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

US09025009B2 Method and systems for obtaining an improved stereo image of an object 有权
标题翻译：用于获得对象的改进的立体图像的方法和系统
公开(公告)号：US09025009B2
公开(公告)日：2015-05-05
申请号：US13509666
申请日：2010-11-23
申请人： Sammy Lievens , Donny Tytgat , Jean-Francois Macq , Maarten Aerts
发明人： Sammy Lievens , Donny Tytgat , Jean-Francois Macq , Maarten Aerts
IPC分类号： H04N13/02 , H04N13/00
CPC分类号： H04N13/239 , H04N13/128 , H04N13/243 , H04N13/246
摘要： An exemplary technique is provided for obtaining an improved depth precision for a stereo image of an object of interest. The technique includes imaging a first image of the object of interest from a first position, imaging a second image of the object of interest from a second position different from the first position, determining a rough estimate of a depth for the object of interest based on the first image and the second image, determining an improved set of imaging positions corresponding to an improved depth precision for the object of interest based on the rough estimate of the depth, imaging improved images from the improved set of imaging positions, and determining an improved depth based on the improved images.
摘要翻译：提供了一种用于获得感兴趣对象的立体图像的改进的深度精度的示例性技术。该技术包括从第一位置成像感兴趣对象的第一图像，从不同于第一位置的第二位置对感兴趣对象的第二图像进行成像，基于以下方式确定感兴趣对象的深度的粗略估计：第一图像和第二图像，基于深度的粗略估计确定对应于针对感兴趣对象的改进的深度精度的改进的成像位置集合，从改进的成像位置集合成像改进的图像，以及确定改进的基于改进图像的深度。

2. 发明申请

US20120307017A1 METHOD AND SYSTEMS FOR OBTAINING AN IMPROVED STEREO IMAGE OF AN OBJECT 有权
标题翻译：用于获得对象改进的立体图像的方法和系统
公开(公告)号：US20120307017A1
公开(公告)日：2012-12-06
申请号：US13509666
申请日：2010-11-23
申请人： Sammy Lievens , Donny Tytgat , Jean-Francois Macq , Maarten Aerts
发明人： Sammy Lievens , Donny Tytgat , Jean-Francois Macq , Maarten Aerts
IPC分类号： H04N13/02
CPC分类号： H04N13/239 , H04N13/128 , H04N13/243 , H04N13/246
摘要： A method for obtaining an improved depth precision for a stereo image of an object of interest is disclosed, comprising: imaging a first image of the object of interest from a first position; imaging a second image of the object of interest from a second position different from the first position; wherein the method comprises determining a rough estimate of the depth for the object of interest, based on the first image and the second image; determining an improved set of imaging positions corresponding to an improved depth precision for the object of interest, based on the rough estimate of the depth; imaging improved images from the improved set of imaging positions; determining an improved depth based on the improved images. Also associated systems have been described.
摘要翻译：公开了一种用于获得感兴趣对象的立体图像的改进的深度精度的方法，包括：从第一位置对所述感兴趣对象的第一图像进行成像; 从与第一位置不同的第二位置成像感兴趣对象的第二图像; 其中所述方法包括基于所述第一图像和所述第二图像来确定所述感兴趣对象的深度的粗略估计; 基于深度的粗略估计，确定对应于针对感兴趣对象的改进的深度精度的改进的成像位置集合; 从改进的成像位置成像改进的图像; 基于改进的图像确定改进的深度。还描述了相关联的系统。

