公开(公告)号：US08467626B2

公开(公告)日：2013-06-18

申请号：US12311452

申请日：2007-06-25

申请人： Sitaram Bhagavathy ,  Joan Llach

发明人： Sitaram Bhagavathy ,  Joan Llach

IPC分类号： G06K9/40 ,  G06K9/20

CPC分类号： G06T5/002 ,  G06T5/20 ,  G06T5/50 ,  G06T2207/10016 ,  G06T2207/20182

摘要： One particular automatic parameter estimation method and apparatus estimates low level filtering parameters from one or more user controlled high-level filtering parameters. The high level filtering parameters are strength and quality, where strength indicates how much noise reduction will be performed, and quality indicates a tolerance which controls the balance between filtering uniformity and loss of detail. The low level filtering parameters that can be estimated include the spatial neighborhood and/or temporal neighborhood size from which pixel candidates are selected, and thresholds used to verify the “goodness” of the spatially or temporally predicted candidate pixels. More generally, a criterion for filtering digital image data is accessed, and a value is determined for a parameter for use in filtering digital image data, the value being determined based on whether the value results in the criterion being satisfied for at least a portion of a digital image.

公开(公告)号：US20130083838A1

公开(公告)日：2013-04-04

申请号：US13618403

申请日：2012-09-14

申请人： David Touze ,  Yannick Olivier ,  Philippe Bordes ,  Dominique Thoreau ,  Joan Llach

发明人： David Touze ,  Yannick Olivier ,  Philippe Bordes ,  Dominique Thoreau ,  Joan Llach

IPC分类号： H04N11/02

CPC分类号： H04N5/2355 ,  H04N5/2356 ,  H04N5/3456 ,  H04N5/355 ,  H04N19/33 ,  H04N19/46 ,  H04N19/59 ,  H04N19/70 ,  H04N19/98

摘要： The invention is made in the field of coding of images of high dynamic range.The invention is based on the concept of Frame Compatible format. The idea is to transport, in a frame, down-sampled LDR content together with additional information allowing reconstructing HDR content from the LDR content. Thus, it is proposed a method of encoding an HDR image of high dynamic range according to claim 1. Said method comprises down-sampling (DWN) an LDR image and additional data, the LDR image providing a lower dynamic range depiction of the HDR image content and the additional data allowing for reconstructing the HDR image from the LDR image.

摘要翻译： 本发明是在高动态范围图像编码领域进行的。 本发明基于帧兼容格式的概念。 这个想法是以一帧的方式传送下采样的LDR内容以及允许从LDR内容重建HDR内容的附加信息。 因此，提出了根据权利要求1对高动态范围的HDR图像进行编码的方法。所述方法包括下采样（DWN）LDR图像和附加数据，LDR图像提供HDR图像的较低动态范围描绘 内容和允许从LDR图像重建HDR图像的附加数据。

公开(公告)号：US20120294369A1

公开(公告)日：2012-11-22

申请号：US13574428

申请日：2011-01-20

申请人： Sitaram Bhagavathy ,  Joan Llach ,  Dong-Qing Zhang

发明人： Sitaram Bhagavathy ,  Joan Llach ,  Dong-Qing Zhang

IPC分类号： H04N7/26 ,  H04N7/46 ,  H04N7/32

CPC分类号： H04N19/577 ,  H04N19/119 ,  H04N19/12 ,  H04N19/132 ,  H04N19/137 ,  H04N19/172 ,  H04N19/20 ,  H04N19/33 ,  H04N19/46 ,  H04N19/527 ,  H04N19/537 ,  H04N19/573 ,  H04N19/59

摘要： Methods and apparatus are provided for sampling-based super resolution video encoding and decoding. The encoding method receives high resolution pictures and generates low resolution pictures and metadata there from, the metadata for guiding post-decoding post-processing of the low resolution pictures and the metadata; and then encodes the low resolution pictures and the metadata using at least one encoder. The corresponding decoding method receives a bitstream and decodes low resolution pictures and metadata there from using a decoder; and then reconstructs high resolution pictures respectively corresponding to the low resolution pictures using the low resolution pictures and the metadata.

