专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明授权

US07346224B2 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：US07346224B2
公开(公告)日：2008-03-18
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： G06K9/40
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。

12. 发明授权

US07324698B2 Error resilient encoding method for inter-frames of compressed videos 失效
标题翻译：压缩视频帧间错误弹性编码方法
公开(公告)号：US07324698B2
公开(公告)日：2008-01-29
申请号：US10717679
申请日：2003-11-20
申请人： Hao-Song Kong , Wei-Ying Kung , Anthony Vetro , Huifang Sun
发明人： Hao-Song Kong , Wei-Ying Kung , Anthony Vetro , Huifang Sun
IPC分类号： G06K9/36
CPC分类号： H04N19/513 , H04N19/895
摘要： A method encodes an inter-frame of a compressed video, the inter-frame including multiple macroblocks in a predetermined order. Each macroblock has an associated motion vector. For each current macroblock in the predetermined order, a set of near macroblocks are identified. An index is assigned to each near macroblock. A difference between the motion vector of the current macroblock and the motion vector of each near macroblocks is determined. The indices of the near macroblocks are then sorted in order of the differences and appended to the inter-frame.
摘要翻译：方法对压缩视频的帧间进行编码，帧间以预定顺序包括多个宏块。每个宏块具有相关的运动矢量。对于按照预定顺序的每个当前宏块，识别一组近似的宏块。索引被分配给每个近似的宏块。确定当前宏块的运动矢量与每个近似宏块的运动矢量之间的差异。然后按照差异的顺序对近宏块的索引进行排序并附加到帧间。

13. 发明申请

US20060146141A1 Method for randomly accessing multiview videos 有权
标题翻译：随机访问多视点视频的方法
公开(公告)号：US20060146141A1
公开(公告)日：2006-07-06
申请号：US11292168
申请日：2005-11-30
申请人： Jun Xin , Emin Martinian , Alexander Behrens , Anthony Vetro , Huifang Sun
发明人： Jun Xin , Emin Martinian , Alexander Behrens , Anthony Vetro , Huifang Sun
IPC分类号： H04N5/232
CPC分类号： H04N19/615 , H04N19/103 , H04N19/105 , H04N19/13 , H04N19/147 , H04N19/159 , H04N19/172 , H04N19/176 , H04N19/46 , H04N19/573 , H04N19/597 , H04N19/61 , H04N19/63
摘要： A method randomly accesses multiview videos. Multiview videos are acquired of a scene with corresponding cameras arranged at poses, such that there is view overlap between any pair of cameras. V-frames are generated from the multiview videos. The V-frames are encoded using only spatial prediction. Then, the V-frames are inserted periodically in an encoded bitstream to provide random temporal access to the multiview videos.
摘要翻译：一种随机访问多视点视频的方法。多视点视频被采集到具有以姿势布置的相应摄像机的场景，使得在任何一对摄像机之间存在视图重叠。 V帧是从多视角视频生成的。 V帧仅使用空间预测编码。然后，将V帧周期性地插入到编码比特流中，以提供对多视图视频的随机临时访问。

14. 发明申请

US20060146138A1 Method and system for synthesizing multiview videos 有权
标题翻译：合成多视点视频的方法和系统
公开(公告)号：US20060146138A1
公开(公告)日：2006-07-06
申请号：US11292167
申请日：2005-11-30
申请人： Jun Xin , Emin Martinian , Alexander Behrens , Anthony Vetro , Huifang Sun
发明人： Jun Xin , Emin Martinian , Alexander Behrens , Anthony Vetro , Huifang Sun
IPC分类号： H04N5/225
CPC分类号： H04N19/615 , H04N19/103 , H04N19/105 , H04N19/13 , H04N19/176 , H04N19/46 , H04N19/597 , H04N19/61 , H04N19/63
摘要： A system and method synthesizes multiview videos. Multiview videos are acquired of a scene with corresponding cameras arranged at a poses such that there is view overlap between any pair of cameras. A synthesized multiview video is generated from the acquired multiview videos for a virtual camera. A reference picture list is maintained for each current frame of each of the multiview videos and the synthesized video. The reference picture list indexes temporal reference pictures and spatial reference pictures of the acquired multiview videos and the synthesized reference pictures of the synthesized multiview video. Then, each current frame of the multiview videos is predicted according to reference pictures indexed by the associated reference picture list during encoding and decoding.
摘要翻译：系统和方法合成多视点视频。获取多视角视频，其中相应的相机布置成姿势，使得在任何一对相机之间存在视图重叠。从获取的用于虚拟相机的多视点视频生成合成的多视角视频。为每个多视角视频和合成视频的每个当前帧维护参考图片列表。参考图片列表索引所获取的多视角视频的时间参考图片和空间参考图片以及合成的多视角视频的合成参考图片。然后，在编码和解码期间，根据由相关联的参考图片列表索引的参考图片来预测多视图视频的每个当前帧。

