专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

21. 发明申请

US20080152009A1 Scaling the complexity of video encoding 审中-公开
标题翻译：缩小视频编码的复杂度
公开(公告)号：US20080152009A1
公开(公告)日：2008-06-26
申请号：US11643130
申请日：2006-12-21
申请人： Emrah Akyol , Debargha Mukherjee
发明人： Emrah Akyol , Debargha Mukherjee
IPC分类号： H04N7/32 , H04N7/26
CPC分类号： H04N19/557 , H04N19/103 , H04N19/146 , H04N19/156 , H04N19/164 , H04N19/196 , H04N19/523 , H04N19/61
摘要： Video encoding that enables fine-grained control over the complexity of motion estimation to meet encoding constraints includes scaling a set of complexity control parameters in response to an encoding constraint and encoding the video in response to the complexity control parameters.
摘要翻译：能够对运动估计的复杂度进行细粒度控制以满足编码约束的视频编码包括响应于编码约束来缩放一组复杂度控制参数并响应于复杂度控制参数对视频进行编码。

22. 发明申请

US20070253479A1 Robust and efficient compression/decompression providing for adjustable division of computational complexity between encoding/compression and decoding/decompression 有权
标题翻译：强大而有效的压缩/解压缩，可以对编码/压缩和解码/解压缩之间的计算复杂度进行可调划分
公开(公告)号：US20070253479A1
公开(公告)日：2007-11-01
申请号：US11415258
申请日：2006-04-30
申请人： Debargha Mukherjee
发明人： Debargha Mukherjee
IPC分类号： H04B1/66 , H04N7/12
CPC分类号： H03M7/30 , H04N19/12 , H04N19/159 , H04N19/172 , H04N19/192 , H04N19/395 , H04N19/46 , H04N19/59 , H04N19/61
摘要： Various embodiments of the present invention include compression/decompression methods, systems, and devices that adjust a division of a total computational complexity of compression and decompression between encoding and decoding. These embodiments include an encoder that encodes a received signal at a selectable level of computational complexity and a decoder that decodes a received, encoded signal at a selectable level computational complexity. Video-codec embodiments of the present invention may be incorporated into relatively inexpensive video-recording devices, including hand-held, video-recording consumer devices such as video recorders and cell phones.
摘要翻译：本发明的各种实施例包括压缩/解压缩方法，系统和装置，其调节编码和解码之间的压缩和解压缩的总计算复杂度的划分。这些实施例包括以可选择的计算复杂度水平编码接收信号的编码器和以可选择的级别计算复杂度对接收的编码信号进行解码的解码器。本发明的视频编解码器实施例可以并入相对便宜的视频记录设备中，包括手持式视频记录消费者设备，诸如录像机和手机。

23. 发明授权

US07027647B2 Coder matched layer separation for compression of compound documents 有权
公开(公告)号：US07027647B2
公开(公告)日：2006-04-11
申请号：US10036979
申请日：2001-12-31
申请人： Debargha Mukherjee , Nasir Memon , Amir Said
发明人： Debargha Mukherjee , Nasir Memon , Amir Said
IPC分类号： G06K9/34
CPC分类号： G06K9/00456 , G06T9/00 , H04N1/40062 , H04N1/41 , H04N1/415 , Y02E50/14
摘要： Methods for decomposing compound documents for mixed raster content representation are provided. A method for decomposing an image includes the step of decomposing the image into a plurality of stripes. Each stripe is decomposed into foreground, background, and mask layers. The layers are interpolated to modify values of irrelevant pixels in order to achieve more efficient compression. The layers may subsequently be compressed with a coder.

24. 发明授权

US09111350B1 Conversion of monoscopic visual content to stereoscopic 3D 有权
标题翻译：单视觉视觉内容转换为立体3D
公开(公告)号：US09111350B1
公开(公告)日：2015-08-18
申请号：US13370736
申请日：2012-02-10
申请人： Debargha Mukherjee , Meng Wang , Chen Wu
发明人： Debargha Mukherjee , Meng Wang , Chen Wu
IPC分类号： G06T7/00 , G06T7/40
CPC分类号： H04N13/261 , G06T7/40 , G06T15/00 , G06T2207/10028 , H04N2013/0081
摘要： An image converter receives a two-dimensional image to be converted to a first three-dimensional image. The image converter identifies a feature-to-depth mapping function associated with a second three-dimensional image in a data store. The second three-dimensional image shares a characteristic with the two-dimensional image. The image converter determines a depth value for a plurality of pixels of the two-dimensional image according to the feature-to-depth mapping function and generates the first three-dimensional image based on the depth value for the plurality of pixels of the two-dimensional image.
摘要翻译：图像转换器接收要转换为第一三维图像的二维图像。图像转换器识别与数据存储器中的第二三维图像相关联的特征到深度映射函数。第二个三维图像与二维图像共享一个特征。图像转换器根据特征对深度映射函数确定二维图像的多个像素的深度值，并且基于二维图像的多个像素的深度值生成第一三维图像，三维图像。

