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. 发明申请

WO2009148422A1 SYSTEM AND METHOD FOR SIMILARITY SEARCH OF IMAGES 审中-公开
标题翻译：用于图像相似搜索的系统和方法
公开(公告)号：WO2009148422A1
公开(公告)日：2009-12-10
申请号：PCT/US2008/007208
申请日：2008-06-06
申请人： THOMSON LICENSING , ZHANG, Dong-Qing , JOSHI, Rajan , BENITEZ, Ana B. , LUO, Ying , GUO, Ju
发明人： ZHANG, Dong-Qing , JOSHI, Rajan , BENITEZ, Ana B. , LUO, Ying , GUO, Ju
IPC分类号： G06F17/30
CPC分类号： G06F17/30247 , G06F17/30265
摘要： A system and method for an efficient semantic similarity search of images with a classification structure are provided. The system and method provide for building a semantic classification-search tree for the plurality of images (202), the classification tree including at least two categories of images, each category of images representing a subset of the plurality of images, receiving a query image (204), classifying the query image to select one of the at least two categories of images (208), and restricting the search for the image of interest using the query image to the selected one of the at least two categories of images (210).
摘要翻译：提供了一种用于具有分类结构的图像的有效语义相似性搜索的系统和方法。该系统和方法提供用于构建多个图像（202）的语义分类搜索树，分类树包括至少两个图像类别，每个类别的图像表示多个图像的子集，接收查询图像（204），对所述查询图像进行分类以选择所述至少两个类别的图像（208）中的一个，并且使用所述查询图像将所搜索的所述图像搜索到所述至少两个图像类别（210 ）。

2. 发明申请

WO2009139740A1 SYSTEM AND METHOD FOR MEASURING POTENTIAL EYESTRAIN OF STEREOSCOPIC MOTION PICTURES 审中-公开
标题翻译：用于测量立体运动图像的潜在眼睛的系统和方法
公开(公告)号：WO2009139740A1
公开(公告)日：2009-11-19
申请号：PCT/US2008/006036
申请日：2008-05-12
申请人： THOMSON LICENSING , ZHANG, Dong-Qing , BENITEZ, Ana B.
发明人： ZHANG, Dong-Qing , BENITEZ, Ana B.
IPC分类号： H04N17/00 , A61B3/00 , A61B5/00 , G06F19/00
CPC分类号： H04N17/00 , H04N13/128 , H04N13/144 , H04N2213/002
摘要： A system and method for measuring the potential eyestrain felt by audiences while watching a 3D presentation, e.g., a stereoscopic motion picture, are provided. The eyestrain measurement system and method of the present disclosure is based on the measurement of disparity (or depth) and disparity transition of stereoscopic images of the 3D presentation. The system and method of the present disclosure provide for acquiring a first image and a second image from a first segment (202), estimating disparity of at least one point in the first image with at least one corresponding point in the second image (204), estimating disparity transition of a sequence of first and second images (206), and determining potential eyestrain felt while viewing the 3D presentation based on the disparity and the disparity transition of the sequence of the first and second images (208).
摘要翻译：提供了一种用于在观看3D呈现（例如，立体声电影）的同时测量受众感觉到的潜在眼睛疲劳的系统和方法。本公开的眼睛疲劳测量系统和方法基于对3D呈现的立体图像的视差（或深度）和视差转变的测量。本公开的系统和方法提供从第一段（202）获取第一图像和第二图像，用第二图像（204）中的至少一个对应点估计第一图像中的至少一个点的视差，估计第一和第二图像序列的视差转变，以及基于所述第一和第二图像（208）的序列的视差和视差转变来确定在观看3D呈现期间感觉到的潜在眼睛疲劳。

