公开(公告)号：US20100128789A1

公开(公告)日：2010-05-27

申请号：US12451264

申请日：2008-04-25

Applicant: Joel Sole ,  Yu Huang ,  Joan Llach

Inventor： Joel Sole ,  Yu Huang ,  Joan Llach

IPC: H04N7/30 ,  H04N7/26 ,  H04N7/64

CPC classification number: G06T7/2006 ,  G06T5/005 ,  G06T7/194 ,  G06T7/215 ,  G06T2207/10016

Abstract: 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.

Abstract translation: 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。

公开(公告)号：US20100054536A1

公开(公告)日：2010-03-04

申请号：US12312737

申请日：2007-11-30

Applicant: Yu Huang ,  Joan Llach

Inventor： Yu Huang ,  Joan Llach

IPC: G06K9/00

CPC classification number: G06K9/32 ,  G06K2009/3291 ,  G06T7/277 ,  G06T2207/10016 ,  G06T2207/30224 ,  G06T2207/30241

Abstract: An implementation provides a method including forming a metric surface in a particle-based framework for tracking an object, the metric surface relating to a particular image in a sequence of digital images. Multiple hypotheses are formed of a location of the object in the particular image, based on the metric surface. The location of the object is estimated based on probabilities of the multiple hypotheses.

Abstract translation: 实现提供了一种方法，包括在用于跟踪对象的基于粒子的框架中形成度量表面，该度量表面与数字图像序列中的特定图像相关。 基于公制表面，由特定图像中对象的位置形成多个假设。 基于多个假设的概率来估计对象的位置。

公开(公告)号：US09554056B2

公开(公告)日：2017-01-24

申请号：US13618403

申请日：2012-09-14

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

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

IPC: H04N7/12 ,  H04N5/235 ,  H04N5/355 ,  H04N19/70 ,  H04N19/46 ,  H04N19/33 ,  H04N19/98 ,  H04N19/59 ,  H04N5/345

CPC classification number: H04N5/2355 ,  H04N5/2356 ,  H04N5/3456 ,  H04N5/355 ,  H04N19/33 ,  H04N19/46 ,  H04N19/59 ,  H04N19/70 ,  H04N19/98

Abstract: 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.

Abstract translation: 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：US20130091430A1

公开(公告)日：2013-04-11

申请号：US13805185

申请日：2011-06-23

Applicant: Jiefu Zhai ,  Joan Llach ,  Zhe Wang

Inventor： Jiefu Zhai ,  Joan Llach ,  Zhe Wang

IPC: G06F3/0484

CPC classification number: G06F3/0484 ,  G06T5/007 ,  G06T5/40 ,  G06T2200/24 ,  G06T2207/10016 ,  G06T2207/20092 ,  G06T2207/20208

Abstract: A tone mapping graphical user interface is provided that allows a video engineer to process a video using a set of tools for changing high dynamic range data into lower dynamic range data.

Abstract translation: 提供了一种色调映射图形用户界面，其允许视频工程师使用一组用于将高动态范围数据改变为较低动态范围数据的工具来处理视频。

公开(公告)号：US08345975B2

公开(公告)日：2013-01-01

申请号：US12803371

申请日：2010-06-25

Applicant: Zhe Wang ,  Jiefu Zhai ,  Joan Llach

Inventor： Zhe Wang ,  Jiefu Zhai ,  Joan Llach

IPC: G06K9/34

CPC classification number: G06K9/6223 ,  G06K9/6226 ,  G06T5/009 ,  G06T5/40 ,  G06T2207/20208 ,  H04N1/40062 ,  H04N1/4074

Abstract: A method of segmenting regions of an image wherein a number of partitions are determined based on a range of an image histogram in a logarithmic luminance domain. Regions are defined by the partitions. A mean value of each region is calculated by K-means clustering wherein the clustering is initialized, data is assigned and centroids are updated. Anchor points are determined based on the centroids and a weight of each pixel is computed based on the anchor points.

Abstract translation: 一种分割图像区域的方法，其中基于对数亮度域中的图像直方图的范围来确定多个分区。 区域由分区定义。 通过K-means聚类计算每个区域的平均值，其中初始化聚类，分配数据并更新质心。 根据重心确定锚点，并根据锚点计算每个像素的重量。

公开(公告)号：US20120263437A1

公开(公告)日：2012-10-18

申请号：US13516228

申请日：2010-12-10

Applicant: Jesus Barcons-Palau ,  Sitaram Bhagavathy ,  Joan Llach ,  Dong-Qing Zhang

Inventor： Jesus Barcons-Palau ,  Sitaram Bhagavathy ,  Joan Llach ,  Dong-Qing Zhang

IPC: H04N9/80

CPC classification number: G06K9/00711 ,  G06K9/00335 ,  G06K9/00724 ,  G06K9/033 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/30228 ,  G06T2207/30241

Abstract: A method and associated apparatus for using a trajectory-based technique to detect a moving object in a video sequence at incorporates human interaction through a user interface. The method comprises steps of identifying and evaluating sets of connected components in a video frame, filtering the list of connected components by comparing features of the connected components to predetermined criteria, identifying candidate trajectories across multiple frames, evaluating the candidate trajectories to determine a selected trajectory, eliminating incorrect trajectories through use of the interface and processing images in said video sequence responsive to the evaluating and eliminating steps.

