公开(公告)号：US20130258052A1

公开(公告)日：2013-10-03

申请号：US13771897

申请日：2013-02-20

Applicant: QUALCOMM INCORPORATED

Inventor： Xiang LI ,  Ying CHEN ,  Marta KARCZEWICZ

IPC: H04N13/00

CPC classification number: H04N13/161 ,  H04N19/597

Abstract: In general, this disclosure describes techniques for improved inter-view residual prediction (IVRP) in three-dimensional video coding. These techniques include determining IVRP availability based on coded block flags and coding modes of residual reference blocks, disallowing IVRP coding when a block is inter-view predicted, using picture order count (POC) values to determine whether IVRP is permitted, applying IVRP to prediction units (PUs) rather than coding units (CUs), inferring values of IVRP flags when a block is skip or merge mode coded, using an IVRP flag of a neighboring block to determine context for coding an IVRP flag of a current block, and avoiding resetting of samples of a residual reference block to zeros during generation.

Abstract translation: 一般来说，本公开描述了三维视频编码中用于改进视角间残差预测（IVRP）的技术。 这些技术包括基于编码块标志和残差参考块的编码模式确定IVRP可用性，当块被视图预测时不允许IVRP编码，使用图像顺序计数（POC）值来确定是否允许IVRP，将IVRP应用于预测 单位（PU）而不是编码单位（CU），当块被跳过或合并模式编码时推断IVRP标志的值，使用相邻块的IVRP标志来确定用于对当前块的IVRP标志进行编码的上下文，并避免 在生成期间将残差参考块的样本重置为零。

公开(公告)号：US20130243093A1

公开(公告)日：2013-09-19

申请号：US13801350

申请日：2013-03-13

Applicant: QUALCOMM INCORPORATED

Inventor： Ying CHEN ,  Ye-Kui WANG ,  Li ZHANG

IPC: H04N7/26

CPC classification number: H04N19/51 ,  H04N19/105 ,  H04N19/139 ,  H04N19/52 ,  H04N19/597 ,  H04N19/70

Abstract: In one example, a device includes a video coder (e.g., a video encoder or a video decoder) configured to determine that a block of video data is to be coded in accordance with a three-dimensional extension of High Efficiency Video Coding (HEVC), and, based the determination that the block is to be coded in accordance with the three-dimensional extension of HEVC, disable temporal motion vector prediction for coding the block. The video coder may be further configured to, when the block comprises a bi-predicted block (B-block), determine that the B-block refers to a predetermined pair of pictures in a first reference picture list and a second reference picture list, and, based on the determination that the B-block refers to the predetermined pair, equally weight contributions from the pair of pictures when calculating a predictive block for the block.

Abstract translation: 在一个示例中，设备包括被配置为根据高效率视频编码（HEVC）的三维扩展来确定视频数据块要被编码的视频编码器（例如，视频编码器或视频解码器） 并且基于根据HEVC的三维扩展来确定块要被编码的确定，禁止对块进行编码的时间运动矢量预测。 视频编码器还可以被配置为当块包括双预测块（B块）时，确定B块参考第一参考图像列表和第二参考图像列表中的预定图像对， 并且基于当计算块的预测块时，基于B块参考预定对的确定，来自该对图像的同等重量贡献。

公开(公告)号：US20190065833A1

公开(公告)日：2019-02-28

申请号：US16107896

申请日：2018-08-21

Applicant: QUALCOMM Incorporated

Inventor： Lei WANG ,  Ning BI ,  Ying CHEN

IPC: G06K9/00

Abstract: Techniques and systems are provided for detecting false positive faces in one or more video frames. For example, a video frame of a scene can be obtained. The video frame includes a face of a user associated with at least one characteristic feature. The face of the user is determined to match a representative face from stored representative data. The representative face is associated with the at least one characteristic feature. The face of the user is determined to match the representative face based on the at least one characteristic feature. The face of the user can then be determined to be a false positive face based on the face of the user matching the representative face.

公开(公告)号：US20180253848A1

公开(公告)日：2018-09-06

申请号：US15599281

申请日：2017-05-18

Applicant: QUALCOMM Incorporated

Inventor： Ying CHEN ,  Ning BI ,  Zhongmin WANG

IPC: G06T7/11 ,  G06T7/70

CPC classification number: G06T7/11 ,  G06T7/70 ,  G06T2210/12

Abstract: Methods, apparatuses, and computer-readable media are provided for splitting one or more merged blobs for one or more video frames. A blob detected for a current video frame is identified. The identified blob includes pixels of at least a portion of a foreground object in the current video frame. The identified blob is determined to be associated with two or more blob trackers from a plurality of blob trackers. The plurality of blob trackers are received from an object tracking operation performed for a previous video frame. It is then determined whether one or more splitting conditions are met. The splitting conditions can be based on a spatial relationship between bounding regions of the two or more blob trackers and a bounding region of the identified blob. The identified blob can be split into a first blob and a second blob in response to determining the one or more splitting conditions are met. If the identified blob is split, the first blob and the second blob are output for object tracking for the current frame by an object tracking system. In some cases, the identified blob is not output for object tracking for the current frame.

