专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

111. 发明授权

US08625671B2 Look-ahead system and method for pan and zoom detection in video sequences 有权
公开(公告)号：US08625671B2
公开(公告)日：2014-01-07
申请号：US12685464
申请日：2010-01-11
申请人： Adriana Dumitras , Barin G. Haskell
发明人： Adriana Dumitras , Barin G. Haskell
IPC分类号： H04N9/64
CPC分类号： H04N5/147 , H04N5/144 , H04N5/145 , H04N19/102 , H04N19/137 , H04N19/139 , H04N19/142 , H04N19/182 , H04N19/527 , H04N19/543 , H04N19/61
摘要： A look-ahead system and method for pan and zoom detection in video sequences is disclosed. The system and method use motion vectors in a reference coordinate system to identify pans and zooms in video sequences. The identification of pans and zooms enables parameter switching for improved encoding in various video standards (e.g., H.264) and improved video retrieval of documentary movies and other video sequences in video databases or other storage devices.

112. 发明申请

US20130205208A1 User Interface Control for Media Editing Application 有权
标题翻译：媒体编辑应用程序的用户界面控制
公开(公告)号：US20130205208A1
公开(公告)日：2013-08-08
申请号：US13367363
申请日：2012-02-06
申请人： Hans H. Kim , Andrew Bryant , Adriana Dumitras
发明人： Hans H. Kim , Andrew Bryant , Adriana Dumitras
IPC分类号： G06F3/048
CPC分类号： G11B27/034 , G11B27/34 , H04N5/262
摘要： Some embodiments provide a method that provides a graphical user interface (GUI) on a first device for controlling application of color corrections to a media item by a media editing application on a second device. The method provides a display area that includes several different locations. Each location in the display area corresponds to a set of values. The method provides several user interface (UI) items that are each for (1) moving in the display area and (2) specifying a set of values for a color correction operation that the media editing application applies to the media item. The set of values for the color correction operation specified by each UI item is the set of values is associated with the location at which the UI item is positioned in the display area.
摘要翻译：一些实施例提供了一种在第一设备上提供图形用户界面（GUI）的方法，用于通过第二设备上的媒体编辑应用来控制对媒体项的颜色校正的应用。该方法提供包括几个不同位置的显示区域。显示区域中的每个位置对应于一组值。该方法提供了多个用户界面（UI）项目，每个用户界面（UI）项目用于（1）在显示区域中移动;以及（2）为媒体编辑应用程序应用于媒体项目的颜色校正操作指定一组值。每个UI项目指定的颜色校正操作的值集合是一组值与UI项目在显示区域中的位置相关联。

113. 发明申请

US20120051658A1 MULTI-IMAGE FACE-BASED IMAGE PROCESSING 有权
标题翻译：多图像基于图像的图像处理
公开(公告)号：US20120051658A1
公开(公告)日：2012-03-01
申请号：US13221888
申请日：2011-08-30
申请人： Xin Tong , Adriana Dumitras , Andrew Bryant , Olivier Fedkiw , Daniel Pettigrew , Peter Warner
发明人： Xin Tong , Adriana Dumitras , Andrew Bryant , Olivier Fedkiw , Daniel Pettigrew , Peter Warner
IPC分类号： G06K9/62
CPC分类号： G11B27/034 , G11B27/28 , G11B27/34 , H04N5/262
摘要： Some embodiments provide a method for detecting and/or identifying a set of faces in a video frame and performing a set of image processing operations based on locations of the set of faces. In particular, the method identifies a set of respective locations of the set of faces in the video frame and applies one or more image processing operations based on the locations of the set of faces found in the video frame. The image processing operations include color correction operations, non-color correction operations, and image processing operations that modify areas inside or outside of the detected and/or identified faces. Additionally, some embodiments provide a graphical user interface for automatically applying image processing operations to an area of a video frame isolated by an ellipse-shaped mask. Furthermore, some embodiments provide a system for automatically applying image processing operations to an area of a video frame isolated by an ellipse-shaped mask.
摘要翻译：一些实施例提供了一种用于检测和/或识别视频帧中的一组面部并且基于该组面部的位置执行一组图像处理操作的方法。具体地，该方法识别视频帧中的一组面部的相应位置的集合，并且基于在视频帧中找到的面部集合的位置来应用一个或多个图像处理操作。图像处理操作包括修改检测到的和/或识别的面部内部或外部的区域的颜色校正操作，非颜色校正操作和图像处理操作。另外，一些实施例提供了一种图形用户界面，用于将图像处理操作自动应用于由椭圆形掩模隔离的视频帧的区域。此外，一些实施例提供了一种用于将图像处理操作自动应用于由椭圆形掩模隔离的视频帧的区域的系统。

