公开(公告)号：US20150373324A1

公开(公告)日：2015-12-24

申请号：US14763940

申请日：2013-06-09

申请人： Ning LIAO ,  Zhibo CHEN ,  Fan ZHANG ,  THOMSON LICENSING

发明人： Ning Liao ,  Zhibo Chen ,  Fan Zhang

IPC分类号： H04N17/00 ,  H04N19/114 ,  G06T7/00 ,  G06K9/03 ,  G06K9/00 ,  H04N19/103 ,  H04N19/154

CPC分类号： H04N17/004 ,  G06K9/00536 ,  G06K9/00711 ,  G06K9/036 ,  G06T7/0002 ,  G06T2207/10016 ,  H04N19/103 ,  H04N19/114 ,  H04N19/154 ,  H04N19/48 ,  H04N19/89

摘要： Spatial distortion (i.e., when a frame is viewed independently of other frames in a video sequence) may be quite different from temporal distortion (i.e., when frames are viewed continuously). To estimate temporal distortion, a sliding window approach is used. Specifically, multiple sliding windows around a current frame are considered. Within each sliding window, a large distortion density is calculated and a sliding window with the highest large distortion density is selected. A distance between the current frame and the closest frame with large distortion in the selected window is calculated. Subsequently, the temporal distortion is estimated as a function of the highest large distortion ratio, the spatial distortion for the current frame, and the distance. In another embodiment, a median of spatial distortion values is calculated for each sliding window and the maximum of median spatial distortion values is used to estimate the temporal distortion.

摘要翻译： 空间失真（即，当视频序列中独立于其他帧观看帧）可能与时间失真（即，连续观看帧时）完全不同。 为了估计时间失真，使用滑动窗口方法。 具体地说，考虑当前帧周围的多个滑动窗口。 在每个滑动窗口内，计算出较大的失真密度，并选择具有最大大失真密度的滑动窗口。 计算当前帧与所选窗口中具有大失真的最近帧之间的距离。 随后，将时间失真估计为最大的大失真比，当前帧的空间失真和距离的函数。 在另一个实施例中，为每个滑动窗口计算空间失真值的中值，并且使用中值空间失真值的最大值来估计时间失真。

公开(公告)号：US20150304709A1

公开(公告)日：2015-10-22

申请号：US14443841

申请日：2012-11-30

申请人： Qian ZHANG ,  Ning LIAO ,  Fan ZHANG ,  Zhibo CHEN

发明人： Qian Zhang ,  Ning Liao ,  Fan Zhang ,  Zhibo Chen

IPC分类号： H04N21/44 ,  H04N21/61 ,  H04N21/647 ,  H04N21/643 ,  H04N21/442 ,  H04N21/234

CPC分类号： H04N21/44008 ,  H04N21/23418 ,  H04N21/44209 ,  H04N21/4425 ,  H04N21/6125 ,  H04N21/64322 ,  H04N21/6473 ,  H04N21/64738 ,  H04N21/64769

摘要： A method and apparatus are disclosed for predicting subjective quality of a video contained in a bit stream on a packet layer. Header information of the bit-stream is parsed and frame layer information, such as frame type, is estimated. Visible artifact levels are then estimated based on frame layer information. An overall artifact level and quality metric are estimated based on artifact levels for individual frames with other parameters. Specifically, different weighting factors are used for different frame types when estimating the levels of initial visible artifacts and propagated visible artifacts. The number of slices per frame is used as a parameter when estimating the overall artifact level for the video. Moreover, the quality assessment model considers quality loss caused by both coding and channel artifacts.

