利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

267 条记录 (耗时 0.059 秒)

    System and method for progressive stereo matching of digital images
    104.
    发明申请
    System and method for progressive stereo matching of digital images 审中-公开
    数字图像进行立体匹配的系统和方法

    公开(公告)号：US20050123191A1

    公开(公告)日：2005-06-09

    申请号：US11028416

    申请日：2004-12-30

    申请人： Zhengyou Zhang ,  Ying Shan

    发明人： Zhengyou Zhang ,  Ying Shan

    IPC分类号： G06K9/00 ,  G06T7/00 ,  H04N13/00 ,  G06K9/64

    CPC分类号： G06K9/32 ,  G06K9/00201 ,  G06T7/593 ,  G06T7/97 ,  G06T2207/10012 ,  H04N13/239 ,  H04N13/243 ,  H04N2013/0081

    摘要： System and method for progressive stereo matching of digital images representing a scene. In general, the progressive stereo matching system includes an initialization module, that obtains a set of previous unambiguous matches of pixels within the digital images, and a search range module, that determines a search range in the first and second digital images to look for a candidate pixel match. The progressive stereo matching system also includes a correlation module, that computes a correlation score between the candidate pixel match, and a classification module, that classifies the pixel match based on its correlation score.

    摘要翻译： 表示场景的数字图像的渐进立体匹配的系统和方法。 通常，渐进立体匹配系统包括初始化模块，其获得数字图像内的像素的先前的明确匹配的集合，以及搜索范围模块，其确定第一和第二数字图像中的搜索范围，以寻找 候选像素匹配。 逐行立体匹配系统还包括相关模块，其计算候选​​像素匹配之间的相关分数，以及分类模块，其根据其相关分数对像素匹配进行分类。

    Incremental motion estimation through local bundle adjustment
    106.
    发明申请
    Incremental motion estimation through local bundle adjustment 失效
    通过局部束调整进行增量运动估计

    公开(公告)号：US20050025343A1

    公开(公告)日：2005-02-03

    申请号：US10931768

    申请日：2004-08-31

    申请人： Zhengyou Zhang ,  Ying Shan

    发明人： Zhengyou Zhang ,  Ying Shan

    IPC分类号： G06T7/00 ,  G06T7/20 ,  G06K9/00

    CPC分类号： G06T7/251 ,  G06T7/80 ,  G06T2207/10016 ,  G06T2207/30244

    摘要： An incremental motion estimation system and process for estimating the camera pose parameters associated with each image of a long image sequence. Unlike previous approaches, which rely on point matches across three or more views, the present system and process also includes those points shared only by two views. The problem is formulated as a series of localized bundle adjustments in such a way that the estimated camera motions in the whole sequence are consistent with each other. The result of the inclusion of two-view matching points and the localized bundle adjustment approach is more accurate estimates of the camera pose parameters for each image in the sequence than previous incremental techniques, and providing an accuracy approaching that of global bundle adjustment techniques except with processing times about 100 to 700 times faster than the global approaches.

    摘要翻译： 用于估计与长图像序列的每个图像相关联的相机姿态参数的增量运动估计系统和过程。 不同于以上三种或更多视图中依赖点匹配的方法，本系统和过程也包括仅由两个视图共享的点。 该问题被形成为一系列本地化的束调整，使得整个序列中估计的摄像机运动彼此一致。 包含双视点匹配点和局部束调整方法的结果是对序列中每个图像的相机姿态参数的估计值比以前的增量技术更准确，并提供接近全局束调整技术的精度，除了 处理时间比全球方法快100到700倍。

    System and method providing improved head motion estimations for animation
    107.
    发明申请
    System and method providing improved head motion estimations for animation 有权
    系统和方法为动画提供改进的头部运动估计

    公开(公告)号：US20050008196A1

    公开(公告)日：2005-01-13

    申请号：US10912279

    申请日：2004-08-04

    申请人： Zicheng Liu ,  Zhengyou Zhang

    发明人： Zicheng Liu ,  Zhengyou Zhang

    IPC分类号： G06T7/00 ,  G06T7/20 ,  G06T13/00 ,  G06T15/70 ,  G06K9/00 ,  G06K9/36 ,  G06K9/66

    CPC分类号： G06K9/00248 ,  G06T7/251 ,  G06T7/70 ,  G06T2207/10016 ,  G06T2207/30201

    摘要： The system provides improved procedures to estimate head motion between two images of a face. Locations of a number of distinct facial features are identified in two images. The identified locations can correspond to the eye corners, mouth corners and nose tip. The locations are converted into as a set of physical face parameters based on the symmetry of the identified distinct facial features. The set of physical parameters reduces the number of unknowns as compared to the number of equations used to determine the unknowns. An initial head motion estimate is determined by: (a) estimating each of the set of physical parameters, (b) estimating a first head pose transform corresponding to the first image, and (c) estimating a second head pose transform corresponding to the second image. The head motion estimate can be incorporated into a feature matching algorithm to refine the head motion estimation and the physical facial parameters. In one implementation, an inequality constraint is placed on a particular physical parameter—such as a nose tip, such that the parameter is constrained within a predetermined minimum and maximum value. The inequality constraint is converted to an equality constraint by using a penalty function. Then, the inequality constraint is used during the initial head motion estimation to add additional robustness to the motion estimation.