114. 发明申请

US20110194611A1 METHOD AND SYSTEM FOR VIDEO ENCODING USING A VARIABLE NUMBER OF B FRAMES 有权
标题翻译：使用可变数量的B框架进行视频编码的方法和系统
公开(公告)号：US20110194611A1
公开(公告)日：2011-08-11
申请号：US13025802
申请日：2011-02-11
申请人： Adriana Dumitras , Barin Geoffry Haskell
发明人： Adriana Dumitras , Barin Geoffry Haskell
IPC分类号： H04N7/26
CPC分类号： H04N19/87 , H04N19/109 , H04N19/114 , H04N19/139 , H04N19/142 , H04N19/172
摘要： An effective method for dynamically selecting the number of I, P and B frames during video coding is proposed. Short-term look-ahead analysis of a video sequence yields a variable number of B frames to be coded between any two stored pictures. The first picture of a group of frames (GOF) may be coded as a B picture. Motion speed is calculated for each picture of the GOF with respect to the first picture of the GOF. Subject to exceptions, as long as the subsequent pictures exhibit motion speeds that are similar and motion vector displacements that are co-linear with those of the first picture in the GOF, they may be coded as B pictures. When a picture is encountered having a motion speed that is not the same as that of the first picture in the GOF, the picture may be coded as a P picture. In some embodiments, a sequence of B pictures that terminates in a P picture may be called a “group of frames” (GOF).
摘要翻译：提出了一种在视频编码过程中动态选择I，P和B帧数量的有效方法。视频序列的短期预先分析产生在任何两个存储的图像之间编码的可变数量的B帧。一组帧（GOF）的第一图像可以被编码为B图像。针对GOF的第一张照片计算GOF的每张照片的运动速度。除了例外，只要后续图像显示与GOF中的第一图像的运动速度相似的运动速度和与第一图像的运动矢量位移共线的运动矢量位移，则它们可以被编码为B图像。当遇到具有与GOF中的第一图像的运动速度不同的运动速度的图像时，图像可以被编码为P图像。在一些实施例中，终止于P图像的B图像序列可以被称为“帧组”（GOF）。

115. 发明授权

US07809207B2 Pre-processing method and system for data reduction of video sequences and bit rate reduction of compressed video sequences using spatial filtering 有权
标题翻译：使用空间滤波的视频序列数据缩减和压缩视频序列比特率降低的预处理方法和系统
公开(公告)号：US07809207B2
公开(公告)日：2010-10-05
申请号：US12185777
申请日：2008-08-04
申请人： Adriana Dumitras , James Oliver Normile , Ryan R. Salsbury
发明人： Adriana Dumitras , James Oliver Normile , Ryan R. Salsbury
IPC分类号： G06K9/40 , G06K9/36 , H04N7/12
CPC分类号： H04N19/117 , G06K9/00234 , H04N5/21 , H04N9/8042 , H04N19/136 , H04N19/14 , H04N19/17 , H04N19/186 , H04N19/192 , H04N19/80
摘要： Methods for pre-processing video sequences prior to compression to provide data reduction of the video sequence. Also, after compression of the pre-processed video sequence, the bit rate of the pre-processed and compressed video sequence will be lower than the bit rate of the video sequence after compression but without pre-processing. Pre-processing may include spatial anisotropic diffusion filtering such as Perona-Malik filtering, Fallah-Ford filtering, or omni-directional filtering that extends Perona-Malik filtering to perform filtering in at least one diagonal direction. Pre-processing may also include performing filtering differently on a foreground region than on a background region of a video frame. This method includes identifying pixel locations having pixel values matching characteristics of human skin and determining a bounding shape for each contiguous grouping of matching pixel locations. The foreground region is comprised of pixel locations contained in a bounding shape and the background region is comprised of all other pixel locations.
摘要翻译：用于在压缩之前预处理视频序列以提供视频序列的数据缩减的方法。此外，在经过预处理的视频序列的压缩之后，预处理和压缩的视频序列的比特率将低于压缩后的视频序列的比特率，但是没有预处理。预处理可以包括空间各向异性扩散滤波，例如Perona-Malik滤波，Fallah-Ford滤波或全向滤波，其延伸Perona-Malik滤波以在至少一个对角线方向上执行滤波。预处理还可以包括在前景区域上比在视频帧的背景区域上执行不同的滤波。该方法包括识别具有与人皮肤特征相匹配的像素值的像素位置，并确定匹配像素位置的每个连续分组的边界形状。前景区域由包含在边界形状中的像素位置组成，并且背景区域由所有其它像素位置组成。