摘要翻译： 公开了一种用于预测分组层中的比特流中包含的视频的主观质量的方法和装置。 解析比特流的报头信息，并估计帧类信息，如帧类型。 然后基于帧层信息来估计可见的伪像级别。 基于具有其他参数的单个帧的伪像级别来估计整体神器级别和质量度量。 具体来说，当估计初始可见伪像和传播的可见伪像的水平时，不同的加权因子被用于不同的帧类型。 当估计视频的整体神器级别时，每帧的片数被用作参数。 此外，质量评估模型考虑了由编码和通道伪影引起的质量损失。

公开(公告)号：US10075710B2

公开(公告)日：2018-09-11

申请号：US14353351

申请日：2011-11-24

申请人： Fan Zhang ,  Ning Liao ,  Kai Xie ,  Zhibo Chen

发明人： Fan Zhang ,  Ning Liao ,  Kai Xie ,  Zhibo Chen

IPC分类号： H04N19/89 ,  H04N17/00 ,  H04N19/895

CPC分类号： H04N19/176 ,  H04N17/004 ,  H04N19/895

摘要： A particular implementation receives a bitstream and derives parameters from the bitstream. The parameters include quantization parameters, content unpredictability parameters, ratios of lost blocks, ratios of propagated blocks, error concealment distances, motion vectors, durations of freezing, and frame rates. Using these parameters, a compression distortion factor, a slicing distortion factor, and a freezing distortion factor are estimated respectively for distortions resulting from video compression, a slicing mode error concealment, and a freezing slicing mode error concealment. The distortion factors are then mapped to a composite video quality score. For applications with limited computational power, the estimation of distortion factors can be simplified. In particular, the compression distortion factor, the slicing distortion factor, and the freezing distortion factor can be predicted from quantization parameters, ratios of lost blocks, and durations of freezing, respectively.

公开(公告)号：US09961340B2

公开(公告)日：2018-05-01

申请号：US14364144

申请日：2011-12-15

申请人： Fan Zhang ,  Ning Liao ,  Kai Xie ,  Zhibo Chen

发明人： Fan Zhang ,  Ning Liao ,  Kai Xie ,  Zhibo Chen

IPC分类号： H04N7/12 ,  H04N17/00 ,  H04N19/176 ,  H04N19/124 ,  H04N19/154

CPC分类号： H04N17/004 ,  H04N19/124 ,  H04N19/154 ,  H04N19/176

摘要： Accuracy and efficiency of video quality measurement are major problems to be solved. According to the invention, a method for accurately predicting video quality uses a rational function of the quantization parameter QP, which is corrected by a correction function that depends on content unpredictability CU. Exemplarily, the correction function is a power function of the CU. Both QP and CU can be computed from the video elementary stream, without full decoding the video. This ensures high efficiency.

公开(公告)号：US20140301486A1

公开(公告)日：2014-10-09

申请号：US14355975

申请日：2011-11-25

申请人： Ning Liao ,  Zhibo Chen ,  Fan Zhang ,  Kai Xie

发明人： Ning Liao ,  Zhibo Chen ,  Fan Zhang ,  Kai Xie

IPC分类号： H04N19/86 ,  H04N19/89 ,  H04N19/87

CPC分类号： H04N19/48 ,  H04N19/154 ,  H04N19/87 ,  H04N19/895

摘要： A particular implementation detects scene cut artifacts in a bitstream without reconstructing the video. A scene cut artifact is usually observed in the decoded video (1) when a scene cut picture in the original video is partially received or (2) when a picture refers to a lost scene cut picture in the original video. To detect scene cut artifacts, candidate scene cut pictures are first selected and scene cut artifact detection is then performed on the candidate pictures. When a block is determined to have a scene cut artifact, a lowest quality level is assigned to the block.

摘要翻译： 特定的实现检测比特流中的场景切割伪像，而不重建视频。 通常在解码视频（1）中观察到原始视频中的场景切换图像被部分接收或（2）当图片参考原始视频中的丢失的场景切换图像时，场景切割伪影。 为了检测场景切割伪像，首先选择候选场景切割图像，然后对候选图像执行场景切割伪影检测。 当确定块具有场景切割伪影时，将最低质量级别分配给块。