15. 发明授权

US06925120B2 Transcoder for scalable multi-layer constant quality video bitstreams 失效
标题翻译：用于可扩展多层恒定质量视频比特流的转码器
公开(公告)号：US06925120B2
公开(公告)日：2005-08-02
申请号：US09961987
申请日：2001-09-24
申请人： Ximin Zhang , Anthony Vetro , Yun-Qing Shi , Huifang Sun
发明人： Ximin Zhang , Anthony Vetro , Yun-Qing Shi , Huifang Sun
IPC分类号： H04N7/26 , H04N21/2343 , H04N21/2365 , H04N21/24 , H04N21/2662 , H04N21/434 , H04N21/4402 , H04N7/12
CPC分类号： H04N21/2662 , H04N19/147 , H04N19/154 , H04N19/19 , H04N19/33 , H04N19/34 , H04N19/40 , H04N21/234327 , H04N21/23655 , H04N21/2402 , H04N21/4347
摘要： A method codes an output bitstream of an input video so the decoded output bitstream has a constant perceived quality. A base layer bitstream having a constant bit-rate is generated from the input video, and an input enhancement layer bitstream is generated from a difference between the input video and the base layer bitstream. Rate and distortion characteristics are extracted from the base layer bitstream and the input enhancement layer bitstream, and an output enhancement layer bitstream having a variable bit-rate is generated from the input enhancement layer bitstream according to the rate and distortion characteristics. The base layer bitstream and the output enhancement layer bitstream, in combination, form an output bitstream having a variable bit-rate and a constant distortion.
摘要翻译：一种方法对输入视频的输出比特流进行编码，使得解码的输出比特流具有恒定的感知质量。从输入视频产生具有恒定比特率的基本层比特流，并且从输入视频和基本层比特流之间的差异生成输入增强层比特流。从基本层比特流和输入增强层比特流中提取速率和失真特性，并且根据速率和失真特性从输入增强层比特流生成具有可变比特率的输出增强层比特流。基本层比特流和输出增强层比特流组合形成具有可变比特率和恒定失真的输出比特流。

16. 发明申请

US20050036547A1 Resource-constrained sampling of multiple compressed videos 失效
标题翻译：资源受限的多个压缩视频采样
公开(公告)号：US20050036547A1
公开(公告)日：2005-02-17
申请号：US10659904
申请日：2003-09-11
申请人： Anthony Vetro , Huifang Sun
发明人： Anthony Vetro , Huifang Sun
IPC分类号： H04N7/26 , H04N7/12 , H04N7/24
CPC分类号： H04N21/234381 , H04N19/115 , H04N19/156 , H04N21/21805 , H04N21/21815 , H04N21/231
摘要： A method acquires compressed videos. Intra-, or inter-frames of each compressed video are acquired at a fixed sampling rate. Joint analysis is applied concurrently and in parallel to the compressed videos to determine a variable and non-uniform temporal sampling rate for each compressed video so that a combined distortion is minimized and a combined frame rate constraint is satisfied. Each compressed video is then sampled at the associated variable and non-uniform temporal sampling rate to produce output compressed videos having variable temporal resolutions.
摘要翻译：一种方法获取压缩视频。以固定的采样率获取每个压缩视频的帧内或帧间。联合分析同时并行地应用于压缩视频，以确定每个压缩视频的可变和不均匀的时间采样率，使得组合失真被最小化并且组合的帧速率约束被满足。然后以相关联的变量和非均匀时间采样率对每个压缩视频进行采样，以产生具有可变时间分辨率的输出压缩视频。

17. 发明授权

US06618507B1 Methods of feature extraction of video sequences 失效
标题翻译：视频序列特征提取方法
公开(公告)号：US06618507B1
公开(公告)日：2003-09-09
申请号：US09236838
申请日：1999-01-25
申请人： Ajay Divakaran , Huifang Sun , Hiroshi Ito
发明人： Ajay Divakaran , Huifang Sun , Hiroshi Ito
IPC分类号： G06K946
CPC分类号： G06K9/00744 , G06F17/30811
摘要： This invention relates to methods of feature extraction from MPEG-2 and MPEG-4 compressed video sequences. The spatio-temporal compression complexity of video sequences is evaluated for feature extraction by inspecting the compressed bitstream and the complexity is used as a descriptor of the spatio-temporal characteristics of the video sequence. The spatio-temporal compression complexity measure is used as a matching criterion and can also be used for absolute indexing. Feature extraction can be accomplished in conjunction with scene change detection techniques and the combination has reasonable accuracy and the advantage of high simplicity since it is based on entropy decoding of signals in compressed form and does not require computationally expensive inverse Discrete Cosine Transformation (DCT).
摘要翻译：本发明涉及从MPEG-2和MPEG-4压缩视频序列中提取特征的方法。通过检查压缩比特流来评估视频序列的时空压缩复杂度，并将复杂度用作视频序列的时空特征的描述符。时空压缩复杂度测量用作匹配标准，也可用于绝对索引。特征提取可以结合场景变化检测技术来实现，并且组合具有合理的精度和高简单性的优点，因为它是基于压缩形式的信号的熵解码，并且不需要计算上昂贵的反离散余弦变换（DCT）。

