知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

6 records (took 0.029 seconds)

    IMAGE MODIFICATION
    1.
    发明申请
    IMAGE MODIFICATION 有权
    图像修改

    公开(公告)号：US20160019223A1

    公开(公告)日：2016-01-21

    申请号：US14331928

    申请日：2014-07-15

    Applicant: Google Inc.

    Inventor： Andrew Vytas Kisielius ,  Wenfeng Li ,  Michael Paul Rolig ,  Chunfeng Hao ,  Jacqueline Anne Lai ,  Alena Viktorovna Repina ,  Bryan M. Klingner ,  Robert William Christy

    IPC: G06F17/30 ,  G06F3/0484

    CPC classification number: G06F17/30061 ,  G06F3/04845 ,  G06T11/60

    Abstract: In one aspect, a request to alter a first image is received. The request includes a portion of the first image that is provided for display with a second image. The second image is associated with three-dimensional (3D) geometry data for an object depicted in both the first and second images and date information identifying when the second image was captured. Input identifying an area of the second image is received. A third image is identified based on the date information of the third image and the second image. The third image is associated with 3D geometry data for the object. An area of the third image is determined based on the 3D geometry data of the second image, the 3D geometry data of the second image, and the area of the second image. Information identifying the area of the third image is provided for display with the third image.

    Abstract translation: 在一个方面，接收到改变第一图像的请求。 该请求包括提供用于与第二图像一起显示的第一图像的一部分。 第二图像与用于在第一和第二图像中描绘的对象的三维（3D）几何数据相关联，以及识别何时捕获第二图像的日期信息。 接收识别第二图像的区域的输入。 基于第三图像和第二图像的日期信息来识别第三图像。 第三个图像与对象的3D几何数据相关联。 基于第二图像的3D几何数据，第二图像的3D几何数据和第二图像的区域来确定第三图像的区域。 提供识别第三图像的区域的信息用于与第三图像一起显示。

    Correcting path errors for vehicle navigation
    2.
    发明授权
    Correcting path errors for vehicle navigation 有权
    纠正车辆导航的路径错误

    公开(公告)号：US08825373B1

    公开(公告)日：2014-09-02

    申请号：US13705376

    申请日：2012-12-05

    Applicant: Google Inc.

    Inventor： David R. Martin ,  Bryan M. Klingner

    IPC: G01C21/34

    CPC classification number: G01C21/32 ,  G01C21/005

    Abstract: An apparatus and method are disclosed for performing loop closing on one or more paths to be optimized. The paths may include poses associated with imagery obtained by a vehicle. The apparatus may identify candidate intersections from the paths based on their proximity, and may further determine relative poses from the poses of the paths using structure-from-motion techniques. The apparatus may then apply a partitioning schema to the paths to be optimized to obtain individual partition cells. The partition cells may then be sent to one or more client devices for optimizing the paths included in the partition cells. When the apparatus receives a set of optimized paths from the client devices, the apparatus may re-partition the paths to be optimized to ensure that non-optimized portions of paths are optimized.

    Abstract translation: 公开了一种用于在要优化的一个或多个路径上进行闭环的装置和方法。 路径可以包括与由车辆获得的图像相关联的姿势。 该装置可以基于它们的接近度从路径识别候选交叉点，并且还可以使用运动结构技术从路径的姿势确定相对姿势。 然后，设备可以将分区模式应用于要优化的路径以获得单个分区单元。 然后可以将分区单元发送到一个或多个客户端设备，以优化包含在分区单元中的路径。 当设备从客户端设备接收到一组优化的路径时，设备可以重新划分要优化的路径，以确保路径的非优化部分被优化。

    Image modification
    4.
    发明授权
    Image modification 有权
    图像修改

    公开(公告)号：US09529803B2

    公开(公告)日：2016-12-27

    申请号：US14331928

    申请日：2014-07-15

    Applicant: Google Inc.

