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.     

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.     

Realistic wrinkle generation for 3D face modeling based on automatically extracted curves and improved shape control functions

Realistic wrinkles are extremely important for enhancing the realism of three-dimensional (3D) virtual face models. This paper proposes an approach for generating realistic wrinkle on a 3D face model based on a face image. It includes image preprocessing, automatically extracting wrinkle curves and generating wrinkles on a 3D surface. For image preprocessing, we use a linear transform method to conduct a grayscale conversion. We then use a transfinite-pixel neighborhood averaging method to reduce the noise, and a high pass filter to sharpen the image. For the automatic extraction of wrinkle curves, an improved Canny edge detector is employed. For wrinkle generation on a 3D surface, a number of novel techniques are employed. Some feature points are firstly defined both on the face image and on the 3D face model. By aligning these feature points, the extracted wrinkle curves are then projected onto the 3D face model. Finally, three shape control functions are used to produce more realistic properties of the 3D wrinkles. They are the proposed cross-section shape control function (CSCF) to determine the cross-section shape and size, the depth attenuation function (DAF) and the width attenuation function (WAF) to control the depth and width amplitude variations of the wrinkles, respectively. For better results, an adaptive subdivision is applied to the predefined influence region to adjust the resolution around the wrinkle mesh. The experiment results of applying this method to individualized 3D human models demonstrate the ability of our method to generate more natural wrinkles.     

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。     

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。     

个性化三维人体模型快速建模方法

采用模型重用的思想,通过输入21个人体测量学参数对标准人体模型进行编辑,实时获得相应体型的个性化三维人体模型．该方法使得编辑过程能够实时完成;生成的人体模型可以方便地驱动;精选的21个人体测量学参数覆盖了人体各处的细节,能够比较完整地描述人体的外形特征,满足对人体模型个性化的需求．     

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．     

基于二维点云图的三维人体建模方法

近年来基于二维图像的三维建模方法取得了快速发展,但就人体建模而言,由于摄像头采集到的二维人体图像包含衣物、发丝等大量的纹理信息,而像虚拟试衣等相关应用需要将人体表面的衣物褶皱等纹理信息去除,同时考虑到裸体数据采集侵犯了用户的隐私,因此提出一种基于二维点云图像到三维人体模型的新型建模方法。与摄像机等辅助设备进行二维图片数据集的采集不同,该算法的输入是由三维人体点云模型以顶点模式绘制的二维点云渲染图。主要工作是建立一个由二维点云图和相应的人体黑白二值图构成的数据集,并训练一个由前者生成后者的生成对抗网络模型。该模型将二维点云图转化为相应的黑白二值图。将该二值图输入一个训练好的卷积神经网络,用于评估二维图像到三维人体模型构建的效果。考虑到由不完整三维点云数据重建完整的三维人体网格模型是一个具有挑战性的问题,因此通过模拟二维点云的破损和残缺状态,使得算法能够处理不完整的二维点云图。大量的实验结果表明,该方法重建出的三维人体模型能够有效实现视觉上的真实感,为了对重建后的精度进行定量的分析,选取了人体特征中具有代表性的腰围特征作为误差评估;为了增加三维人体模型库中人体形态的多样性,还引入一种便捷的三维人体模型数据增强技术。实验结果表明,该算法只需要输入一张二维点云图像,就能快速创建出相应的数字化人体模型。     

面向人机工程的三维人体尺度空间模型

建立三维人体模型以及分析人体肢体可及空间，对于人机工程设计、人体关节运动控制和人体模型的碰撞检测研究都具有重要的意义。然而多关节的真实人体可及空间难以描述，目前没有很好地解决。该文在研究人机工程仿真的基础上，建立了逼真三维人体模型，探讨了多关节且关节转角受限制的三维人体尺度空间模型，并应用虚拟现实建模语言(VRML)对上述模型和方法进行了验证。结果表明：该方法计算量小，生成的空间模型直观准确。     

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.     

Observation-oriented silhouette-aware fast full body tracking with Kinect

We present a novel approach to track full human body mesh with a single depth camera, e.g. Microsoft Kinect, using a template body model. The proposed observation-oriented tracking mainly targets at fitting the body mesh silhouette to the 2D user boundary in video stream by deforming the body. It is fast to be integrated into real-time or interactive applications, which is impossible with traditional iterative optimization based approaches. Our method is a composite of two main stages: user-specific body shape estimation and on-line body tracking. We first develop a novel method to fit a 3D morphable human model to the actual body shape of the user in front of the depth camera. A strategy, making use of two constrains, i.e. point clouds from depth images and correspondence between foreground user mask contour and the boundary of projected body model, is designed. On-line tracking is made possible in successive steps. At each frame, the joint angles of template skeleton are optimized towards the captured Kinect skeleton. Then, the aforementioned contour correspondence is adopted to adjust the projected body model vertices towards the contour points of foreground user mask, using a Laplacian deformation technique. Experimental results show that our method achieves fast and high quality tracking. We also show that the proposed method is benefit to three applications: virtual try-on, full human body scanning and applications in manufacturing systems.     

