公开(公告)号：US10567789B2

公开(公告)日：2020-02-18

申请号：US15318340

申请日：2014-06-16

Applicant: QUALCOMM Incorporated ,  Ying Chen ,  Hongbin Liu

Inventor： Ying Chen ,  Hongbin Liu

IPC: H04N19/52 ,  H04N19/56 ,  H04N19/70 ,  H04N19/517 ,  H04N19/176

Abstract: A device for coding three-dimensional includes a video coder configured to add one or more motion vector candidates to a motion vector candidate list; identify, from the one or more motion vector candidates in the motion vector candidate list, a disparity motion vector candidate; based on the disparity motion vector candidate, determine a disparity shifted motion vector (DSMV) candidate; and add the DSMV candidate to the motion vector candidate list; and code the block of video data using a motion vector corresponding to the identified candidate.

公开(公告)号：US10553091B2

公开(公告)日：2020-02-04

申请号：US15655065

申请日：2017-07-20

Applicant: QUALCOMM Incorporated

Inventor： Ying Chen ,  Ning Bi ,  Yang Zhou

IPC: G06K9/00 ,  G08B13/196 ,  G06T7/215 ,  G06T7/246 ,  G06K9/34 ,  G06K9/68 ,  G06K9/38 ,  G06T7/277 ,  G06K9/62 ,  G06K9/46 ,  G06K9/48 ,  G06T7/254 ,  G06K9/32

Abstract: Methods, apparatuses, and computer-readable media are provided for splitting one or more merged blobs for one or more video frames. For example, a merged blob detected for a current video frame is identified. The merged blob includes pixels of at least a portion of at least two foreground objects in the current video frame. The merged blob is associated with a first blob tracker and a second blob tracker. A shape of the first blob tracker can be adjusted. For instance, adjusting the shape of the first blob tracker can include shifting at least one boundary of a bounding region of the first blob tracker based on the shape of the merged blob. The merged blob can be split into a first blob and a second blob, with the first blob being associated with the adjusted bounding region of the first blob tracker and the second blob being associated with a bounding region of the a second blob tracker. The first blob and the second blob can then be output for object tracking for the current video frame.

公开(公告)号：US10447990B2

公开(公告)日：2019-10-15

申请号：US13779468

申请日：2013-02-27

Applicant: QUALCOMM Incorporated

Inventor： Ying Chen ,  Ye-Kui Wang ,  Marta Karczewicz

IPC: H04N13/161 ,  H04N19/597 ,  H04N19/70 ,  H04N19/12 ,  H04N19/169

Abstract: A video encoder generates a network abstraction layer (NAL) unit that includes at least a first syntax element and a second syntax element. The first syntax element indicates that the NAL unit belongs to a particular NAL unit type. Coded slices of texture view components and depth view components are encapsulated within NAL units that belong to the particular NAL unit type. The second syntax element indicates whether a NAL unit header of the NAL unit includes an Advanced Video Coding (AVC)-compatible 3-dimensional video (3DV) header extension or includes a Multiview Video Coding (MVC)-compatible 3DV header extension. The video encoder outputs a bitstream that includes the NAL unit. A video decoder receives the NAL unit and determines whether the second syntax element indicates that the NAL unit header of the NAL unit includes the AVC-compatible 3DV header extension or the MVC-compatible 3DV header extension.

公开(公告)号：US10395385B2

公开(公告)日：2019-08-27

申请号：US15635059

申请日：2017-06-27

Applicant: QUALCOMM Incorporated

Inventor： Yang Zhou ,  Ying Chen ,  Yingyong Qi ,  Ning Bi

IPC: G06T7/70 ,  G06K9/46 ,  G06K9/62 ,  G06T7/246

Abstract: In various implementations, object tracking in a video content analysis system can be augmented with an image-based object re-identification system (e.g., for person re-identification or re-identification of other objects) to improve object tracking results for objects moving in a scene. The object re-identification system can use image recognition principles, which can be enhanced by considering data provided by object trackers that can be output by an object traffic system. In a testing stage, the object re-identification system can selectively test object trackers against object models. For most input video frames, not all object trackers need be tested against all object models. Additionally, different types of object trackers can be tested differently, so that a context provided by each object tracker can be considered. In a training stage, object models can also be selectively updated.

