利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

267 条记录 (耗时 0.034 秒)

    System and method for determining structure and motion using multiples sets of images from different projection models for object modeling
    1.
    发明授权
    System and method for determining structure and motion using multiples sets of images from different projection models for object modeling 有权
    用于使用来自不同投影模型的多组图像来确定结构和运动的系统和方法用于对象建模

    公开(公告)号：US06661913B1

    公开(公告)日：2003-12-09

    申请号：US09336218

    申请日：1999-06-19

    申请人： Zhengyou Zhang ,  Padmanabhan Anandan ,  Heung-Yeung Shum

    发明人： Zhengyou Zhang ,  Padmanabhan Anandan ,  Heung-Yeung Shum

    IPC分类号： G06K900

    CPC分类号： G06K9/209 ,  G06K2209/40 ,  G06T7/246 ,  G06T7/579

    摘要： The present invention is embodied in systems and methods for determining structure and motion of a three-dimensional (3D) object using two-dimensional (2D) images of the object obtained from multiple sets of views with different projection models, such as from a full perspective view and a weak perspective views. A novel fundamental matrix is derived that embodies the epipolar geometry between a full perspective view and a weak perspective view. The systems and methods of the present invention preferably uses the derived fundamental matrix together with the 2D image information of the full and weak perspective views to digitally reconstruct the 3D object and produce results with multi-resolution processing techniques. These techniques include recovering and refining motion parameters and recovering and refining structure parameters of the fundamental matrix. The results can include, for example, 3D positions of points, camera position between different views, texture maps, and the like.

    摘要翻译： 本发明体现在使用具有不同投影模型的多组视图获得的对象的二维（2D）图像来确定三维（3D）对象的结构和运动的系统和方法中，例如从完整的 透视和弱视角。 导出了一种新颖的基本矩阵，其体现了全透视图和弱透视图之间的对极几何。 本发明的系统和方法优选地将衍生的基本矩阵与全部和弱透视图的2D图像信息一起数字重建3D对象并且使用多分辨率处理技术产生结果。 这些技术包括恢复和精炼运动参数，并恢复和完善基本矩阵的结构参数。 结果可以包括例如点的3D位置，不同视图之间的相机位置，纹理贴图等。

    Method and apparatus for recovering a three-dimensional scene from two-dimensional images
    2.
    发明授权
    Method and apparatus for recovering a three-dimensional scene from two-dimensional images 有权
    从二维图像中恢复三维场景的方法和装置

    公开(公告)号：US07352386B1

    公开(公告)日：2008-04-01

    申请号：US09338176

    申请日：1999-06-22

    申请人： Heung-Yeung Shum ,  Zhengyou Zhang ,  Qifa Ke

    发明人： Heung-Yeung Shum ,  Zhengyou Zhang ,  Qifa Ke

    IPC分类号： H04N13/00

    CPC分类号： G06T17/00 ,  G06T7/246 ,  G06T7/579 ,  G06T2200/08 ,  G06T2207/10016 ,  H04N13/221 ,  H04N13/261

    摘要： A method and apparatus for recovering a three-dimensional (3D) scene from two-dimensional (2D) images. A sequence of images is divided into a number of smaller segments and a 3D reconstruction is performed on each segment individually. All the reconstructed segments are then combined together through an efficient bundle adjustment to complete the 3D reconstruction. Segmenting may be achieved by dividing the segments based on the number of feature points that are in each frame. The number of frames per segment is reduced by creating virtual key frames. The virtual key frames encode the 3D structure for each segment, but are only a small subset of the original frames in the segment. A final bundle adjustment is performed on the virtual key frames, rather than all of the original frames. Thus, the final bundle adjustment is two orders of magnitude faster than a conventional bundle adjustment.

    摘要翻译： 一种用于从二维（2D）图像中恢复三维（3D）场景的方法和装置。 图像序列被分成多个较小的段，并且对每个段单独执行3D重建。 然后通过有效的束调整将所有重建的段组合在一起以完成3D重建。 可以通过基于每个帧中的特征点的数量来划分段来实现分段。 通过创建虚拟键帧来减少每个段的帧数。 虚拟关键帧对每个段的3D结构进行编码，但只是该段中原始帧的一小部分。 在虚拟关键帧上执行最终的捆绑调整，而不是所有的原始帧。 因此，最终的捆绑调整比常规捆绑调整快两个数量级。