18. 发明授权

US06600784B1 Descriptor for spatial distribution of motion activity in compressed video 有权
标题翻译：压缩视频中运动活动空间分布的描述符
公开(公告)号：US06600784B1
公开(公告)日：2003-07-29
申请号：US09496707
申请日：2000-02-02
申请人： Ajay Divakaran , Kadir A. Peker , Huifang Sun
发明人： Ajay Divakaran , Kadir A. Peker , Huifang Sun
IPC分类号： H04N712
CPC分类号： G06F17/30781 , G06K9/00335 , G06K9/00711 , G06T7/215 , G06T2207/10016 , G06T2207/20021
摘要： A method describes motion activity in a video sequence. A motion activity matrix is determined for the video sequence. A threshold for the motion activity matrix is determined. Connected regions of motion vectors at least equal to the threshold are identified and measured for size. A histogram of the distribution of the sizes of the connected areas is constructed for the entire video sequence. The histogram is normalized to characterize the spatial distribution of the video sequence in a motion activity descriptor.
摘要翻译：一种方法描述视频序列中的运动活动。为视频序列确定运动活动矩阵。确定运动活动矩阵的阈值。至少等于阈值的运动矢量的连接区域被识别并测量尺寸。为整个视频序列构建连接区域的大小分布的直方图。将直方图归一化以表征运动活动描述符中的视频序列的空间分布。

19. 发明授权

US06307964B1 Method for ordering image spaces to represent object shapes 失效
标题翻译：用于排序图像空间来表示对象形状的方法
公开(公告)号：US06307964B1
公开(公告)日：2001-10-23
申请号：US09326759
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： G06K900
CPC分类号： G06T9/001 , G06T9/20
摘要： A method represents a shape of an object in an image. Portions of the image interior to a boundary of the object are ordered. A medial axis for the ordered portions of the image is derived. The medial axis is segmented to produce an ordered tree. The ordered tree is transformed to a partial ordered tree to represent the shape of the object.
摘要翻译：方法表示图像中的对象的形状。将图像内部部分到对象的边界进行排序。导出图像的有序部分的中间轴。内侧轴被分割以产生有序树。有序树被转换为部分有序树以表示对象的形状。

20. 发明授权

US5828788A System for processing data in variable segments and with variable data resolution 失效
标题翻译：用于处理可变段和可变数据分辨率数据的系统
公开(公告)号：US5828788A
公开(公告)日：1998-10-27
申请号：US572844
申请日：1995-12-14
申请人： Tihao Chiang , Huifang Sun , Joel Walter Zdepski
发明人： Tihao Chiang , Huifang Sun , Joel Walter Zdepski
IPC分类号： G06T9/00 , H03M7/30 , H04N7/26 , G06K9/46 , H04N7/12
CPC分类号： H04N19/37 , H04N19/30
摘要： A dynamically configurable video signal processing system partitions and encodes data using a variable number of data segments and variable data resolution. The system partitions data into a variable number of data segments by predicting, as a function of the data rate, first and second distortion factors for the data partitioned into first and second numbers of data segments. The first and second distortion factors are mutually compared and the data is partitioned into the number of data segments which exhibits the lower distortion factor value. First and second distortion factors for the data encoded with first and second data resolutions are also predicted. The first and second distortion factors are similarly compared and the data is encoded with the resolution exhibiting the lower distortion factor value.
摘要翻译：动态可配置的视频信号处理系统使用可变数量的数据段和可变数据分辨率对数据进行分区和编码。该系统通过根据数据速率预测分割为第一和第二数量数据段的数据的第一和第二失真因子来将数据分割成可变数量的数据段。相互比较第一和第二失真因子，并将数据划分成具有较低失真因子值的数据段的数量。还预测了用第一和第二数据分辨率编码的数据的第一和第二失真因子。类似地比较第一和第二失真因子，并且数据以表现出较低失真因子值的分辨率进行编码。

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