公开(公告)号：US10375411B2

公开(公告)日：2019-08-06

申请号：US14773161

申请日：2013-03-15

Applicant: Xin Zhao ,  Li Zhang ,  Ying Chen ,  QUALCOMM Incorporated

Inventor： Xin Zhao ,  Li Zhang ,  Ying Chen

IPC: H04N19/50 ,  H04N19/119 ,  H04N19/182 ,  H04N19/11 ,  H04N19/124 ,  H04N19/176 ,  H04N19/61 ,  H04N19/597

Abstract: In an example, a process for coding video data includes determining a partitioning pattern for a block of depth values comprising assigning one or more samples of the block to a first partition and assigning one or more other samples of the block to a second partition. The process also includes determining a predicted value for at least one of the first partition and the second partition based on the determined partition pattern. The process also includes coding the at least one of the first partition and the second partition based on the predicted value.

公开(公告)号：US10306269B2

公开(公告)日：2019-05-28

申请号：US14878783

申请日：2015-10-08

Applicant: QUALCOMM Incorporated

Inventor： Fnu Hendry ,  Ying Chen ,  Ye-Kui Wang

IPC: H04N19/85 ,  H04N19/463 ,  H04N19/44 ,  H04N19/597 ,  H04N19/70 ,  H04N19/30 ,  H04N19/187 ,  H04N19/169

Abstract: A device for processing a bitstream including video data, such as a demultiplexer, extracts a descriptor from the bitstream, wherein the bitstream includes layers of video data for operation points, separate from the descriptor, such that each operation point includes one or more of the layers of video data, and wherein the descriptor includes a set of profile, tier, and level (PTL) structures and data that associates each of the layers of each of the operation points with a corresponding one of the PTL structures, extracts video data for one of the operation points from the bitstream based at least in part on the PTL structures to which the layers of the one of the operation points correspond, and provides the extracted video data to a video decoder.

公开(公告)号：US10230980B2

公开(公告)日：2019-03-12

申请号：US15005934

申请日：2016-01-25

Applicant: QUALCOMM Incorporated

Inventor： Hongbin Liu ,  Ying Chen ,  Jianle Chen ,  Xiang Li ,  Marta Karczewicz

IPC: H04N19/583 ,  H04N19/44 ,  H04N19/176 ,  H04N19/423 ,  H04N19/167 ,  H04N19/70

Abstract: In an example, a method of decoding video data may include receiving a first block of video data. The first block of video data may be a sub-block of a prediction unit. The method may include receiving one or more blocks of video data that neighbor the first block of video data. The method may include determining motion information of at least one of the one or more blocks of video data that neighbor the first block of video data. The method may include decoding, using overlapped block motion compensation, the first block of video data based at least in part on the motion information of the at least one of the one or more blocks that neighbor the first block of video data.

公开(公告)号：US10229503B2

公开(公告)日：2019-03-12

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

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：US10223590B2

公开(公告)日：2019-03-05

申请号：US15262700

申请日：2016-09-12

Applicant: QUALCOMM Incorporated

Inventor： Ying Chen ,  Lei Wang ,  Jinglun Gao ,  Ning Bi

IPC: G06T5/30 ,  G06K9/00 ,  G06T5/00 ,  G06T7/155 ,  G06T7/194 ,  G06K9/38 ,  G06T7/11

Abstract: Techniques and systems are provided for processing video data. For example, techniques and systems are provided for performing content-adaptive morphology operations. A first erosion function can be performed on a foreground mask of a video frame, including setting one or more foreground pixels of the frame to one or more background pixels. A temporary foreground mask can be generated based on the first erosion function being performed on the foreground mask. One or more connected components can be generated for the frame by performing connected component analysis to connect one or more neighboring foreground pixels. A complexity of the frame (or of the foreground mask of the frame) can be determined by comparing a number of the one or more connected components to a threshold number. A second erosion function can be performed on the temporary foreground mask when the number of the one or more connected components is higher than the threshold number. The one or more connected components can be output for blob processing when the number of the one or more connected components is lower than the threshold number.

公开(公告)号：US10205961B2

公开(公告)日：2019-02-12

申请号：US13867924

申请日：2013-04-22

Applicant: QUALCOMM Incorporated

Inventor： Ying Chen ,  Ye-Kui Wang

IPC: H04N19/52 ,  H04N19/597 ,  H04N19/70 ,  H04N19/30 ,  H04N19/51 ,  H04N19/105

Abstract: This disclosure described techniques for coding layer dependencies for a block of video data. According to these techniques, a video encoder generates layer dependencies associated with a given layer. The video encoder also generates a type of prediction associated with one or more of the layer dependencies. In some examples, the video encoder generates a first syntax element to signal layer dependencies and a second syntax element to signal a type of prediction associated with one or more of the layer dependencies. A video decoder may obtain the layer dependencies associated with a given layer and the type of prediction associated with one or more of the layer dependencies.