公开(公告)号：US09076220B2

公开(公告)日：2015-07-07

申请号：US13642622

申请日：2010-04-29

申请人： Debing Liu ,  Zhibo Chen ,  Xiaodong Gu ,  Feng Xu

发明人： Debing Liu ,  Zhibo Chen ,  Xiaodong Gu ,  Feng Xu

IPC分类号： G06K9/34 ,  G06T7/00 ,  G06T7/40 ,  H04N19/159 ,  H04N19/176 ,  H04N19/117 ,  H04N19/86

CPC分类号： G06T7/0081 ,  G06T7/0002 ,  G06T7/11 ,  G06T7/181 ,  G06T7/41 ,  G06T2207/20021 ,  G06T2207/30168 ,  H04N19/117 ,  H04N19/159 ,  H04N19/176 ,  H04N19/86 ,  H04N19/865

摘要： A method for processing an image divided into blocks of pixels is described. The method includes detecting a largest sub-block whose pixels have an equal luminance value and identifying if the detected largest sub-block is or is not a natural texture. Thereafter, a weighted luminance difference is calculated between the detected largest sub-block and neighboring pixels and a block blockiness level is determined on the basis of the number of pixels within the detected largest sub-block, of the identification step and of the weighted luminance difference. The image is then processed on the basis of the block blockiness level.

摘要翻译： 描述用于处理被划分成像素块的图像的方法。 该方法包括检测其像素具有相等亮度值的最大子块，并且识别检测到的最大子块是否是自然纹理。 此后，在检测到的最大子块和相邻像素之间计算加权亮度差，并且基于检测到的最大子块中的像素数，确定步骤的加权亮度和 区别。 然后基于块块化级别处理图像。

公开(公告)号：US08824783B2

公开(公告)日：2014-09-02

申请号：US13695060

申请日：2010-04-30

申请人： Feng Xu ,  Zhibo Chen ,  Debing Liu ,  Xiaodong Gu

发明人： Feng Xu ,  Zhibo Chen ,  Debing Liu ,  Xiaodong Gu

IPC分类号： G06K9/62 ,  G06K9/46 ,  H04N17/00 ,  G06T7/00

CPC分类号： H04N17/004 ,  G06N99/005 ,  G06T7/0002 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/30168

摘要： The invention is made in the technical field of video quality measurement. More precisely, the invention is related to mean observer score prediction using a trained semi-supervised learning regressor. That is, a method and apparatus for measuring video quality using a semi-supervised learning system for mean observer score prediction is proposed. Said semi-supervised learning system comprises at least one semi-supervised learning regressor and said method comprises training the learning system and retraining the trained learning system using a selection of test data wherein the test data is used for determining at least one mean observer score prediction using the trained learning system and the selection is indicated by a feedback received through a user interface upon presenting, in the user interface, said at least one mean observer score prediction. Doing so, prediction quality can be improved after re-training at least for the selection.

摘要翻译： 本发明是在视频质量测量技术领域进行的。 更准确地说，本发明涉及使用训练有素的半监督学习回归器的平均观察者评分预测。 也就是说，提出了一种使用半监督学习系统测量视频质量的方法和装置，用于平均观察员评分预测。 所述半监督学习系统包括至少一个半监督学习回归器，并且所述方法包括训练学习系统并且使用测试数据的选择重新训练训练学习系统，其中测试数据用于确定至少一个平均观察者评分预测 使用训练的学习系统和选择由在用户界面中呈现所述至少一个平均观察者分数预测时通过用户界面接收的反馈来指示。 做到这一点，至少在选择后再进行训练后，可以提高预测质量。