公开(公告)号：US20140286441A1

公开(公告)日：2014-09-25

申请号：US14353351

申请日：2011-11-24

申请人： Fan Zhang ,  Ning Liao ,  Kai Xie ,  Zhibo Chen

发明人： Fan Zhang ,  Ning Liao ,  Kai Xie ,  Zhibo Chen

IPC分类号： H04N19/89

CPC分类号： H04N19/00933 ,  H04N17/004 ,  H04N19/895

摘要： A particular implementation receives a bitstream and derives parameters from the bitstream. The parameters include quantization parameters, content unpredictability parameters, ratios of lost blocks, ratios of propagated blocks, error concealment distances, motion vectors, durations of freezing, and frame rates. Using these parameters, a compression distortion factor, a slicing distortion factor, and a freezing distortion factor are estimated respectively for distortions resulting from video compression, a slicing mode error concealment, and a freezing slicing mode error concealment. The distortion factors are then mapped to a composite video quality score. For applications with limited computational power, the estimation of distortion factors can be simplified. In particular, the compression distortion factor, the slicing distortion factor, and the freezing distortion factor can be predicted from quantization parameters, ratios of lost blocks, and durations of freezing, respectively.

摘要翻译： 特定实现接收比特流并从比特流导出参数。 参数包括量化参数，内容不可预测性参数，丢失块的比率，传播块的比率，错误隐藏距离，运动向量，冻结持续时间和帧速率。 分别使用这些参数来估计压缩失真因子，切片失真因子和冻结失真因子，用于由视频压缩，切片模式错误隐藏和冷冻切片模式错误隐藏产生的失真。 然后将失真因子映射到复合视频质量得分。 对于具有有限计算能力的应用，可以简化失真因子的估计。 具体地，压缩失真因子，切片失真因子和冻结失真因子可以分别从量化参数，丢失块的比率和冻结时间预测。

公开(公告)号：US09769501B2

公开(公告)日：2017-09-19

申请号：US14405079

申请日：2012-07-17

申请人： Ning Liao ,  Zhibo Chen ,  Kai Xie

发明人： Ning Liao ,  Zhibo Chen ,  Kai Xie

IPC分类号： H04N19/895 ,  H04N19/44 ,  H04N19/184 ,  H04N19/139 ,  H04N19/177 ,  H04N17/00 ,  H04N19/86 ,  H04N19/89 ,  H04N19/154

CPC分类号： H04N19/895 ,  H04N17/004 ,  H04N19/139 ,  H04N19/154 ,  H04N19/177 ,  H04N19/184 ,  H04N19/44 ,  H04N19/86 ,  H04N19/89

摘要： A macroblock in a video sequence may be undecodable because the corresponding compressed data is lost or the syntax is out of synchronization. An undecodable macroblock may be concealed using error concealment technique. The level of initial visible artifacts caused by undecodable macroblocks may be estimated as a function of motion magnitude, error concealment distance, and/or residual energy. The initial visible artifacts may propagate spatially or temporally to other macroblocks through prediction. Considering both initial visible artifacts and propagated artifacts, levels of overall artifacts may be estimated for individual macroblocks. The visual quality for the video sequence can then be estimated by pooling the macroblock level artifact levels.

公开(公告)号：US09288071B2

公开(公告)日：2016-03-15

申请号：US13695058

申请日：2010-04-30

申请人： Ning Liao ,  Zhibo Chen ,  Xianlei Wang

发明人： Ning Liao ,  Zhibo Chen ,  Xianlei Wang

IPC分类号： H04L12/725 ,  H04L12/24 ,  H04N17/00 ,  H04N21/435 ,  H04N21/6437 ,  H04L29/06 ,  H04N19/46 ,  H04N19/196 ,  H04N19/61 ,  H04N19/154 ,  H04N19/86 ,  H04N19/895

CPC分类号： H04L12/24 ,  H04L41/00 ,  H04L65/4076 ,  H04L65/80 ,  H04N17/004 ,  H04N19/154 ,  H04N19/196 ,  H04N19/46 ,  H04N19/61 ,  H04N19/86 ,  H04N19/895 ,  H04N21/435 ,  H04N21/6437

摘要： Objective video quality assessment models at media-layer or at packet-layer are known for estimating audio/video quality of experience. Existing models are not able to provide stable performance. A method for enabling quality assessment of a stream of frames of video data comprises receiving a sequence of packets, generating a set of parameters and inserting said generated set of parameters as side information into said stream of frames, wherein at least one parameter refers to a video slice level. A method for assessing the quality of a stream of frames of video data comprises receiving a sequence of packets, extracting a set of parameters from said sequence of packets and generating an estimated mean opinion score, wherein the video data comprise a slice level and wherein the extracted set of parameters comprises at least one parameter that refers to a video slice level.

