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. 发明公开

EP1825438A4 SYSTEM AND METHOD FOR CAPTURING FACIAL AND BODY MOTION 有权
标题翻译： SYSTEM UND VERFAHREN ZUR ERFASSUNG VON GESICHTS- UNDKÖRPERBEWEGUNGEN
公开(公告)号：EP1825438A4
公开(公告)日：2017-06-21
申请号：EP05852558
申请日：2005-11-30
申请人： SONY CORP , SONY PICTURES ENTERTAINMENT INC
发明人： GORDON DEMIAN
IPC分类号： G06T7/246 , G06K9/00 , G06T7/593 , G06T15/70 , H04N5/222
CPC分类号： G06K9/00255 , G06K9/3216 , G06T7/246 , G06T7/596 , G06T7/80 , H04N5/222
摘要： A system and method for capturing motion comprises a motion capture volume adapted to contain at least one actor having body markers defining plural body points and facial markers defining plural facial points. A plurality of motion cameras are arranged around a periphery of the motion capture volume. The motion cameras are arranged such that all laterally exposed surfaces of the actor while in motion within the motion capture volume are within the field of view of at least one of the plurality of the motion cameras at substantially all times. A motion capture processor is coupled to the plurality of motion cameras to produce a digital model reflecting combined body and facial motion of the actor. At least one microphone may be oriented to pick up audio from the motion capture volume.
摘要翻译：用于捕捉运动的系统和方法包括运动捕捉体积，该运动捕捉体积适于包含至少一个具有定义多个身体点的身体标记和定义多个面部点的面部标记的演员。多个运动摄像机围绕运动捕捉体积的外围布置。运动摄像机被布置为使得运动捕捉体积内运动者在运动中的所有横向暴露表面在基本上所有时间内都处于多个运动摄像机中的至少一个运动摄像机的视野内。运动捕捉处理器耦合到多个运动相机以产生反映演员的组合身体和面部运动的数字模型。至少一个麦克风可以被定向为从运动捕捉体积拾取音频。

2. 发明公开

EP2987140A1 MIXING INFRARED AND COLOR COMPONENT DATA POINT CLOUDS 有权
标题翻译：密执安红十字国际委员会
公开(公告)号：EP2987140A1
公开(公告)日：2016-02-24
申请号：EP14726821.3
申请日：2014-04-14
申请人： Microsoft Technology Licensing, LLC
发明人： SWEENEY, Patrick John , HARNETT, David F.
IPC分类号： G06T7/00 , G06K9/62 , G06K9/38 , G06K9/03 , H04N9/75 , H04N13/02 , G01S17/48
CPC分类号： H04N13/106 , G01B11/22 , G06K9/03 , G06K9/38 , G06K9/6293 , G06T7/11 , G06T7/136 , G06T7/174 , G06T7/194 , G06T7/521 , G06T7/593 , G06T7/596 , G06T2207/10016 , G06T2207/10024 , G06T2207/10028 , G06T2207/10048 , G06T2207/20021 , H04N5/272 , H04N9/75 , H04N13/271
摘要： The subject disclosure is directed towards mixing RGB data with infrared data so as to provide depth-related data in regions where infrared data are sparse. Infrared data, such as corresponding to point cloud data, are processed to determine sparse regions therein. For any such sparse regions, RGB data corresponding to a counterpart region in the RGB data are added to a data structure. The data structure, which may include or be concatenated to the IR data, may be used for depth-related data, e.g., with a point cloud.
摘要翻译：本发明涉及将RGB数据与红外数据混合，以便在红外数据稀疏的区域中提供深度相关数据。处理红点数据，例如对应于点云数据，以确定其中的稀疏区域。对于任何这样的稀疏区域，对应于RGB数据中的对应区域的RGB数据被添加到数据结构。可以包括或连接到IR数据的数据结构可以用于例如与点云相关的深度相关数据。

3. 发明公开

EP2987139A1 MULTIMODAL FOREGROUND BACKGROUND SEGMENTATION 审中-公开
标题翻译： MULTIMODALE SEGMENTIERUNG VON VORDER- UNDHINTERGRÜNDEN
公开(公告)号：EP2987139A1
公开(公告)日：2016-02-24
申请号：EP14726262.0
申请日：2014-04-14
申请人： Microsoft Technology Licensing, LLC
发明人： COLLET ROMEA, Alvaro , ZHANG, Bao , KIRK, Adam, G.
IPC分类号： G06T7/00 , G06K9/62 , G06K9/38 , G06K9/03 , H04N9/75
CPC分类号： H04N13/106 , G01B11/22 , G06K9/03 , G06K9/38 , G06K9/6293 , G06T7/11 , G06T7/136 , G06T7/174 , G06T7/194 , G06T7/521 , G06T7/593 , G06T7/596 , G06T2207/10016 , G06T2207/10024 , G06T2207/10028 , G06T2207/10048 , G06T2207/20021 , H04N5/272 , H04N9/75 , H04N13/271
摘要： The subject disclosure is directed towards mixing RGB data with infrared data so as to provide depth-related data in regions where infrared data are sparse. Infrared data, such as corresponding to point cloud data, are processed to determine sparse regions therein. For any such sparse regions, RGB data corresponding to a counterpart region in the RGB data are added to a data structure. The data structure, which may include or be concatenated to the IR data, may be used for depth-related data, e.g., with a point cloud.
摘要翻译：本发明涉及将RGB数据与红外数据混合，以便在红外数据稀疏的区域中提供深度相关数据。处理红点数据，例如对应于点云数据，以确定其中的稀疏区域。对于任何这样的稀疏区域，对应于RGB数据中的对应区域的RGB数据被添加到数据结构。可以包括或连接到IR数据的数据结构可以用于例如与点云相关的深度相关数据。