摘要翻译： 提供了基于采样的超分辨率视频编码和解码的方法和装置。 编码方法接收高分辨率图像，并从其中生成低分辨率图像和元数据，用于引导低分辨率图像的后解码后处理的元数据和元数据; 然后使用至少一个编码器对低分辨率图像和元数据进行编码。 相应的解码方法接收比特流并且使用解码器解码低分辨率图像和元数据; 然后使用低分辨率图像和元数据重建分别对应于低分辨率图像的高分辨率图像。

公开(公告)号：US20110293247A1

公开(公告)日：2011-12-01

申请号：US13138384

申请日：2010-01-05

申请人： Sitaram Bhagavathy ,  Joan Llach

发明人： Sitaram Bhagavathy ,  Joan Llach

IPC分类号： G11B27/00

CPC分类号： G06T7/254 ,  G06T7/174 ,  G06T2207/10016 ,  G06T2207/20092 ,  G06T2207/20096

摘要： A method for propagating user-provided foreground-background constraint information for a first video frame to subsequent frames allows extraction of moving foreground objects with minimal user interaction. Video matting is performed wherein constraints derived from user input with respect to a first frame are propagated to subsequent frames using the estimated alpha matte of each frame. The matte of a frame is processed in order to arrive at a rough foreground-background segmentation which is then used for estimating the matte of the next frame. At each frame, the propagated constraints are used by an image matting method for estimating the corresponding matte which is in turn used for propagating the constraints to the next frame, and so on.

摘要翻译： 用于将第一视频帧的用户提供的前景 - 背景约束信息传播到后续帧的方法允许以最小的用户交互提取移动的前景对象。 执行视频消隐，其中从相对于第一帧的用户输入导出的约束使用每帧的估计的α遮罩传播到后续帧。 处理帧的哑光以便获得粗糙的前景 - 背景分割，然后将其用于估计下一帧的无光泽。 在每个帧处，通过图像消隐方法使用传播的约束来估计相应的无光泽，其依次用于将约束传播到下一帧，等等。

公开(公告)号：US20110026607A1

公开(公告)日：2011-02-03

申请号：US12736496

申请日：2009-04-07

申请人： Sitaram Bhagavathy ,  Joan Llach ,  Yu Huang

发明人： Sitaram Bhagavathy ,  Joan Llach ,  Yu Huang

IPC分类号： H04N7/26 ,  G06K9/40 ,  H04N5/21

CPC分类号： G06T5/002 ,  G06T5/003 ,  G06T5/20 ,  G06T2207/10016 ,  H04N19/119 ,  H04N19/124 ,  H04N19/162 ,  H04N19/167 ,  H04N19/17 ,  H04N19/20 ,  H04N19/46 ,  H04N19/80 ,  H04N19/85

摘要： The visibility of an object in a digital picture is enhanced by comparing an input video of the digital picture with stored information representative of the nature and characteristics of the object to develop object localization information that identifies and locates the object. The input video and the object localization information are encoded and transmitted to a receiver where the input video and the object localization information are decoded and the decoded input video is enhanced by the decoded object localization information

摘要翻译： 通过将数字图像的输入视频与表示对象的性质和特征的存储信息进行比较，以开发识别和定位对象的对象定位信息来增强数字图像中对象的可视性。 输入视频和对象定位信息被编码并发送到接收机，其中输入视频和对象定位信息被解码，并且解码的输入视频被解码的对象定位信息增强

公开(公告)号：US20100098307A1

公开(公告)日：2010-04-22

申请号：US12450410

申请日：2007-11-06

申请人： Yu Huang ,  Joan Llach ,  Sitaram Bhagavathy

发明人： Yu Huang ,  Joan Llach ,  Sitaram Bhagavathy

IPC分类号： G06K9/62

CPC分类号： G06K9/00711 ,  G06K9/44 ,  G06K9/4652

摘要： A method is disclosed for detecting and locating players in soccer video frames without errors caused by artifacts by a shape analysis-based approach to identify the players and the ball from roughly extracted foregrounds obtained by color segmentation and connected component analysis, by performing a Euclidean distance transform to extract skeletons for every foreground blob, by performing a shape analysis to remove false alarms (non-players and non-ball), and then by performing skeleton pruning and a reverse Euclidean distance transform to cut-off the artifacts primarily caused by playing field lines.

摘要翻译： 公开了一种用于通过基于形状分析的方法来检测和定位足球视频帧中的玩家而产生错误的方法，以通过执行欧几里德距离从颜色分割和连接分量分析获得的大致提取的前景识别玩家和球， 通过执行形状分析来消除假警报（非玩家和非球），然后通过执行骨架修剪和反向欧几里得距离变换来截取主要由玩耍造成的伪影，从而转换为每个前景斑点提取骨架 现场线。

公开(公告)号：US20100067802A1

公开(公告)日：2010-03-18

申请号：US12312743

申请日：2007-11-30

申请人： Yu Huang ,  Joan Llach

发明人： Yu Huang ,  Joan Llach

IPC分类号： G06K9/46

CPC分类号： G06K9/32 ,  G06K2009/3291 ,  G06T7/277 ,  G06T2207/10016 ,  G06T2207/30224 ,  G06T2207/30241

摘要： An implementation provides a method for estimating a location for an object in a particular image of a sequence of images. The location is estimated using a particle-based framework, such as a particle filter. It is determined that the estimated location for the object in the particular image is occluded. A trajectory is estimated for the object based on one or more previous locations of the object in one or more previous images in the sequence of images. The estimated location of the object is changed based on the estimated trajectory.

