草绘3维人体建模的模板形变方法

目的 采用草绘交互方式直接构造3维人体模型是当前人体建模研究的重要课题之一.提出一种草绘3维人体建模的模板形变方法.方法 针对输入的草图,首先,采用关节点定位方法获取草图中的人体关节点,根据人体结构学约束识别人体骨架结构,通过解析人体轮廓草图获取人体草图特征;其次,通过骨架模板和外观轮廓模板形变,将草图特征映射到3维人体模型,实现3维人体建模.结果 草图解析方法能有效提取草图特征,通过模板形变方法生成3维人体模型,并在模型上保持草图特征;能适应不同用户的绘制习惯,且生成的3维人体模型可用于人体动画设计.结论 提出一种草绘3维人体建模的模板形变方法,支持用户采用草绘方式进行3维人体模型设计,方法具有良好的用户适应性,对3维动画创作具有重要意义.     

Parameterization and parametric design of mannequins

This paper presents a novel feature based parameterization approach of human bodies from the unorganized cloud points and the parametric design method for generating new models based on the parameterization. The parameterization consists of two phases. First, the semantic feature extraction technique is applied to construct the feature wireframe of a human body from laser scanned 3D unorganized points. Secondly, the symmetric detail mesh surface of the human body is modeled. Gregory patches are utilized to generate G¹ continuous mesh surface interpolating the curves on feature wireframe. After that, a voxel-based algorithm adds details on the smooth G¹ continuous surface by the cloud points. Finally, the mesh surface is adjusted to become symmetric. Compared to other template fitting based approaches, the parameterization approach introduced in this paper is more efficient. The parametric design approach synthesizes parameterized sample models to a new human body according to user input sizing dimensions. It is based on a numerical optimization process. The strategy of choosing samples for synthesis is also introduced. Human bodies according to a wide range of dimensions can be generated by our approach. Different from the mathematical interpolation function based human body synthesis methods, the models generated in our method have the approximation errors minimized. All mannequins constructed by our approach have consistent feature patches, which benefits the design automation of customized clothes around human bodies a lot.     

基于语义参数的三维复杂模型变形方法研究

针对含有自由曲面的三维模型不易变形的问题,提出一种基于语义参数的三维复杂模型变形方法,旨在实现三维模型的快速设计。该方法利用变形控制点作为模型变形的基本元素,通过设置语义参数实现层次化变形：以变形控制点带动分组部件变形,以分组部件促进三维模型整体变形。首先,采用Hausdorff测距法和均值聚类法,将已分组的电动车的自由曲面替换成二次曲面;然后,根据变形控制点间及与部件顶点的关系,计算各分组部件内部和外部的约束条件;最后,编辑修改定义在变形控制点上的语义参数,实现模型自定义变形。以电动车三维模型验证实验,结果表明,本方法支持用户通过修改少量语义参数对模型变形,有效提升三维模型个性化设计的效率。     

服装CAD中三维人体模型的参数化研究

针对三角网格曲面表示的3D人体模型缺少语义信息，提出一种3D人体模型的参数化方法：首先通过三角面片求交的采样策略得到采样点，然后使用B样条曲线构造人体轮廓线，最后由用户交互得到3D人体模型的参数化信息，建立3D人体模型的参数化模板．这样，在参数化人体模型模板的基础上，可以根据用户所输入的特定人体参数信息，动态地调整轮廓线和重建人体模型体表曲面，快速生成逼真的3D人体模型，从而满足服装CAD中根据用户身材尺寸大小定制服装的应用需求．     

基于尺寸建立个性化人体模型的方法

近年来,人体模型定制已成为计算机图形学领域的重要研究课题之一。文中提出一种基于少量人体尺寸生成个性化人体模型的方法——分块优化法。首先,根据MPI人体扫描模型数据库获得人体外形形变参数与尺寸参数,采用线性相关分析方法实现由若干尺寸恢复完整人体尺寸集。其次,通过参数优化的线性回归方法分析各部位三维人体外形参数与二维尺寸数据之间的关系,并根据输入尺寸对人体模型进行进一步精调。实验表明,上述方法能够生成准确反映人体外形的人体模型。     

