公开(公告)号：US08000533B2

公开(公告)日：2011-08-16

申请号：US11559852

申请日：2006-11-14

申请人： Yasuyuki Matsushita ,  Hong-Wen Kang ,  Xiaoou Tang

发明人： Yasuyuki Matsushita ,  Hong-Wen Kang ,  Xiaoou Tang

IPC分类号： G06K9/46

CPC分类号： G11B27/034 ,  G06F17/30802 ,  G06F17/30843 ,  G06K9/00751 ,  G06K9/4671 ,  G11B27/28

摘要： Systems and methods for space-time video montage are described. In one aspect, one or more arbitrary space-time volumes representing informative video portion(s) of at least one input video data sequence are identified. A video summary representing a montage of the at least one input video data sequence is generated for presentation to user from the one or more arbitrary space-time volumes.

摘要翻译： 描述了时空视频蒙太奇的系统和方法。 在一个方面中，识别表示至少一个输入视频数据序列的信息性视频部分的一个或多个任意时空容量。 生成表示至少一个输入视频数据序列的蒙太奇的视频摘要，用于从一个或多个任意时空卷呈现给用户。

公开(公告)号：US20080112684A1

公开(公告)日：2008-05-15

申请号：US11559852

申请日：2006-11-14

申请人： Yasuyuki Matsushita ,  Hong-Wen Kang ,  Xiaoou Tang

发明人： Yasuyuki Matsushita ,  Hong-Wen Kang ,  Xiaoou Tang

IPC分类号： H04N5/93

CPC分类号： G11B27/034 ,  G06F17/30802 ,  G06F17/30843 ,  G06K9/00751 ,  G06K9/4671 ,  G11B27/28

摘要： Systems and methods for space-time video montage are described. In one aspect, one or more arbitrary space-time volumes representing informative video portion(s) of at least one input video data sequence are identified. A video summary representing a montage of the at least one input video data sequence is generated for presentation to user from the one or more arbitrary space-time volumes.

摘要翻译： 描述了时空视频蒙太奇的系统和方法。 在一个方面中，识别表示至少一个输入视频数据序列的信息性视频部分的一个或多个任意时空容量。 生成表示至少一个输入视频数据序列的蒙太奇的视频摘要，用于从一个或多个任意时空卷呈现给用户。

公开(公告)号：US08243805B2

公开(公告)日：2012-08-14

申请号：US11559861

申请日：2006-11-14

申请人： Yasuyuki Matsushita ,  Sing Bing Kang ,  Xiaoou Tang ,  Takaaki Shiratori

发明人： Yasuyuki Matsushita ,  Sing Bing Kang ,  Xiaoou Tang ,  Takaaki Shiratori

IPC分类号： H04N7/12

CPC分类号： G06T5/005 ,  G06T5/20 ,  G06T5/50 ,  G06T2207/10016 ,  G06T2207/20016

摘要： Systems and methods for video completion by motion field transfer are described. In one aspect, a spatio-temporal target patch of an input video data sequence is filled in or replaced by motion field transfer from a spatio-temporal source patch of the input video data sequence. Color is propagated to corresponding portions of the spatio-temporal target patch by treating the transferred motion information as directed edges. These motion field transfer and color propagation operations result in a video completed spatio-temporal target patch. The systems and methods present the video data sequence, which now includes the video completed spatio-temporal target patch, to user for viewing.

摘要翻译： 描述了通过运动场传输进行视频完成的系统和方法。 在一个方面，输入视频数据序列的时空目标贴片由输入视频数据序列的时空源片段填充或由运动场传输代替。 通过将转移的运动信息作为有向边缘进行处理，将颜色传播到时空目标贴片的相应部分。 这些运动场传输和颜色传播操作导致视频完成时空目标补丁。 系统和方法呈现视频数据序列，其现在包括视频完成的时空目标补丁，供用户观看。

公开(公告)号：US07711047B2

公开(公告)日：2010-05-04

申请号：US11275265

申请日：2005-12-21

申请人： Yasuyuki Matsushita ,  Xiaoou Tang ,  Francois Alter

发明人： Yasuyuki Matsushita ,  Xiaoou Tang ,  Francois Alter

IPC分类号： H04N7/18

CPC分类号： G06K9/38 ,  G06K9/40

摘要： A Poisson-quantization noise model for modeling noise in low-light conditions is described. In one aspect, image information is received. A Poisson-quantization noise model is then generated from a Poisson noise model and a quantization noise model. Poisson-quantization noise is then estimated in the image information using the Poisson-quantization noise model.

