专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

131. 发明申请

US20050100236A1 System and method for classifying pixels in images 失效
标题翻译：用于对图像中的像素进行分类的系统和方法
公开(公告)号：US20050100236A1
公开(公告)日：2005-05-12
申请号：US10964756
申请日：2004-10-14
申请人： Hao-Song Kong , Yao Nie , Anthony Vetro , Huifang Sun
发明人： Hao-Song Kong , Yao Nie , Anthony Vetro , Huifang Sun
IPC分类号： G06T5/20 , G06K9/00 , G06K9/36 , G06K9/40 , G06T5/00 , H04N1/41 , H04N5/21 , H04N7/24 , H04N7/26 , H04N7/50
CPC分类号： H04N19/176 , G06K9/4604 , G06K9/4642 , G06T7/11 , G06T7/143 , G06T2207/20012 , G06T2207/20021 , H04N19/117 , H04N19/14 , H04N19/61 , H04N19/86
摘要： A method classifies pixels in an image by first partitioning the image into blocks. A variance of an intensity is determined for each pixel, and for each block the pixel with the maximum variance is identified. Then, the blocks are classified into classes according to the maximum variance.
摘要翻译：一种方法是通过首先将图像划分成块来对图像中的像素进行分类。对于每个像素确定强度的方差，并且对于每个块，识别具有最大方差的像素。然后，块根据最大方差分类。

132. 发明申请

US20050084014A1 Video encoding with motion-selective wavelet transform 失效
标题翻译：具有运动选择小波变换的视频编码
公开(公告)号：US20050084014A1
公开(公告)日：2005-04-21
申请号：US10688133
申请日：2003-10-17
申请人： Beibei Wang , Anthony Vetro , Yao Wang
发明人： Beibei Wang , Anthony Vetro , Yao Wang
IPC分类号： H04N7/12 , H04N7/26
CPC分类号： H04N19/615 , H04N19/13 , H04N19/39 , H04N19/61 , H04N19/63 , H04N19/635
摘要： A method encodes a video by applying a dual-tree discrete wavelet transform to the video to generate sequences of wavelet coefficients. The sequences are compressed to produce a compressed bitstream corresponding to the video. The compression iteratively selects the wavelet coefficients in a large to small order, and entropy encodes the selected wavelet coefficient.
摘要翻译：一种方法通过对视频应用双树离散小波变换来编码视频以产生小波系数序列。这些序列被压缩以产生对应于视频的压缩比特流。压缩以大到小的顺序迭代地选择小波系数，并且熵编码所选择的小波系数。

133. 发明申请

US20050063314A1 Method and system for content aware and energy efficient transmission of videos and images 审中-公开
标题翻译：视频和图像的内容感知和能量效率传输的方法和系统
公开(公告)号：US20050063314A1
公开(公告)日：2005-03-24
申请号：US10665606
申请日：2003-09-19
申请人： Zafer Sahinoglu , Wei Yu , Anthony Vetro
发明人： Zafer Sahinoglu , Wei Yu , Anthony Vetro
IPC分类号： H03M7/30 , H04L1/00 , H04L12/26 , H04L29/06 , H04N1/41 , H04N7/24 , H04N19/00
CPC分类号： H04L65/602 , H04L29/06027 , H04L65/80
摘要： A method selects source and channel codec parameters according to varying channel conditions and signal to noise ratio for a given distortion constraint. The processes of source and channel encoding and decoding with the selected parameter values and transmit power level per quality layer minimize a total energy consumption for delivery of multimedia content from a transmitting terminal to a receiving terminal. The total energy consumption is defined as the energy consumed while processing and transmitting the multimedia. Coding parameters, such as channel code rates, error resilience redundancy, unequal error protection level, and transmit power level can vary from layer to layer.
摘要翻译：一种方法根据变化的信道条件和给定失真约束的信噪比来选择源和信道编解码器参数。使用所选参数值的源和信道编码和解码的过程以及每个质量层的发射功率电平最小化用于从发射终端向接收终端传送多媒体内容的总能量消耗。总能量消耗被定义为处理和传输多媒体时消耗的能量。编码参数，例如信道码率，错误恢复冗余，不等错误保护级别和发射功率级别可以在不同的层次之间变化。

