专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US09607397B2 Methods and systems for generating a user-hair-color model 有权
公开(公告)号：US09607397B2
公开(公告)日：2017-03-28
申请号：US14842525
申请日：2015-09-01
申请人： Personify, Inc.
发明人： Dennis Lin , Glenn Francisco , Yi Zhang , Gia Dang , Simion Venshtain , Quang Nguyen , Long Dang
IPC分类号： G06K9/00 , G06T7/00 , G06K9/46 , H04N5/225
CPC分类号： G06T7/12 , G06K9/4652 , G06T7/11 , G06T7/507 , G06T7/90 , G06T2207/30196 , H04N5/225
摘要： Disclosed herein are methods and systems for generating a user-hair-color model. One embodiment takes the form of a process that includes obtaining video data depicting a head of a user. The process also includes determining a set of line segments of pixels of the video data, wherein each line segment in the determined set of line segments intersects an upper contour of the depicted head of the user. The process also includes grouping at least some of the pixels of at least one of the line segments in the determined set of line segments into three sets of pixels based at least in part on respective color data of the pixels. The three sets of pixels include a skin-pixel set, a hair-pixel set, and a background-pixel set. The process also includes updating a user hair-color model based at least in part on the skin-pixel set.

2. 发明授权

US09563962B2 Methods and systems for assigning pixels distance-cost values using a flood fill technique 有权
标题翻译：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。

3. 发明申请

US20150189146A1 Systems and Methods for Iterative Adjustment of Video-Capture Settings Based on Identified Persona 有权
标题翻译：基于识别的角色的视频捕获设置的迭代调整系统和方法
公开(公告)号：US20150189146A1
公开(公告)日：2015-07-02
申请号：US14145880
申请日：2013-12-31
申请人： Personify, Inc.
发明人： Simion Venshtain , Sanjay Patel , Dennis J. Lin
IPC分类号： H04N5/235 , H04N7/15 , H04N5/243 , G06T7/00
CPC分类号： H04N5/2352 , G06K9/00234 , G06K9/00288 , G06T7/11 , G06T7/143 , G06T7/194 , G06T7/73 , G06T2207/10016 , G06T2207/30196 , H04N5/23219 , H04N5/23296 , H04N5/2353 , H04N5/243 , H04N7/147
摘要： Disclosed herein are systems and methods for iterative adjustment of video-capture settings based on identified persona. In an embodiment, a method includes receiving video frames being captured by a video camera of an ongoing scene. The method also includes identifying a persona in one or more of the received frames at least in part by identifying, in each such frame, a set of pixels that is representative of the persona in the frame and that does not include any pixels representative of a background of the frame. The method also includes selecting, based collectively on the brightness values of the pixels in the identified set of pixels of one or more frames, an adjustment command for one or more adjustable video-capture settings of the camera, as well as outputting the selected commands to the camera for use in continuing to capture video data representative of the ongoing scene.
摘要翻译：本文公开了用于基于识别的角色迭代地调整视频捕获设置的系统和方法。在一个实施例中，一种方法包括接收由正在进行的场景的摄像机捕获的视频帧。该方法还包括至少部分地通过在每个这样的帧中识别表示帧中的角色的一组像素，并且不包括代表一个或多个框架的背景。该方法还包括集中地基于所识别的一个或多个帧的像素集合中的像素的亮度值来选择用于照相机的一个或多个可调视频捕捉设置的调整命令，以及输出所选择的命令用于继续拍摄表示正在进行的场景的视频数据。

4. 发明申请

US20190043266A1 SYSTEMS AND METHODS FOR REFERENCE-MODEL-BASED MODIFICATION OF A THREE-DIMENSIONAL (3D) MESH DATA MODEL 审中-公开
公开(公告)号：US20190043266A1
公开(公告)日：2019-02-07
申请号：US15865129
申请日：2018-01-08
申请人： Personify, Inc.
发明人： Simion Venshtain , Po-Han Huang
IPC分类号： G06T19/20 , G06T17/20 , G06T7/73
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 a three-dimensional (3D) mesh of a subject generated from depth-camera-captured information about the subject, obtaining a facial-mesh model, locating a facial portion of the obtained 3D mesh of the subject, computing a geometric transform based on the facial portion and the facial-mesh model, the geometric transform determined in response to one or more aggregated error differences between a plurality of feature points on the facial-mesh model and a plurality of corresponding feature points on the facial portion of the obtained 3D mesh, generating a transformed facial-mesh model using the geometric transform and generating a hybrid mesh of the subject at least in part by combining the transformed facial-mesh model and at least a portion of the obtained 3D mesh.

5. 发明申请

US20170061640A1 METHODS AND SYSTEMS FOR GENERATING A USER-HAIR-COLOR MODEL 有权
标题翻译：用于生成用户头发颜色模型的方法和系统
公开(公告)号：US20170061640A1
公开(公告)日：2017-03-02
申请号：US14842525
申请日：2015-09-01
申请人： Personify, Inc.
发明人： Dennis Lin , Glenn Francisco , Yi Zhang , Gia Dang , Simion Venshtain , Quang Nguyen , Long Dang
IPC分类号： G06T7/00 , H04N5/225 , G06K9/46
CPC分类号： G06T7/12 , G06K9/4652 , G06T7/11 , G06T7/507 , G06T7/90 , G06T2207/30196 , H04N5/225
摘要： Disclosed herein are methods and systems for generating a user-hair-color model. One embodiment takes the form of a process that includes obtaining video data depicting a head of a user. The process also includes determining a set of line segments of pixels of the video data, wherein each line segment in the determined set of line segments intersects an upper contour of the depicted head of the user. The process also includes grouping at least some of the pixels of at least one of the line segments in the determined set of line segments into three sets of pixels based at least in part on respective color data of the pixels. The three sets of pixels include a skin-pixel set, a hair-pixel set, and a background-pixel set. The process also includes updating a user hair-color model based at least in part on the skin-pixel set.
摘要翻译：这里公开了用于生成用户头发颜色模型的方法和系统。一个实施例采用包括获取描绘用户头部的视频数据的过程的形式。该过程还包括确定视频数据的像素的一组线段，其中所确定的一组线段中的每个线段与所描绘的用户头部的上部轮廓相交。该过程还包括至少部分地基于像素的相应颜色数据将所确定的线段集合中的至少一个线段的至少一些像素分组为三组像素。三组像素包括皮肤像素组，头发像素组和背景像素组。该过程还包括至少部分地基于皮肤像素集更新用户头发颜色模型。