摘要翻译： 描述了用于在低光条件下建模噪声的泊松量化噪声模型。 一方面，接收图像信息。 然后从泊松噪声模型和量化噪声模型生成泊松量化噪声模型。 然后使用泊松量化噪声模型在图像信息中估计泊松量化噪声。

公开(公告)号：US20080112642A1

公开(公告)日：2008-05-15

申请号：US11559861

申请日：2006-11-14

申请人： Yasuyuki Matsushita ,  Sing Bing Kang ,  Xiaoou Tang ,  Takaaki Shiratori

发明人： Yasuyuki Matsushita ,  Sing Bing Kang ,  Xiaoou Tang ,  Takaaki Shiratori

IPC分类号： G06K9/40

CPC分类号： G06T5/005 ,  G06T5/20 ,  G06T5/50 ,  G06T2207/10016 ,  G06T2207/20016

摘要： Systems and methods for video completion by motion field transfer are described. In one aspect, a spatio-temporal target patch of an input video data sequence is filled in or replaced by motion field transfer from a spatio-temporal source patch of the input video data sequence. Color is propagated to corresponding portions of the spatio-temporal target patch by treating the transferred motion information as directed edges These motion field transfer and color propagation operations result in a video completed spatio-temporal target patch. The systems and methods present the video data sequence, which now includes the video completed spatio-temporal target patch, to user for viewing.

摘要翻译： 描述了通过运动场传输进行视频完成的系统和方法。 在一个方面，输入视频数据序列的时空目标贴片由输入视频数据序列的时空源片段填充或由运动场传输代替。 通过将转移的运动信息作为有向边缘进行处理，将颜色传播到时空目标贴片的相应部分。这些运动场转移和颜色传播操作导致视频完成的时空目标贴片。 系统和方法呈现视频数据序列，其现在包括视频完成的时空目标补丁，供用户观看。

公开(公告)号：US20100303367A1

公开(公告)日：2010-12-02

申请号：US12772690

申请日：2010-05-03

申请人： Yasuyuki Matsushita ,  Xiaoou Tang ,  Francois Alter

发明人： Yasuyuki Matsushita ,  Xiaoou Tang ,  Francois Alter

IPC分类号： G06K9/68

CPC分类号： G06K9/38 ,  G06K9/40

摘要： A Poisson-quantization noise model for modeling noise in low-light conditions is described. In one aspect, image information is received. A Poisson-quantization noise model is then generated from a Poisson noise model and a quantization noise model. Poisson-quantization noise is then estimated in the image information using the Poisson-quantization noise model.

摘要翻译： 描述了用于在低光条件下建模噪声的泊松量化噪声模型。 一方面，接收图像信息。 然后从泊松噪声模型和量化噪声模型生成泊松量化噪声模型。 然后使用泊松量化噪声模型在图像信息中估计泊松量化噪声。

公开(公告)号：US20070147677A1

公开(公告)日：2007-06-28

申请号：US11275265

申请日：2005-12-21

申请人： Yasuyuki Matsushita ,  Xiaoou Tang ,  Francois Alter

发明人： Yasuyuki Matsushita ,  Xiaoou Tang ,  Francois Alter

IPC分类号： G06K9/62

CPC分类号： G06K9/38 ,  G06K9/40

摘要： A Poisson-quantization noise model for modeling noise in low-light conditions is described. In one aspect, image information is received. A Poisson-quantization noise model is then generated from a Poisson noise model and a quantization noise model. Poisson-quantization noise is then estimated in the image information using the Poisson-quantization noise model.