公开(公告)号：US08723960B2

公开(公告)日：2014-05-13

申请号：US13807875

申请日：2010-07-02

申请人： Xiaodong Gu ,  Debing Liu ,  Feng Xu ,  Zhibo Chen

发明人： Xiaodong Gu ,  Debing Liu ,  Feng Xu ,  Zhibo Chen

IPC分类号： H04N17/00

CPC分类号： H04N5/14 ,  G06K9/00758 ,  G06K9/6212 ,  H04N17/004

摘要： The purpose of an objective video quality evaluation is to automatically assess the quality of video sequences in agreement with human quality perception. The invention addresses the effects of the introduction of a temporal dimension by focusing on the temporal evolutions of spatial distortions, since it has been found that a spatial quality variation cannot be evaluated by simple subtraction of the spatial quality of neighboring frames. An improved method for estimating perceived video quality comprises steps of calculating a first similarity map between adjacent frames of a current sequence, calculating a second similarity map between the corresponding reference frames, and calculating (smg3) a third similarity map, which provides a numerical quality value.

摘要翻译： 客观视频质量评估的目的是自动评估视频序列的质量，符合人的素质感知。 本发明通过关注空间失真的时间演变来解决引入时间维度的效果，因为已经发现空间质量变化不能通过简单地减去相邻帧的空间质量来评估。 一种用于估计感知视频质量的改进方法包括以下步骤：计算当前序列的相邻帧之间的第一相似度图，计算相应参考帧之间的第二相似度映射，以及计算（smg3）第三相似度图，其提供数值质量 值。

公开(公告)号：US08121428B2

公开(公告)日：2012-02-21

申请号：US11141363

申请日：2005-05-31

申请人： Guo Bin Shen ,  Debing Liu ,  Shipeng Li ,  Yuwen He

发明人： Guo Bin Shen ,  Debing Liu ,  Shipeng Li ,  Yuwen He

IPC分类号： G06K9/36

CPC分类号： H04N19/59 ,  H04N19/48 ,  H04N19/60 ,  H04N19/70 ,  H04N19/91

摘要： Systems and methods are presented for accelerated image rendering. In one implementation, the systems and methods receive digital image data and derive intermediate data associated with the digital image data to accelerate image rendering.

摘要翻译： 提出了加速图像渲染的系统和方法。 在一个实现中，系统和方法接收数字图像数据并导出与数字图像数据相关联的中间数据以加速图像渲染。

公开(公告)号：US20150382083A1

公开(公告)日：2015-12-31

申请号：US14770071

申请日：2013-03-06

申请人： Zhibo CHEN ,  Debing LIU ,  Xiaodong GU ,  Fan ZHANG

发明人： ZHIBO CHEN ,  DEBING LIU ,  XIAODONG GU ,  FAN ZHANG

IPC分类号： H04N21/8549

CPC分类号： H04N21/8549 ,  G06F16/739

摘要： Various implementations relate to providing a pictorial summary, also referred to as a comic book or a narrative abstraction. In one particular implementation, a first portion in a video is accessed, and a second portion in the video is accessed. A weight for the first portion is determined, and a weight for the second portion is determined. A first number and a second number are determined. The first number identifies how many pictures from the first portion are to be used in a pictorial summary of the video. The first number is one or more, and is determined based on the weight for the first portion. The second number identifies how many pictures from the second portion are to be used in the pictorial summary of the video. The second number is one or more, and is determined based on the weight for the second portion.

摘要翻译： 各种实现涉及提供图形摘要，也称为漫画书或叙事抽象。 在一个具体实现中，访问视频中的第一部分，并且访问视频中的第二部分。 确定第一部分的重量，并确定第二部分的重量。 确定第一个数字和第二个数字。 第一个数字标识了在视频的图形总结中使用第一部分的图片数量。 第一个数字是一个或多个，并且基于第一部分的权重来确定。 第二个数字识别在视频的图片摘要中将使用第二部分的图片数量。 第二个数是一个或多个，并且基于第二部分的权重来确定。