4. 发明公开

EP2856431A4 COMBINING NARROW-BASELINE AND WIDE-BASELINE STEREO FOR THREE-DIMENSIONAL MODELING 无效
标题翻译： STEREOIN控股与窄基线和宽基线组合用于三维建模
公开(公告)号：EP2856431A4
公开(公告)日：2015-07-29
申请号：EP13794453
申请日：2013-05-09
申请人： GOOGLE INC
发明人： GALLUP DAVID , GOLOVINSKIY ALEKSY , LIN MICHAEL HONGMAI , REINHARDT TILMAN
IPC分类号： G06T7/00 , G06T17/00
CPC分类号： G06T7/596 , G06T17/00

5. 发明公开

EP2271123A3 Apparatus acquiring 3D distance information and image 审中-公开
标题翻译： Vorrichtung zur Erwerbung von 3D Entfernungsdaten und zur Bildaufnahme
公开(公告)号：EP2271123A3
公开(公告)日：2012-01-04
申请号：EP10167076.8
申请日：2010-06-23
申请人： SiliconFile Technologies Inc.
发明人： Lee, Byoung Su
IPC分类号： H04N13/00 , G01C11/06 , G06T7/00 , G01S11/12 , G01S17/48
CPC分类号： G01S11/12 , G01C11/06 , G06T7/596 , G06T2207/10012 , H04N13/243
摘要： An apparatus for acquiring distance information and images includes an image sensor unit including a left image sensor, a central image sensor, and a right image sensor, which are arranged on one board while being spaced apart from one another at a predetermined interval, and a distance information extraction unit that extracts distance information by comparing an image of a reference object acquired through the central image sensor with an image of the reference object acquired through the left image sensor and an image of the reference object acquired through the right image sensor.
摘要翻译：一种用于获取距离信息和图像的装置包括：图像传感器单元，包括左图像传感器，中央图像传感器和右图像传感器，它们以预定的间隔彼此间隔开地布置在一个板上;以及距离信息提取单元，其通过将通过中央图像传感器获取的参考对象的图像与通过左图像传感器获取的参考对象的图像和通过右图像传感器获取的参考对象的图像进行比较来提取距离信息。

6. 发明公开

EP2076055A1 Method for displaying a virtual image 有权
标题翻译：一种用于显示虚拟图像的方法
公开(公告)号：EP2076055A1
公开(公告)日：2009-07-01
申请号：EP07445047.9
申请日：2007-12-27
申请人： Saab AB
发明人： Andersson, Ingmar , Isaksson, Folke , Haglund, Leif
IPC分类号： H04N13/00 , G06T7/00
CPC分类号： H04N13/10 , G06T7/596 , G06T2207/10012 , G06T2207/20088 , G06T2207/30181
摘要： The present invention relates to a method for displaying a virtual image of three dimensional objects in an area using stereo recordings (23) of the area for storing (24) a pixel and a height for each point of the area. The object of the invention is to obtain a method enabling displaying of vertical surfaces or even slightly downwards and inwards inclined surfaces. The object is obtained by a method using stereo recordings from at least three different stereo recordings of different solid angels. For each different solid angel at least one data base comprising data about texture and height pixel point wise is established. Data for displaying the virtual image are combined (26) from the different data bases in dependence of the direction in which the virtual image is to be displayed (27).

7. 发明公开

EP1940181A1 Solid-state imaging device, camera, vehicle and surveillance device. 审中-公开
标题翻译：固态成像设备，照相机，车辆监视装置
公开(公告)号：EP1940181A1
公开(公告)日：2008-07-02
申请号：EP07119569.7
申请日：2007-10-30
申请人： Matsushita Electric Industrial Co., Ltd.
发明人： Takeda, Katsumi
IPC分类号： H04N13/00
CPC分类号： G01S11/12 , G06T7/596 , G06T2207/10012 , G06T2207/10021 , H04N13/218 , H04N13/257
摘要： The solid-state imaging device according to the present invention includes: an imaging unit which includes photoelectric conversion elements arranged in a matrix in a region having a first imaging region and a second imaging region; a first light introduction unit which guides and introduces light into the first imaging region; a second light introduction unit provided apart from the first light introduction unit and which guide and introduces light into the second imaging region; an output unit which: converts signal charge, which the photoelectric conversion elements arranged in the first imaging region have photoelectrically converted, into voltage or current and outputs the converted voltage or current as a first video signal; and converts signal charge, which the photoelectric conversion elements arranged in the second imaging region have photoelectrically converted, into voltage or current, and outputs the converted voltage or current as a second video signal; and a calculation unit which calculates information related to distance to an object using the first video signal and the second video signal outputted by the output unit; wherein the imaging unit, the output unit and the calculation unit are formed on the same semiconductor substrate.

