中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

7 records (took 0.017 seconds)

    REAL-TIME THREE-DIMENSIONAL RECONSTRUCTION OF A SCENE FROM A SINGLE CAMERA
    1.
    发明申请
    REAL-TIME THREE-DIMENSIONAL RECONSTRUCTION OF A SCENE FROM A SINGLE CAMERA 有权
    从单个摄像机实时三维重建场景

    公开(公告)号：US20150279083A1

    公开(公告)日：2015-10-01

    申请号：US14226732

    申请日：2014-03-26

    Applicant: Microsoft Corporation

    Inventor： Vivek Pradeep ,  Christoph Rhemann ,  Shahram Izadi ,  Christopher Zach ,  Michael Bleyer ,  Steven Bathiche

    IPC: G06T15/08 ,  G06T7/00 ,  G06T19/00

    CPC classification number: G06T7/337 ,  G06T7/593 ,  G06T17/00 ,  G06T2207/10016 ,  G06T2207/30244

    Abstract: A combination of three computational components may provide memory and computational efficiency while producing results with little latency, e.g., output can begin with the second frame of video being processed. Memory usage may be reduced by maintaining key frames of video and pose information for each frame of video. Additionally, only one global volumetric structure may be maintained for the frames of video being processed. To be computationally efficient, only depth information may be computed from each frame. Through fusion of multiple depth maps from different frames into a single volumetric structure, errors may average out over several frames, leading to a final output with high quality.

    Abstract translation: 三个计算组件的组合可以提供存储器和计算效率，同时产生具有很小延迟的结果，例如，输出可以从正在处理的视频的第二帧开始。 可以通过维护每帧视频的视频和姿势信息的关键帧来减少存储器的使用。 另外，对于正在处理的视频帧，可以仅保持一个全局体积结构。 为了计算效率，可以从每个帧计算深度信息。 通过将来自不同帧的多个深度图融合到单个体积结构中，错误可以平均超过几帧，导致最终输出具有高质量。

    Global and Local Light Detection in Optical Sensor Systems
    3.
    发明申请
    Global and Local Light Detection in Optical Sensor Systems 有权
    光学传感器系统中的全局和局部光检测

    公开(公告)号：US20150205445A1

    公开(公告)日：2015-07-23

    申请号：US14162440

    申请日：2014-01-23

    Applicant: Microsoft Corporation

    Inventor： Vivek Pradeep ,  Liang Wang ,  Pablo Sala ,  Luis Eduardo Cabrera-Cordon ,  Steven Nabil Bathiche

    IPC: G06F3/042 ,  G06K9/46

    CPC classification number: G06F3/0425 ,  G06F3/0416 ,  G06F3/042 ,  G06K9/4642

    Abstract: Global and local light detection techniques in optical sensor systems are described. In one or more implementations, a global lighting value is generated that describes a global lighting level for a plurality of optical sensors based on a plurality of inputs received from the plurality of optical sensors. An illumination map is generated that describes local lighting conditions of respective ones of the plurality of optical sensors based on the plurality of inputs received from the plurality of optical sensors. Object detection is performed using an image captured using the plurality of optical sensors along with the global lighting value and the illumination map.

    Abstract translation: 描述了光学传感器系统中的全局和局部光检测技术。 在一个或多个实施方案中，产生基于从多个光学传感器接收的多个输入来描述多个光学传感器的全局照明水平的全局照明值。 产生基于从多个光学传感器接收的多个输入来描述多个光学传感器中的相应光学传感器的本地照明条件的照明图。 使用使用多个光学传感器捕获的图像以及全局照明值和照明映射来执行对象检测。

    3D SILHOUETTE SENSING SYSTEM
    5.
    发明申请
    3D SILHOUETTE SENSING SYSTEM 有权
    3D SILHOUETTE感应系统

    公开(公告)号：US20150199018A1

    公开(公告)日：2015-07-16

    申请号：US14154571

    申请日：2014-01-14

    Applicant: Microsoft Corporation

    Inventor： David Kim ,  Shahram Izadi ,  Vivek Pradeep ,  Steven Bathiche ,  Timothy Andrew Large ,  Karlton David Powell

