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

US08503783B2 Optimization of multi-label problems in computer vision 失效
标题翻译：计算机视觉中多标签问题的优化
公开(公告)号：US08503783B2
公开(公告)日：2013-08-06
申请号：US13050825
申请日：2011-03-17
申请人： Carsten Rother , Victor Lempitsky , Andrew Blake
发明人： Carsten Rother , Victor Lempitsky , Andrew Blake
IPC分类号： G06K9/34
CPC分类号： G06K9/342 , G06K9/4638
摘要： A method of labeling pixels in an image is described where the pixel label is selected from a set of three or more labels. The pixel labeling problem is reduced to a sequence of binary optimizations by representing the label value for each pixel as a binary word and then optimizing the value of each bit within the word, starting with the most significant bit. Data which has been learned from one or more training images is used in the optimization to provide information about the less significant bits within the word.
摘要翻译：描述了一种标记图像中的像素的方法，其中从一组三个或更多个标签中选择像素标签。通过将每个像素的标签值表示为二进制字，然后优化字中每个位的值，从最高有效位开始，将像素标注问题简化为一系列二进制优化。在优化中使用已经从一个或多个训练图像中学习的数据来提供关于该单词内较低有效位的信息。

2. 发明授权

US07925089B2 Optimization of multi-label problems in computer vision 失效
标题翻译：计算机视觉中多标签问题的优化
公开(公告)号：US07925089B2
公开(公告)日：2011-04-12
申请号：US11857075
申请日：2007-09-18
申请人： Carsten Rother , Victor Lempitsky , Andrew Blake
发明人： Carsten Rother , Victor Lempitsky , Andrew Blake
IPC分类号： G06K9/34
CPC分类号： G06K9/342 , G06K9/4638
摘要： A method of labeling pixels in an image is described where the pixel label is selected from a set of three or more labels. The pixel labeling problem is reduced to a sequence of binary optimizations by representing the label value for each pixel as a binary word and then optimizing the value of each bit within the word, starting with the most significant bit. Data which has been learned from one or more training images is used in the optimization to provide information about the less significant bits within the word.
摘要翻译：描述了一种标记图像中的像素的方法，其中从一组三个或更多个标签中选择像素标签。通过将每个像素的标签值表示为二进制字，然后优化字中每个位的值，从最高有效位开始，将像素标注问题简化为一系列二进制优化。在优化中使用已经从一个或多个训练图像中学习的数据来提供关于该单词内较低有效位的信息。

3. 发明申请

US20100128984A1 Labeling Image Elements 有权
标题翻译：标记图像元素
公开(公告)号：US20100128984A1
公开(公告)日：2010-05-27
申请号：US12323355
申请日：2008-11-25
申请人： Victor Lempitsky , Carsten Rother , Andrew Blake
发明人： Victor Lempitsky , Carsten Rother , Andrew Blake
IPC分类号： G06K9/34
CPC分类号： G06K9/6224
摘要： An image processing system is described which automatically labels image elements of a digital image. In an embodiment an energy function describing the quality of possible labelings of an image is globally optimized to find an output labeled image. In the embodiment, the energy function comprises terms that depend on at least one non-local parameter. For example, the non-local parameter describes characteristics of image elements having the same label. In an embodiment the global optimization is achieved in a practical, efficient manner by using a tree structure to represent candidate values of the non-local parameter and by using a branch and bound process. In some embodiments, the branch and bound process comprises evaluating a lower bound of the energy function by using a min-cut process. For example, the min-cut process enables the lower bound to be evaluated efficiently using a graphical data structure to represent the lower bound.
摘要翻译：描述了自动标记数字图像的图像元素的图像处理系统。在一个实施例中，描述图像的可能标记的质量的能量函数被全局优化以找到输出标记图像。在该实施例中，能量函数包括依赖于至少一个非局部参数的项。例如，非本地参数描述具有相同标签的图像元素的特征。在一个实施例中，通过使用树结构来表示非局部参数的候选值并且通过使用分支和绑定过程，以实用，有效的方式实现全局优化。在一些实施例中，分支和绑定过程包括通过使用最小切割过程来评估能量函数的下限。例如，最小切割过程使得能够使用图形数据结构有效地评估下限来表示下限。

4. 发明申请

US20110164819A1 Optimization of Multi-Label Problems in Computer Vision 失效
标题翻译：计算机视觉中多标签问题的优化
公开(公告)号：US20110164819A1
公开(公告)日：2011-07-07
申请号：US13050825
申请日：2011-03-17
申请人： Carsten Rother , Victor Lempitsky , Andrew Blake
发明人： Carsten Rother , Victor Lempitsky , Andrew Blake
IPC分类号： G06K9/34
CPC分类号： G06K9/342 , G06K9/4638
摘要： A method of labeling pixels in an image is described where the pixel label is selected from a set of three or more labels. The pixel labeling problem is reduced to a sequence of binary optimizations by representing the label value for each pixel as a binary word and then optimizing the value of each bit within the word, starting with the most significant bit. Data which has been learned from one or more training images is used in the optimization to provide information about the less significant bits within the word.
摘要翻译：描述了一种标记图像中的像素的方法，其中从一组三个或更多个标签中选择像素标签。通过将每个像素的标签值表示为二进制字，然后优化字中每个位的值，从最高有效位开始，将像素标注问题简化为一系列二进制优化。在优化中使用已经从一个或多个训练图像中学习的数据来提供关于该单词内较低有效位的信息。