116. 发明授权

US07564465B2 Texture replacement in video sequences and images 有权
标题翻译：视频序列和图像中的纹理替换
公开(公告)号：US07564465B2
公开(公告)日：2009-07-21
申请号：US11926868
申请日：2007-10-29
申请人： Adriana Dumitras , Barin Geoffry Haskell
发明人： Adriana Dumitras , Barin Geoffry Haskell
IPC分类号： G09G5/00
CPC分类号： G06T11/001 , G06T7/40 , G06T7/41 , G06T9/00 , G06T9/001 , H04N19/14 , H04N19/167 , H04N19/17 , H04N19/186 , H04N19/23 , H04N19/27
摘要： Systems and methods for reducing bit rates by replacing original texture in a video sequence with synthesized texture. Reducing the bit rate of the video sequence begins by identifying and removing selected texture from frames in a video sequence. The removed texture is analyzed to generate texture parameters. New texture is synthesized using the texture parameters in combination with a set of constraints. Then, the newly synthesized texture is mapped back into the frames of the video sequence from which the original texture was removed. The resulting frames are then encoded. The bit rate of the video sequence with the synthesized texture is less than the bit rate of the video sequence with the original texture. Also, the ability of a decoder to decode the new video sequence is not compromised because no assumptions are made about the texture synthesis capabilities of the decoder.
摘要翻译：通过用合成纹理替换视频序列中的原始纹理来降低比特率的系统和方法。通过从视频序列中的帧识别和去除所选纹理，降低视频序列的比特率。分析去除的纹理以生成纹理参数。使用纹理参数和一组约束组合新的纹理。然后，将新合成的纹理映射回去除原始纹理的视频序列的帧。然后对所得到的帧进行编码。具有合成纹理的视频序列的比特率小于具有原始纹理的视频序列的比特率。此外，解码器解码新视频序列的能力不会受到损害，因为没有对解码器的纹理合成能力做出假设。

117. 发明授权

US07545989B1 System and method for encoding and decoding using texture replacement 有权
公开(公告)号：US07545989B1
公开(公告)日：2009-06-09
申请号：US11876262
申请日：2007-10-22
申请人： Adriana Dumitras , Barin Geoffry Haskell
发明人： Adriana Dumitras , Barin Geoffry Haskell
IPC分类号： G06K9/36 , G06K9/40 , G06K9/46
CPC分类号： G06T11/001 , G06T7/40 , G06T7/41 , G06T9/00 , G06T9/001 , H04N19/14 , H04N19/167 , H04N19/17 , H04N19/186 , H04N19/23 , H04N19/27
摘要： The invention provides devices and methods that process images. The invention processes a received signal representing information of texture and information of an image, which has the texture removed from at least one region. The image information is encoded to obtain encoded information of the image. An output signal is generated representing the texture information and the encoded image information. In another embodiment, the invention synthesizes texture based on the received texture information, decodes received image information, which is encoded, to obtain a decoded image, and then maps the synthesized texture onto the decoded image.