    System and method for determining structure and motion from two-dimensional images for multi-resolution object modeling
    3.
    发明授权
    System and method for determining structure and motion from two-dimensional images for multi-resolution object modeling 有权
    用于确定二维图像的结构和运动的系统和方法用于多分辨率对象建模

    公开(公告)号：US06614429B1

    公开(公告)日：2003-09-02

    申请号：US09336550

    申请日：1999-06-19

    申请人： Zhengyou Zhang ,  Padmananbhan Anandan ,  Heung-Yeung Shum

    发明人： Zhengyou Zhang ,  Padmananbhan Anandan ,  Heung-Yeung Shum

    IPC分类号： G06T1700

    CPC分类号： G06K9/209 ,  G06K2209/40 ,  G06T7/246 ,  G06T7/579 ,  G06T7/97 ,  G06T2207/10016

    摘要： The present invention is embodied in systems and methods for determining structure and motion of a three-dimensional (3D) object using two-dimensional (2D) images of the object obtained from multiple sets of views with different projection models, such as from a full perspective view and a weak perspective views. A novel fundamental matrix is derived that embodies the epipolar geometry between a full perspective view and a weak perspective view. The systems and methods of the present invention preferably uses the derived fundamental matrix together with the 2D image information of the full and weak perspective views to digitally reconstruct the 3D object and produce results with multi-resolution processing techniques. These techniques include recovering and refining motion parameters and recovering and refining structure parameters of the fundamental matrix. The results can include, for example, 3D positions of points, camera position between different views, texture maps, and the like.

    摘要翻译： 本发明体现在使用具有不同投影模型的多组视图获得的对象的二维（2D）图像来确定三维（3D）对象的结构和运动的系统和方法中，例如从完整的 透视和弱视角。 导出了一种新颖的基本矩阵，其体现了全透视图和弱透视图之间的对极几何。 本发明的系统和方法优选地将衍生的基本矩阵与全部和弱透视图的2D图像信息一起数字重建3D对象并且使用多分辨率处理技术产生结果。 这些技术包括恢复和精炼运动参数，并恢复和完善基本矩阵的结构参数。 结果可以包括例如点的3D位置，不同视图之间的相机位置，纹理贴图等。

    Dynamic hand gesture recognition using depth data
    4.
    发明授权
    Dynamic hand gesture recognition using depth data 有权
    使用深度数据的动态手势识别

    公开(公告)号：US09536135B2

    公开(公告)日：2017-01-03

    申请号：US13526501

    申请日：2012-06-18

    申请人： Zhengyou Zhang ,  Alexey Vladimirovich Kurakin

    发明人： Zhengyou Zhang ,  Alexey Vladimirovich Kurakin

    IPC分类号： G06K9/00

    CPC分类号： G06F3/017 ,  G06K9/00355 ,  G06K9/6277 ,  G06K9/6297

    摘要： The subject disclosure is directed towards a technology by which dynamic hand gestures are recognized by processing depth data, including in real-time. In an offline stage, a classifier is trained from feature values extracted from frames of depth data that are associated with intended hand gestures. In an online stage, a feature extractor extracts feature values from sensed depth data that corresponds to an unknown hand gesture. These feature values are input to the classifier as a feature vector to receive a recognition result of the unknown hand gesture. The technology may be used in real time, and may be robust to variations in lighting, hand orientation, and the user's gesturing speed and style.

    摘要翻译： 主题公开涉及一种通过处理深度数据（包括实时）来识别动态手势的技术。 在离线阶段，从与预期的手势相关联的深度数据的帧中提取的特征值训练分类器。 在在线阶段，特征提取器从对应于未知手势的感测深度数据中提取特征值。 将这些特征值作为特征向量输入到分类器，以接收未知手势的识别结果。 该技术可以实时使用，并且对于照明，手取向和用户的手势速度和风格的变化可能是鲁棒的。

    Data buddy
    5.
    发明授权
    Data buddy 有权
    资料好友

    公开(公告)号：US09055607B2

    公开(公告)日：2015-06-09

    申请号：US12323570

    申请日：2008-11-26

    申请人： Michael J. Sinclair ,  Yuan Kong ,  Zhengyou Zhang ,  Behrooz Chitsaz ,  David W. Williams ,  Silviu-Petru Cucerzan ,  Zicheng Liu

    发明人： Michael J. Sinclair ,  Yuan Kong ,  Zhengyou Zhang ,  Behrooz Chitsaz ,  David W. Williams ,  Silviu-Petru Cucerzan ,  Zicheng Liu