5. 发明申请

US20090074292A1 Optimization of Multi-Label Problems in Computer Vision 失效
标题翻译：计算机视觉中多标签问题的优化
公开(公告)号：US20090074292A1
公开(公告)日：2009-03-19
申请号：US11857075
申请日：2007-09-18
申请人： Carsten Rother , Victor Lempitsky , Andrew Blake
发明人： Carsten Rother , Victor Lempitsky , Andrew Blake
IPC分类号： G06K9/34
CPC分类号： G06K9/342 , G06K9/4638
摘要： A method of labeling pixels in an image is described where the pixel label is selected from a set of three or more labels. The pixel labeling problem is reduced to a sequence of binary optimizations by representing the label value for each pixel as a binary word and then optimizing the value of each bit within the word, starting with the most significant bit. Data which has been learned from one or more training images is used in the optimization to provide information about the less significant bits within the word.
摘要翻译：描述了一种标记图像中的像素的方法，其中从一组三个或更多个标签中选择像素标签。通过将每个像素的标签值表示为二进制字，然后优化字中每个位的值，从最高有效位开始，将像素标注问题简化为一系列二进制优化。在优化中使用已经从一个或多个训练图像中学习的数据来提供关于该单词内较低有效位的信息。

6. 发明授权

US08249349B2 Labeling image elements 有权
标题翻译：标记图像元素
公开(公告)号：US08249349B2
公开(公告)日：2012-08-21
申请号：US12323355
申请日：2008-11-25
申请人： Andrew Blake , Carsten Rother , Victor Lempitsky
发明人： Andrew Blake , Carsten Rother , Victor Lempitsky
IPC分类号： G06K9/34
CPC分类号： G06K9/6224
摘要： An image processing system is described which automatically labels image elements of a digital image. In an embodiment an energy function describing the quality of possible labelings of an image is globally optimized to find an output labeled image. In the embodiment, the energy function comprises terms that depend on at least one non-local parameter. For example, the non-local parameter describes characteristics of image elements having the same label. In an embodiment the global optimization is achieved in a practical, efficient manner by using a tree structure to represent candidate values of the non-local parameter and by using a branch and bound process. In some embodiments, the branch and bound process comprises evaluating a lower bound of the energy function by using a min-cut process. For example, the min-cut process enables the lower bound to be evaluated efficiently using a graphical data structure to represent the lower bound.
摘要翻译：描述了自动标记数字图像的图像元素的图像处理系统。在一个实施例中，描述图像的可能标记的质量的能量函数被全局优化以找到输出标记图像。在该实施例中，能量函数包括依赖于至少一个非局部参数的项。例如，非本地参数描述具有相同标签的图像元素的特征。在一个实施例中，通过使用树结构来表示非局部参数的候选值并且通过使用分支和绑定过程，以实用，有效的方式实现全局优化。在一些实施例中，分支和绑定过程包括通过使用最小切割过程来评估能量函数的下限。例如，最小切割过程使得能够使用图形数据结构有效地评估下限来表示下限。

7. 发明授权

US08213726B2 Image labeling using multi-scale processing 有权
标题翻译：图像标注使用多尺度处理
公开(公告)号：US08213726B2
公开(公告)日：2012-07-03
申请号：US12488119
申请日：2009-06-19
申请人： Pushmeet Kohli , Carsten Rother , Victor Lempitsky
发明人： Pushmeet Kohli , Carsten Rother , Victor Lempitsky
IPC分类号： G06K9/68
CPC分类号： G06K9/6857 , G06K9/6297 , G06T7/143
摘要： Multi-scale processing may be used to reduce the memory and computational requirements of optimization algorithms for image labeling, for example, for object segmentation, 3D reconstruction, stereo correspondence, optical flow and other applications. For example, in order to label a large image (or 3D volume) a multi-scale process first solves the problem at a low resolution, obtaining a coarse labeling of an original high resolution problem. This labeling is refined by solving another optimization on a subset of the image elements. In examples, an energy function for a coarse level version of an input image is formed directly from an energy function of the input image. In examples, the subset of image elements may be selected using a measure of confidence in the labeling.
摘要翻译：可以使用多尺度处理来减少用于图像标记的优化算法的存储器和计算要求，例如用于对象分割，3D重建，立体声对应，光流等应用。例如，为了标注大图像（或3D体积），多尺度处理首先以低分辨率解决问题，获得原始高分辨率问题的粗略标签。通过在图像元素的子集上求解另一个优化来改进该标记。在示例中，输入图像的粗略级版本的能量函数直接从输入图像的能量函数形成。在示例中，图像元素的子集可以使用标签中置信度的度量来选择。