公开(公告)号：US20160330479A1

公开(公告)日：2016-11-10

申请号：US15108759

申请日：2013-12-30

Applicant: QUALCOMM INCORPORATED

Inventor： Hongbin LIU ,  Ying CHEN ,  Li ZHANG

IPC: H04N19/597 ,  H04N19/13 ,  H04N19/182 ,  H04N19/159 ,  H04N19/91

CPC classification number: H04N19/597 ,  H04N19/13 ,  H04N19/159 ,  H04N19/176 ,  H04N19/182 ,  H04N19/70 ,  H04N19/91

Abstract: This disclosure describes techniques for simplifying delta DC residual coding in a 3D video coding process, such as 3D-HEVC. In some examples, the techniques may modify binarization and/or context modeling processes to reduce the complexity of entropy coding of one or more syntax elements used to represent delta DC residual values.

Abstract translation: 本公开描述了用于简化3D视频编码过程（诸如3D-HEVC）中的ΔDC残差编码的技术。 在一些示例中，技术可以修改二值化和/或上下文建模过程以减少用于表示ΔDC残差值的一个或多个语法元素的熵编码的复杂度。

公开(公告)号：US20150103923A1

公开(公告)日：2015-04-16

申请号：US14513034

申请日：2014-10-13

Applicant: QUALCOMM Incorporated

Inventor： Adarsh Krishnan RAMASUBRAMONIAN ,  Ying CHEN ,  Ye-Kui WANG ,  Fnu HENDRY

IPC: H04N19/37

CPC classification number: H04N19/187 ,  H04N19/30 ,  H04N19/46 ,  H04N19/68 ,  H04N19/70 ,  H04N19/80 ,  H04N19/86

Abstract: An apparatus configured to code video information includes a memory unit and a processor in communication with the memory unit. The memory unit is configured to store video information associated with a video layer having a picture. The processor is configured to determine whether the picture is a non-picture-order-count (POC)-anchor picture, and based on the determination of whether the picture is a non-POC-anchor picture, perform one of (1) refraining from indicating a POC reset in connection with the picture, or (2) indicating the POC reset in connection with the picture. The processor may encode or decode the video information.

Abstract translation: 被配置为对视频信息进行编码的装置包括与存储器单元通信的存储器单元和处理器。 存储单元被配置为存储与具有图像的视频层相关联的视频信息。 处理器被配置为确定图像是非图像顺序计数（POC）图像，并且基于图像是否是非POC锚图像的确定，执行以下中的一个：（1）避免 指示与图像相关的POC复位，或（2）指示与图像相关的POC复位。 处理器可以对视频信息进行编码或解码。

公开(公告)号：US20140301466A1

公开(公告)日：2014-10-09

申请号：US14242679

申请日：2014-04-01

Applicant: QUALCOMM INCORPORATED

Inventor： Xiang LI ,  Ye-Kui WANG ,  Ying CHEN ,  Jianle CHEN ,  Adarsh Krishnan RAMASUBRAMONIAN ,  Marta KARCZEWICZ

IPC: H04N19/51 ,  H04N19/34

CPC classification number: H04N19/105 ,  H04N19/136 ,  H04N19/187 ,  H04N19/30 ,  H04N19/597

Abstract: An apparatus for decoding video information according to certain aspects includes a memory unit and a processor operationally coupled to the memory unit. The memory unit is configured to store at least one reference picture list of an enhancement layer, the at least one reference picture list comprising residual prediction reference picture information. The processor is configured to: decode signaled information about residual prediction reference picture generation; generate a residual prediction reference picture based on an enhancement layer reference picture and the decoded signaled information such that the generated residual prediction reference picture has the same motion field and the same picture order count (POC) as the enhancement layer reference picture from which it is generated; and store the generated residual prediction reference picture in the at least one reference picture list of the enhancement layer.