3. 发明授权

US09589369B2 Method and arrangement for improved image matching 有权
标题翻译：改进图像匹配的方法和布置
公开(公告)号：US09589369B2
公开(公告)日：2017-03-07
申请号：US13509760
申请日：2010-12-07
申请人： Donny Tytgat , Jean-Francois Macq , Sammy Lievens , Maarten Aerts
发明人： Donny Tytgat , Jean-Francois Macq , Sammy Lievens , Maarten Aerts
IPC分类号： G06T7/20 , G06K9/00 , G06T7/00
CPC分类号： G06T7/285 , G06K9/00201 , G06T7/579 , G06T7/593 , G06T2207/10021
摘要： A method and device for determining at least one set of matching attributes between a plurality of images is disclosed. Two dimensional images are projected to a three dimensional space then searched for matching attributes. Searching for corresponding attributes is much easier and computationally less intensive in the 3D space compared to a search in the 2D space. The method includes steps of projecting at least part of the images of said plurality to a 3-dimensional space resulting in a plurality of 3-D projected images (image1_3D, image2_3D), searching for at least one corresponding set of elements within the 3D projected images of the plurality of 3-D projected images, and calculating back said corresponding elements within the original images of the plurality and providing said corresponding elements within said original images as said at least one set of matched attributes.
摘要翻译：公开了一种用于确定多个图像之间的至少一组匹配属性的方法和装置。将二维图像投影到三维空间，然后搜索匹配属性。与2D空间中的搜索相比，搜索相应的属性在3D空间中容易得多，计算量少。该方法包括以下步骤：将所述多个图像的至少部分图像投影到三维空间，从而产生多个3D投影图像（image3_3D，image2_3D），搜索3D投影中的至少一个对应的元素组并且计算所述多个原始图像内的所述对应元素，并将所述原始图像内的所述相应元素提供为所述至少一组匹配的属性。

4. 发明授权

US09303525B2 Method and arrangement for multi-camera calibration 有权
标题翻译：多相机校准的方法和布置
公开(公告)号：US09303525B2
公开(公告)日：2016-04-05
申请号：US13582164
申请日：2011-03-08
申请人： Maarten Aerts , Donny Tytgat , Jean-Francois Macq , Sammy Lievens
发明人： Maarten Aerts , Donny Tytgat , Jean-Francois Macq , Sammy Lievens
IPC分类号： F01D21/00 , G06T7/00 , F01D25/00 , G01N21/15 , G01N21/85 , G02B23/24 , G01N21/954
CPC分类号： F01D21/003 , F01D25/00 , F05D2260/80 , G01N21/15 , G01N21/85 , G01N21/954 , G01N2021/151 , G01N2201/08 , G02B23/2492 , G06T7/85 , G06T2207/10012
摘要： A method for determining calibration data for at least two cameras (camera1, camera2) in a multi view position, includes a step of determining respective parameters ((h100, . . . , h122), (h200, . . . , h222)) for identifying at least one respective homographic transformation on respective images (image1,image2) taken by said cameras of a same scene, by performing respective geometry analyses on said respective images (image1, image2), a step of performing at least one respective combined homographic transformation/feature detection step on said respective images thereby obtaining respective sets (feature set1, feature set2) of features on respective transformed images, such that said calibration data are obtained from matches (ml, . . . , mk) determined between said respective sets of features.
摘要翻译：一种用于确定多视点位置中的至少两个照相机（camera1，camera2）的校准数据的方法，包括确定各个参数（（h100，...，h122），（h200，...，h222））的步骤用于通过对所述各个图像（image1，image2）执行相应的几何分析来识别由相同场景的所述相机拍摄的各个图像（image1，image2）上的至少一个相应的单色变换;执行至少一个相应的组合同形变换/特征检测步骤，从而获得各个变换图像上的特征的相应集合（特征集1，特征集2），使得所述校准数据从在所述各组之间确定的匹配（ml，...，mk）的功能。