118. 发明申请

US20080284904A1 PRE-PROCESSING METHOD AND SYSTEM FOR DATA REDUCTION OF VIDEO SEQUENCES AND BIT RATE REDUCTION OF COMPRESSED VIDEO SEQUENCES USING SPATIAL FILTERING 有权
公开(公告)号：US20080284904A1
公开(公告)日：2008-11-20
申请号：US12107072
申请日：2008-04-21
申请人： Adriana Dumitras , James Oliver Normile , Ryan R. Salsbury
发明人： Adriana Dumitras , James Oliver Normile , Ryan R. Salsbury
IPC分类号： H04N11/02
CPC分类号： H04N19/117 , G06K9/00234 , H04N5/21 , H04N9/8042 , H04N19/136 , H04N19/14 , H04N19/17 , H04N19/186 , H04N19/192 , H04N19/80
摘要： Methods for pre-processing video sequences prior to compression to provide data reduction of the video sequence. Also, after compression of the pre-processed video sequence, the bit rate of the pre-processed and compressed video sequence will be lower than the bit rate of the video sequence after compression but without pre-processing. Pre-processing may include spatial anisotropic diffusion filtering such as Perona-Malik filtering, Fallah-Ford filtering, or omni-directional filtering that extends Perona-Malik filtering to perform filtering in at least one diagonal direction. Pre-processing may also include performing filtering differently on a foreground region than on a background region of a video frame. This method includes identifying pixel locations having pixel values matching characteristics of human skin and determining a bounding shape for each contiguous grouping of matching pixel locations. The foreground region is comprised of pixel locations contained in a bounding shape and the background region is comprised of all other pixel locations.

119. 发明授权

US07057671B2 Image and video processing with chrominance attenuation 有权
公开(公告)号：US07057671B2
公开(公告)日：2006-06-06
申请号：US10123993
申请日：2002-04-16
申请人： Adriana Dumitras , Barin Geoffry Haskell
发明人： Adriana Dumitras , Barin Geoffry Haskell
IPC分类号： H04N9/64
CPC分类号： H04N9/68 , H04N9/67
摘要： The values of the primary color space components of an image signal, such as the components of RGB video signal, are maintained within their allowed range by modifying the signal in a different color space, such as YUV space. Specifically, the U and V chrominance components are attenuated by an attenuation factor g while the luminance component Y is not modified. The value of g is the largest possible value less than 1 that will cause all primary color space components that would otherwise be outside the allowed range to be within that range. A high quality of the displayed image is maintained.

120. 发明授权

US08896616B2 Texture replacement in video sequences and images 有权
标题翻译：视频序列和图像中的纹理替换
公开(公告)号：US08896616B2
公开(公告)日：2014-11-25
申请号：US13204868
申请日：2011-08-08
申请人： Adriana Dumitras , Barin Geoffry Haskell
发明人： Adriana Dumitras , Barin Geoffry Haskell
IPC分类号： G09G5/00 , G06T7/40 , H04N19/17 , G06T11/00 , H04N19/186 , H04N19/23 , G06T9/00 , H04N19/27 , H04N19/14
CPC分类号： G06T11/001 , G06T7/40 , G06T7/41 , G06T9/00 , G06T9/001 , H04N19/14 , H04N19/167 , H04N19/17 , H04N19/186 , H04N19/23 , H04N19/27
摘要： Systems and methods for reducing bit rates by replacing original texture in a video sequence with synthesized texture. Reducing the bit rate of the video sequence begins by identifying and removing selected texture from frames in a video sequence. The removed texture is analyzed to generate texture parameters. New texture is synthesized using the texture parameters in combination with a set of constraints. Then, the newly synthesized texture is mapped back into the frames of the video sequence from which the original texture was removed. The resulting frames are then encoded. The bit rate of the video sequence with the synthesized texture is less than the bit rate of the video sequence with the original texture. Also, the ability of a decoder to decode the new video sequence is not compromised because no assumptions are made about the texture synthesis capabilities of the decoder.
摘要翻译：通过用合成纹理替换视频序列中的原始纹理来降低比特率的系统和方法。通过从视频序列中的帧识别和去除所选纹理，降低视频序列的比特率。分析去除的纹理以生成纹理参数。使用纹理参数和一组约束组合新的纹理。然后，将新合成的纹理映射回去除原始纹理的视频序列的帧。然后对所得到的帧进行编码。具有合成纹理的视频序列的比特率小于具有原始纹理的视频序列的比特率。此外，解码器解码新视频序列的能力不会受到损害，因为没有对解码器的纹理合成能力做出假设。

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