利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

11 条记录 (耗时 0.027 秒)

    METHODS AND SYSTEMS FOR IDENTIFYING BACKGROUND IN VIDEO DATA USING GEOMETRIC PRIMITIVES
    1.
    发明申请
    METHODS AND SYSTEMS FOR IDENTIFYING BACKGROUND IN VIDEO DATA USING GEOMETRIC PRIMITIVES 有权
    使用几何原理识别视频数据背景的方法和系统

    公开(公告)号：US20160343148A1

    公开(公告)日：2016-11-24

    申请号：US14716511

    申请日：2015-05-19

    申请人： Personify, Inc.

    发明人： Cong Nguyen ,  Quang Nguyen ,  Dennis Lin

    IPC分类号： G06T7/40 ,  G06K9/46 ,  G06T11/00 ,  G06K9/62

    CPC分类号： G06T11/001 ,  G06K9/00718 ,  G06K9/38 ,  G06K9/4604 ,  G06K9/4638 ,  G06K9/4652 ,  G06K9/6267 ,  G06T7/12 ,  G06T7/194 ,  G06T11/60 ,  H04N5/2226

    摘要： Disclosed herein are methods and systems for identifying background in video data using geometric primitives. One embodiment takes the form of a process that includes obtaining video data depicting at least a portion of a user. The process also includes detecting at least one geometric primitive within the video data. The at least one detected geometric primitive is a type of geometric primitive included in a set of geometric-primitive models. The process also includes identifying a respective region within the video data associated with each detected geometric primitive. The process also includes classifying each respective region as background of the video data.

    摘要翻译： 这里公开了用于使用几何图元识别视频数据中的背景的方法和系统。 一个实施例采用包括获取描绘用户的至少一部分的视频数据的过程的形式。 该过程还包括检测视频数据内的至少一个几何基元。 所述至少一个检测到的几何图元是包括在几何图元模型集合中的几何图元的类型。 该过程还包括识别与每个检测到的几何图元相关联的视频数据内的相应区域。 该过程还包括将每个相应区域分类为视频数据的背景。

    METHODS AND SYSTEMS FOR CLASSIFYING PIXELS AS FOREGROUND USING BOTH SHORT-RANGE DEPTH DATA AND LONG-RANGE DEPTH DATA
    2.
    发明申请
    METHODS AND SYSTEMS FOR CLASSIFYING PIXELS AS FOREGROUND USING BOTH SHORT-RANGE DEPTH DATA AND LONG-RANGE DEPTH DATA 审中-公开
    使用两个短距离深度数据和长距离深度数据分类像素的方法和系统

    公开(公告)号：US20160353080A1

    公开(公告)日：2016-12-01

    申请号：US14721428

    申请日：2015-05-26

    申请人： Personify, Inc.

    发明人： Quang Nguyen ,  Long Dang ,  Cong Nguyen ,  Dennis Lin ,  Simion Venshtain ,  Minh Do

    IPC分类号： H04N13/00 ,  H04N13/02 ,  G06K9/62

    CPC分类号： H04N13/158 ,  G06K9/00201 ,  G06K9/6267 ,  G06T7/11 ,  G06T7/174 ,  G06T7/194 ,  G06T2207/10016 ,  G06T2207/10028 ,  G06T2207/20076 ,  G06T2207/30201 ,  H04N13/15 ,  H04N13/271 ,  H04N2013/0085 ,  H04N2013/0092

    摘要： Disclosed herein are methods and systems for classifying pixels as foreground using both short-range depth data and long-range depth data. One embodiment takes the form of a process that includes obtaining video data depicting at least a portion of a user. The process also includes obtaining short-range depth data associated with the video data. The process also includes obtaining long-range depth data associated with the video data. The video data, short-range depth data, and long-range depth data may be obtained via a single 3-D video camera. The process also includes classifying pixels of the video data as foreground based at least in part on both the short-range depth data and the long-range depth data. In some embodiments, classifying pixels of the video data as foreground comprises employing an alpha mask. The alpha mask may comprise binary foreground (hard) indicators. The alpha mask may comprise foreground-likelihood (soft) indicators.

    摘要翻译： 这里公开了使用短距离深度数据和远程深度数据两者将像素分类为前景的方法和系统。 一个实施例采用包括获取描绘用户的至少一部分的视频数据的过程的形式。 该过程还包括获得与视频数据相关联的短距离深度数据。 该过程还包括获得与视频数据相关联的长距离深度数据。 可以通过单个3-D摄像机获得视频数据，短距离深度数据和远程深度数据。 该过程还包括至少部分地基于短程深度数据和远程深度数据两者将视频数据的像素分类为前景。 在一些实施例中，将视频数据的像素分类为前景包括采用α掩模。 alpha掩码可以包括二进制前景（硬）指示符。 α掩模可以包括前景似然（软）指示符。

    Methods and systems for assigning pixels distance-cost values using a flood fill technique
    3.
    发明授权
    Methods and systems for assigning pixels distance-cost values using a flood fill technique 有权
    使用洪水填充技术分配像素距离成本值的方法和系统

    公开(公告)号：US09563962B2

    公开(公告)日：2017-02-07

    申请号：US14716495

    申请日：2015-05-19

    申请人： Personify, Inc.