Abstract translation: 一种用于使用基于轨迹的技术来检测视频序列中的移动对象的方法和相关联的装置，其通过用户界面并入人类交互。 该方法包括以下步骤：识别和评估视频帧中的连接分量集合，通过将所连接分量的特征与预定标准进行比较来过滤所连接分量的列表，识别跨多个帧的候选轨迹，评估候选轨迹以确定所选择的轨迹 通过使用界面消除不正确的轨迹，并响应于评估和消除步骤来处理所述视频序列中的图像。

公开(公告)号：US08159606B2

公开(公告)日：2012-04-17

申请号：US12460814

申请日：2009-07-24

Applicant: Joel Sole ,  Joan Llach

Inventor： Joel Sole ,  Joan Llach

IPC: H04N7/01 ,  H04N11/20

CPC classification number: G06T3/4007

Abstract: A method and apparatus are provided for reversible, polynomial based image scaling. The apparatus includes a video scaler for performing image scaling from a first base resolution image to a higher resolution image, and from the higher resolution image to a second base resolution image. The first and the second base resolution images are equal on a pixel-by-pixel basis for an entirety of the first and the second base resolution images. A scaling function used for the image scaling is based on a polynomial function having two or more degrees.

Abstract translation: 提供了一种用于可逆的，基于多项式的图像缩放的方法和装置。 该装置包括用于执行从第一基本分辨率图像到较高分辨率图像以及从较高分辨率图像到第二基本分辨率图像的图像缩放的视频缩放器。 对于第一和第二基本分辨率图像的整体，第一和第二基本分辨率图像在逐个像素的基础上是相等的。 用于图像缩放的缩放函数基于具有两度或更多度的多项式函数。

公开(公告)号：US20110211816A1

公开(公告)日：2011-09-01

申请号：US12932156

申请日：2011-02-18

Applicant: Richard Edwin Goedeken ,  Jesus Barcons-Palau ,  Joan Llach

Inventor： Richard Edwin Goedeken ,  Jesus Barcons-Palau ,  Joan Llach

IPC: H04N5/93

CPC classification number: H04N5/76 ,  H04N5/765 ,  H04N9/7921 ,  H04N9/8227

Abstract: A method and apparatus are disclosed and described for providing a synchronized workstation with two-dimensional and three-dimensional outputs. The apparatus includes a video decoder (315) for decoding picture data. The video decoder includes a data manager (320) for receiving video production commands and managing a video playback of the picture data in at least one of a two-dimensional video output mode and a three-dimensional video output mode responsive to the video production commands. The two-dimensional video output mode and the three-dimensional video output mode are capable of being used independently and simultaneously.

Abstract translation: 公开和描述了一种提供具有二维和三维输出的同步工作站的方法和装置。 该装置包括用于解码图像数据的视频解码器（315）。 视频解码器包括数据管理器（320），用于接收视频制作命令并且响应于视频制作命令以二维视频输出模式和三维视频输出模式中的至少一个来管理图像数据的视频回放 。 二维视频输出模式和三维视频输出模式能够独立且同时使用。

公开(公告)号：US20110211643A1

公开(公告)日：2011-09-01

申请号：US12932062

申请日：2011-02-16

Applicant: Hua Yang ,  Richard Edwin Goedeken ,  Joan Llach

Inventor： Hua Yang ,  Richard Edwin Goedeken ,  Joan Llach

IPC: H04N7/24

CPC classification number: H04N19/60 ,  H04N19/115 ,  H04N19/124 ,  H04N19/149 ,  H04N19/156 ,  H04N19/187 ,  H04N19/192 ,  H04N19/30

Abstract: A method and apparatus are disclosed and described for providing bit rate configuration for multi-view video coding. In the video encoder, the method includes encoding image data for at least one picture for at least two joint views of multi-view video content, the at least two joint views including a base view and at least one dependent view. The bit rate configuration for encoding the image data is determined to include an average bit rate and a maximum bit rate for the base view and the average bit rate and the maximum bit rate for the at least two joint views (235, 215, 220).

Abstract translation: 公开和描述了一种用于提供用于多视点视频编码的比特率配置的方法和装置。 在视频编码器中，该方法包括编码用于多视点视频内容的至少两个联合视图的至少一个图像的图像数据，该至少两个关节视图包括基本视图和至少一个从属视图。 确定用于编码图像数据的比特率配置被确定为包括用于基本视图的平均比特率和最大比特率以及用于至少两个关节视图（235,215,220）的平均比特率和最大比特率， 。

公开(公告)号：US07945106B2

公开(公告)日：2011-05-17

申请号：US10572820

申请日：2004-09-10

Applicant: Cristina Gomila ,  Joan Llach ,  Jill MacDonald Boyce

Inventor： Cristina Gomila ,  Joan Llach ,  Jill MacDonald Boyce

IPC: G06K9/00 ,  G06K9/36 ,  G06K9/46 ,  G06K9/40 ,  G06K9/20 ,  H04N7/01 ,  H04N11/20 ,  H04N5/917 ,  H04N5/93

CPC classification number: G06T5/002 ,  G06T5/10 ,  G06T2207/20021 ,  G06T2207/20052 ,  G06T2207/20204 ,  H04N19/176 ,  H04N19/46 ,  H04N19/61 ,  H04N19/85 ,  H04N19/86

Abstract: Film grain is simulated in an output image using pre-established blocks of film grain from a pool of pre-established blocks. Successive film grain blocks are selected by matching the average intensity of a block from the pool to the average intensity of a successive one of a set of M×N pixels in an incoming image. Once all of the successive pixel blocks from the image are matched to selected film grain blocks, the selected film grain blocks are “mosaiced”, that is composited into a larger image mapped to the incoming image.

Abstract translation: 在输出图像中使用来自预先建立的块的预先建立的胶片颗粒块来模拟胶片颗粒。 通过将来自池的块的平均强度与输入图像中的一组M×N个像素中的连续的一个的平均强度进行匹配来选择连续的胶片颗粒块。 一旦来自图像的所有连续的像素块与所选的胶片颗粒块相匹配，则所选择的胶片颗粒块被“镶嵌”，其被合成到映射到输入图像的较大图像中。