数据库与Pro/Engineer二次开发相结合在产品开发中的应用

现有三维CAD软件中,Pro/Engineer有全相关性、单一数据库、并发管理等特点。但Pro/Engineer中单一数据库的管理方式对普通用户来说是封装的。该文在研究内部装配图树状结构的实现方法基础上,在SQLServer中建立了新的装配树结构。通过SQLServer的统一管理,实现了零件的几何模型与零件设计过程信息的集成。能方便地实现模型的自动生成以及设计历史信息的查看,实现了设计参数和设计结果的版本管理。有利于缩短产品研发周期,提高研发效率,并方便企业积累宝贵的知识财富。     

M2S maps: supporting real-world navigation with mobile VR

Mobile devices are becoming increasingly integrated into our society. In addition to entertaining people with applications like pervasive games, mobile devices can also help to address cognitive challenges people face in the real world. This paper, by drawing on research findings from cognitive psychology and geography, explores a design to use mobile VR to help people overcome one cognitive barrier in navigation, which is to establish the correspondence between 2D spatial information found in maps and 3D entities they perceive from the real world. The design offers users multi-format, multi-scale, and semantic (M²S) maps, ranging from 2D maps to 3D immersive environments, and helps users to connect 2D maps to the real world through 3D environments which are equipped with semantic representation and animation techniques. Consequently, users can apply various kinds of spatial knowledge, 2D or 3D, in understanding the real world as well as assisting in navigation. This research enhances the design repertoire of mobile VR, and suggests a way to integrate virtual environments into people’s real-world life by examining the cognitive implications of 3D models on users’ activities.     

A model-based approach for estimating human 3D poses in static images

Estimating human body poses in static images is important for many image understanding applications including semantic content extraction and image database query and retrieval. This problem is challenging due to the presence of clutter in the image, ambiguities in image observation, unknown human image boundary, and high-dimensional state space due to the complex articulated structure of the human body. Human pose estimation can be made more robust by integrating the detection of body components such as face and limbs, with the highly constrained structure of the articulated body. In this paper, a data-driven approach based on Markov chain Monte Carlo (DD-MCMC) is used, where component detection results generate state proposals for 3D pose estimation. To translate these observations into pose hypotheses, we introduce the use of "proposal maps," an efficient way of consolidating the evidence and generating 3D pose candidates during the MCMC search. Experimental results on a set of test images show that the method is able to estimate the human pose in static images of real scenes.     

3D Body Shapes Estimation from Dressed‐Human Silhouettes

Estimation of 3D body shapes from dressed‐human photos is an important but challenging problem in virtual fitting. We propose a novel automatic framework to efficiently estimate 3D body shapes under clothes. We construct a database of 3D naked and dressed body pairs, based on which we learn how to predict 3D positions of body landmarks (which further constrain a parametric human body model) automatically according to dressed‐human silhouettes. Critical vertices are selected on 3D registered human bodies as landmarks to represent body shapes, so as to avoid the time‐consuming vertices correspondences finding process for parametric body reconstruction. Our method can estimate 3D body shapes from dressed‐human silhouettes within 4 seconds, while the fastest method reported previously need 1 minute. In addition, our estimation error is within the size tolerance for clothing industry. We dress 6042 naked bodies with 3 sets of common clothes by physically based cloth simulation technique. To the best of our knowledge, We are the first to construct such a database containing 3D naked and dressed body pairs and our database may contribute to the areas of human body shapes estimation and cloth simulation.     

A sketch-based approach to human body modelling

In this paper, we present a new approach and a novel interface, Virtual Human Sketcher (VHS), which enables those who can draw, to sketch-out various human body models. Our approach supports freehand drawing input and a “Stick Figure→Fleshing-out→Skin Mapping” modelling pipeline. Following this pipeline, a stick figure is drawn first to illustrate a figure pose, which is automatically reconstructed into 3D through a “Multi-layered Back-Front Ambiguity Clarifier”. It is then fleshed-out with freehand body contours. A “Creative Model-based Method” is developed for interpreting the body size, shape, and fat distribution of the sketched figure and transferring it into a 3D human body through graphical comparisons and generic model morphing. The generic model is encapsulated with three distinct layers: skeleton, fat tissue, and skin. It can be transformed sequentially through rigid morphing, fatness morphing, and surface matching to match the 2D figure sketch. The initial resulting 3D body model can be incrementally modified through sketching directly on the 3D model. In addition, this body surface can be mapped onto a series of posed stick figures to be interpolated as a 3D character animation. VHS has been tested by various users on Tablet PC. After minimal training, even a beginner can create plausible human bodies and animate them within minutes.     

