汉语复韵母的三维动态视位模型

根据汉语拼音的构成及发音时的唇动特点,对汉语复韵母进行了分类,提出了一套适合各类汉语复韵母发音特点的动态视位模型,再利用Directx9．0进行图形的变换及渲染,使三维人脸口形的变换过程更加丰富自然．较传统的二维人脸动画更加灵活、生动,可广泛应用于三维游戏中角色语音动画的制作、虚拟主持人配音等方面。     

一种对应用透明跨Java和C++平台转换动画系统

下一代智能手机的图形用户界面追求崭新的用户体验，在各种应用软件(窗口)打开、关闭和切换时．显示各式各样给人耳目一新感觉的动画。同时，这个图形用户界面转换动画系统必须既支持大量现存的在本地C 平台开发的应用软件，又支持将来大量在Java平台开发的应用软件，即“跨Java，本地C 平台990同时，为节省开发应用软件的难度和精力，不能让已开发的应用软件做改动；将开发的应用软件也不用知道和实现转换动画功能．这个系统自动赋予所有应用软件这个功能，即“对应用软件透明”。这里成功实现了这个关键难点系统。     

Analysis and Reproduction of Facial Expressions for Realistic Communicating Clones

This paper presents a novel view-based approach to quantify and reproduce facial expressions, by systematically exploiting the degrees of freedom allowed by a realistic face model. This approach embeds efficient mesh morphing and texture animations to synthesize facial expressions. We suggest using eigenfeatures, built from synthetic images, and designing an estimator to interpret the responses of the eigenfeatures on a facial expression in terms of animation parameters.     

Expression transfer for facial sketch animation

This paper presents a hierarchical animation method for transferring facial expressions extracted from a performance video to different facial sketches. Without any expression example obtained from target faces, our approach can transfer expressions by motion retargetting to facial sketches. However, in practical applications, the image noise in each frame will reduce the feature extraction accuracy from source faces. And the shape difference between source and target faces will influence the animation quality for representing expressions. To solve these difficulties, we propose a robust neighbor-expression transfer (NET) model, which aims at modeling the spatial relations among sparse facial features. By learning expression behaviors from neighbor face examples, the NET model can reconstruct facial expressions from noisy signals. Based on the NET model, we present a hierarchical method to animate facial sketches. The motion vectors on the source face are adjusted from coarse to fine on the target face. Accordingly, the animation results are generated to replicate source expressions. Experimental results demonstrate that the proposed method can effectively and robustly transfer expressions by noisy animation signals.     

基于互联网的快速3D户外动画创作展示平台

为实现快速的3D交互展示内容制作,利用WebGL图像引擎设计了基于互联网的快速3D内容展示创作平台。互联网创作平台的主要3D功能包括多媒体内容导入和关联、3D模型配置、3D动画自动生成、画笔地图绘制等。互联网创作平台利用WEB服务器和PHP,支持瘦客户端的3D内容创作和HTML应用生成。经本项目联合参与单位的实际应用,交互动画设计师在没有程序员参与的条件下能够顺利完成交互3D内容创作和3D动画内容快速生成。本创作平台为互联网3D展览展示提供了简便的设计方案和新的设计模式。最后,在调整本创作平台的部分功能后能够满足城市紧急救援方案3D交互推演和3D动画生成、战术方案3D交互推演和3D动画生成、互联网3D虚拟展馆制作、室内外建筑展示内容制作。     

Audiovisual speech processing

We have reported activities in audiovisual speech processing, with emphasis on lip reading and lip synchronization. These research results have shown that, with lip reading, it is possible to enhance the reliability of audio speech recognition, which may result in a computer that can truly understand the user via hand-free natural spoken language even in a very noisy environments. Similarly, with lip synchronization, it is possible to render realistic talking heads with lip movements synchronized with the voice, which is very useful for human-computer interactions. We envision that in the near future, advancement in audiovisual speech processing will greatly increase the usability of computers. Once that happens, the cameras and the microphone may replace the keyboard and the mouse as better mechanisms for human-computer interaction     

An interactive 3D video system for human facial reconstruction and expression modeling