    IPC分类号： H04M1/00 ,  H04W88/06 ,  H04M1/725 ,  H04W8/24 ,  H04W92/02 ,  H04W92/10

    CPC分类号： H04W88/06 ,  H04M1/72572 ,  H04M2250/12 ,  H04M2250/58 ,  H04W8/245 ,  H04W92/02 ,  H04W92/10

    摘要： Multi-modal, multi-lingual devices can be employed to consolidate numerous items including, but not limited to, keys, remote controls, image capture devices, audio recorders, cellular telephone functionalities, location/direction detectors, health monitors, calendars, gaming devices, smart home inputs, pens, optical pointing devices or the like. For example, a corner of a cellular telephone can be used as an electronic pen. Moreover, the device can be used to snap multiple pictures stitching them together to create a panoramic image. A device can automate ignition of an automobile, initiate appliances, etc. based upon relative distance. The device can provide for near to eye capabilities for enhanced image viewing. Multiple cameras/sensors can be provided on a single device to provide for stereoscopic capabilities. The device can also provide assistance to blind, privacy, etc. by consolidating services.

    摘要翻译： 可以使用多模式，多语言设备来整合许多项目，包括但不限于键，遥控器，图像捕获设备，音频记录器，蜂窝电话功能，位置/方向检测器，健康监视器，日历，游戏设备 智能家庭输入，笔，光学指向装置等。 例如，蜂窝电话的角落可以用作电子笔。 此外，该设备可以用于将多个图片拼接在一起以创建全景图像。 设备可以基于相对距离自动点火汽车，起动电器等。 该设备可以提供近眼睛的功能，以增强图像观看效果。 可以在单个设备上提供多个摄像机/传感器以提供立体能力。 该设备还可以通过整合服务来提供盲人，隐私等方面的帮助。

    Spatialized audio over headphones
    8.
    发明授权
    Spatialized audio over headphones 有权
    通过耳机进行空间化音频

    公开(公告)号：US08737648B2

    公开(公告)日：2014-05-27

    申请号：US12472080

    申请日：2009-05-26

    申请人： Wei-ge Chen ,  Zhengyou Zhang

    发明人： Wei-ge Chen ,  Zhengyou Zhang

    IPC分类号： H04R5/02

    CPC分类号： H04R27/00

    摘要： A spatial element is added to communications, including over telephone conference calls heard through headphones or a stereo speaker setup. Functions are created to modify signals from different callers to create the illusion that the callers are speaking from different parts of the room.

    摘要翻译： 一个空间元素添加到通信中，包括通过耳机听到的电话会议通话或立体声扬声器设置。 创建功能来修改来自不同呼叫者的信号，以创建呼叫者从房间的不同部分讲话的错觉。

    Distinguishing live faces from flat surfaces
    9.
    发明授权
    Distinguishing live faces from flat surfaces 有权
    将活的面孔从平坦表面区分开来

    公开(公告)号：US08675926B2

    公开(公告)日：2014-03-18

    申请号：US12796470

    申请日：2010-06-08

    申请人： Zhengyou Zhang ,  Qin Cai ,  Pieter R. Kasselman ,  Arthur H. Baker

    发明人： Zhengyou Zhang ,  Qin Cai ,  Pieter R. Kasselman ,  Arthur H. Baker

    IPC分类号： G06K9/00

    CPC分类号： G06K9/00228 ,  G06K9/00906

    摘要： Multiple images including a face presented by a user are accessed. One or more determinations are made based on the multiple images, such as a determination of whether the face included in the multiple images is a 3-dimensional structure or a flat surface and/or a determination of whether motion is present in one or more face components (e.g., eyes or mouth). If it is determined that the face included in the multiple images is a 3-dimensional structure or that that motion is present in the one or more face components, then an indication is provided that the user can be authenticated. However, if it is determined that the face included in the multiple images is a flat surface or that motion is not present in the one or more face components, then an indication is provided that the user cannot be authenticated.

    摘要翻译： 访问包括用户呈现的脸部的多个图像。 基于多个图像进行一个或多个确定，例如确定包括在多个图像中的面是三维结构还是平面，和/或确定运动是否存在于一个或多个面中 组分（如眼睛或嘴巴）。 如果确定包括在多个图像中的面是三维结构或者该一个或多个面部组件中存在该运动，则提供用户可被认证的指示。 然而，如果确定包括在多个图像中的面是平面或者一个或多个面部组件中不存在运动，则提供用户不能被认证的指示。