中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

7 records (took 0.018 seconds)

    APPARATUS AND METHOD FOR ANALYZING BODY PART ASSOCIATION
    1.
    发明申请
    APPARATUS AND METHOD FOR ANALYZING BODY PART ASSOCIATION 有权
    用于分析身体部位协会的装置和方法

    公开(公告)号：US20130182958A1

    公开(公告)日：2013-07-18

    申请号：US13713351

    申请日：2012-12-13

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Byung In YOO ,  Hee Seob RYU ,  Chang Kyu CHOI ,  Chang Kyo LEE ,  Jae Joon HAN

    IPC: G06K9/00

    CPC classification number: G06K9/00369

    Abstract: An apparatus and method for analyzing body part association. The apparatus and method may recognize at least one body part from a user image extracted from an observed image, select at least one candidate body part based on association of the at least one body part, and output a user pose skeleton related to the user image based on the selected at least one candidate body part.

    Abstract translation: 一种用于分析身体部位关联的装置和方法。 该装置和方法可以从从观察图像提取的用户图像中识别至少一个身体部位，基于至少一个身体部位的关联来选择至少一个候选人体部分，并且输出与用户图像相关的用户姿势骨架 基于所选择的至少一个候选身体部位。

    APPARATUS AND METHOD FOR CREATING POSE CLUSTER
    2.
    发明申请
    APPARATUS AND METHOD FOR CREATING POSE CLUSTER 审中-公开
    用于创建位置集合的装置和方法

    公开(公告)号：US20130181988A1

    公开(公告)日：2013-07-18

    申请号：US13738509

    申请日：2013-01-10

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Byung In YOO ,  Chang Kyu CHOI ,  Hee Seob RYU ,  Chang Kyo LEE ,  Jae Joon HAN

    IPC: G06T17/00

    CPC classification number: G06T17/00 ,  G06K9/00369 ,  G06K9/6272

    Abstract: Provided is a method of creating a body pose cluster, including performing feature extraction from pose data about at least one pose, classifying, as a single cluster, similar poses from a feature vector space using a similarity measure, and configuring the number of poses included in each cluster from the feature vector space to be uniform using an imbalance measure.

    Abstract translation: 提供了一种创建身体姿势群集的方法，包括从关于至少一个姿势的姿势数据执行特征提取，使用相似度度量从特征向量空间分类为单个群集类似的姿势，以及配置包括的姿势数 在每个聚类中从特征向量空间中均匀使用不平衡度量。

    METHOD OF GENERATING THREE-DIMENSIONAL (3D) VOLUMETRIC DATA
    3.
    发明申请
    METHOD OF GENERATING THREE-DIMENSIONAL (3D) VOLUMETRIC DATA 有权
    产生三维（3D）体积数据的方法

    公开(公告)号：US20130271449A1

    公开(公告)日：2013-10-17

    申请号：US13858336

    申请日：2013-04-08

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Chang Kyo LEE ,  Byung In Yoo ,  Chang Kyu Choi ,  Jae Joon Han

    IPC: G06T15/08

    CPC classification number: G06T15/08 ,  G06T13/40

    Abstract: A method of generating three-dimensional (3D) volumetric data may be performed by generating a multilayer image, generating volume information and a type of a visible part of an object, based on the generated multilayer image, and generating volume information and a type of an invisible part of the object, based on the generated multilayer image. The volume information and the type of each of the visible part and invisible part may be generated based on the generated multilayered image which may be include at least one of a ray-casting-based multilayer image, a chroma key screen-based multilayer image, and a primitive template-based multilayer image.

    Abstract translation: 可以通过生成多层图像，基于生成的多层图像生成体信息和对象的可见部分的类型，并且生成体积信息和类型的多个图像，来生成三维（3D）体积数据的方法 基于生成的多层图像，对象的不可见部分。 可以基于所生成的多层图像来生成可见部分和不可见部分中的每一个的体积信息和类型，所述多层图像可以包括基于射线铸造的多层图像，基于色度键屏幕的多层图像， 和基于模板的原始多层图像。

    APPARATUS AND METHOD FOR RECOGNIZING OBJECT USING DEPTH IMAGE
    6.
    发明申请
    APPARATUS AND METHOD FOR RECOGNIZING OBJECT USING DEPTH IMAGE 有权
    用于识别使用深度图像的对象的装置和方法

    公开(公告)号：US20140233848A1

    公开(公告)日：2014-08-21

    申请号：US14074247

    申请日：2013-11-07

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Jae Joon HAN ,  Chang Kyu CHOI ,  Chang Kyo LEE

    IPC: G06K9/00 ,  G06K9/46 ,  G06K9/80

    CPC classification number: G06K9/00375 ,  G06K9/00201 ,  G06K9/4652 ,  G06K9/6282 ,  G06K9/6298

    Abstract: An apparatus recognizes an object using a hole in a depth image. An apparatus may include a foreground extractor to extract a foreground from the depth image, a hole determiner to determine whether a hole is present in the depth image, based on the foreground and a color image, a feature vector generator to generate a feature vector, by generating a plurality of features corresponding to the object based on the foreground and the hole, and an object recognizer to recognize the object, based on the generated feature vector and at least one reference feature vector.

    Abstract translation: 设备使用深度图像中的孔识别对象。 装置可以包括从深度图像提取前景的前景提取器，基于前景和彩色图像确定深度图像中是否存在孔的孔确定器，用于生成特征向量的特征向量生成器， 通过基于所述前景和所述孔生成对应于所述对象的多个特征，以及基于所生成的特征向量和至少一个参考特征向量来识别所述对象的对象识别器。

    SYSTEM AND METHOD FOR LEARNING POSE CLASSIFIER BASED ON DISTRIBUTED LEARNING ARCHITECTURE
    7.
    发明申请
    SYSTEM AND METHOD FOR LEARNING POSE CLASSIFIER BASED ON DISTRIBUTED LEARNING ARCHITECTURE 审中-公开
    基于分布式学习架构学习分类器的系统与方法

    公开(公告)号：US20130185233A1

    公开(公告)日：2013-07-18

    申请号：US13740597

    申请日：2013-01-14

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Byung In YOO ,  Chang Kyu CHOI ,  Jae Joon HAN ,  Chang Kyo LEE

    IPC: G06N99/00

    CPC classification number: G06N20/00

    Abstract: A system and method for learning a pose classifier based on a distributed learning architecture. A pose classifier learning system may include an input unit to receive an input of a plurality of pieces of learning data, and a plurality of pose classifier learning devices to receive an input of a plurality of learning data sets including the plurality of pieces of learning data, and to learn each pose classifier. The pose classifier learning devices may share learning information in each stage, using a distributed/parallel framework.

    Abstract translation: 一种基于分布式学习架构学习姿态分类器的系统和方法。 姿态分类器学习系统可以包括用于接收多条学习数据的输入的输入单元和多个姿态分类器学习装置，用于接收包括多条学习数据的多个学习数据集的输入 ，并学习每个姿态分类器。 姿态分类器学习装置可以使用分布式/并行框架在每个阶段共享学习信息。

Patent Agency Ranking