    摘要翻译： 该系统提供改进的程序来估计脸部的两个图像之间的头部运动。 在两个图像中识别出许多不同的脸部特征的位置。 识别的位置可以对应于眼角，嘴角和鼻尖。 基于识别出的不同面部特征的对称性，这些位置被转换为一组物理面部参数。 与用于确定未知数的等式的数量相比，该组物理参数减少了未知数的数量。 通过以下方式确定初始头部运动估计：（a）估计所述一组物理参数中的每一个，（b）估计与所述第一图像相对应的第一头部姿态变换，以及（c）估计与所述第二头部姿态变换相对应的第二头部姿态变换 图片。 头部运动估计可以被并入到特征匹配算法中以改进头部运动估计和物理面部参数。 在一个实现中，对特定物理参数（例如鼻尖）施加不等式约束，使得参数被限制在预定的最小值和最大值内。 不等式约束通过使用惩罚函数转换为等式约束。 然后，在初始头部运动估计期间使用不等式约束以向运动估计添加额外的鲁棒性。

    System and method for expression mapping
    108.
    发明授权
    System and method for expression mapping 有权
    用于表达映射的系统和方法

    公开(公告)号：US06828972B2

    公开(公告)日：2004-12-07

    申请号：US10131972

    申请日：2002-04-24

    申请人： Zhengyou Zhang ,  Zicheng Liu ,  Ying Shan

    发明人： Zhengyou Zhang ,  Zicheng Liu ,  Ying Shan

    IPC分类号： G06T1500

    CPC分类号： G06T13/40 ,  G06K9/00268 ,  G06K9/00308 ,  G06T2210/44

    摘要： A system and method for mapping facial expressions. Facial expressions exhibit not only facial feature motions, but also subtle changes in illumination and appearance (e.g., facial creases and wrinkles). These details are important visual cues, but they are difficult to synthesize. Traditional expression mapping techniques consider feature motions while the details in illumination changes are ignored. A novel technique for facial expression mapping is presented. The illumination change of one person's expression is captured in what is called expression ratio image (ERI). Together with geometric warping, an ERI is mapped to any other person's face image to generate more expressive facial expressions.

    摘要翻译： 一种用于映射面部表情的系统和方法。 面部表情不仅表现出面部特征运动，还表现出照明和外观的微妙变化（例如面部皱纹和皱纹）。 这些细节是重要的视觉线索，但它们很难合成。 传统表达映射技术考虑特征运动，而照明变化的细节被忽略。 提出了一种面部表情映射的新技术。 一个人的表情的照明变化被称为表达比例图像（ERI）。 与几何翘曲一起，ERI被映射到任何其他人的脸部图像，以产生更具表现力的面部表情。

    System and method for transforming an ordinary computer monitor screen into a touch screen
    109.
    发明授权
    System and method for transforming an ordinary computer monitor screen into a touch screen 失效
    将普通计算机监视器画面变换为触摸屏的系统和方法

    公开(公告)号：US06774889B1

    公开(公告)日：2004-08-10

    申请号：US09696251

    申请日：2000-10-24

    申请人： Zhengyou Zhang ,  Ying Shan

    发明人： Zhengyou Zhang ,  Ying Shan

    IPC分类号： G09G500

    CPC分类号： G06F3/0425

    摘要： A system and method for turning a regular computer monitor screen into a touch screen using an ordinary camera. It includes an image-screen mapping procedure to correct for the non-flatness of the computer screen. It also includes a segmentation method to distinguish the foreground, for example an indicator such as a finger, from the background of a computer screen. Additionally, this system and method includes a robust technique of finding the tip point location of the indicator (such as the finger tip). The screen coordinates of the tip point are then used to control the position of the system indicator.

    摘要翻译： 一种使用普通相机将普通计算机显示器屏幕转换成触摸屏的系统和方法。 它包括一个图像屏幕映射程序来校正计算机屏幕的非平坦性。 它还包括一个分割方法，从计算机屏幕的背景区分前景，例如诸如手指的指示器。 此外，该系统和方法包括找到指示器的尖端位置（例如指尖）的鲁棒技术。 然后使用尖端点的屏幕坐标来控制系统指示器的位置。

    Object modeling system and process employing noise elimination and robust surface extraction techniques
    110.
    发明授权
    Object modeling system and process employing noise elimination and robust surface extraction techniques 有权
    对象建模系统和采用噪声消除和鲁棒表面提取技术的过程

    公开(公告)号：US06476803B1

    公开(公告)日：2002-11-05

    申请号：US09479408

    申请日：2000-01-06

    申请人： Zhengyou Zhang ,  Charles Loop ,  Ying Shan

    发明人： Zhengyou Zhang ,  Charles Loop ,  Ying Shan

    IPC分类号： G06T1700

    CPC分类号： G06T17/005 ,  G06T15/00 ,  G06T2200/08

    摘要： A system and process for computer modeling of an object involving first capturing images of the object that collectively depict all the object's surfaces which are to be modeled. A series of 3D reconstructions are then derived from the images. Each of the reconstructions represent a portion of the object's surfaces. Noise elimination techniques are employed to reduce the number of extraneous reconstruction points. The individual 3D reconstructions are then registered to a common coordinate system to produce an overall 3D reconstruction of the object's surfaces. A surface representation of the object is extracted from the overall 3D reconstruction using robust surface extraction techniques, and if desired, a texture map for the surface representation of the object can be computed using the previously captured images to produce a photorealistic model of the object.

    摘要翻译： 一种用于对象的计算机建模的系统和过程，其涉及首先捕获对象的图像，该图像共同地描绘要被建模的所有对象的表面。 然后从图像中导出一系列3D重建。 每个重建表示对象表面的一部分。 采用噪声消除技术来减少无关重建点的数量。 然后将单独的3D重建记录到公共坐标系中以产生对象表面的整体3D重建。 使用鲁棒的表面提取技术从整体3D重建中提取对象的表面表示，并且如果需要，可以使用先前捕获的图像来计算对象的表面表示的纹理图，以产生对象的照片写实模型。