3. 发明申请

WO2009008864A1 SYSTEM AND METHOD FOR THREE-DIMENSIONAL OBJECT RECONSTRUCTION FROM TWO-DIMENSIONAL IMAGES 审中-公开
标题翻译：用于三维图像三维对象重建的系统和方法
公开(公告)号：WO2009008864A1
公开(公告)日：2009-01-15
申请号：PCT/US2007/015891
申请日：2007-07-12
申请人： THOMSON LICENSING , IZZAT, Izzat H. , ZHANG, Dong-Qing , BENITEZ, Ana B.
发明人： IZZAT, Izzat H. , ZHANG, Dong-Qing , BENITEZ, Ana B.
IPC分类号： G06T7/00
CPC分类号： G06T7/55
摘要： A system and method for three-dimensional acquisition and modeling of a scene using two-dimensional images are provided. The present disclosure provides a system and method for selecting and combining the three-dimensional acquisition techniques that best fit the capture environment and conditions under consideration, and hence produce more accurate three-dimensional models. The system and method provide for acquiring at least two two-dimensional images of a scene (202), applying a first depth acquisition function to the at least two two-dimensional images (214), applying a second depth acquisition function to the at least two two-dimensional images (218), combining an output of the first depth acquisition function with an output of the second depth acquisition function (222), and generating a disparity or depth map from the combined output (224). The system and method also provide for reconstructing a three-dimensional model of the scene from the generated disparity or depth map.
摘要翻译：提供了一种使用二维图像对场景进行三维采集和建模的系统和方法。本公开提供了一种用于选择和组合最适合所考虑的捕获环境和条件的三维捕获技术并因此产生更准确的三维模型的系统和方法。所述系统和方法提供用于获取场景（202）的至少两个二维图像，将至少两个二维图像（214）应用第一深度获取功能，至少向所述至少两个二维图像应用第二深度获取功能两个二维图像（218），将第一深度获取函数的输出与第二深度获取函数（222）的输出组合，以及从组合输出（224）生成视差或深度图。该系统和方法还提供从生成的视差或深度图重构场景的三维模型。

4. 发明公开

EP2089852A1 METHODS AND SYSTEMS FOR COLOR CORRECTION OF 3D IMAGES 审中-公开
标题翻译： VERFAHREN UND SYSTEME ZUR FARBKORREKTUR VON 3D-BILDERN
公开(公告)号：EP2089852A1
公开(公告)日：2009-08-19
申请号：EP06838107.8
申请日：2006-11-21
申请人： Thomson Licensing
发明人： BENITEZ, Ana B. , ZHANG, Dong-Qing , FANCHER, James A.
IPC分类号： G06T15/20 , G06T15/50 , H04N1/60
CPC分类号： G06T15/20 , G06T15/50
摘要： A system and method for color correction of 3D images including at least two separate image streams captured for a same scene include determining three-dimensional properties of at least a portion of a selected image stream, the three-dimensional properties including light and surface reflectance properties, surface color, reflectance properties, scene geometry and the like. A look of the portion of the selected image stream is then modified by altering the value of at least one of the determined three-dimensional properties and, in one embodiment, applying image formation theory. The modifications are then rendered in an output 3D picture either automatically and/or according to user inputs. In various embodiments, corrections made to the selected one of the at least two image streams can be automatically applied to the other of the image streams.
摘要翻译：包括为相同场景捕获的至少两个单独图像流的3D图像的颜色校正的系统和方法包括确定所选图像流的至少一部分的三维特性，包括光和表面反射性质的三维特性，表面颜色，反射性，场景几何等。然后通过改变所确定的三维属性中的至少一个的值，并且在一个实施例中应用图像形成理论来修改所选图像流的部分的外观。然后，这些修改将自动地和/或根据用户输入呈现在输出3D图片中。在各种实施例中，对所选择的至少两个图像流中的一个进行的校正可以被自动地应用于另一个图像流。

