公开(公告)号：US20190304102A1

公开(公告)日：2019-10-03

申请号：US16290790

申请日：2019-03-01

Applicant: QUALCOMM Incorporated

Inventor： Ying CHEN ,  Songan MAO ,  Yang ZHOU ,  Karthik NAGARAJAN

IPC: G06T7/246 ,  G06T7/73 ,  G06K9/62 ,  G06T7/11 ,  G06N20/00 ,  G06N3/08

Abstract: Techniques and systems are provided for classifying objects in one or more video frames. An object tracker associated with an object in a current video frame can be selected for object classification. Object classification can be determined to be performed in a next video frame (instead of the current video frame) for the object associated with the selected tracker. An image patch to use for the object classification can be obtained from the next video frame. The image patch can be based on a first bounding region associated with the object tracker in the current video frame, can be based on a second bounding region associated with the tracker in the next video frame, or can be based on both the first and second bounding regions. The object classification can be performed for the object associated with the selected object tracker using the image patch from the next video frame.

公开(公告)号：US20190130583A1

公开(公告)日：2019-05-02

申请号：US16172540

申请日：2018-10-26

Applicant: QUALCOMM Incorporated

Inventor： Ying CHEN ,  Yang ZHOU ,  Karthik NAGARAJAN

IPC: G06T7/20 ,  G06K9/00 ,  G06T7/11 ,  G06T7/194

Abstract: Techniques and systems are provided for tracking objects in a sequence of video frames. For example, an object tracker maintained for the sequence of video frames is identified. An object tracked by the object tracker is detected based on an application of an object detector to at least one key frame in the sequence of video frames. The object detector can include a complex object detector. A status of the object tracker can be updated to a still status in a current video frame of the sequence of video frames. A tracker having the still status is associated with an object that is static in one or more video frames of the sequence of video frames. The object can be tracked in the current video frame using the object tracker based on the status of the object tracker being updated to the still status in the current video frame. For example, a bounding region of the object tracker in the current frame can be replaced with a previous bounding region of the object tracker in a previous frame based on the status of the object tracker being updated to the still status in the current video frame.

公开(公告)号：US20190130189A1

公开(公告)日：2019-05-02

申请号：US16160970

申请日：2018-10-15

Applicant: QUALCOMM Incorporated

Inventor： Yang ZHOU ,  Ying CHEN ,  Ning BI

IPC: G06K9/00 ,  G06T7/246

Abstract: Techniques and systems are provided for tracking objects in one or more video frames. For example, based on an application of an object detector to at least one key frame in the one or more video frames, a first set of bounding regions for a video frame can be obtained. A group of bounding regions can be determined from the first set of bounding regions. A bounding region from the group of bounding regoins can be removed based on one or more metrics associated with the bounding region. Object tracking for the video frame can be performed using an updated set of bounding regions that is based on removal of the bounding region from the group of bounding regions.

公开(公告)号：US20140161179A1

公开(公告)日：2014-06-12

申请号：US14049649

申请日：2013-10-09

Applicant: QUALCOMM Incorporated

Inventor： Vadim SEREGIN ,  Ying CHEN ,  Jianle CHEN

IPC: H04N7/26 ,  H04N7/46

CPC classification number: H04N19/30 ,  H04N19/33 ,  H04N19/34 ,  H04N19/463 ,  H04N19/50 ,  H04N19/55 ,  H04N19/59

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 an enhancement layer having a first block and a base layer having a second block, the second block in the base layer corresponding to the first block in the enhancement layer. The processor is configured to predict, by inter layer prediction, the first block in the enhancement layer based on information derived from the second block in the base layer. At least a portion of the second block is located outside of a reference region of the base layer, the reference region being available for use for the inter layer prediction of the first block. 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。 存储器单元被配置为存储与具有第一块的增强层相关联的视频信息和具有第二块的基本层，所述基本层中的第二块对应于增强层中的第一块。 处理器被配置为基于从基层中的第二块导出的信息，通过层间预测来预测增强层中的第一块。 第二块的至少一部分位于基本层的参考区域的外部，该参考区域可用于第一块的层间预测。 处理器可以对视频信息进行编码或解码。

