任意拓扑结构人脸动画系统的关键．通过搜索三维模型的二维纹理图像特征，提出一种自动地在任意拓扑结构三维人脸模型上定位特征点的方法．通过利用任意拓扑结构人脸模型上的三维特征点变形标准人脸模型，并根据标准人脸模型的动画定义表，实现了自动、准确地构造任意拓扑结构人脸模型动画定义表的方法．给定一个任意拓扑结构三维人脸模型，通过文中方法可以全自动地驱动所给人脸模型做动画．     

交互的极线几何建模方法

讨论了一种基于图像的交互式几何建模方法，该方法利用手动方式标定模型的平行线、特征点，得到照相机参数，进而计算出模型的几何信息，并从图像中提取纹理，提出一种最优纹理选取算法，以确保拼接纹理的合理性，该算法主要应用于构造形状规则的模型，不需要知识照相机的内外参数，简便实用，实验结果表明，该方法在一定的场合下可以满足重建要求，重建出的三维模型具有照片真实感，并且能够实时漫游。     

三维人脸建模与应用

三维建模是计算机视觉和计算机图形学领域中一个基本的问题，人脸借助其特有的普遍性和易用性成为众多先进三维建模算法的实验平台。但是由于人脸的复杂性、易变性，建立逼真的三维人脸模型成为众多研究者挑战的课题。本文分析了三维人脸建模的研究内容和研究难点，总结了1990年以来出现的最新方法和进展，从三维数据的获取、标准三维人脸建模、特定三维人脸建模及应用等三维建模的几个主要环节进行了分类综述，重点介绍了一些主要算法的基本思路和最新进展，并对该领域的研究热点和方向作了较为详细的分析。     

三维人脸建模及在跨姿态人脸匹配中的有效性验证

针对现有三维人脸采集技术对采集场景存在诸多限制,提出了自由场景下基于多张图像的三维人脸建模技术,并对其进行了有效性验证。首先,提出一个姿态及深度值迭代计算模型,实现了特征点深度值的准确估计;然后,进行了基于多张图像的深度值融合及整体形状建模;最后,将深度迭代优化算法（IPDO）与目前最优的非线性最小二乘法（NLS1_SR）在Bosphorus Database数据集上进行了对比,建模精度提高了9%,所重建的三维人脸模型投影图像与二维图像具有较高的相似度。实验结果表明,在大姿态变化条件下,该识别算法借助三维信息相较于未借助的情况下,其识别率可以提高50%以上。     

基于物理模型的人脸表情动画技术研究

用计算机建立人脸表情动画是当前计算机图形学研究领域的一个富有挑战性的课题，该文在总结了国内外有关该课题研究方法的基础上，提出了一种基于物理模型的人脸表情画生成算法，并依该算法计和开发了一个实际的人脸表情动画系统HUFACE。该算法将人的脸部模拟为一个弹性体，为使计算简化，又将人脸表面依其生理特性分为八个子块，脸部表情所产生的五官动作模拟为弹性体的形变，并建立相应的弹性形变模型，当脸部表情引起脸部各子块形变时，每个子块上的各点将发生位移，于是利用该模型计算这些点的位移量，由此获得表情动画中的每一帧画面，由于脸部动作由该形变模型控制，且计算简单，速度快，因此不需存储表情动画中的各个画面，提高了系统的效率，实验结果表明，由HUFACE系统生成的人脸表情真实，自然。     

一种参数化的表情映射方法*

人脸表情细节的合成是生成高度真实感人脸动画的重要环节,传统的表情映射技术仅考虑了人脸特征点的位置变化,无法处理表情细节;最新的研究考虑了表情纹理细节的合成,但仅能根据已有的表情样本一对一地获取纹理细节,应用范围很有限。有效地结合小波金字塔分解和表情比例图像两种技术,提出了一种进行表情合成的新算法。该算法既可以映射表情纹理细节,又可以生成表情动画,且表情夸张程度可参数化地控制,算法简单有效。     

基于Candide-3算法的图像中面部替换技术

提出了一种基于CANDIDE-3算法的人脸替换算法,该算法使用CLM作为面部特征点定位算法,将2维的面部特征点和CANDIDE中3维的顶点相对应,建立相应的源人脸算法。根据面部特征点估计出头部姿态和表情相关参数,对源人脸进行方向和角度调整,通过颜色转移算法,将源人脸的色彩转换为目标人脸的色彩,然后利用图像融合算法进行融合。实验结果表明,本文的方法能够在图像和视频中进行有效的进行人脸替换。     

Feature-based design for heterogeneous objects

Heterogeneous objects are objects composed of different constituent materials. In these objects, multiple desirable properties from different constituent materials can be synthesized into one part. In order to obtain mass applications of such heterogeneous objects, efficient and effective design methodologies for heterogeneous objects are crucial.In this paper, we present a feature based design methodology to facilitate heterogeneous object design. Under this methodology, designers design heterogeneous objects using high-level design components that have engineering significance. These high level components are form features and material features. In this paper, we first examine the relationships between form features and material features in heterogeneous objects. We then propose three synthesized material features in accordance with our examination of these features. Based on these proposed features, we develop a feature based design methodology for heterogeneous objects. Two enabling methods for this design methodology, material heterogeneity specification within each feature and combination of these material features, are developed. A physics (diffusion) based B-spline method is developed to (1) allow design intent of material variation be explicitly captured by boundary conditions, (2) ensure smooth material variation across the feature volume. A novel method, direct face neighborhood alteration, is developed to increase the efficiency of combining heterogeneous material features.Examples of using this feature based design methodology for heterogeneous object design, such as a prosthesis design, are presented.     