    发明人： Dennis Lin ,  Quang Nguyen ,  Gia Dang ,  Yi Zhang ,  Simion Venshtain ,  Cong Nguyen

    IPC分类号： G06K9/34 ,  G06T7/00 ,  G06K9/00 ,  G06T7/40 ,  G06K9/46 ,  G06K9/62

    CPC分类号： G06K9/00718 ,  G06K9/00281 ,  G06K9/00758 ,  G06K9/4604 ,  G06K9/4652 ,  G06K9/52 ,  G06K9/627 ,  G06T7/0002 ,  G06T7/11 ,  G06T7/12 ,  G06T7/181 ,  G06T7/187 ,  G06T7/194 ,  G06T7/50 ,  G06T7/73 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/20156 ,  G06T2207/30196 ,  G06T2207/30201

    摘要： Disclosed herein are methods and systems for assigning pixels distance-cost values using a flood fill technique. One embodiment takes the form of a process that includes obtaining video data depicting a head of a user, obtaining depth data associated with the video data, and selecting seed pixels for a flood fill at least in part by using the depth information. The process also includes performing the flood fill from the selected seed pixels. The flood fill assigns respective distance-cost values to pixels of the video data based on position-space cost values and color-space cost values. In some embodiments, the process also includes classifying pixels of the video data as foreground based at least in part on the assigned distance-cost values. In some other embodiments, the process also includes assigning pixels of the video data foreground-likelihood values based at least in part on the assigned distance-cost values.

    摘要翻译： 这里公开了使用洪水填充技术来分配像素距离成本值的方法和系统。 一个实施例采取以下处理的形式：包括获取描绘用户头部的视频数据，获得与视频数据相关联的深度数据，以及至少部分地通过使用深度信息来选择洪水填充的种子像素。 该过程还包括从所选择的种子像素执行洪水填充。 洪水填充基于位置空间成本值和颜色空间成本值，将相应的距离成本值分配给视频数据的像素。 在一些实施例中，该过程还包括至少部分地基于所分配的距离成本值将视频数据的像素分类为前景。 在一些其它实施例中，该过程还包括至少部分地基于所分配的距离成本值来分配视频数据前景似然值的像素。

    SYSTEMS AND METHODS FOR RECONSTRUCTION AND RENDERING OF VIEWPOINT-ADAPTIVE THREE-DIMENSIONAL (3D) PERSONAS
    4.
    发明申请
    SYSTEMS AND METHODS FOR RECONSTRUCTION AND RENDERING OF VIEWPOINT-ADAPTIVE THREE-DIMENSIONAL (3D) PERSONAS 审中-公开

    公开(公告)号：US20190045157A1

    公开(公告)日：2019-02-07

    申请号：US15865120

    申请日：2018-01-08

    申请人： Personify, Inc.

    发明人： Simion Venshtain ,  Yi Zhang ,  Cong Nguyen

    IPC分类号： H04N7/15 ,  H04L29/06 ,  G06T19/00

    摘要： Systems and methods relate receiving video streams captured of a subject by video cameras, each video stream including video frames that are time-synchronized with the video, each video camera having a known vantage point in a predetermined coordinate system; obtaining at least one three-dimensional (3D) mesh of the subject, the mesh being time-synchronized and including a plurality of mesh vertices with known locations; identifying a user-selected viewpoint, and identifying a viewpoint-specific subset of the mesh vertices visible; generating 3D submeshes of the subject by calculating visible-vertices lists from the vantage point of each video camera from which the viewpoint-specific subset of mesh vertices is visible; projecting mesh vertices from the calculated visible-vertices lists on to video pixels; and rendering viewpoint-adaptive 3D personas of the subject by weighting video pixel colors from different video-camera vantage points according to the geometric relationship of each video-camera vantage point to the user-selected viewpoint.

    Methods and systems for real-time user extraction using deep learning networks
    5.
    发明授权
    Methods and systems for real-time user extraction using deep learning networks 有权

    公开(公告)号：US09881207B1

    公开(公告)日：2018-01-30

    申请号：US15333623

    申请日：2016-10-25

    申请人： Personify, Inc.