5. 发明公开

EP2274920A1 SYSTEM AND METHOD FOR MEASURING POTENTIAL EYESTRAIN OF STEREOSCOPIC MOTION PICTURES 审中-公开
标题翻译：体系和计量张力的运动立体图像的潜在眼病方法
公开(公告)号：EP2274920A1
公开(公告)日：2011-01-19
申请号：EP08754362.5
申请日：2008-05-12
申请人： Thomson Licensing
发明人： ZHANG, Dong-Qing , BENITEZ, Ana B.
IPC分类号： H04N17/00 , A61B3/00 , A61B5/00 , G06F19/00
CPC分类号： H04N17/00 , H04N13/128 , H04N13/144 , H04N2213/002
摘要： A system and method for measuring the potential eyestrain felt by audiences while watching a 3D presentation, e.g., a stereoscopic motion picture, are provided. The eyestrain measurement system and method of the present disclosure is based on the measurement of disparity (or depth) and disparity transition of stereoscopic images of the 3D presentation. The system and method of the present disclosure provide for acquiring a first image and a second image from a first segment, estimating disparity of at least one point in the first image with at least one corresponding point in the second image, estimating disparity transition of a sequence of first and second images, and determining potential eyestrain felt while viewing the 3D presentation based on the disparity and the disparity transition of the sequence of the first and second images.

6. 发明公开

EP2300941A1 SYSTEM AND METHOD FOR SIMILARITY SEARCH OF IMAGES 审中-公开
标题翻译：系统和方法相似搜索IMAGES
公开(公告)号：EP2300941A1
公开(公告)日：2011-03-30
申请号：EP08768276.1
申请日：2008-06-06
申请人： Thomson Licensing
发明人： ZHANG, Dong-Qing , JOSHI, Rajan , BENITEZ, Ana B. , LUO, Ying , GUO, Ju
IPC分类号： G06F17/30
CPC分类号： G06F17/30247 , G06F17/30265
摘要： A system and method for an efficient semantic similarity search of images with a classification structure are provided. The system and method provide for building a semantic classification-search tree for the plurality of images (202), the classification tree including at least two categories of images, each category of images representing a subset of the plurality of images, receiving a query image (204), classifying the query image to select one of the at least two categories of images (208), and restricting the search for the image of interest using the query image to the selected one of the at least two categories of images (210).

7. 发明公开

EP2168096A1 SYSTEM AND METHOD FOR THREE-DIMENSIONAL OBJECT RECONSTRUCTION FROM TWO-DIMENSIONAL IMAGES 审中-公开
标题翻译：系统在VERFAHREN ZUR DREIDIMENSIONALEN OBJEKTREKONSTRUKTION AUS ZWEIDIMENSIONALEN BILDERN
公开(公告)号：EP2168096A1
公开(公告)日：2010-03-31
申请号：EP07796821.2
申请日：2007-07-12
申请人： Thomson Licensing
发明人： IZZAT, Izzat H. , ZHANG, Dong-Qing , BENITEZ, Ana B.
IPC分类号： G06T7/00
CPC分类号： G06T7/55
摘要： A system and method for three-dimensional acquisition and modeling of a scene using two-dimensional images are provided. The present disclosure provides a system and method for selecting and combining the three-dimensional acquisition techniques that best fit the capture environment and conditions under consideration, and hence produce more accurate three-dimensional models. The system and method provide for acquiring at least two two-dimensional images of a scene (202), applying a first depth acquisition function to the at least two two-dimensional images (214), applying a second depth acquisition function to the at least two two-dimensional images (218), combining an output of the first depth acquisition function with an output of the second depth acquisition function (222), and generating a disparity or depth map from the combined output (224). The system and method also provide for reconstructing a three-dimensional model of the scene from the generated disparity or depth map.
摘要翻译：提供了一种使用二维图像对场景进行三维采集和建模的系统和方法。本公开提供了一种用于选择和组合最适合所考虑的捕获环境和条件的三维捕获技术的系统和方法，因此产生更准确的三维模型。所述系统和方法提供用于获取场景的至少两个二维图像，对所述至少两个二维图像应用第一深度获取功能，向所述至少两个二维图像应用第二深度获取功能，将第一深度获取功能的输出与第二深度获取功能的输出组合，以及从组合输出生成视差或深度图。该系统和方法还提供从生成的视差或深度图重建场景的三维模型。

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