公开(公告)号：US20180046863A1

公开(公告)日：2018-02-15

申请号：US15400118

申请日：2017-01-06

Applicant: QUALCOMM Incorporated

Inventor： Ying Chen ,  Lei Wang

IPC: G06K9/00 ,  G06T7/11 ,  G06T7/70

CPC classification number: G06K9/00744 ,  G06K9/00771 ,  G06T7/11 ,  G06T7/246 ,  G06T7/70 ,  G06T2207/10016 ,  G06T2207/30232 ,  G06T2207/30241 ,  G06T2210/12

Abstract: Techniques and systems are provided for maintaining lost blob trackers for one or more video frames. In some examples, one or more blob trackers maintained for a sequence of video frames are identified. The one or more blob trackers are associated with one or more blobs of the sequence of video frames. A transition of a blob tracker from a first type of tracker to a lost tracker is detected at a first video frame. For example, the blob tracker can be transitioned from the first type of tracker to the lost tracker when a blob for which the blob tracker was associated with in a previous frame is not detected in the first video frame. A recovery duration is determined for the lost tracker at the first video frame. For one or more subsequent video frames obtained after the first video frame, the lost tracker is removed from the one or more blob trackers maintained for the sequence of video frames when a lost duration for the lost tracker is greater than the recovery duration. The blob tracker can be transitioned back to the first type of tracker if the lost tracker is associated with a blob in a subsequent video frame prior to expiration of the recovery duration. Trackers and associated blobs are output as identified blob tracker-blob pairs when the trackers are converted from new trackers to trackers of the first type.

公开(公告)号：US20180046857A1

公开(公告)日：2018-02-15

申请号：US15384997

申请日：2016-12-20

Applicant: QUALCOMM Incorporated

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

IPC: G06K9/00

CPC classification number: G06K9/00335 ,  G06K9/00718 ,  G06K9/00771 ,  G06T7/246 ,  G06T2207/30232 ,  G06T2207/30241

Abstract: Techniques and systems are provided for processing video data. For example, techniques and systems are provided for performing context-aware object or blob tracker updates (e.g., by updating a motion model of a blob tracker). In some cases, to perform a context-aware blob tracker update, a blob tracker is associated with a first blob. The first blob includes pixels of at least a portion of one or more foreground objects in one or more video frames. A split of the first blob and a second blob in a current video frame can be detected, and a motion model of the blob tracker is reset in response to detecting the split of the first blob and the second blob. In some cases, a motion model of a blob tracker associated with a merged blob is updated to include a predicted location of the blob tracker in a next video frame. The motion model can be updated by using a previously predicted location of blob tracker as the predicted location of the blob tracker in the next video frame in response to the blob tracker being associated with the merged blob. The previously predicted location of the blob tracker can be determined using a blob location of a blob from a previous video frame.

公开(公告)号：US09762927B2

公开(公告)日：2017-09-12

申请号：US14497128

申请日：2014-09-25

Applicant: QUALCOMM Incorporated

Inventor： Ying Chen ,  Li Zhang

IPC: H04N19/53 ,  H04N19/56 ,  H04N19/196 ,  H04N19/597 ,  H04N19/52 ,  H04N19/96

CPC classification number: H04N19/53 ,  H04N19/197 ,  H04N19/52 ,  H04N19/56 ,  H04N19/597 ,  H04N19/96

Abstract: Techniques are described for sub-prediction unit (PU) based motion prediction for video coding in HEVC and 3D-HEVC. In one example, the techniques include an advanced temporal motion vector prediction (TMVP) mode to predict sub-PUs of a PU in single layer coding for which motion vector refinement may be allowed. The advanced TMVP mode includes determining motion vectors for the PU in at least two stages to derive motion information for the PU that includes different motion vectors and reference indices for each of the sub-PUs of the PU. In another example, the techniques include storing separate motion information derived for each sub-PU of a current PU predicted using a sub-PU backward view synthesis prediction (BVSP) mode even after motion compensation is performed. The additional motion information stored for the current PU may be used to predict subsequent PUs for which the current PU is a neighboring block.