Assembly features in modeling and planning

In recent years, features have been introduced in modeling and planning for manufacturing of parts. Such features combine geometric and functional information. Here it is shown that the feature concept is also useful in assembly modeling and planning. For modeling and planning of both single parts and assemblies, an integrated object-oriented product model is introduced. For specific assembly-related information, assembly features are used. Handling features contain information for handling components, connection features information on connections between components. A prototype modeling environment has been developed. The product model has been successfully verified within several analyses and planning modules, in particular stability analyses, grip planning, motion planning and assembly sequence planning. Altogether, feature-based product models for assembly can considerably help in both assembly modeling and planning, on the one hand by integrating single-part and assembly modeling, and on the other hand by integrating modeling and planning.     

语音识别中基于发音特征的声调集成算法

提出基于发音特征的声调建模改进方法,并将其用于随机段模型的一遍解码中。根据普通话的发音特点,确定了用于区别汉语元音、辅音信息的7种发音特征,并以此为目标值利用阶层式多层感知器计算语音信号属于发音特征的35个类别后验概率,将该概率作为发音特征与传统的韵律特征一起用于声调建模。根据随机段模型的解码特点,在两层剪枝后对保留下来的路径计算其声调模型概率得分,加权后加入路径总的概率得分中。在“863-test”测试集上进行的实验结果显示,使用了新的发音特征集合中声调模型的识别精度提高了3.11%;融入声调信息后随机段模型的字错误率从13.67%下降到12.74%。表明了将声调信息应用到随机段模型的可行性。     

Modeling plants with sensor data

Sensor data, typically images and laser data, are essential to modeling real plants. However, due to the complex geometry of the plants, the measurement data are generally limited, thereby bringing great difficulties in classifying and constructing plant organs, comprising leaves and branches. The paper presents an approach to modeling plants with the sensor data by detecting reliable sharp features, i.e. the leaf apexes of the plants with leaves and the branch tips of the plants without leaves, on volumes recovered from the raw data. The extracted features provide good estimations of correct positions of the organs. Thereafter, the leaves are reconstructed separately by simply fitting and optimizing a generic leaf model. One advantage of the method is that it involves limited manual intervention. For plants without leaves, we develop an efficient strategy for decomposition-based skeletonization by using the tip features to reconstruct the 3D models from noisy laser data. Experiments show that the sharp feature detection algorithm is effective, and the proposed plant modeling approach is competent in constructing realistic models with sensor data. Supported in part by the National Basic Research Program of China (Grant No. 2004CB318000), the National High-Tech Research & Development Program of China (Grant Nos. 2006AA01Z301, 2006AA01Z302, 2007AA01Z336), Key Grant Project of Chinese Ministry of Education (Grant No. 103001)     

MuscleBuilder: A modeling tool for human anatomy

A traditional multi-layered approach is adopted to human body modeling and deformation. The model is split into three general anatomical structures: the skeleton, musculature and skin. It is shown that each of these layers is modeled and deformed by using fast, procedural, ad-hoc methods that can painlessly be reimplemented. The modeling approach is generic enough to handle muscles of varying shape, size and characteristics and does not break in extreme skeleton poses. It is also described that the integrated MuscleBuilder system whose main features are: i) easy and quick creation of muscle deformation models; ii) automatic deformation of an overlying skin. It is shown that visually realistic results can be obtained at interactive frame rates with very little input from the designer.     

User Intention Modeling in Web Applications Using Data Mining

The problem of inferring a user's intentions in Machine–Human Interaction has been the key research issue for providing personalized experiences and services. In this paper, we propose novel approaches on modeling and inferring user's actions in a computer. Two linguistic features – keyword and concept features – are extracted from the semantic context for intention modeling. Concept features are the conceptual generalization of keywords. Association rule mining is used to find the proper concept of corresponding keyword. A modified Naïve Bayes classifier is used in our intention modeling. Experimental results have shown that our proposed approach achieved 84% average accuracy in predicting user's intention, which is close to the precision (92%) of human prediction.     

Interactive global and local deformations for virtual clay

Making virtual modeling as easy and intuitive as real-clay manipulation is still an unsolved problem. This paper takes a step in this direction: in addition to offering standard features such as addition and removal of material, it uses a new real-time plasticity model to let the user apply local and global deformations such as those made in real clay by pressing with a finger or bending a sculpture with one hand. Although not completely physically accurate, the model exhibits several important features of real clay, namely plasticity, mass conservation, and surface tension effects. These features make the model intuitive, since the user obtains the shapes he expects, as demonstrated by our results.     

Efficient Simplification Methods for Generating High Quality LODs of 3D Meshes

Two simplification algorithms are proposed for automatic decimation of polygonal models,and for generating their LODs.Each algorithm orders vertices according to their priority values and then removes them iteratively.For setting the priority value of each vertex,exploiting normal field of its one-ring neighborhood,we introduce a new measure of geometric fidelity that reflects well the local geometric features of the vertex.After a vertex is selected,using other measures of geometric distortion that are ...     

AML与面向对象建模

在面向对象建模中 ,状态机模型的继承是对象行为继承的重要组成部分 .为便于理解子类型的状态机模型与其父类型的状态机模型间的关系 ,我们研究了一种状态机模型及其继承的描述技术 ,从一定程度上解决了现有的状态机模型继承的描述技术中存在的一些问题 .本文在分析 AML中支持面向对象特征的主要设施的基础上 ,着重讨论了状态机模型的继承问题 .     

在I－DEAS系统上开发特征造型系统的研究

本文介绍在Ｉ－ＤＥＡＳＶ系统上开发特征造型系统的方法，详细讲述了特征造型系统的用户界面。结合实例，论述了特征识别与信息匹配的过程，形成以特征为基础的机械零件信息模型。在商品化实体造型系统上开发特征造型系统，可以充分利用实体造型软件，加速新系统的开发，节省资金。