134. 发明授权

US06763069B1 Extraction of high-level features from low-level features of multimedia content 有权
标题翻译：从多媒体内容的低级功能中提取高级功能
公开(公告)号：US06763069B1
公开(公告)日：2004-07-13
申请号：US09610763
申请日：2000-07-06
申请人： Ajay Divakaran , Anthony Vetro , Huifang Sun , Peng Xu , Shih-Fu Chang
发明人： Ajay Divakaran , Anthony Vetro , Huifang Sun , Peng Xu , Shih-Fu Chang
IPC分类号： H04N712
CPC分类号： G06K9/00711
摘要： A method extracts high-level features from a video including a sequence of frames. Low-level features are extracted from each frame of the video. Each frame of the video is labeled according to the extracted low-level features to generate sequences of labels. Each sequence of labels is associated with one of the extracted low-level feature. The sequences of labels are analyzed using learning machine learning techniques to extract high-level features of the video.
摘要翻译：一种方法从包括帧序列的视频中提取高级特征。从视频的每个帧中提取低级功能。视频的每个帧根据提取的低级特征进行标记，以生成标签序列。标签的每个序列与提取的低级特征之一相关联。使用学习机器学习技术来分析标签序列以提取视频的高级特征。

135. 发明授权

US06671324B2 Estimating total average distortion in a video with variable frameskip 失效
公开(公告)号：US06671324B2
公开(公告)日：2003-12-30
申请号：US09835650
申请日：2001-04-16
申请人： Anthony Vetro , Huifang Sun , Yao Wang
发明人： Anthony Vetro , Huifang Sun , Yao Wang
IPC分类号： H04N712
CPC分类号： H04N17/004 , H04N19/132 , H04N19/139 , H04N19/147 , H04N19/149 , H04N19/15 , H04N19/152 , H04N19/172 , H04N19/61
摘要： A method determines distortion in a video by measuring a spatial distortion in coded frames, and by measuring a temporal distortion and spatial distortion in uncoded frames. The spatial distortion of the coded frames is combined with the temporal distortion and the spatial distortion of the uncoded frames to determine a total average distortion in the video.

136. 发明授权

US06546135B1 Method for representing and comparing multimedia content 失效
标题翻译：用于表示和比较多媒体内容的方法
公开(公告)号：US06546135B1
公开(公告)日：2003-04-08
申请号：US09385169
申请日：1999-08-30
申请人： I-Jong Lin , Anthony Vetro , Ajay Divakaran , Sun-Yuan Kung
发明人： I-Jong Lin , Anthony Vetro , Ajay Divakaran , Sun-Yuan Kung
IPC分类号： G06K946
CPC分类号： G06F17/30858 , Y10S707/99945 , Y10S707/99948
摘要： A method for generating a representation of multimedia content by first segmenting the multimedia content spatially and temporally to extract objects. Feature extraction is applied to the objects to produce semantic and syntactic attributes, relations, and a containment set of content entities. The content entities are coded to produce directed acyclic graphs of the content entities, where each directed acyclic graph represents a particular interpretation of the multimedia content.
摘要翻译：一种用于通过首先在空间和时间上分割多媒体内容以提取对象来生成多媒体内容的表示的方法。特征提取被应用于对象以产生语义和句法属性，关系以及内容实体的包含集合。内容实体被编码以产生内容实体的有向非循环图，其中每个有向无环图表示多媒体内容的特定解释。

137. 发明授权

US06542545B1 Estimating rate-distortion characteristics of binary shape data 失效
标题翻译：估计二进制形状数据的速率 - 失真特性
公开(公告)号：US06542545B1
公开(公告)日：2003-04-01
申请号：US09410552
申请日：1999-10-01
申请人： Anthony Vetro , Huifang Sun , Yao Wang , Onur G. Guleyruz
发明人： Anthony Vetro , Huifang Sun , Yao Wang , Onur G. Guleyruz
IPC分类号： H04N1102
CPC分类号： G06T9/20 , H04N19/147 , H04N19/21 , H04N19/29 , H04N19/33 , H04N19/40
摘要： A method estimates rate and distortion characteristics of a video object. First and second object shape features are respectively extracted at a first and second resolution of the video object. First and second rate distortion characteristics of the video object are respectively determined from the extracted first and second object shape features according to first and second modeling parameters. The extracted object shape features can be discrete, such as states of binary shape patterns of the video object, or the object shape features can be continuous such as a set of statistical moments representing a probability density function of the video object.
摘要翻译：方法估计视频对象的速率和失真特性。分别以视频对象的第一和第二分辨率提取第一和第二对象形状特征。根据第一和第二建模参数，从所提取的第一和第二对象形状特征分别确定视频对象的第一和第二速率失真特性。所提取的对象形状特征可以是离散的，诸如视频对象的二进制形状图案的状态，或者对象形状特征可以是连续的，例如表示视频对象的概率密度函数的一组统计矩。