25. 发明授权

US08982185B1 Systems and methods for 2D-to-3D conversion 有权
标题翻译： 2D到3D转换的系统和方法
公开(公告)号：US08982185B1
公开(公告)日：2015-03-17
申请号：US13408960
申请日：2012-02-29
申请人： Vijnan Shastri , Jonathan Huang , Sam Kvaalen , Debargha Mukherjee , Chen Wu
发明人： Vijnan Shastri , Jonathan Huang , Sam Kvaalen , Debargha Mukherjee , Chen Wu
IPC分类号： H04N13/00 , H04N15/00
CPC分类号： H04N13/139 , H04N13/167 , H04N13/356 , H04N21/23418 , H04N21/2343 , H04N21/816 , H04N21/854
摘要： Systems and methods can facilitate identifying 2D content in media that is suitable for conversion into 3D content, and converting the suitable 2D content into 3D content. The identifying can be based on quality criteria applied to the 2D content. For 2D content converted into 3D content, a user can be offered a choice between viewing the content in its original 2D form, or viewing the content in its converted, 3D form. The systems and methods can thereby provide users with greater choice of content and an enhanced viewing experience.
摘要翻译：系统和方法可以促进识别适合于转换成3D内容的媒体中的2D内容，以及将合适的2D内容转换为3D内容。识别可以基于应用于2D内容的质量标准。对于转换为3D内容的2D内容，可以向用户提供以其原始2D形式查看内容或以其转换的3D形式查看内容的选择。因此，系统和方法可以为用户提供更多的内容选择和增强的观看体验。

26. 发明授权

US08934538B2 Rate-distortion-complexity optimization of video encoding 有权
标题翻译：视频编码的速率失真复杂度优化
公开(公告)号：US08934538B2
公开(公告)日：2015-01-13
申请号：US13275084
申请日：2011-10-17
申请人： Lei Yang , Debargha Mukherjee
发明人： Lei Yang , Debargha Mukherjee
IPC分类号： H04N19/154 , H04N19/152 , H04N19/192 , H04N19/40 , H04N19/53 , H04N19/15 , H04N21/2662 , H04N21/2743 , H04N19/115 , H04N19/147 , H04N19/127 , H04N19/194
CPC分类号： H04N19/154 , H04N19/10 , H04N19/115 , H04N19/127 , H04N19/147 , H04N19/15 , H04N19/152 , H04N19/192 , H04N19/194 , H04N19/40 , H04N21/2662 , H04N21/2743
摘要： A system and method provide a video coding system for optimizing encoding bitrate, distortion and complexity for a video hosting service. The system comprises an encoding module configured to encode multiple videos with a bitrate control strategy, a pair of complexity allocation control parameters and one or more target output video formats specifications, which include target resolution, target bitrate and target quality information. The encoding module obtains encoding bitrate, distortion and complexity performance samples from the encoding. From the encoding bitrate, distortion and complexity performance samples, the encoding module is configured to select optimal encoding bitrate, distortion and complexity performance samples. The encoding computation profile mapping module is configured to obtain multiple computation levels from the optimal encoding bitrate, distortion and complexity performance samples. For each computational level, a pair of optimized complexity allocation control parameters and number of encoding passes are selected.
摘要翻译：系统和方法提供用于优化视频托管服务的编码比特率，失真和复杂度的视频编码系统。该系统包括：编码模块，被配置为利用比特率控制策略，一对复杂度分配控制参数和一个或多个目标输出视频格式规范来编码多个视频，其包括目标分辨率，目标比特率和目标质量信息。编码模块从编码中获得编码比特率，失真和复杂度性能样本。从编码比特率，失真和复杂度性能样本中，编码模块被配置为选择最佳编码比特率，失真和复杂度性能样本。编码计算简档映射模块被配置为从最佳编码比特率，失真和复杂度性能样本获得多个计算级别。对于每个计算级别，选择一对优化的复杂度分配控制参数和编码遍数。

27. 发明授权

US08891888B2 Entropy coding for recompression of images 有权
标题翻译：用于图像重新压缩的熵编码
公开(公告)号：US08891888B2
公开(公告)日：2014-11-18
申请号：US13604494
申请日：2012-09-05
申请人： Debargha Mukherjee
发明人： Debargha Mukherjee
IPC分类号： G06K9/36 , G06K9/46
CPC分类号： H04N19/13 , H04N19/136 , H04N19/176 , H04N19/91
摘要： A code is received. The code conveys data about a quantized coefficient that corresponds to a pixel of an image file. A decoding mode and a version of a code mapping format for decoding the received code is determined. The decoding mode and the version of the code mapping format dynamically change based on a previously-decoded code. The received code is decoded, during the decoding mode, according to the version of the code mapping format to obtain the data about the quantized coefficient.
摘要翻译：收到代码。代码传达关于与图像文件的像素对应的量化系数的数据。确定用于解码接收到的代码的解码模式和代码映射格式的版本。解码模式和代码映射格式的版本基于先前解码的代码动态地改变。在解码模式期间，根据代码映射格式的版本解码接收到的代码，以获得关于量化系数的数据。