    IPC: G06F3/01 ,  G06K9/52 ,  H04N13/02 ,  H04N5/33 ,  G01B11/24 ,  G06K9/00

    CPC classification number: G06F3/017 ,  G01B11/24 ,  G06F3/0325 ,  G06F3/0416 ,  G06F3/0421 ,  G06F3/0425 ,  G06K9/00355 ,  G06K9/00362 ,  G06K9/2036 ,  G06K9/4604 ,  G06K9/52 ,  H04N5/33 ,  H04N13/204

    Abstract: A 3D silhouette sensing system is described which comprises a stereo camera and a light source. In an embodiment, a 3D sensing module triggers the capture of pairs of images by the stereo camera at the same time that the light source illuminates the scene. A series of pairs of images may be captured at a predefined frame rate. Each pair of images is then analyzed to track both a retroreflector in the scene, which can be moved relative to the stereo camera, and an object which is between the retroreflector and the stereo camera and therefore partially occludes the retroreflector. In processing the image pairs, silhouettes are extracted for each of the retroreflector and the object and these are used to generate a 3D contour for each of the retroreflector and object.

    Abstract translation: 描述了包括立体相机和光源的3D轮廓感测系统。 在一个实施例中，3D感测模块在光源照亮场景的同时触发立体摄像机拍摄图像对。 可以以预定的帧速率捕获一系列图像对。 然后分析每对图像以跟踪可以相对于立体相机移动的场景中的后向反射器，以及位于后向反射器和立体相机之间并因此部分遮挡后向反射器的物体。 在处理图像对时，为后向反射器和对象中的每一个提取剪影，并且这些剪影用于为每个后向反射器和对象生成3D轮廓。

    IN-SCENE REAL-TIME DESIGN OF LIVING SPACES
    6.
    发明申请
    IN-SCENE REAL-TIME DESIGN OF LIVING SPACES 审中-公开
    现场生活空间的实时设计

    公开(公告)号：US20140132595A1

    公开(公告)日：2014-05-15

    申请号：US13676151

    申请日：2012-11-14

    Applicant: MICROSOFT CORPORATION

    Inventor： Catherine N. Boulanger ,  Matheen Siddiqui ,  Vivek Pradeep ,  Paul Dietz ,  Steven Bathiche

    IPC: G06T15/00 ,  G09G5/00

    CPC classification number: G09G5/00 ,  G06F3/017 ,  G06T7/564 ,  G06T13/40 ,  G06T13/60 ,  G06T19/006 ,  G06T19/20 ,  G06T2219/2016

    Abstract: A display that renders realistic objects allows a designer to redesign a living space in real time based on an existing layout. A computer system renders simulated objects on the display such that the simulated objects appear to the viewer to be in substantially the same place as actual objects in the scene. The displayed simulated objects can be spatially manipulated on the display through various user gestures. A designer can visually simulate a redesign of the space in many ways, for example, by adding selected objects, or by removing or rearranging existing objects, or by changing properties of those objects. Such objects also can be associated with shopping resources to enable related goods and services to be purchased, or other commercial transactions to be engaged in.

    Abstract translation: 呈现现实对象的显示器允许设计者基于现有布局实时重新设计生活空间。 计算机系统在显示器上呈现模拟对象，使得模拟对象对于观看者显示为与场景中实际对象基本相同的位置。 显示的模拟物体可以通过各种用户手势在显示屏上进行空间操纵。 设计人员可以通过多种方式可视化地模拟空间的重新设计，例如，添加选定的对象，或通过删除或重新排列现有对象，或通过更改这些对象的属性。 这样的对象也可以与购物资源相关联，以便购买相关商品和服务，或者要进行其他商业交易。

Patent Agency Ranking