摘要翻译： 实现提供了一种用于估计图像序列的特定图像中的对象的位置的方法。 使用基于粒子的框架（如粒子滤波器）来估计位置。 确定特定图像中对象的估计位置被遮挡。 基于图像序列中的一个或多个先前图像中的物体的一个或多个先前位置来估计对象的轨迹。 基于估计的轨迹改变对象的估计位置。

公开(公告)号：US20070047658A1

公开(公告)日：2007-03-01

申请号：US10572690

申请日：2004-09-21

申请人： Alexandros Tourapis ,  Jill MacDonald ,  Joan Llach

发明人： Alexandros Tourapis ,  Jill MacDonald ,  Joan Llach

IPC分类号： H04N11/02 ,  H04B1/66

CPC分类号： H04N19/85 ,  G06T5/001 ,  G06T2207/20204 ,  H04N5/21 ,  H04N5/4401 ,  H04N19/86 ,  Y02E60/324

摘要： A decoding arrangement for decoding pictures in an incoming video stream includes a noise generator for adding a dither signal containing random noise to the pictures after video decoding, to improve the subjective video quality. The noise generator adds noise to each pixel in an amount correlated to the luminance of at least a portion of the current picture.

摘要翻译： 用于对输入视频流中的图像进行解码的解码装置包括：噪声发生器，用于在视频解码之后将包含随机噪声的抖动信号加到图像上，以改善主观视频质量。 噪声发生器以与当前图像的至少一部分的亮度相关的量向每个像素增加噪声。

公开(公告)号：US09230315B2

公开(公告)日：2016-01-05

申请号：US13991567

申请日：2010-12-08

申请人： Timothy Alan Barrett ,  Pierre Hughes Routhier ,  Joan Llach ,  Ben Crosby

发明人： Timothy Alan Barrett ,  Pierre Hughes Routhier ,  Joan Llach ,  Ben Crosby

IPC分类号： G06T7/00 ,  G06T15/00 ,  G06T15/20 ,  H04N13/04 ,  G06K9/46 ,  H04N13/02

CPC分类号： G06T7/00 ,  G06K9/46 ,  G06T15/00 ,  G06T15/20 ,  G06T2200/08 ,  G06T2200/16 ,  H04N13/261 ,  H04N13/30

摘要： Automatic determination of the complexity associated with converting image content from 2-dimensions to 3-dimensions commences by first determining how many different scenes exist within the image content. Each scene then undergoes analysis to determine its complexity based on the motion, texture and occlusion within the scene. The scene complexities are added to the scene transition complexity and the total gets weighted to yield an overall indication of the complexity of converting of image content from 2-dimensions to 3-dimensions.

摘要翻译： 通过首先确定图像内容中存在多少不同场景，自动确定将图像内容从二维转换为三维的相关开始。 然后每个场景进行分析以根据场景内的运动，纹理和遮挡来确定其复杂性。 场景复杂性被添加到场景转换复杂性，并且总体被加权以产生将图像内容从二维转换为三维的复杂性的总体指示。

公开(公告)号：US09214030B2

公开(公告)日：2015-12-15

申请号：US12451264

申请日：2008-04-25

申请人： Joel Sole ,  Yu Huang ,  Joan Llach

发明人： Joel Sole ,  Yu Huang ,  Joan Llach

IPC分类号： H04N7/30 ,  H04N7/26 ,  H04N7/64 ,  G06T7/20 ,  G06T5/00

CPC分类号： G06T7/2006 ,  G06T5/005 ,  G06T7/194 ,  G06T7/215 ,  G06T2207/10016

摘要： A method for processing a video sequence having a plurality of frames includes the steps of: extracting features from each of the frames, determining correspondences between the extracted features from two of the frames, estimating motion in the video sequence based on the determined correspondences, generating a background mosaic for the video sequence based on the estimated motion, and performing foreground-background segmentation on each of the frames based on the background mosaic.

摘要翻译： 一种用于处理具有多个帧的视频序列的方法包括以下步骤：从每个帧中提取特征，确定来自两帧中提取的特征之间的对应关系，基于所确定的对应度估计视频序列中的运动，产生 基于估计运动的视频序列的背景马赛克，以及基于背景马赛克对每个帧执行前景背景分割。