基于局部姿态先验的深度图像3D人体运动捕获方法

提出一种基于局部姿态先验的从深度图像中实时在线捕获3D人体运动的方法.关键思路是根据从捕获的深度图像中自动提取具有语义信息的虚拟稀疏3D标记点,从事先建立的异构3D人体姿态数据库中快速检索K个姿态近邻并构建局部姿态先验模型,通过迭代优化求解最大后验概率,实时地在线重建3D人体姿态序列.实验结果表明,该方法能够实时跟踪重建出稳定、准确的3D人体运动姿态序列,并且只需经过个体化人体参数自动标定过程,可跟踪身材尺寸差异较大的不同表演者;帧率约25fps.因此,所提方法可应用于3D游戏/电影制作、人机交互控制等领域.     

Building a user-centered semantic hierarchy in image databases

Recent development in the field of digital media technology has resulted in the generation of a huge number of images. Consequently, content-based image retrieval has emerged as an important area in multimedia computing. Research in human perception of image content suggests that the semantic cues play an important role in image retrieval. In this paper, we present a new paradigm to establish the semantics in image databases based on multi-user relevance feedback. Relevance feedback mechanism is one way to incorporate the users’ perception during image retrieval. By treating each feedback as a weak classifier and combining them together, we are able to capture the categories in the users’ mind and build a user-centered semantic hierarchy in the database to support semantic browsing and searching. We present an image retrieval system based on a city-landscape image database comprising of 3,009 images. We also compare our approach with other typical methods to organize an image database. Superior results have been achieved by the proposed framework.     

From laser-scanned data to feature human model: a system based on fuzzy logic concept

This paper describes the development of a prototype system using fuzzy logic concept for constructing a feature human model, which is to be stored in a 3D digital human model database. In our approach, the feature human model is constructed by unorganized cloud points obtained from 3D laser scanners. Firstly, noisy points are removed, and the orientation of the human model is adjusted; secondly, a feature based mesh generation algorithm is applied on the cloud points to construct the mesh surface of a human model; lastly, semantic features of the human model are extracted from the mesh surface. Compared with earlier approach, our method strongly preserves the topology of a human model; more details can be constructed; and both the robustness and the efficiency of the algorithm are improved. At the end of the paper, in order to demonstrate the functionality of feature human models, potential applications are given.     

Automatic Lighting Design using a Perceptual Quality Metric

Lighting has a crucial impact on the appearance of 3D objects and on the ability of an image to communicate information about a 3D scene to a human observer. This paper presents a new automatic lighting design approach for comprehensible rendering of 3D objects. Given a geometric model of a 3D object or scene, the material properties of the surfaces in the model, and the desired viewing parameters, our approach automatically determines the values of various lighting parameters by optimizing a perception-based image quality objective function. This objective function is designed to quantify the extent to which an image of a 3D scene succeeds in communicating scene information, such as the 3D shapes of the objects, fine geometric details, and the spatial relationships between the objects.
Our results demonstrate that the proposed approach is an effective lighting design tool, suitable for users without expertise or knowledge in visual perception or in lighting design.     

Constructing 3D human model from front and side images

Constructing 3D human model from 2D images provides a cost-effective approach to visualize digital human in virtual environment. This paper presents a systematic approach for constructing 3D human model using the front and side images of a person. The silhouettes of human body are first detected and the feature points on the silhouettes are subsequently identified. The feature points are further used to obtain the body dimensions that are necessary for identifying a template 3D human model. The shape of the template human model can be modified by the free-form deformation method. Moreover, the proposed approach has been applied for constructing the 3D human models of 30 subjects. The comparisons between the constructed 3D models and the 3D scanning models of the 30 subjects indicate that the proposed system is very effective and robust.     