公开(公告)号：US09762905B2

公开(公告)日：2017-09-12

申请号：US14172410

申请日：2014-02-04

Applicant: QUALCOMM Incorporated

Inventor： Jewon Kang ,  Ying Chen

IPC: H04N19/597 ,  H04N19/51 ,  H04N19/533

CPC classification number: H04N19/533 ,  H04N19/51 ,  H04N19/597

Abstract: A video coding device performs a disparity vector derivation process for a current block of multi-view video data. The current block is in a current view. An availability value indicates that a disparity vector for the current block is unavailable when the disparity vector derivation process is unable to derive the disparity vector for the current block. When the availability value indicates that the disparity vector derivation process has not derived the disparity vector for the current block, the video coding device generates a disparity vector for the current block in another manner.

公开(公告)号：US20170237990A1

公开(公告)日：2017-08-17

申请号：US15585918

申请日：2017-05-03

Applicant: QUALCOMM Incorporated

Inventor： Vadim Seregin ,  Jianle Chen ,  Xiang Li ,  Krishnakanth Rapaka ,  Marta Karczewicz ,  Ying Chen

IPC: H04N19/159 ,  H04N19/463 ,  H04N19/176 ,  H04N19/33

Abstract: In one embodiment, an apparatus configured to code video data includes a processor and a memory unit. The memory unit stores video data associated with a first layer having a first spatial resolution and a second layer having a second spatial resolution. The video data associated with the first layer includes at least a first layer block and first layer prediction mode information associated with the first layer block, and the first layer block includes a plurality of sub-blocks where each sub-block is associated with respective prediction mode data of the first layer prediction mode information. The processor derives the predication mode data associated with one of the plurality of sub-blocks based at least on a selection rule, upsamples the derived prediction mode data and the first layer block, and associates the upsampled prediction mode data with each upsampled sub-block of the upsampled first layer block.

公开(公告)号：US09716899B2

公开(公告)日：2017-07-25

申请号：US14316088

申请日：2014-06-26

Applicant: QUALCOMM Incorporated

Inventor： Vijayaraghavan Thirumalai ,  Li Zhang ,  Ying Chen

IPC: H04N19/597 ,  H04N19/70 ,  H04N19/52

CPC classification number: H04N19/597 ,  H04N19/52 ,  H04N19/70

Abstract: An example video coding device is configured to determine a depth value associated with a block of video data included in a dependent depth view, based on one or more neighboring pixels positioned adjacent to the block of video data in the dependent depth view, and generate a disparity vector associated with the block of video data, based at least in part on the determined depth value associated with the block of video data. The video coding device may further be configured to use the disparity vector to generate an inter-view disparity motion vector candidate (IDMVC), generate an inter-view predicted motion vector candidate (IPMVC) associated with the block of video data based on a corresponding block of video data in a base view, and determine whether to add any of the IDMVC and the IPMVC to a merge candidate list associated with the block of video data.

公开(公告)号：US09648326B2

公开(公告)日：2017-05-09

申请号：US14318193

申请日：2014-06-27

Applicant: QUALCOMM Incorporated

Inventor： Jianle Chen ,  Ying Chen ,  Ye-Kui Wang ,  Krishnakanth Rapaka ,  Fnu Hendry

IPC: H04N19/105 ,  H04N19/196 ,  H04N19/187 ,  H04N19/174 ,  H04N19/30 ,  H04N19/46 ,  H04N19/597 ,  H04N19/70

CPC classification number: H04N19/105 ,  H04N19/174 ,  H04N19/196 ,  H04N19/30 ,  H04N19/46 ,  H04N19/597 ,  H04N19/70