Abstract translation: 根据某些方面的用于解码视频信息的装置包括存储器单元和可操作地耦合到存储器单元的处理器。 存储器单元被配置为存储增强层的至少一个参考图像列表，该至少一个参考图像列表包括残留预测参考图像信息。 处理器被配置为：解码关于残差预测参考图片生成的信号信息; 基于增强层参考图像和解码信号信息生成残差预测参考图像，使得所生成的残差预测参考图像具有与其相同的运动场和与其相同的图像顺序计数（POC） 生成的 并将生成的残差预测参考图像存储在增强层的至少一个参考图像列表中。

公开(公告)号：US20140098881A1

公开(公告)日：2014-04-10

申请号：US14043706

申请日：2013-10-01

Applicant: QUALCOMM Incorporated

Inventor： Ying CHEN ,  Vadim SEREGIN

IPC: H04N7/34

CPC classification number: H04N19/33 ,  H04N19/52

Abstract: An apparatus for coding video information according to certain aspects includes a memory unit and a processor in communication with the memory unit. The memory unit is configured to store video information associated with a first layer having a first spatial resolution and a corresponding second layer having a second spatial resolution, wherein the first spatial resolution is less than the second spatial resolution. The video information includes at least motion field information associated with the first layer. The processor upsamples the motion field information associated with the first layer. The processor further adds an inter-layer reference picture including the upsampled motion field information in association with an upsampled texture picture of the first layer to a reference picture list to be used for inter prediction. The processor may encode or decode the video information.

Abstract translation: 根据某些方面的用于编码视频信息的装置包括存储器单元和与存储器单元通信的处理器。 存储器单元被配置为存储与具有第一空间分辨率的第一层相关联的视频信息和具有第二空间分辨率的对应的第二层，其中第一空间分辨率小于第二空间分辨率。 视频信息至少包括与第一层相关联的运动场信息。 处理器对与第一层相关联的运动场信息进行采样。 处理器还将包括上采样的运动场信息的层间参考图像与第一层的上采样纹理图像相关联以用于帧间预测的参考图片列表。 处理器可以对视频信息进行编码或解码。

公开(公告)号：US20140016701A1

公开(公告)日：2014-01-16

申请号：US13937130

申请日：2013-07-08

Applicant: QUALCOMM Incorporated

Inventor： Ying CHEN ,  Vadim SEREGIN ,  Marta KARCZEWICZ ,  Li ZHANG

IPC: H04N7/36

CPC classification number: H04N19/503 ,  H04N19/105 ,  H04N19/147 ,  H04N19/172

Abstract: A first reference index value indicates a position, within a reference picture list associated with a current prediction unit (PU) of a current picture, of a first reference picture. A reference index of a co-located PU of a co-located picture indicates a position, within a reference picture list associated with the co-located PU of the co-located picture, of a second reference picture. When the first reference picture and the second reference picture belong to different reference picture types, a video coder sets a reference index of a temporal merging candidate to a second reference index value. The second reference index value is different than the first reference index value.

Abstract translation: 第一参考索引值指示与第一参考图片的当前图片的当前预测单元（PU）相关联的参考图片列表内的位置。 同位置图片的同位置PU的参考索引指示与第二参考图片的同位置图片的同位置PU相关联的参考图片列表内的位置。 当第一参考图像和第二参考图像属于不同的参考图像类型时，视频编码器将时间合并候选的参考索引设置为第二参考索引值。 第二参考索引值不同于第一参考索引值。

公开(公告)号：US20130343465A1

公开(公告)日：2013-12-26

申请号：US13926387

申请日：2013-06-25

Applicant: Qualcomm Incorporated

Inventor： Ying CHEN ,  Ye-Kui WANG

IPC: H04N7/26

CPC classification number: H04N19/597 ,  H04N19/174 ,  H04N19/23 ,  H04N19/30 ,  H04N19/70

Abstract: An example method of decoding video data includes determining a header parameter set that includes one or more syntax elements specified individually by each of one or more slice headers, the header parameter set being associated with a header parameter set identifier (HPS ID), and determining one or more slice headers that reference the header parameter set to inherit at least one of the syntax elements included in the header parameter set, where the slice headers are each associated with a slice of the encoded video data, and where the slice headers each reference the header parameter set using the HPS ID.

Abstract translation: 解码视频数据的示例性方法包括：确定包括由一个或多个片标头中的每一个分别指定的一个或多个语法元素的标题参数集，所述标题参数集与标题参数集标识符（HPS ID）相关联，并且确定 引用标题参数集的一个或多个片标题，以继承包含在标题参数集中的语法元素中的至少一个，其中片标题与编码视频数据的片段相关联，并且片标头每个引用 使用HPS ID设置标题参数。