A 3D facial reconstruction and expression modeling system which creates 3D video sequences of test subjects and facilitates interactive generation of novel facial expressions is described. Dynamic 3D video sequences are generated using computational binocular stereo matching with active illumination and are used for interactive expression modeling. An individual’s 3D video set is annotated with control points associated with face subregions. Dragging a control point updates texture and depth in only the associated subregion so that the user generates new composite expressions unseen in the original source video sequences. Such an interactive manipulation of dynamic 3D face reconstructions requires as little preparation on the test subject as possible. Dense depth data combined with video-based texture results in realistic and convincing facial animations, a feature lacking in conventional marker-based motion capture systems.     

XYZ视频图像压缩编码

本文讨论并实现了基于3-D DCT的XYZ视频图像压缩编码方法.该方法不涉及运动估计和运动补偿,复杂度低.实验结果表明,这种算法能快速地、高质量地压缩视频图像,是一种很有潜力的视频编码方法.     

Kerberos: an authentication service for computer networks

When using authentication based on cryptography, an attacker listening to the network gains no information that would enable it to falsely claim another's identity. Kerberos is the most commonly used example of this type of authentication technology. The authors concentrate on authentication for real-time, interactive services that are offered on computer networks. They use the term real-time loosely to mean that a client process is waiting for a response to a query or command so that it can display the results to the user, or otherwise continue performing its intended function. This class of services includes remote login, file system reads and writes, and information retrieval for applications like Mosaic     

Face and 2-D mesh animation in MPEG-4

This paper presents an overview of some of the synthetic visual objects supported by MPEG-4 version-1, namely animated faces and animated arbitrary 2D uniform and Delaunay meshes. We discuss both specification and compression of face animation and 2D-mesh animation in MPEG-4. Face animation allows to animate a proprietary face model or a face model downloaded to the decoder. We also address integration of the face animation tool with the text-to-speech interface (TTSI), so that face animation can be driven by text input.     

The Outsourcing of “Creative” Work and the Limits of Capability: The Case of the Philippines’ Animation Industry

The animation industry, like many information-technology-enabled services sectors, has been of interest to many developing countries interested in developing services outsourcing industries. We analyze the case of the Philippines’ animation industry. This paper investigates the outsourcing process in animation and the nature of capabilities within that, with the goal of contributing to a more general understanding of services outsourcing. We examine the industry's history, interview data with industry participants, and secondary data. We find that strong labor force skills have been central to capabilities rather than organizational abilities. Outsourcing of production takes place only so far as the work is codifiable, i.e., instructions and interface documents, or that tacit interactions between providers and their clients can facilitate the transfer of the work. This makes it extremely difficult for the industry to move into higher value work such as the conceptualization stage of product development. A major downturn in the past and technological automation shows that the industry has not been sustainable in the face of external influences, but stronger policies and company strategies that support investments in upgrading capabilities and workforce skills could ameliorate some of these effects. A strong foreign presence has also been found to support the development of the industry.      

Creating a multiuser 3-D virtual environment

For many years online text chat software such as ICQ has been used as a means of multiuser interaction. As higher bandwidth is available, multipoint videoconferencing systems such as NetMeeting or CUseeMe that allow people from different geographical locations to see and talk to each other are becoming popular. However, these videoconferencing systems lack the sense of immersion because each participant sees other participants in separate windows, and it is often difficult to tell who is talking to whom. Based on user study, Argyle and Dean (1965) suggested that during face-to-face communication people vary physical proximity, eye contact, and other behaviors to optimize an overall level of intimacy. In addition, Tang and Isaacs (1993) found that gaze awareness is important because participants can use the visual cue to determine when another participant is paying attention to them. These studies suggest that a more immersive way of multiuser communication is to connect the users in a three-dimensional (3-D) virtual environment so that users feel that they are communicating face to face. Moving from a text-based chat room environment to a 3-D environment creates new challenges in several areas such as computer animation, signal processing, and computer vision. We introduce immersive interactive technologies used in multiuser 3-D virtual environments. We also survey existing systems     

Animated Talking Head with Personalized 3D Head Model

Natural Human-Computer Interface requires integration of realistic audio and visual information for perception and display. An example of such an interface is an animated talking head displayed on the computer screen in the form of a human-like computer agent. This system converts text to acoustic speech with synchronized animation of mouth movements. The talking head is based on a generic 3D human head model, but to improve realism, natural looking personalized models are necessary. In this paper, we report a semi-automatic method for adapting a generic head model to 3D range data of a human head obtained from a 3D-laser range scanner. This personalized model is incorporated into the talking head system. With texture mapping, the personalized model offers a more natural and realistic look than the generic model. The model created with the proposed method compares favorable to generic models.     