公开(公告)号：US20140023138A1

公开(公告)日：2014-01-23

申请号：US13945547

申请日：2013-07-18

Applicant: QUALCOMM Incorporated

Inventor： Ying CHEN

IPC: H04N7/32

CPC classification number: H04N19/597 ,  H04N19/30 ,  H04N19/463 ,  H04N19/70

Abstract: In one example, a device includes a video coder (e.g., a video encoder or a video decoder) configured to code parameter set information for a video bitstream, code video data of a base layer of the video bitstream using the parameter set information, and code video data of an enhancement layer of the video bitstream using at least a portion of the parameter set information. The parameter set information may include, for example, profile and level information and/or hypothetical reference decoder (HRD) parameters. For example, the video coder may code a sequence parameter set (SPS) for a video bitstream, code video data of a base layer of the video bitstream using the SPS, and code video data of an enhancement layer of the video bitstream using at least a portion of the SPS, without using any other SPS for the enhancement layer.

Abstract translation: 在一个示例中，设备包括视频编码器（例如，视频编码器或视频解码器），其被配置为使用视频比特流编码参数集信息，使用参数集信息对视频比特流的基本层的视频数据进行编码;以及 使用参数集信息的至少一部分对视频比特流的增强层的视频数据进行编码。 参数集信息可以包括例如简档和级别信息和/或假设参考解码器（HRD）参数。 例如，视频编码器可以使用SPS编码视频比特流的序列参数集（SPS），使用SPS对视频比特流的基本层的视频数据进行编码，并且至少使用视频比特流的增强层的视频数据 SPS的一部分，而不使用任何其他SPS用于增强层。

公开(公告)号：US20140016699A1

公开(公告)日：2014-01-16

申请号：US13940064

申请日：2013-07-11

Applicant: QUALCOMM Incorporated

Inventor： Ying CHEN ,  Adarsh Krishnan RAMASUBRAMONIAN

IPC: H04N7/32

CPC classification number: H04N19/50 ,  H04N19/573 ,  H04N19/61 ,  H04N19/70

Abstract: A video decoder generates an initial reference picture list (RPL). Furthermore, the video decoder determines that an ordered set of reference picture list modification (RPLM) syntax elements does not include any additional syntax elements when a syntax element in the ordered set of RPLM syntax elements has a particular value. Furthermore, the video decoder generates a final RPL. For each respective RPLM syntax element in the ordered set of syntax elements, when the respective RPLM syntax element does not have the particular value, the final RPL includes, at an insertion position for the respective RPLM syntax element, a particular reference picture. The respective syntax element indicates a position in the initial RPL of the particular RPLM reference picture. The insertion position for the respective RPLM syntax element corresponds to a position in the ordered set of RPLM syntax elements of the respective RPLM syntax element.

Abstract translation: 视频解码器生成初始参考图像列表（RPL）。 此外，当RPLM语法元素的有序集合中的语法元素具有特定值时，视频解码器确定参考图像列表修改（RPLM）语法元素的有序集合不包括任何附加语法元素。 此外，视频解码器产生最终的RPL。 对于有序集合语法元素中的每个相应RPLM语法元素，当相应的RPLM语法元素不具有特定值时，最终RPL在相应RPLM语法元素的插入位置处包括特定参考图片。 相应的语法元素指示特定RPLM参考图片的初始RPL中的位置。 相应RPLM语法元素的插入位置对应于相应RPLM语法元素的RPLM语法元素的有序集合中的位置。

公开(公告)号：US20140010277A1

公开(公告)日：2014-01-09

申请号：US13777413

申请日：2013-02-26

Applicant: QUALCOMM, INCORPORATED

Inventor： Ye-Kui WANG ,  Ying CHEN

IPC: H04N7/26

CPC classification number: H04N19/90 ,  H04N19/463 ,  H04N19/70

Abstract: Systems, methods, and devices are disclosed that code a supplemental enhancement information (SEI) message. In some examples, the SEI message may contain an identifier of an active video parameter set (VPS). In some examples, the identifier may be fixed-length coded.