摘要翻译： 用于估计音频/视频体验质量的媒体层或分组层的目标视频质量评估模型是已知的。 现有型号不能提供稳定的性能。 一种用于实现视频数据帧流的质量评估的方法包括接收分组序列，产生一组参数，并将所述生成的参数集合作为辅助信息插入所述帧流中，其中至少一个参数是指 视频切片级别。 一种用于评估视频数据帧流的质量的方法包括接收分组序列，从所述分组序列中提取一组参数并生成估计的平均意见分数，其中所述视频数据包括切片级别，其中， 提取的参数集合包括参考视频片段级别的至少一个参数。

公开(公告)号：US20150215619A1

公开(公告)日：2015-07-30

申请号：US14423325

申请日：2012-12-29

申请人： Ning Liao ,  Zhibo Chen ,  Kai Xie

发明人： Ning Liao ,  Zhibo Chen ,  Kai Xie

IPC分类号： H04N19/109 ,  H04N19/176 ,  H04N19/182 ,  H04N19/154 ,  H04N19/142 ,  H04N19/184

CPC分类号： H04N19/109 ,  H04N5/147 ,  H04N17/004 ,  H04N19/11 ,  H04N19/142 ,  H04N19/154 ,  H04N19/176 ,  H04N19/182 ,  H04N19/184 ,  H04N19/48

摘要： The invention provides a method and apparatus for detecting a gradual transition picture in a bitstream. The method comprises: accessing a bitstream including encoded pictures; and determining a gradual transition picture in the bitstream using information from the bitstream without decoding the bitstream to derive pixel information.

摘要翻译： 本发明提供一种用于检测比特流中的逐渐转换图像的方法和装置。 该方法包括：访问包括编码图像的比特流; 以及使用来自所述比特流的信息确定所述比特流中的逐渐转换图像，而不解码所述比特流以导出像素信息。

公开(公告)号：US09549183B2

公开(公告)日：2017-01-17

申请号：US14116342

申请日：2011-05-12

申请人： Ning Liao ,  Xiao Dong Gu ,  Zhibo Chen ,  Kai Xie

发明人： Ning Liao ,  Xiao Dong Gu ,  Zhibo Chen ,  Kai Xie

IPC分类号： H04N19/107 ,  H04N19/89 ,  H04N19/513 ,  H04N19/154 ,  H04N19/895

CPC分类号： H04N19/513 ,  H04N19/107 ,  H04N19/154 ,  H04N19/895

摘要： A method for estimating video quality on bit-stream level, wherein the video quality refers to a video after error concealment and the method is performed on bit-stream level before said error concealment, comprises extracting and/or calculating a plurality of global condition features from a video bit-stream, extracting and/or calculating a plurality of local effectiveness features at least for a lost MB, calculating a numeric error concealment effectiveness level for each (or at least for each lost) MB by emulating an error concealment method that is used in said error concealment, and providing the calculated error concealment effectiveness level as an estimated visible artifacts level of video quality.

摘要翻译： 一种用于估计比特流级别的视频质量的方法，其中所述视频质量是指在错误隐藏之后的视频，并且所述方法在所述错误隐藏之前的比特流级别上执行，包括提取和/或计算多个全局条件特征 至少对于丢失MB提取和/或计算多个局部有效特征，通过模拟错误隐藏方法（或至少对于每个丢失的）MB来计算数字错误隐藏有效性级别 用于所述错误隐藏，并将计算出的错误隐藏有效性级别提供为视频质量的估计可见伪像级别。