融入唇语识别技术提升人脸识别安全性的研究

为了解决人脸识别的安全性问题,提高对恶意攻击人脸识别系统的安全防护,使人脸识别技术能够获得更广泛应用,本文提出了在人脸识别技术上融入一种基于深度神经网络的唇语识别技术的系统。与现有的唇语识别技术不同的是,该系统主要是识别用户的唇动习惯。运用本系统,用户在进行人脸识别的同时可按照检测方的提示,读出相应的内容,并在对用户的人脸进行验证的过程中,对用户通过唇动说出的内容分别实现唇动识别、比对,从而有效地提升人脸识别的安全性水平。实验结果表明,在故意针对人脸识别系统的攻击中,融入本技术的系统有更好的识别准确率。     

Model-based approach to control over concurrency in interactive CSCW applications. Application to telemedicine

The aim of this paper is to present a model-based approach (Petri Net) to control over concurrency and solve the problem of event collision in cscw interactive software applications. Theoretical background is provided and experimental results are illustrated through telemedicine applications. From the user viewpoint, progress is achieved: the natural use of these applications is strongly enhanced and the reliability level is increased. This new approach may be applied to a large set of interactive collaborative applications as well as in the control of user interfaces. It led to an international patent application n^o pct/fr02/04472 entitled: “Management procedure for synchronous collaborative session integrated in a distributed supervisored application”.     

基于对象的新型激光动画表演文件格式设计

激光动画表演是新型激光显示技术的一种表现形式，广泛应用于游乐、娱乐和信息广告业。本文提出一种基于对象的新型激光动画表演文件格式设计，它包括轮廓对象(contour)、帧对象(picture)、动画对象(animation)和节目对象(film)。基于对象技术，在激光表演节目内部采用时间、空间、声音和动画属性来记录激光动画演示中所需要的控制信息。     

Talking heads

My colleagues and I are developing a system that emulates these popular everyday communication styles. Through the UCI's (University of California at Irvine) Technology Outreach Program, this project is producing a system that not only observes and listens to the talking head of the operator, but also provides a talking head on-screen for the user to hear and watch. Our project specifically uses multimedia to address an immediate and practical goal-better speech recognition. Although implementing “natural” multimedia is a key goal of this project, comfortable use in itself is important, even if only as a motivating or marketing attribute. However, where increased efficiency does not result from using more natural and comfortable procedures, the situation may still improve if the computer begins to act more like a human team-mate     

Multimedia via Inmarsat

Inmarsat's provision of multimedia services over its current satellites, as well as over a possible new generation of satellites, will enable technologies for support of higher data rates for mobile terminals. Inmarsat's next-generation satellite communications system will extend current capabilities by supporting fully interactive multimedia communications to small portable user terminals     

一种基于共振峰分析的语音驱动人脸动画方法

快速、高效地实现语音驱动下的唇形自动合成,以及优化语音与唇动的同步是语音驱动人脸动画的重点。提出了一种基于共振峰分析的语音驱动人脸动画的方法。对语音信号进行加窗分帧,DFT变换,再对短时音频信号的频谱进行第一、第二共振峰分析,将分析结果映射为一组控制序列,并对控制序列进行去奇异点等后处理。设定三维人脸模型的动态基本口形,以定时方式将控制序列导入模型,完成人脸动画驱动。实验结果表明,该方法简单快速,有效实现了语音和唇形的同步,动画效果连贯自然,可广泛用于各类虚拟角色的配音,缩短虚拟人物的制作周期。