中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

21 records (took 0.015 seconds)

    3-dimensional scene analysis for augmented reality operations
    2.
    发明授权
    3-dimensional scene analysis for augmented reality operations 有权

    公开(公告)号：US10229542B2

    公开(公告)日：2019-03-12

    申请号：US15046614

    申请日：2016-02-18

    Applicant: INTEL CORPORATION

    Inventor： Gershom Kutliroff ,  Yaron Yanai ,  Shahar Fleishman ,  Mark Kliger

    IPC: G06K9/00 ,  G06T19/00 ,  G06T7/10

    Abstract: Techniques are provided for 3D analysis of a scene including detection, segmentation and registration of objects within the scene. The analysis results may be used to implement augmented reality operations including removal and insertion of objects and the generation of blueprints. An example method may include receiving 3D image frames of the scene, each frame associated with a pose of a depth camera, and creating a 3D reconstruction of the scene based on depth pixels that are projected and accumulated into a global coordinate system. The method may also include detecting objects, and associated locations within the scene, based on the 3D reconstruction, the camera pose and the image frames. The method may further include segmenting the detected objects into points of the 3D reconstruction corresponding to contours of the object and registering the segmented objects to 3D models of the objects to determine their alignment.

    APPLICATION OF CONVOLUTIONAL NEURAL NETWORKS TO OBJECT MESHES
    6.
    发明申请
    APPLICATION OF CONVOLUTIONAL NEURAL NETWORKS TO OBJECT MESHES 审中-公开

    公开(公告)号：US20180286120A1

    公开(公告)日：2018-10-04

    申请号：US15478534

    申请日：2017-04-04

    Applicant: Intel Corporation

    Inventor： Shahar Fleishman ,  Mark Kliger

    IPC: G06T17/20

    Abstract: Convolutional Neural Networks are applied to object meshes to allow three-dimensional objects to be analyzed. In one example, a method includes performing convolutions on a mesh, wherein the mesh represents a three-dimensional object of an image, the mesh having a plurality of vertices and a plurality of edges between the vertices, performing pooling on the convolutions of an edge of a mesh, and applying fully connected and loss layers to the pooled convolutions to provide metadata about the three-dimensional object.

    3-DIMENSIONAL SCENE ANALYSIS FOR AUGMENTED REALITY OPERATIONS
    7.
    发明申请
    3-DIMENSIONAL SCENE ANALYSIS FOR AUGMENTED REALITY OPERATIONS 审中-公开

    公开(公告)号：US20170243352A1

    公开(公告)日：2017-08-24

    申请号：US15046614

    申请日：2016-02-18

    Applicant: INTEL CORPORATION

    Inventor： Gershom Kutliroff ,  Yaron Yanai ,  Shahar Fleishman ,  Mark Kliger

    IPC: G06T7/00

    CPC classification number: G06T19/006 ,  G06T7/10 ,  G06T2207/10021 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/30244

    Abstract: Techniques are provided for 3D analysis of a scene including detection, segmentation and registration of objects within the scene. The analysis results may be used to implement augmented reality operations including removal and insertion of objects and the generation of blueprints. An example method may include receiving 3D image frames of the scene, each frame associated with a pose of a depth camera, and creating a 3D reconstruction of the scene based on depth pixels that are projected and accumulated into a global coordinate system. The method may also include detecting objects, and associated locations within the scene, based on the 3D reconstruction, the camera pose and the image frames. The method may further include segmenting the detected objects into points of the 3D reconstruction corresponding to contours of the object and registering the segmented objects to 3D models of the objects to determine their alignment.

    Labeling component parts of objects and detecting component properties in imaging data
    8.
    发明授权
    Labeling component parts of objects and detecting component properties in imaging data 有权
    在成像数据中标记对象的组成部分和检测组件属性

    公开(公告)号：US09501716B2

    公开(公告)日：2016-11-22

    申请号：US14567187

    申请日：2014-12-11

    Applicant: Intel Corporation

    Inventor： Shahar Fleishman ,  Mark Kliger

    IPC: G06K9/00 ,  G06K9/48 ,  G06K9/66

    CPC classification number: G06K9/481 ,  G06K9/00355 ,  G06K9/00375 ,  G06K9/66

    Abstract: Techniques related to labeling component parts and detecting component properties in imaging data are discussed. Such techniques may include generating a feature vector including invariant features associated with an area of interest within an image of an object such as an image of a hand and providing a component label such as a hand part label for the area of interest based on an application of a machine learning classifier to the feature vector.

    Abstract translation: 讨论了与成像数据标注零件和检测元件特性相关的技术。 这样的技术可以包括生成特征向量，其特征向量包括与诸如手的图像的对象的图像内的感兴趣区域相关联的不变特征，并且基于应用提供诸如感兴趣区域的手部标签的组件标签 的机器学习分类器到特征向量。

    Three dimensional scene reconstruction based on contextual analysis
    9.
    发明授权
    Three dimensional scene reconstruction based on contextual analysis 有权

    公开(公告)号：US10573018B2

    公开(公告)日：2020-02-25

    申请号：US15209014

    申请日：2016-07-13

    Applicant: INTEL CORPORATION

    Inventor： Gershom Kutliroff ,  Shahar Fleishman ,  Mark Kliger

    IPC: G06T7/60 ,  G06T17/00 ,  G06T9/00 ,  H04N13/128 ,  H04N13/257 ,  G06T11/60 ,  G06T7/33 ,  G06T7/90 ,  G06T7/50 ,  G06K9/00 ,  H04N13/271 ,  H04N13/111

    Abstract: Techniques are provided for context-based 3D scene reconstruction employing fusion of multiple instances of an object within the scene. A methodology implementing the techniques according to an embodiment includes receiving 3D image frames of the scene, each frame associated with a pose of a depth camera, and creating a 3D reconstruction of the scene based on depth pixels that are projected and accumulated into a global coordinate system. The method may also include detecting objects, based on the 3D reconstruction, the camera pose and the image frames. The method may further include classifying the detected objects into one or more object classes; grouping two or more instances of objects in one of the object classes based on a measure of similarity of features between the object instances; and combining point clouds associated with each of the grouped object instances to generate a fused object.

Patent Agency Ranking