138. 发明授权

US06400846B1 Method for ordering image spaces to search for object surfaces 失效
标题翻译：用于排序图像空间以搜索对象表面的方法
公开(公告)号：US06400846B1
公开(公告)日：2002-06-04
申请号：US09326750
申请日：1999-06-04
申请人： I-Jong Lin , Anthony Vetro , Huifang Sun , Sun-Yuan Kung
发明人： I-Jong Lin , Anthony Vetro , Huifang Sun , Sun-Yuan Kung
IPC分类号： G06K936
CPC分类号： G06T7/20 , G06T7/12 , G06T7/162 , G06T7/174 , G06T2207/10016
摘要： A method determines a surface of an object in a sequence of images. The method begins by estimating a boundary of the object in each image of the sequence using motion information of adjacent images of the sequence. Then, portions of each image of the sequence are ordered to produce an ordered sequence of images. The ordered portions are exterior to the estimated object boundary. Edges in each ordered image are filtered using the motion information, and each ordered image of the sequence is searched to locate the filtered edges to form a new boundary outside the estimated boundary. The filtering and searching are repeated, while projecting the new object boundaries over the sequence of images, until the new object boundaries converges to a surface of the object.
摘要翻译：方法确定图像序列中的对象的表面。该方法通过使用序列的相邻图像的运动信息来估计序列的每个图像中的对象的边界来开始。然后，序列的每个图像的部分被排序以产生有序的图像序列。有序部分在估计对象边界的外部。使用运动信息对每个有序图像中的边缘进行滤波，并且搜索序列的每个有序图像以定位经滤波的边缘以在估计边界外部形成新的边界。重复过滤和搜索，同时在图像序列上投影新对象边界，直到新对象边界收敛到对象的表面。

139. 发明授权

US08630444B2 Method for embedding messages into structure shapes 失效
标题翻译：将消息嵌入结构形状的方法
公开(公告)号：US08630444B2
公开(公告)日：2014-01-14
申请号：US12650289
申请日：2009-12-30
申请人： Shantanu Rane , Samarjit Das , Anthony Vetro
发明人： Shantanu Rane , Samarjit Das , Anthony Vetro
IPC分类号： G06K9/00
CPC分类号： G06K9/00416 , G06T1/005 , G06T2201/0051 , G06T2201/0062 , H04N1/3224
摘要： Embodiments of the invention disclose a system and a method for embedding a symbol in a glyph, comprising the steps of determining a set of landmarks representing an outline of the glyph; determining a data segment between two landmarks, wherein the data segment is suitable for embedding the symbol; modifying the data segment according to the symbol to produce a modified glyph such that the symbol is embedded in the modified glyph; and outputting the modified glyph.
摘要翻译：本发明的实施例公开了一种用于将符号嵌入字形中的系统和方法，包括以下步骤：确定表示字形轮廓的一组地标; 确定两个地标之间的数据段，其中所述数据段适于嵌入所述符号; 根据符号修改数据段以产生经修改的字形，使得符号嵌入在修改的字形中; 并输出修改的字形。

140. 发明授权

US08630341B2 Method for training and utilizing separable transforms for video coding 有权
标题翻译：用于训练和利用视频编码的可分离变换的方法
公开(公告)号：US08630341B2
公开(公告)日：2014-01-14
申请号：US13007394
申请日：2011-01-14
申请人： Robert A. Cohen , Osman G Sezer , Anthony Vetro
发明人： Robert A. Cohen , Osman G Sezer , Anthony Vetro
IPC分类号： H04N7/26
CPC分类号： H04N19/192 , H04N19/122 , H04N19/137 , H04N19/147 , H04N19/157 , H04N19/176 , H04N19/19 , H04N19/61
摘要： A video encoded as a bit stream is decoded using trained sparse orthonormal transforms generated from decoded prediction residual signals, wherein the transforms have associated indices. A current macroblock is entropy decoded and inverse quantized to produce decoded coefficients. For the current macroblock, an L0-norm regularized training process generates a set of mode-dependent sparse orthonormal inverse transforms, selected according to a prediction mode signaled in the bit stream. Decoded coefficients are inverse transformed and then are combined with previously decoded macroblocks to generate an output macroblock of a reconstructed video.
摘要翻译：使用经过解码的预测残差信号生成的训练稀疏正交变换来解码编码为比特流的视频，其中变换具有相关联的索引。当前宏块被熵解码并被反量化以产生解码系数。对于当前宏块，L0范数正则化训练处理产生根据在比特流中发信号的预测模式选择的一组依赖于模式的稀疏正交逆变换。解码的系数被逆变换，然后与先前解码的宏块组合，以产生重构视频的输出宏块。

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