5. 发明申请

US20130070108A1 METHOD AND ARRANGEMENT FOR MULTI-CAMERA CALIBRATION 有权
标题翻译：多相度校准的方法和布置
公开(公告)号：US20130070108A1
公开(公告)日：2013-03-21
申请号：US13582164
申请日：2011-03-08
申请人： Maarten Aerts , Donny Tytgat , Jean-Francois Macq , Sammy Lievens
发明人： Maarten Aerts , Donny Tytgat , Jean-Francois Macq , Sammy Lievens
IPC分类号： H04N17/00 , G06K9/46
CPC分类号： F01D21/003 , F01D25/00 , F05D2260/80 , G01N21/15 , G01N21/85 , G01N21/954 , G01N2021/151 , G01N2201/08 , G02B23/2492 , G06T7/85 , G06T2207/10012
摘要： A method for determining calibration data for at least two cameras (camera1, camera2) in a multi view position, includes a step of determining respective parameters ((h100, . . . , h122), (h200, . . . , h222)) for identifying at least one respective homographic transformation on respective images (image1,image2) taken by said cameras of a same scene, by performing respective geometry analyses on said respective images (image1, image2), a step of performing at least one respective combined homographic transformation/feature detection step on said respective images thereby obtaining respective sets (feature set1, feature set2) of features on respective transformed images, such that said calibration data are obtained from matches (m1, . . . , mk) determined between said respective sets of features.
摘要翻译：一种用于确定多视点位置中的至少两个照相机（camera1，camera2）的校准数据的方法，包括确定各个参数（（h100，...，h122），（h200，...，h222））的步骤用于通过对所述各个图像（image1，image2）执行相应的几何分析来识别由相同场景的所述相机拍摄的各个图像（image1，image2）上的至少一个相应的单色变换;执行至少一个相应的组合同形变换/特征检测步骤，从而获得各个变换图像上的特征的各个集合（特征集1，特征集2），使得所述校准数据从在所述各个集合之间确定的匹配（m1，...，mk）的功能。

6. 发明申请

US20120299911A1 METHOD AND ARRANGEMENT FOR IMPROVED IMAGE MATCHING 有权
标题翻译：改进图像匹配的方法和布置
公开(公告)号：US20120299911A1
公开(公告)日：2012-11-29
申请号：US13509760
申请日：2010-12-07
申请人： Donny Tytgat , Jean-Francois Macq , Sammy Lievens , Maarten Aerts
发明人： Donny Tytgat , Jean-Francois Macq , Sammy Lievens , Maarten Aerts
IPC分类号： G06T15/00
CPC分类号： G06T7/285 , G06K9/00201 , G06T7/579 , G06T7/593 , G06T2207/10021
摘要： A method and device for determining at least one set of matching attributes between a plurality of images is disclosed. Two dimensional images are projected to a three dimensional space then searched for matching attributes. Searching for corresponding attributes is much easier and computationally less intensive in the 3D space compared to a search in the 2D space. The method includes steps of projecting at least part of the images of said plurality to a 3-dimensional space resulting in a plurality of 3-D projected images (image1_3D, image2_3D), searching for at least one corresponding set of elements within the 3D projected images of the plurality of 3-D projected images, and calculating back said corresponding elements within the original images of the plurality and providing said corresponding elements within said original images as said at least one set of matched attributes.
摘要翻译：公开了一种用于确定多个图像之间的至少一组匹配属性的方法和装置。将二维图像投影到三维空间，然后搜索匹配属性。与2D空间中的搜索相比，搜索相应的属性在3D空间中容易得多，计算量少。该方法包括以下步骤：将所述多个图像的至少部分图像投影到三维空间，从而产生多个3D投影图像（image3_3D，image2_3D），搜索3D投影中的至少一个对应的元素组并且计算所述多个原始图像内的所述对应元素，并将所述原始图像内的所述相应元素提供为所述至少一组匹配的属性。