8. 发明申请

US20080310743A1 Optimizing Pixel Labels for Computer Vision Applications 有权
标题翻译：优化计算机视觉应用的像素标签
公开(公告)号：US20080310743A1
公开(公告)日：2008-12-18
申请号：US11764002
申请日：2007-06-15
申请人： Carsten Rother , Victor Lempitsky , Vladimir Kolmogorov
发明人： Carsten Rother , Victor Lempitsky , Vladimir Kolmogorov
IPC分类号： G06K9/36
CPC分类号： G06K9/38 , G06T7/11 , G06T7/143
摘要： Computer vision applications often require each pixel within an image to be assigned one of a set of labels. A method of improving the labels assigned to pixels is described which uses the quadratic pseudoboolean optimization (QPBO) algorithm. Starting with a partially labeled solution, an unlabeled pixel is assigned a value from a fully labeled reference solution and the energy of the partially labeled solution plus this additional pixel is calculated. The calculated energy is then used to generate a revised partially labeled solution using QPBO.
摘要翻译：计算机视觉应用程序通常需要将图像中的每个像素分配给一组标签之一。描述了改进分配给像素的标签的方法，其使用二次伪布尔优化（QPBO）算法。从部分标记的解决方案开始，将未标记的像素从完全标记的参考解决方案中分配一个值，并计算部分标记溶液的能量加上该附加像素。然后计算的能量用于使用QPBO产生修正的部分标记溶液。

9. 发明授权

US08041114B2 Optimizing pixel labels for computer vision applications 有权
标题翻译：优化计算机视觉应用的像素标签
公开(公告)号：US08041114B2
公开(公告)日：2011-10-18
申请号：US11764002
申请日：2007-06-15
申请人： Carsten Rother , Victor Lempitsky , Vladimir Kolmogorov
发明人： Carsten Rother , Victor Lempitsky , Vladimir Kolmogorov
IPC分类号： G06K9/34
CPC分类号： G06K9/38 , G06T7/11 , G06T7/143
摘要： Computer vision applications often require each pixel within an image to be assigned one of a set of labels. A method of improving the labels assigned to pixels is described which uses the quadratic pseudoboolean optimization (QPBO) algorithm. Starting with a partially labeled solution, an unlabeled pixel is assigned a value from a fully labeled reference solution and the energy of the partially labeled solution plus this additional pixel is calculated. The calculated energy is then used to generate a revised partially labeled solution using QPBO.
摘要翻译：计算机视觉应用程序通常需要将图像中的每个像素分配给一组标签之一。描述了改进分配给像素的标签的方法，其使用二次伪布尔优化（QPBO）算法。从部分标记的解决方案开始，将未标记的像素从完全标记的参考解决方案中分配一个值，并计算部分标记溶液的能量加上该附加像素。然后计算的能量用于使用QPBO产生修正的部分标记溶液。

10. 发明申请

US20100322525A1 Image Labeling Using Multi-Scale Processing 有权
标题翻译：使用多尺度处理的图像标记
公开(公告)号：US20100322525A1
公开(公告)日：2010-12-23
申请号：US12488119
申请日：2009-06-19
申请人： Pushmeet Kohli , Carsten Rother , Victor Lempitsky
发明人： Pushmeet Kohli , Carsten Rother , Victor Lempitsky
IPC分类号： G06K9/68
CPC分类号： G06K9/6857 , G06K9/6297 , G06T7/143
摘要： Multi-scale processing may be used to reduce the memory and computational requirements of optimization algorithms for image labeling, for example, for object segmentation, 3D reconstruction, stereo correspondence, optical flow and other applications. For example, in order to label a large image (or 3D volume) a multi-scale process first solves the problem at a low resolution, obtaining a coarse labeling of an original high resolution problem. This labeling is refined by solving another optimization on a subset of the image elements. In examples, an energy function for a coarse level version of an input image is formed directly from an energy function of the input image. In examples, the subset of image elements may be selected using a measure of confidence in the labeling.
摘要翻译：可以使用多尺度处理来减少用于图像标记的优化算法的存储器和计算要求，例如用于对象分割，3D重建，立体声对应，光流等应用。例如，为了标注大图像（或3D体积），多尺度处理首先以低分辨率解决问题，获得原始高分辨率问题的粗略标签。通过在图像元素的子集上求解另一个优化来改进该标记。在示例中，输入图像的粗略级版本的能量函数直接从输入图像的能量函数形成。在示例中，图像元素的子集可以使用标签中置信度的度量来选择。

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