28. 发明授权

US08797402B2 Methods and apparatus for imaging and displaying a navigable path 有权
标题翻译：用于成像和显示导航路径的方法和装置
公开(公告)号：US08797402B2
公开(公告)日：2014-08-05
申请号：US10300103
申请日：2002-11-19
申请人： Amir Said , Debargha Mukherjee , Ullas Gargi
发明人： Amir Said , Debargha Mukherjee , Ullas Gargi
IPC分类号： H04N7/00 , H04N7/18
CPC分类号： G01C21/3647 , G01C21/3632 , G01C21/367 , G01C21/3682 , G05D1/0246 , G05D1/0255
摘要： Various methods for imaging and navigating a selected path are described. A method of navigating a path includes the step of identifying a selected path. At least one image stream associated with navigating the selected path is identified. The displayed image stream includes visual information corresponding to traveling the selected path. In one embodiment, display of the image stream is varied in accordance with an actual location and a speed of a traveler along the selected path. Various single pass and multi-pass systems are described for capturing the visual information associated with a path. One method of acquiring visual information includes generating first and second image streams comprising visual information representing traversal of the path. Audio cues are recorded at the same plurality of locations on each pass. The audio cues permit synchronization of the image streams to locations along the path.
摘要翻译：描述用于成像和导航所选路径的各种方法。导航路径的方法包括识别所选路径的步骤。识别与导航所选路径相关联的至少一个图像流。所显示的图像流包括与行进所选路径相对应的视觉信息。在一个实施例中，图像流的显示根据沿着所选路径的旅行者的实际位置和速度而变化。描述了用于捕获与路径相关联的视觉信息的各种单遍和多遍系统。获取视觉信息的一种方法包括生成包括表示路径遍历的视觉信息的第一和第二图像流。音频提示记录在每次通过的相同多个位置。音频提示允许图像流同步到沿着路径的位置。

29. 发明申请

US20130106837A1 DEPTH-MAP GENERATION FOR AN INPUT IMAGE USING AN EXAMPLE APPROXIMATE DEPTH-MAP ASSOCIATED WITH AN EXAMPLE SIMILAR IMAGE 有权
标题翻译：使用与示例类似图像相关联的示例近似深度图的输入图像的深度图生成
公开(公告)号：US20130106837A1
公开(公告)日：2013-05-02
申请号：US13478449
申请日：2012-05-23
申请人： Debargha Mukherjee , Chen Wu , Meng Wang
发明人： Debargha Mukherjee , Chen Wu , Meng Wang
IPC分类号： G06T15/00
CPC分类号： G06T7/0065 , G06T7/55 , G06T15/00 , G06T15/40 , G06T2207/10024 , H04N13/122 , H04N13/128 , H04N13/261 , H04N2013/0081
摘要： An image converter receives a two-dimensional image to be converted to a first three-dimensional image. The image converter computes a feature-to-depth mapping function based on an approximate depth map associated with a second three-dimensional image. The image converter applies the feature-to-depth mapping function to a plurality of pixels of the two-dimensional image to determine a depth value for each of the plurality of pixels and generates the first three-dimensional image based on the depth values for the plurality of pixels of the two-dimensional image.
摘要翻译：图像转换器接收要转换为第一三维图像的二维图像。图像转换器基于与第二三维图像相关联的近似深度图来计算特征到深度映射函数。图像转换器将特征到深度映射函数应用于二维图像的多个像素，以确定多个像素中的每一个的深度值，并且基于所述二维图像的深度值生成第一三维图像二维图像的多个像素。

30. 发明授权

US08244895B2 Method and apparatus for applying receiving attributes using constraints 有权
标题翻译：使用约束应用接收属性的方法和装置
公开(公告)号：US08244895B2
公开(公告)日：2012-08-14
申请号：US10724284
申请日：2003-11-26
申请人： Debargha Mukherjee , Geraldine Kuo
发明人： Debargha Mukherjee , Geraldine Kuo
IPC分类号： G06F15/173
CPC分类号： H04N21/435 , H04L29/06027 , H04L65/4084 , H04L65/607 , H04N7/165 , H04N21/234327 , H04N21/23439 , H04N21/235 , H04N21/25833 , H04N21/2662
摘要： A method and apparatus for applying at least one receiving attribute at a receiving destination is provided. The design specifies receiving attributes based on constraints on definable multivariate functions, the definable multivariate functions including either linear combinations of products of univariate functions of attribute values or stack functions. The method may process predetermined specified functions at a format independent adaptation engine in a network using XML syntax by specifying an expression for the function using an ordered list of numeric constants, variables, arguments, and operators pushed into an expression stack to evaluate the expression.
摘要翻译：提供了一种在接收目的地应用至少一个接收属性的方法和装置。该设计基于对可定义的多变量函数的约束来定义接收属性，可定义的多变量函数包括属性值或堆栈函数的单变量函数的乘积的线性组合。该方法可以使用XML语法在网络中的格式独立的适配引擎处理预定的指定功能，通过使用推入表达式堆栈的数字常量，变量，参数和运算符的有序列表来指定函数的表达式来评估该表达式。

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