Abstract: A method of coding video data includes receiving one or more layers of video information. Each layer may include at least one picture. The method can include processing an indicator within at least one of a video parameter set (VPS), a sequence parameter set (SPS), or a picture parameter set (PPS) that indicates whether all direct reference layer pictures associated with the at least one of the video parameter set (VPS), the sequence parameter set (SPS), or the picture parameter set (PPS) are added to an inter-layer reference picture set. Based on the indicator, the method can further include refraining from further signaling inter-layer reference picture information in any video slice associated with the at least one of the video parameter set (VPS), the sequence parameter set (SPS), or the picture parameter set (PPS). Alternatively, based on the indicator, the method can further include adding to the inter-layer reference picture set all direct reference layer pictures for any video slice associated with the at least one of the video parameter set (VPS), the sequence parameter set (SPS), or the picture parameter set (PPS).

公开(公告)号：US09648321B2

公开(公告)日：2017-05-09

申请号：US13689559

申请日：2012-11-29

Applicant: Qualcomm Incorporated

Inventor： Ye-Kui Wang ,  Adarsh Krishnan Ramasubramonian ,  Ying Chen

IPC: H04N19/00 ,  H04N19/50 ,  H04N19/503 ,  H04N19/70

CPC classification number: H04N19/50 ,  H04N19/172 ,  H04N19/503 ,  H04N19/58 ,  H04N19/70

Abstract: In general, techniques are described for coding picture order count values identifying long-term reference pictures. A video decoding device comprising a processor may perform the techniques. The processor may determine least significant bits (LSBs) of a picture order count (POC) value that identifies a long-term reference picture (LTRP). The LSBs do not uniquely identify the POC value with respect to the LSBs of any other POC value identifying any other picture in a decoded picture buffer (DPB). The processor may determine most significant bits (MSBs) of the POC value. The MSBs combined with the LSBs is sufficient to distinguish the POC value from any other POC value that identifies any other picture in the DPB. The processor may retrieve the LTRP from the decoded picture buffer based on the LSBs and MSBs of the POC value, and decode a current picture of the video data using the retrieved LTRP.

公开(公告)号：US09628820B2

公开(公告)日：2017-04-18

申请号：US14543470

申请日：2014-11-17

Applicant: QUALCOMM Incorporated

Inventor： Ye-Kui Wang ,  Fnu Hendry ,  Adarsh Krishnan Ramasubramonian ,  Ying Chen

IPC: H04N11/08 ,  H04N19/70 ,  H04N19/30 ,  H04N19/68

CPC classification number: H04N19/70 ,  H04N19/30 ,  H04N19/68

Abstract: A device for coding video data includes a memory comprising a decoded picture buffer (DPB) configured to store video data, and a video coder configured to code data representative of a value for a picture order count (POC) resetting period identifier, wherein the data is included in a slice segment header for a slice associated with a coded picture of a layer of video data, and wherein the value of the POC resetting period identifier indicates a POC resetting period including the coded picture, and reset at least part of a POC value for the coded picture in the POC resetting period in the layer and POC values for one or more pictures in the layer that are currently stored in the DPB.

公开(公告)号：US09609347B2

公开(公告)日：2017-03-28

申请号：US14243610

申请日：2014-04-02

Applicant: QUALCOMM Incorporated

Inventor： Vijayaraghavan Thirumalai ,  Li Zhang ,  Ying Chen

IPC: H04N19/513 ,  H04N19/597 ,  H04N19/56 ,  H04N19/70

CPC classification number: H04N19/513 ,  H04N19/56 ,  H04N19/597 ,  H04N19/70

Abstract: As part of a video encoding process or a video decoding process, a video coder may determine a first available disparity motion vector among spatial neighboring blocks of a current block of the video data. Furthermore, the video coder may shift a horizontal component of the first available disparity motion vector to derive a shifted disparity motion vector candidate (DSMV). The video coder may add the DSMV into a merge candidate list.