NAVIG: augmented reality guidance system for the visually impaired

Navigating complex routes and finding objects of interest are challenging tasks for the visually impaired. The project NAVIG (Navigation Assisted by artificial VIsion and GNSS) is directed toward increasing personal autonomy via a virtual augmented reality system. The system integrates an adapted geographic information system with different classes of objects useful for improving route selection and guidance. The database also includes models of important geolocated objects that may be detected by real-time embedded vision algorithms. Object localization (relative to the user) may serve both global positioning and sensorimotor actions such as heading, grasping, or piloting. The user is guided to his desired destination through spatialized semantic audio rendering, always maintained in the head-centered reference frame. This paper presents the overall project design and architecture of the NAVIG system. In addition, details of a new type of detection and localization device are presented. This approach combines a bio-inspired vision system that can recognize and locate objects very quickly and a 3D sound rendering system that is able to perceptually position a sound at the location of the recognized object. This system was developed in relation to guidance directives developed through participative design with potential users and educators for the visually impaired.     

异常步态3维人体建模和可变视角识别

目的 运用视觉和机器学习方法对步态进行研究已成为当前热点,但多集中在身份识别领域。本文从不同的视角对其进行研究,探讨一种基于点云数据和人体语义特征模型的异常步态3维人体建模和可变视角识别方法。方法 运用非刚性变形和蒙皮方法,构建基于形体和姿态语义特征的参数化3维人体模型;以红外结构光传感器获取的人体异常步态点云数据为观测目标,构建其对应形体和姿态特征的3维人体模型。通过ConvGRU（convolution gated necurrent unit）卷积循环神经网络来提取其投影深度图像的时空特征,并将样本划分为正样本、负样本和自身样本三元组,对异常步态分类器进行训练,以提高分类器对细小差异的鉴别能力。同时对异常步态数据获取难度大和训练视角少的问题,提出了一种基于形体、姿态和视角变换的训练样本扩充方法,以提高模型在面对视角变化时的泛化能力。结果 使用CSU（Central South University）3维异常步态数据库和DHA（depth-included human action video）深度人体行为数据库进行实验,并对比了不同异常步态或行为识别方法的效果。结果表明,本文方法在CSU异常步态库实验中,0°、45°和90°视角下对异常步态的综合检测识别率达到了96.6%,特别是在90°到0°交叉和变换视角实验中,比使用DMHI（difference motion history image）和DMM-CNN（depth motion map-convolutional neural network）等步态动作特征要高出25%以上。在DHA深度人体运动数据库实验中,本文方法识别率接近98%,比DMM等相关算法高出2%~3%。结论 提出的3维异常步态识别方法综合了3维人体先验知识、循环卷积网络的时空特性和虚拟视角样本合成方法的优点,不仅能提高异常步态在面对视角变换时的识别准确性,同时也为3维异常步态检测和识别提供一种新思路。     

基于三维语义空间的色彩设计方法研究

从色彩的语义空间理论出发,研究了三维语义空间的构建原理,建立了抽象语言和色彩关联的三维风格语义空间,并在此基础上构建了基于三维语义空间的色彩设计方法模型,实现了基于三维语义空间的色彩设计的具体技术路线,以辅助用户能够快速的依据语义匹配原则进行色彩设计。最后,通过产品色彩设计实例验证了该方法在色彩设计中的应用。     

基于实例和约束的三维场景概念设计和系统实现

3D场景设计是VR建模中最重要也最耗人力的工作之一,如何解决该问题是一项重要的课题.本文提出一种新的基于实例和约束的三维场景概念设计方法.首先,根据所获取的场景实例中所蕴涵的不同层次的语义信息,对其进行场景元素过滤和场景语义标注,并由此构建三维场景实例库.相应地,对场景中可能出现的元素类别进行分类和语义标注,并建立场景元素库.接着,应用基于实例的方法,并结合场景设计过程中所涉及到的知识(约束),给出三维场景概念设计的一般方法;最后以一个实例对该方法做进一步的说明.研究表明,该方法符合人们对场景设计的一般过程.此外,由于场景实例和场景元素具有丰富的语义信息,使得所生成的场景除了常规的可视效果,还可以直接应用于虚拟现实环境以及三维动画等数字内容制作中.