    发明人： Quang Nguyen ,  Cong Nguyen ,  Long Dang ,  Gia Dang ,  Simion Venshtain

    IPC分类号： G06K9/00 ,  G06K9/46 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08

    CPC分类号： G06K9/00369 ,  G06K9/4652 ,  G06K9/6232 ,  G06N3/0445 ,  G06N3/08

    摘要： Methods and systems for real-time user extraction using deep learning networks. In one embodiment, user extraction comprises obtaining a given frame of color pixel data, checking whether a reset flag is cleared or set, and generating a trimap for the given frame. If the reset flag is cleared, generating the trimap comprises: obtaining a user-extraction contour based on a preceding frame; and generating the trimap based on the obtained user-extraction contour. If the reset flag is set, generating the trimap comprises: detecting at least one persona feature in the given frame; generating an alpha mask by aligning an intermediate contour with the detected persona feature(s), wherein the intermediate contour is based on a color-based flood-fill operation performed on a previous frame which was segmented by a machine-learning-segmentation process; and generating the trimap based on the generated alpha mask. The generated trimap is output for extracting a user persona.

    METHODS AND SYSTEMS FOR ASSIGNING PIXELS DISTANCE-COST VALUES USING A FLOOD FILL TECHNIQUE
    7.
    发明申请
    METHODS AND SYSTEMS FOR ASSIGNING PIXELS DISTANCE-COST VALUES USING A FLOOD FILL TECHNIQUE 有权
    使用FLOOD FILL技术分配像素距离成本值的方法和系统

    公开(公告)号：US20160343141A1

    公开(公告)日：2016-11-24

    申请号：US14716495

    申请日：2015-05-19

    申请人： Personify, Inc.

    发明人： Dennis Lin ,  Quang Nguyen ,  Gia Dang ,  Yi Zhang ,  Simion Venshtain ,  Cong Nguyen

    IPC分类号： G06T7/00 ,  G06K9/62 ,  G06K9/46 ,  G06K9/00 ,  G06T7/40

    CPC分类号： G06K9/00718 ,  G06K9/00281 ,  G06K9/00758 ,  G06K9/4604 ,  G06K9/4652 ,  G06K9/52 ,  G06K9/627 ,  G06T7/0002 ,  G06T7/11 ,  G06T7/12 ,  G06T7/181 ,  G06T7/187 ,  G06T7/194 ,  G06T7/50 ,  G06T7/73 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/20156 ,  G06T2207/30196 ,  G06T2207/30201

    摘要： Disclosed herein are methods and systems for assigning pixels distance-cost values using a flood fill technique. One embodiment takes the form of a process that includes obtaining video data depicting a head of a user, obtaining depth data associated with the video data, and selecting seed pixels for a flood fill at least in part by using the depth information. The process also includes performing the flood fill from the selected seed pixels. The flood fill assigns respective distance-cost values to pixels of the video data based on position-space cost values and color-space cost values. In some embodiments, the process also includes classifying pixels of the video data as foreground based at least in part on the assigned distance-cost values. In some other embodiments, the process also includes assigning pixels of the video data foreground-likelihood values based at least in part on the assigned distance-cost values.

    摘要翻译： 这里公开了使用洪水填充技术来分配像素距离成本值的方法和系统。 一个实施例采取以下处理的形式：包括获取描绘用户头部的视频数据，获得与视频数据相关联的深度数据，以及至少部分地通过使用深度信息来选择洪水填充的种子像素。 该过程还包括从所选择的种子像素执行洪水填充。 洪水填充基于位置空间成本值和颜色空间成本值，将相应的距离成本值分配给视频数据的像素。 在一些实施例中，该过程还包括至少部分地基于所分配的距离成本值将视频数据的像素分类为前景。 在一些其它实施例中，该过程还包括至少部分地基于所分配的距离成本值来分配视频数据前景似然值的像素。

    SYSTEMS AND METHODS COMPRESSION, TRANSFER, AND RECONSTRUCTION OF THREE-DIMENSIONAL (3D) DATA MESHES
    9.
    发明申请
    SYSTEMS AND METHODS COMPRESSION, TRANSFER, AND RECONSTRUCTION OF THREE-DIMENSIONAL (3D) DATA MESHES 审中-公开

    公开(公告)号：US20190043252A1

    公开(公告)日：2019-02-07

    申请号：US15865126

    申请日：2018-01-08

    申请人： Personify, Inc.

    发明人： Simion Venshtain ,  Yi Zhang ,  Cong Nguyen

    IPC分类号： G06T17/20 ,  H04N7/15 ,  G06F3/0481

    摘要： Systems and methods relate to encoded video streams including geometric-data streams transmitted to a receiver for rendering of a viewpoint-adaptive 3D persona. A method includes obtaining at least one triangle-based three-dimensional (3D) submesh of a subject, wherein the obtained triangle-based 3D submesh includes a plurality of submesh vertices that define a plurality of submesh triangles, identifying a plurality of strips of the submesh triangles, generating triangle-strip data representing the identified strips of submesh triangles, generating compressed-submesh data that includes the triangle-strip data, and transmitting the compressed-submesh data to a receiver for reconstruction of the triangle-based 3D submesh of the subject.