利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

10 条记录 (耗时 0.016 秒)

    HYBRID RECURSIVE ANALYSIS OF SPATIO-TEMPORAL OBJECTS
    2.
    发明授权
    HYBRID RECURSIVE ANALYSIS OF SPATIO-TEMPORAL OBJECTS 有权
    强力混合分析VON RAUM-ZEIT-OBJEKTEN

    公开(公告)号：EP2786344B1

    公开(公告)日：2016-02-24

    申请号：EP12799522.3

    申请日：2012-11-23

    申请人： Fraunhofer Gesellschaft zur Förderung der angewandten Forschung e.V.

    发明人： ATZPADIN, Nicole ,  WAIZENEGGER, Wolfgang ,  SCHREER, Oliver ,  FELDMANN, Ingo ,  KAUFF, Peter ,  EISERT, Peter

    IPC分类号： G06T7/00

    CPC分类号： G06T7/70 ,  G06T7/593 ,  G06T7/97 ,  G06T2207/10012 ,  G06T2207/10028 ,  G06T2207/20076

    摘要： A method for generating 3D-information from multiple images showing a 3D scene from multiple perspectives has: providing at least two hypotheses for the 3D-information; performing a multi-hypotheses test by matching the at least two hypotheses to the multiple images and determining a test-result hypothesis that fulfills a particular matching criterion; updating the test-result hypothesis by varying a parameter set of the test-result hypothesis to further improve the matching criterion or another criterion; and determining the 3D-information on the basis of the parameter set of a resulting hypothesis provided by the action of updating the test-result hypothesis. A corresponding computer readable digital storage medium and a 3D-information generator are also described. Further embodiments perform a correspondence analysis between projections of spatio-temporal objects (STO) in multiple images to select a particular spatio-temporal object on the basis of said correspondence analysis.

    摘要翻译： 用于从多个视角显示3D场景的多个图像生成3D信息的方法具有：为3D信息提供至少两个假设; 通过将所述至少两个假设与所述多个图像进行匹配来执行多假设检验，并且确定满足特定匹配标准的测试结果假设; 通过改变测试结果假设的参数集来更新测试结果假设，以进一步提高匹配标准或另一个标准; 并且基于由更新测试结果假设的动作提供的所得到的假设的参数集来确定3D信息。 还描述了相应的计算机可读数字存储介质和3D信息生成器。 另外的实施例在多个图像中执行时空对象（STO）的投影之间的对应分析，以基于所述对应分析来选择特定的时空对象。

    VIDEO COMMUNICATION METHOD AND SYSTEM
    4.
    发明公开
    VIDEO COMMUNICATION METHOD AND SYSTEM 审中-公开

    公开(公告)号：EP3337165A1

    公开(公告)日：2018-06-20

    申请号：EP16840541.3

    申请日：2016-03-03

    申请人： Huawei Technologies Co., Ltd. ,  Fraunhofer Gesellschaft zur Förderung der angewandten Forschung e.V.

    发明人： REINHARDT, Michael ,  SCHREER, Oliver ,  FELDMANN, Ingo ,  GAO, Shan ,  YAO, Jun

    IPC分类号： H04N7/15

    CPC分类号： H04N7/144 ,  H04L65/403 ,  H04N7/15

    摘要： Embodiments of the present invention provide a video communication method and system, applied to a scenario of video communication between a first location and a second location, and at least two users at the second location participate in the video communication. The method includes: determining a first user and a second user that are in a call or that are going to have a call with each other, where the first user is located at the first location, the second user is located at the second location, and the second user is any one of the at least two users; obtaining an eye-to-eye virtual view image of the first user; and displaying the eye-to-eye virtual view image of the first user on a display at the second location in a manner used for corresponding to the second user, so that the eye-to-eye virtual view image of the first user corresponds to the second user, where the manner used for corresponding to the second user is used to indicate that the first user and the second user are in a call or are going to have a call with each other. According to the embodiments of the present invention, multiple users at the second location can learn that the first user and the second user are in a call, thereby improving user experience.

    HYBRID RECURSIVE ANALYSIS OF SPATIO-TEMPORAL OBJECTS
    5.
    发明公开
    HYBRID RECURSIVE ANALYSIS OF SPATIO-TEMPORAL OBJECTS 有权
    空间时间目标递归混合分析

    公开(公告)号：EP2786344A1

    公开(公告)日：2014-10-08

    申请号：EP12799522.3

    申请日：2012-11-23

    申请人： Fraunhofer Gesellschaft zur Förderung der angewandten Forschung e.V.

    发明人： ATZPADIN, Nicole ,  WAIZENEGGER, Wolfgang ,  SCHREER, Oliver ,  FELDMANN, Ingo ,  KAUFF, Peter ,  EISERT, Peter

    IPC分类号： G06T7/00

    CPC分类号： G06T7/70 ,  G06T7/593 ,  G06T7/97 ,  G06T2207/10012 ,  G06T2207/10028 ,  G06T2207/20076

    摘要： A method for generating 3D-information from multiple images showing a 3D scene from multiple perspectives has: providing at least two hypotheses for the 3D-information; performing a multi-hypotheses test by matching the at least two hypotheses to the multiple images and determining a test-result hypothesis that fulfills a particular matching criterion; updating the test-result hypothesis by varying a parameter set of the test-result hypothesis to further improve the matching criterion or another criterion; and determining the 3D-information on the basis of the parameter set of a resulting hypothesis provided by the action of updating the test-result hypothesis. A corresponding computer readable digital storage medium and a 3D-information generator are also described. Further embodiments perform a correspondence analysis between projections of spatio-temporal objects (STO) in multiple images to select a particular spatio-temporal object on the basis of said correspondence analysis.

    MULTI-DEPTH IMAGE FUSION METHOD AND APPARATUS
    8.
    发明公开
    MULTI-DEPTH IMAGE FUSION METHOD AND APPARATUS 有权

    公开(公告)号：EP3340170A1

    公开(公告)日：2018-06-27

    申请号：EP16850213.6

    申请日：2016-08-19

    申请人： Huawei Technologies Co., Ltd. ,  Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.

    发明人： XI, Ming ,  EBEL, Sascha ,  SCHREER, Oliver ,  FELDMANN, Ingo

    IPC分类号： G06T5/50

    CPC分类号： G06T5/50 ,  G06T7/136 ,  G06T7/50 ,  G06T17/00 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/20221

    摘要： The present invention discloses a method and an apparatus for fusing a plurality of depth images. The method includes: obtaining N depth images collected by N image collection units, where N≥2; obtaining a first foreground pixel of an i th depth image of the N depth images, where i≥1 and i≤N; obtaining N-1 projected points that correspond to the first foreground pixel and that are in depth images respectively collected by N-1 image collection units; and when depth values of a foreground three-dimensional space point in respective coordinate systems of the N-1 image collection units are greater than or equal to depth values of the respective N-1 projected points corresponding to the first foreground pixel, obtaining a three-dimensional point cloud by means of fusion. The method and the apparatus disclosed in the present invention resolve a problem that in a three-dimensional scene, a pixel offset occurs in a depth discontinuous location at which a foreground object borders a background object, and consequently a three-dimensional image finally formed is distorted.