    Inventor： Andrew Vytas Kisielius ,  Wenfeng Li ,  Michael Paul Rolig ,  Chunfeng Hao ,  Jacqueline Anne Lai ,  Alena Viktorovna Repina ,  Bryan M. Klingner ,  Robert William Christy

    IPC: G06F3/048 ,  G06F17/30 ,  G06F3/0484 ,  G06T11/60

    CPC classification number: G06F17/30061 ,  G06F3/04845 ,  G06T11/60

    Abstract: In one aspect, a request to alter a first image is received. The request includes a portion of the first image that is provided for display with a second image. The second image is associated with three-dimensional (3D) geometry data for an object depicted in both the first and second images and date information identifying when the second image was captured. Input identifying an area of the second image is received. A third image is identified based on the date information of the third image and the second image. The third image is associated with 3D geometry data for the object. An area of the third image is determined based on the 3D geometry data of the second image, the 3D geometry data of the second image, and the area of the second image. Information identifying the area of the third image is provided for display with the third image.

    Abstract translation: 在一个方面，接收到改变第一图像的请求。 该请求包括提供用于与第二图像一起显示的第一图像的一部分。 第二图像与用于在第一和第二图像中描绘的对象的三维（3D）几何数据相关联，以及识别何时捕获第二图像的日期信息。 接收识别第二图像的区域的输入。 基于第三图像和第二图像的日期信息来识别第三图像。 第三个图像与对象的3D几何数据相关联。 基于第二图像的3D几何数据，第二图像的3D几何数据和第二图像的区域来确定第三图像的区域。 提供识别第三图像的区域的信息用于与第三图像一起显示。

    Landmark Identification from Point Cloud Generated from Geographic Imagery Data
    6.
    发明申请
    Landmark Identification from Point Cloud Generated from Geographic Imagery Data 有权
    从地理图像数据生成的点云的地标识别

    公开(公告)号：US20150073711A1

    公开(公告)日：2015-03-12

    申请号：US14021222

    申请日：2013-09-09

    Applicant: Google Inc.

    Inventor： Brian Edmond Brewington ,  Bryan M. Klingner ,  David Martin ,  Kirk L. Johnson

    IPC: G01V11/00

    CPC classification number: G01V11/00 ,  G01C21/00 ,  G01C21/005 ,  G01C21/3644 ,  G01C21/3694 ,  G01D21/00 ,  G01S17/89 ,  G06F17/40 ,  G06F19/00 ,  G06K9/00664 ,  G06K9/00671 ,  G06T7/73 ,  G06T17/05

    Abstract: Systems and methods for identifying prominent landmarks in a geographic area are provided. More particularly, geographic imagery data, such as panoramic images captured by a camera from a perspective at or near ground level, can be analyzed to identify landmarks depicted in the geographic imagery data. For instance, structure-from-motion techniques can be used to generate a point cloud of tracked features that are located a threshold distance away from one or more camera perspectives associated with the geographic imagery data. Landmarks that are visible from multiple camera perspectives and that are visible from greater distances relative to one or more camera perspectives can be identified as prominent landmarks in a geographic area. A geographic information system can use the prominent landmarks for a variety of purposes, such as for use in providing travel directions, for rendering landmarks in an emphasized style, and/or for constructing/displaying a three-dimensional model of the landmark.

    Abstract translation: 提供了用于识别地理区域中的突出地标的系统和方法。 更具体地，可以分析地理图像数据，例如由摄像机从地面或附近的角度拍摄的全景图像，以识别地理图像数据中描绘的地标。 例如，可以使用运动结构技术来产生跟踪特征的点云，其位于距离与地理图像数据相关联的一个或多个相机视角的阈值距离处。 从多个相机透视图可见的并且相对于一个或多个相机透视图的距离可见的地标可以被识别为地理区域中的突出的地标。 地理信息系统可以使用突出的地标进行各种目的，例如用于提供旅行方向，用于渲染强调风格的地标和/或用于构建/显示地标的三维模型。

Patent Agency Ranking