公开(公告)号：US20140307103A1

公开(公告)日：2014-10-16

申请号：US14356447

申请日：2011-11-28

申请人： Xiaodong Gu ,  Debing Liu ,  Zhibo Chen

发明人： Xiaodong Gu ,  Debing Liu ,  Zhibo Chen

IPC分类号： H04N17/00

CPC分类号： H04N17/004 ,  H04N19/154 ,  H04N19/895

摘要： Various implementations address distortion and quality measurements. Certain implementations relate to distortions resulting in a freeze-with-skip and/or a freeze-without-skip. In one implementation, a pause term provides an indication of distortion associated with a pause arising from not displaying one or more consecutive pictures that are not to be displayed. A motion term provides an indication of distortion associated with a related change in motion. A combined indicator is based on an addition of the pause term and the motion term. In another particular implementation, a first indicator indicates distortion across one or more types of distortive effects that results from not displaying a first set of pictures. A second indicator indicates corresponding distortion with respect to a second set of pictures. The first indicator and the second indicator are combined in a non-linear manner.

摘要翻译： 各种实现解决了失真和质量测量。 某些实施方式涉及导致冻结与跳过和/或冻结无跳跃的失真。 在一个实现中，暂停项提供与不显示一个或多个不被显示的连续图像产生的暂停相关联的失真指示。 运动项提供与相关运动变化相关联的失真的指示。 组合指示器基于暂停项和运动项的添加。 在另一具体实现中，第一指示符指示由不显示第一组图像而导致的一种或多种类型的失真效应的失真。 第二指示符指示相对于第二组图像的相应失真。 第一指示符和第二指示符以非线性方式组合。

公开(公告)号：US20140254938A1

公开(公告)日：2014-09-11

申请号：US14359926

申请日：2011-11-24

申请人： Xiaodong Gu ,  Debing Liu ,  Zhibo Chen

发明人： Xiaodong Gu ,  Debing Liu ,  Zhibo Chen

IPC分类号： G06T5/00 ,  G06T5/20

CPC分类号： G06T5/002 ,  G06T5/20 ,  G06T2207/20192 ,  H04N19/117 ,  H04N19/14 ,  H04N19/17 ,  H04N19/895

摘要： Methods and apparatus for artifact detection are provided by the present principles that measure the level of artifacts, such as those caused by temporal concealment of errors due to packet loss, for conditional error concealment. The principles are based on an assumption that sharp edges of video are rarely aligned with macroblock boundaries so video discontinuities are checked throughout the video. The scheme solves the problem of error propagation when temporal concealment of artifacts is used and the high false alarm rates of prior methods. Artifact detection methods are provided for regions of an image, an entire image, or for a video sequence, with error concealment provided conditionally based on the artifact levels.

摘要翻译： 用于伪影检测的方法和装置由用于条件错误隐藏的测量诸如由于分组丢失引起的错误的时间隐藏而引起的伪影等级的本原理提供。 这些原理基于这样一种假设：视频的锐利边缘很少与宏块边界对齐，因此在整个视频中检查视频不连续性。 该方案解决了使用伪像的时间隐藏和先前方法的高误报率时的误差传播问题。 为图像，整个图像或视频序列的区域提供伪像检测方法，其中错误隐藏基于伪像级别有条件地提供。

公开(公告)号：US08823873B2

公开(公告)日：2014-09-02

申请号：US13500921

申请日：2009-10-10

申请人： Debing Liu ,  Zhibo Chen ,  Xaiodong Gu ,  Feng Xu

发明人： Debing Liu ,  Zhibo Chen ,  Xaiodong Gu ,  Feng Xu

IPC分类号： H04N7/01

CPC分类号： G06T7/0002 ,  G06T2207/10016 ,  G06T2207/20004 ,  G06T2207/20021 ,  G06T2207/30168 ,  H04N7/012 ,  H04N19/117 ,  H04N19/14 ,  H04N19/162 ,  H04N19/85

摘要： Blur is one of the most important features related to image quality. Accurately estimating the blur level of an image is a great help to accurately evaluate its quality. A method for calculating blur of video images comprises calculating a horizontal blur value, and determining characteristic parameters of the video images, including at last progressive/interlaced and spatial resolution level. If the video images are progressive, also a vertical blur value is calculated, and combined with the horizontal blur value. The next step is normalizing the horizontal blur value, or the combined horizontal and vertical blur value, according to predefined min and max values, wherein the min and max values are adapted to the spatial resolution level.