基于深度扫描仪的高辨识度三维人体模型重建方法

3D 照相打印馆人像的打印质量取决于3D 扫描获得的三维人体模型的辨识度。然 而,由于现有3D 人体扫描仪价格昂贵、操作复杂等原因,使得3D 人像打印成本高、耗时长和 打印精度较低。针对这些缺点提出一种基于深度扫描仪重建高辨识度三维人体模型方法。利用 多组深度扫描仪分工协作、优势互补,分别获取高辨识度的人体面部五官点云数据,上半身与 全身表面轮廓点云数据。然后,通过引入特征点和改进的最近点迭代法将采集到的三组点云数 据进行对齐、替换、拼接,将拼接后的无拓扑关系的点云数据进行曲面重构即可获得高辨识度 的三维人体模型。该方法的扫描时间较短,以较低的成本构建了具有高辨识度的三维人像模型。     

基于特征线的三维服装部件参数化造型

基于特征线的服装三维造型方法有诸多优点,但是现有服装模型并不能很好地支持服装参数化设计.为此将参数化造型方法引入三维服装部件造型中,以得到参数化的服装部件.基于光顺人体模型,依据服装部件特点设计服装特征线,将特征线分为截面环和轮廓线,依次通过截面环和轮廓线的生成与调整、特征线综合调整和特征线添加约束3个步骤,得到服装特征线框架;并对该框架利用曲面插值方法得到服装曲面模型.实例结果表明,文中方法功能强大、方便灵活.     

一种单幅图像及其辅助曲线的三维建模方法

针对单幅图像的三维建模存在对用户的建模意图还原度不高、模型不够真实的问题,提出了一种通过构造曲线和辅助曲线来创建三维模型的方法.离散图像并补全构造曲线,为每条构造曲线添加辅助曲线.寻找离散后构造曲线间的对称关系并设置对称平面,计算曲线在三维空间中的位置.移动、旋转辅助曲线,得到三维模型,根据特征点位置和类型组合三维模型.实验结果表明,该方法得到的三维模型较符合用户的建模意图,同时具有算法简单、建模速度快、实用性强等特点.     

任意姿态虚拟人网格模型骨骼提取算法

人体骨骼动画技术是虚拟人物建模中的研究重点。在现有人体骨骼动画的制作过程中,动画师必需手工标定人体各主要关节点位置及人体骨架每一关键帧的姿态,工作量巨大。因此提出一种自动提取人体任意姿态网格模型骨架结构的方法。该方法首先利用模型各顶点间测地距离的几何关系自动识别人体位于四肢和头顶末端的5个特征点,再以特征点为起点生成等测地距离曲线族,利用等测地距离曲线将人体四肢和躯干区分开来,将这些相邻等测地线中心连接起来生成5条骨骼中心线,最后在中心线上根据中心夹角极小值及等测地距离曲线似圆率来确定人体关节的确切位置。实验结果表明,该算法能适应不同姿态的人体模型,计算结果准确性高,能完全自动实现关节点定位和骨骼提取。     

Exemplar-based statistical model for semantic parametric design of human body

This paper presents an exemplar-based method to provide intuitive way for users to generate 3D human body shape from semantic parameters. In our approach, human models and their semantic parameters are correlated as a single linear system of equations. When users input a new set of semantic parameters, a new 3D human body will be synthesized from the exemplar human bodies in the database. This approach involves simpler computation compared to non-linear methods while maintaining quality outputs. A semantic parametric design in interactive speed can be implemented easily. Furthermore, a new method is developed to quickly predict whether the parameter values is reasonable or not, with the training models in the human body database. The reconstructed human bodies in this way will all have the same topology (i.e., mesh connectivity), which facilitates the freeform design automation of human-centric products.     

Realistic modeling and animation of human body based on scanned data

In this paper we propose a novel method for building animation model of real human body from surface scanned data. The human model is represented by a triangular mesh and described as a layered geometric model. The model consists of two layers: the control skeleton generating body animation from motion capture data, and the simplified surface model providing an efficient representation of the skin surface shape. The skeleton is generated automatically from surface scanned data using the feature extraction, and then a point-to-line mapping is used to map the surface model onto the underlying skeleton. The resulting model enables real-time and smooth animation by manipulation of the skeleton while maintaining the surface detail. Compared with earlier approach, the principal advantages of our approach are the automated generation of body control skeletons from the scanned data for real-time animation, and the automatic mapping and animation of the captured human surface shape. The human model constructed in this work can be used for applications of ergonomic design,garment CAD, real-time simulating humans in virtual reality environment and so on.     

Modeling of female human body shapes for apparel design based on cross mean sets

This paper is concerned with a method to build prototypes of human bodies that can be used for apparel design. One of the most important issues in the apparel development process is to define a sizing system to provide a good fitting for the majority of the population. Since anthropometric measures do not present the same linear growth with size in each dimension, it is very important to find a prototype that represents as accurately as possible each class in the sizing system. In this paper we propose a method based on the concept of random compact mean set to define prototypes in apparel design. From a cloud of 3D points obtained with a 3D scanner a solid that represents the human body is obtained. 2D cross sections of this solid are extracted at certain heights corresponding to key points of the body. These different cross-sections can be seen as a realization of a random compact set in the plane. A very popular definition on mean set is applied to each sample of 2D cross sections, and finally the prototype is obtained as the 3D reconstruction of these 2D mean sections. As a real example, the proposed methodology is applied to the 3D database obtained from a anthropometric survey of the Spanish female population conducted in this country in 2006.