7. 发明申请

US20130185353A1 METHOD, SERVER AND TERMINAL FOR GENERATING A COMPOSITE VIEW FROM MULTIPLE CONTENT ITEMS 审中-公开
标题翻译：用于从多个内容项目生成复合视图的方法，服务器和终端
公开(公告)号：US20130185353A1
公开(公告)日：2013-07-18
申请号：US13809939
申请日：2011-07-13
申请人： Patrice Rondao Alface , Jean-Francois Macq
发明人： Patrice Rondao Alface , Jean-Francois Macq
IPC分类号： H04L29/06
CPC分类号： H04L65/60 , H04N5/445 , H04N21/21805 , H04N21/234327 , H04N21/234381 , H04N21/23439 , H04N21/23614 , H04N21/2365 , H04N21/2402 , H04N21/25825 , H04N21/25833 , H04N21/26258 , H04N21/2662 , H04N21/44222 , H04N21/4424 , H04N21/4728 , H04N21/6377 , H04N21/6582 , H04N21/6587 , H04N21/84
摘要： A method for generating a composite view (300) from multiple content items through interaction between a terminal (100) and a server (20), comprising the steps of: —transferring from the terminal (100) to the server (200) a terminal description (111) containing a capability profile of the terminal (100); —transferring from the server (200) to the terminal (100) information (212) indicative for available content items and interaction modes; and —transferring from the terminal (100) to the server (200) information indicative for selected content items and selected interaction modes, and an iterative process of: —streaming from the server (200) to the terminal (100) selected content items (113, 114; 213, 214) optimized according to the terminal description and the selected interaction modes; —fusing one or more of the content items in the terminal (100); —rendering the composite view (300) from fused content items; —transferring feedback from the terminal (100) to the server (200); and —adapting the streamed content items (113, 114; 213, 214) based on the feedback.
摘要翻译：一种用于通过终端（100）和服务器（20）之间的交互从多个内容项目生成复合视图（300）的方法，包括以下步骤： - 从所述终端（100）向所述服务器（200）传送终端包含终端（100）的能力简档的描述（111）; - 从所述服务器（200）向所述终端（100）传送指示可用内容项和交互模式的信息（212）; 以及从终端（100）向服务器（200）发送指示所选择的内容项目和所选择的交互模式的信息，以及从服务器（200）向终端（100）选择的内容项目 113,114; 213,214），根据终端描述和所选择的交互模式进行优化; - 在终端（100）中引用一个或多个内容项; - 从融合内容项目中导出复合视图（300）; - 从终端（100）向服务器（200）传送反馈; 以及基于所述反馈来适应流传输的内容项目（113,114; 213,214）。

8. 发明申请

US20130321576A1 METHODS AND APPARATUS FOR ENCODING AND DECODING A MULTIVIEW VIDEO STREAM 审中-公开
标题翻译：编辑和解码多媒体视频流的方法和装置
公开(公告)号：US20130321576A1
公开(公告)日：2013-12-05
申请号：US13908855
申请日：2013-06-03
申请人： Jean-Francois Macq , Christoph Stevens , Patrice Rondao Alface , Sigurd Van Broeck
发明人： Jean-Francois Macq , Christoph Stevens , Patrice Rondao Alface , Sigurd Van Broeck
IPC分类号： H04N13/00
CPC分类号： H04N13/161 , H04N13/111 , H04N13/156 , H04N13/172 , H04N19/29 , H04N19/30 , H04N19/46 , H04N19/587 , H04N19/597 , H04N19/61
摘要： A method for encoding a multiview video stream representing a plurality of viewpoints of a 3D scenery comprising objects, the method comprising for each of said viewpoints rendering and encoding a plurality of 2D video streams, respective ones of said plurality of 2D video streams including color information, depth information, and transparency information pertaining to objects in respective object layers serializing said plurality of 2D video streams into a combined 2D video stream; including said combined 2D video stream into said multiview video stream.
摘要翻译：一种用于编码表示包括对象的3D风景的多个视点的多视点视频流的方法，所述方法包括用于对所述多个2D视频流进行渲染和编码的每个所述视点，所述多个2D视频流中的相应的2D视频流包括颜色信息，深度信息和与各个对象层中的对象相关联的透明度信息，将所述多个2D视频流串行化为组合的2D视频流; 将所述组合的2D视频流包括到所述多视点视频流中。

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