摘要翻译： 模糊是与图像质量相关的最重要的功能之一。 准确估计图像的模糊水平是准确评估其质量的极大帮助。 一种用于计算视频图像模糊的方法包括计算水平模糊值，以及确定视频图像的特征参数，包括最后渐进/隔行扫描和空间分辨率级别。 如果视频图像是渐进的，则还计算垂直模糊值，并与水平模糊值组合。 下一步是根据预定义的最小值和最大值归一化水平模糊值或组合的水平和垂直模糊值，其中最小值和最大值适应于空间分辨率水平。

公开(公告)号：US09924167B2

公开(公告)日：2018-03-20

申请号：US14358114

申请日：2011-11-28

申请人： Xiaodong Gu ,  Debing Liu ,  Zhibo Chen

发明人： Xiaodong Gu ,  Debing Liu ,  Zhibo Chen

IPC分类号： H04N19/103 ,  H04N19/154 ,  H04N19/192 ,  H04N19/48 ,  H04N19/89 ,  H04N17/00

CPC分类号： H04N19/192 ,  H04N17/004 ,  H04N19/103 ,  H04N19/154 ,  H04N19/48 ,  H04N19/89

摘要： A particular implementation determines objective distortion levels (d,) respectively for a plurality of artifact types. The objective distortion levels are aligned to ensure that the same distortion level of different types of artifacts corresponds to the same perceived distortion level. The aligned distortion levels (d,′) are sorted to obtain sorted distortion levels (d,″). The sorted distortion levels are then pooled together into an overall distortion level or an overall quality metric. The sorted distortion levels may be pooled using a weighted sum, wherein the weight is larger when the sorted distortion level is greater.

公开(公告)号：US08675075B2

公开(公告)日：2014-03-18

申请号：US13811657

申请日：2010-07-30

申请人： Xiaodong Gu ,  Debing Liu ,  Zhibo Chen

发明人： Xiaodong Gu ,  Debing Liu ,  Zhibo Chen

IPC分类号： H04N17/00 ,  H04N5/21

CPC分类号： H04N17/00 ,  H04N5/21 ,  H04N17/002 ,  H04N19/139 ,  H04N19/14 ,  H04N19/172 ,  H04N19/89

摘要： A method and apparatus for measuring the quality of a video sequence, which includes a plurality of frames, among which one or more consecutive frames are lost, wherein during the displaying of the video sequence, the one or more lost frames are substituted by an immediate preceding frame in the video sequence during a period from the displaying of the immediate preceding frame to that of an immediate subsequent frame of the one or more lost frames, the method includes measuring the quality of the video sequence as a function of a first parameter (DF) relating to the stability of the immediate preceding frame during the period, a second parameter (DD) relating to the continuity between the immediate preceding frame and the immediate subsequent frame, and a third parameter (DP) relating to the coherent 20 motions of the video sequence.

摘要翻译： 一种用于测量包括多个帧的视频序列的质量的方法和装置，其中一个或多个连续帧丢失，其中在显示视频序列期间，一个或多个丢失帧被立即替换 在从直接前一帧的显示到所述一个或多个丢失帧的即时后续帧的时间段期间，视频序列中的前一帧的视频序列的前一帧，该方法包括测量作为第一参数的函数的视频序列的质量 DF），与第一参数（DP）有关，该第二参数（DD）涉及在紧接着的前一帧与即时后续帧之间的连续性的第二参数（DD）以及与第二参数 视频序列。