Abstract translation: 公开了编码补充增强信息（SEI）消息的系统，方法和设备。 在一些示例中，SEI消息可以包含活动视频参数集（VPS）的标识符。 在一些示例中，标识符可以是固定长度编码的。

公开(公告)号：US20140003536A1

公开(公告)日：2014-01-02

申请号：US13773060

申请日：2013-02-21

Applicant: QUALCOMM INCORPORATED

Inventor： Ye-Kui WANG ,  Ying CHEN

IPC: H04N7/26

CPC classification number: H04N19/44 ,  H04N19/00 ,  H04N19/102 ,  H04N19/134 ,  H04N19/142 ,  H04N19/162 ,  H04N19/172 ,  H04N19/177 ,  H04N19/42 ,  H04N19/46 ,  H04N19/52 ,  H04N19/593 ,  H04N19/70 ,  H04N19/85 ,  H04N21/23424 ,  H04N21/6336 ,  H04N21/64753

Abstract: Systems, methods, and devices for processing video data are disclosed. Some examples systems, methods, and devices receive an external indication at a video decoder. The example systems, methods, and devices treat a clean random access (CRA) picture as a broken link access (BLA) picture based on the external indication.

Abstract translation: 公开了用于处理视频数据的系统，方法和设备。 一些示例系统，方法和设备在视频解码器处接收外部指示。 示例系统，方法和设备基于外部指示将干净的随机访问（CRA）图像视为断开的链路访问（BLA）图像。

公开(公告)号：US20130195173A1

公开(公告)日：2013-08-01

申请号：US13753278

申请日：2013-01-29

Applicant: Qualcomm Incorporated

Inventor： Ye-Kui WANG ,  Ying CHEN

IPC: H04N7/26

CPC classification number: H04N19/174 ,  H04N19/46 ,  H04N19/70

Abstract: A device comprising a video file creation module is configured to obtain a plurality of slices of coded video content. Parameter sets are associated with the coded video content. The video creation module encapsulates the plurality of slices of coded video content within one or more access units of a video stream. A first type of parameter set may be encapsulated within one or more access units of the video stream. A second type of parameter set may be encapsulated within a sample description. The sample description may include an indicator identifying a number of parameter sets stored within one or more access units of the video stream.

Abstract translation: 包括视频文件创建模块的装置被配置为获得多个编码视频内容片段。 参数集与编码的视频内容相关联。 视频创建模块将多个编码视频内容片段封装在视频流的一个或多个访问单元内。 第一类型的参数集可以被封装在视频流的一个或多个访问单元内。 第二种类型的参数集可以封装在样本描述中。 样本描述可以包括识别存储在视频流的一个或多个访问单元内的参数集的数量的指示符。

公开(公告)号：US20220247807A1

公开(公告)日：2022-08-04

申请号：US17676589

申请日：2022-02-21

Applicant: QUALCOMM Incorporated

Inventor： Michael George LUBY ,  Mark WATSON ,  Lorenzo VICISANO ,  Payam PAKZAD ,  Bin WANG ,  Thomas STOCKHAMMER ,  Ying CHEN

IPC: H04L65/60 ,  H04N21/231 ,  H04N21/234 ,  H04N21/2343 ,  H04N21/235 ,  H04N21/258 ,  H04N21/2662 ,  H04N21/435 ,  H04N21/44 ,  H04N21/4402 ,  H04N21/442 ,  H04N21/84 ,  H04N21/845 ,  H04L65/612 ,  H04L67/02

Abstract: A block-request streaming system provides for low-latency streaming of a media presentation. A plurality of media segments are generated according to an encoding protocol. Each media segment includes a random access point. A plurality of media fragments are encoded according to the same protocol. The media segments are aggregated from a plurality of media fragments.