8. 发明公开

EP1612732A3 Interactive viewpoint video system and process 有权
标题翻译： Interaktives Blickpunktvideo-system und Verfahren
公开(公告)号：EP1612732A3
公开(公告)日：2006-12-06
申请号：EP05105244.7
申请日：2005-06-15
申请人： MICROSOFT CORPORATION
发明人： Zitnick III, Charles , Uyttendaele, Matthew , Szeliski, Richard , Winder, Simon , Kang, Sing Bing
IPC分类号： G06T15/00 , G06T15/20 , G06T7/00
CPC分类号： H04N5/2627 , G06T7/557 , G06T7/596 , G06T15/205 , G06T2207/10021
摘要： A system and process for generating, and then rendering and displaying, an interactive viewpoint video in which a user can watch a dynamic scene while manipulating (freezing, slowing down, or reversing) time and changing the viewpoint at will. In general, the interactive viewpoint video is generated using a small number of cameras to capture multiple video streams. A multi-view 3D reconstruction and matting technique is employed to create a layered representation of the video frames that enables both efficient compression and interactive playback of the captured dynamic scene, while at the same time allowing for real-time rendering.
摘要翻译：用于生成并呈现和交互的视频视频的系统和过程，其中用户可以在操纵（冻结，减慢或反转）时间并随意改变视点的同时观看动态场景。通常，使用少量摄像机生成交互视点视频以捕获多个视频流。采用多视图3D重建和消隐技术来创建视频帧的分层表示，使得能够实现捕获的动态场景的有效压缩和交互式回放，同时允许实时渲染。

9. 发明公开

EP1286307A2 Recovering depth from multiple images using multi-plane and spatial propagation 审中-公开
标题翻译：通过多层次，多空间再现多个图像的深度调查
公开(公告)号：EP1286307A2
公开(公告)日：2003-02-26
申请号：EP02255370.5
申请日：2002-07-31
申请人： STMicroelectronics, Inc.
发明人： Chen, George Q.
IPC分类号： G06T7/00
CPC分类号： G06K9/32 , G06T7/596
摘要： An image processing system recovers 3-D depth information for pixels of a base image representing a view of a scene. The system detects a plurality of pixels in a base image that represents a first view of a scene. The system the determines 3-D depth of the plurality of pixels in the base image by matching correspondence to a plurality of pixels in a plurality of images representing a plurality of views of the scene. The system then traces pixels in a virtual piecewise continuous depth surface by spatial propagation starting from the detected pixels in the base image by using the matching and corresponding plurality of pixels in the plurality of images to create the virtual piecewise continuous depth surface viewed from the base image, each successfully traced pixel being associated with a depth in the scene viewed from the base image.
摘要翻译：一种图像处理系统中恢复用于表示场景的视图中的基本图像的像素的3-D的深度信息。系统检测像素在碱图像的多个做了darstellt一个场景的第一视图。该系统通过在表示视图的场景的多个图像的多元性对应匹配的像素的多个基本图像中的像素的多个所述bestimmt 3-D的深度。然后，该系统跟踪由使用匹配和相应的像素的多元性图像的多元性创建从基观察的虚拟分段连续深度表面在虚拟分段连续深度表面通过空间传播的像素从所述基本图像中检测到的像素开始图像，每个成功地追溯到像素被用在从基本图像观察到的场景的深度相关联。

10. 发明公开

EP3395066A1 DEPTH MAP GENERATION APPARATUS, METHOD AND NON-TRANSITORY COMPUTER-READABLE MEDIUM THEREFOR 有权
公开(公告)号：EP3395066A1
公开(公告)日：2018-10-31
申请号：EP15897379.2
申请日：2015-12-25
申请人： BOE Technology Group Co., Ltd.
发明人： ZHAO, Jibo , YU, Jing
IPC分类号： H04N13/02
CPC分类号： G06T7/596 , G06T7/40 , G06T2207/10028 , H04N13/106 , H04N13/128 , H04N13/20 , H04N13/243 , H04N2013/0081
摘要： The present disclosure provides a depth map generation apparatus, including a camera assembly with at least three cameras, an operation mode determination module and a depth map generation module. The camera assembly with at least three cameras may a first camera, a second camera and a third camera that are sequentially aligned on a same axis. The operation mode determination module may be configured to determine an operation mode of the camera assembly. The operation mode includes at least: a first mode using images of non-adjacent cameras, and a second mode using images of adjacent cameras. Further, the depth map generation module may be configured to generate depth maps according to the determined operation mode.

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