6. 发明授权

US09485433B2 Systems and methods for iterative adjustment of video-capture settings based on identified persona 有权
标题翻译：基于识别角色的视频捕获设置的迭代调整的系统和方法
公开(公告)号：US09485433B2
公开(公告)日：2016-11-01
申请号：US14145880
申请日：2013-12-31
申请人： Personify, Inc.
发明人： Simion Venshtain , Sanjay Patel , Dennis J. Lin
IPC分类号： H04N5/235 , H04N7/15 , H04N5/243 , G06T7/00 , H04N7/14 , G06K9/00
CPC分类号： H04N5/2352 , G06K9/00234 , G06K9/00288 , G06T7/11 , G06T7/143 , G06T7/194 , G06T7/73 , G06T2207/10016 , G06T2207/30196 , H04N5/23219 , H04N5/23296 , H04N5/2353 , H04N5/243 , H04N7/147
摘要： Disclosed herein are systems and methods for iterative adjustment of video-capture settings based on identified persona. In an embodiment, a method includes receiving video frames being captured by a video camera of an ongoing scene. The method also includes identifying a persona in one or more of the received frames at least in part by identifying, in each such frame, a set of pixels that is representative of the persona in the frame and that does not include any pixels representative of a background of the frame. The method also includes selecting, based collectively on the brightness values of the pixels in the identified set of pixels of one or more frames, an adjustment command for one or more adjustable video-capture settings of the camera, as well as outputting the selected commands to the camera for use in continuing to capture video data representative of the ongoing scene.
摘要翻译：本文公开了用于基于识别的角色迭代地调整视频捕获设置的系统和方法。在一个实施例中，一种方法包括接收由正在进行的场景的摄像机捕获的视频帧。该方法还包括至少部分地通过在每个这样的帧中识别表示帧中的角色的一组像素，并且不包括代表一个或多个框架的背景。该方法还包括集中地基于所识别的一个或多个帧的像素集合中的像素的亮度值来选择用于照相机的一个或多个可调视频捕捉设置的调整命令，以及输出所选择的命令用于继续拍摄表示正在进行的场景的视频数据。

7. 发明申请

US20190045157A1 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.

8. 发明授权

US09881207B1 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.

9. 发明申请

US20170147882A1 METHODS AND SYSTEMS FOR ASSIGNING PIXELS DISTANCE-COST VALUES USING A FLOOD FILL TECHNIQUE 有权
公开(公告)号：US20170147882A1
公开(公告)日：2017-05-25
申请号：US15425331
申请日：2017-02-06
申请人： PERSONIFY, INC.
发明人： Dennis Lin , Quang Nguyen , Gia Dang , Yi Zhang , Simion Venshtain , Cong Nguyen
IPC分类号： G06K9/00 , G06T7/73 , G06T7/194 , G06T7/00 , G06K9/52 , G06T7/50 , G06K9/46
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.

10. 发明申请

US20170048440A1 SYSTEMS AND METHODS FOR ITERATIVE ADJUSTMENT OF VIDEO-CAPTURE SETTINGS BASED ON IDENTIFIED PERSONA 有权
标题翻译：基于识别人员的视频收集设置的迭代调整系统和方法
公开(公告)号：US20170048440A1
公开(公告)日：2017-02-16
申请号：US15339274
申请日：2016-10-31
申请人： PERSONIFY, INC.
发明人： Simion Venshtain , Sanjay Patel , Dennis J. Lin
IPC分类号： H04N5/235 , H04N5/232
CPC分类号： H04N5/2352 , G06K9/00234 , G06K9/00288 , G06T7/11 , G06T7/143 , G06T7/194 , G06T7/73 , G06T2207/10016 , G06T2207/30196 , H04N5/23219 , H04N5/23296 , H04N5/2353 , H04N5/243 , H04N7/147
摘要： Disclosed herein are systems and methods for iterative adjustment of video-capture settings based on identified persona. In an embodiment, a method includes receiving video frames being captured by a video camera of an ongoing scene. The method also includes identifying a persona in one or more of the received frames at least in part by identifying, in each such frame, a set of pixels that is representative of the persona in the frame and that does not include any pixels representative of a background of the frame. The method also includes selecting, based collectively on the brightness values of the pixels in the identified set of pixels of one or more frames, an adjustment command for one or more adjustable video-capture settings of the camera, as well as outputting the selected commands to the camera for use in continuing to capture video data representative of the ongoing scene.
摘要翻译：本文公开了用于基于识别的角色迭代地调整视频捕获设置的系统和方法。在一个实施例中，一种方法包括接收由正在进行的场景的摄像机捕获的视频帧。该方法还包括至少部分地通过在每个这样的帧中识别表示帧中的角色的一组像素，并且不包括代表一个或多个框架的背景。该方法还包括集中地基于所识别的一个或多个帧的像素集合中的像素的亮度值来选择用于照相机的一个或多个可调视频捕捉设置的调整命令，以及输出所选择的命令用于继续拍摄表示正在进行的场景的视频数据。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式