摘要翻译： 描述了用于在低光条件下建模噪声的泊松量化噪声模型。 一方面，接收图像信息。 然后从泊松噪声模型和量化噪声模型生成泊松量化噪声模型。 然后使用泊松量化噪声模型在图像信息中估计泊松量化噪声。

公开(公告)号：US20130308853A1

公开(公告)日：2013-11-21

申请号：US13820729

申请日：2010-09-03

申请人： Xiaogang Wang ,  Xiaoou Tang ,  Wei Zhang

发明人： Xiaogang Wang ,  Xiaoou Tang ,  Wei Zhang

IPC分类号： G06K9/66

CPC分类号： G06K9/66 ,  G06T11/60 ,  G06T2210/22

摘要： The present invention discloses a system and method for synthesizing a portrait sketch from a photo. The method includes: dividing the photo into a set of photo patches; determining first matching information between each of the photo patches and training photo patches pre-divided from a set of training photos; determining second matching information between each of the photo patches and training sketch patches pre-divided from a set of training sketches; determining a shape prior for the portrait sketch to be synthesized; determining a set of matched training sketch patches for each of the photo patches based on the first and the second matching information and the shape prior; and synthesizing the portrait sketch from the determined matched training sketch patches.

摘要翻译： 本发明公开了一种用于从照片合成肖像素描的系统和方法。 该方法包括：将照片分成一组照片; 确定每个照片贴片和从一组训练照片预分割的训练照片补丁之间的第一匹配信息; 确定每个照片补丁和从一组训练草图预先划分的训练草图之间的第二匹配信息; 确定要合成的肖像草图之前的形状; 基于第一和第二匹配信息和形状先前，为每个照片贴片确定一组匹配的训练草图斑块; 并从确定的匹配训练草图中合成肖像素描。

公开(公告)号：US20100080450A1

公开(公告)日：2010-04-01

申请号：US12242421

申请日：2008-09-30

申请人： Deli Zhao ,  Zhouchen Lin ,  Xiaoou Tang

发明人： Deli Zhao ,  Zhouchen Lin ,  Xiaoou Tang

IPC分类号： G06K9/62

CPC分类号： G06K9/6234 ,  G06K9/6252

摘要： Described is using semi-Riemannian geometry in supervised learning to learn a discriminant subspace for classification, e.g., labeled samples are used to learn the geometry of a semi-Riemannian submanifold. For a given sample, the K nearest classes of that sample are determined, along with the nearest samples that are in other classes, and the nearest samples in that sample's same class. The distances between these samples are computed, and used in computing a metric matrix. The metric matrix is used to compute a projection matrix that corresponds to the discriminant subspace. In online classification, as a new sample is received, it is projected into a feature space by use of the projection matrix and classified accordingly.

摘要翻译： 描述了在监督学习中使用半黎曼几何学习学习用于分类的判别子空间，例如，标记的样本用于学习半黎曼子流形歧管的几何形状。 对于给定的样本，该样本的K个最近类别以及其他类别中最近的样本以及该样本同一类中最近的样本进行确定。 计算这些样本之间的距离，并用于计算度量矩阵。 度量矩阵用于计算与判别子空间对应的投影矩阵。 在线分类中，作为收到的新样本，通过使用投影矩阵将其投影到特征空间中并进行分类。

公开(公告)号：US20090297046A1

公开(公告)日：2009-12-03

申请号：US12129515

申请日：2008-05-29

申请人： Deli Zhao ,  Zhouchen Lin ,  Rong Xiao ,  Xiaoou Tang

发明人： Deli Zhao ,  Zhouchen Lin ,  Rong Xiao ,  Xiaoou Tang

IPC分类号： G06K9/62

CPC分类号： G06K9/00275 ,  G06K9/6234

摘要： An exemplary method for extracting discriminant feature of samples includes providing data for samples in a multidimensional space; based on the data, computing local similarities for the samples; mapping the local similarities to weights; based on the mapping, formulating an inter-class scatter matrix and an intra-class scatter matrix; and based on the matrices, maximizing the ratio of inter-class scatter to intra-class scatter for the samples to provide discriminate features of the samples. Such a method may be used for classifying samples, recognizing patterns, or other tasks. Various other methods, devices, system, etc., are also disclosed.

摘要翻译： 用于提取样本的判别特征的示例性方法包括在多维空间中提供样本的数据; 基于数据，计算样本的局部相似度; 将局部相似性映射到权重; 基于映射，制定类间散布矩阵和类内散布矩阵; 并且基于矩阵，最大化样本之间的类间散射与类内散射的比率以提供样本的区别特征。 这种方法可用于分类样本，识别模式或其他任务。 还公开了各种其它方法，装置，系统等。