-
公开(公告)号：US10791315B2
公开(公告)日：2020-09-29
申请号：US14137358
申请日：2013-12-20
Applicant: QUALCOMM Incorporated
Inventor： Ye-Kui Wang , Ying Chen
IPC: H04N11/02 , H04N13/161 , H04N19/70 , H04N5/76 , H04N9/804 , H04N19/597 , H04N19/46 , H04N9/82 , H04N5/919 , H04N19/44 , H04N5/765
Abstract: Techniques for encapsulating video streams containing multiple coded views in a media file are described herein. In one example, a method includes parsing a track of multiview video data, wherein the track includes at least one depth view. The method further includes parsing information to determine a spatial resolution associated with the depth view, wherein decoding the spatial resolution does not require parsing of a sequence parameter set of the depth view. Another example method includes composing a track of multiview video data, wherein the track includes the one or more views. The example method further includes composing information to indicate a spatial resolution associated with the depth view, wherein decoding the spatial resolution does not require parsing of a sequence parameter set of the depth view.
-
公开(公告)号：US10771811B2
公开(公告)日：2020-09-08
申请号：US16253049
申请日：2019-01-21
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：US10726302B2
公开(公告)日：2020-07-28
申请号：US16204242
申请日：2018-11-29
Applicant: QUALCOMM Incorporated
Inventor： Shuai Zhang , Ying Chen , Yang Zhou
IPC: G06K9/62
Abstract: Methods, systems, and devices for object localization and classification are described. A device may configure a first unit of a detection layer associated with a learning framework when a quantity of output feature channels of an input feature maps is less than or equal to a quantity of input feature channels of the input feature maps. The first set of layers may include a group convolution layer, a pointwise layer, a batch normalization layer, or a rectified linear layer, or a combination thereof. The device may also configure, a second unit of the detection layer associated with the learning framework, when a second quantity of output feature channels of the input feature maps is less than or equal to a second quantity of input feature channels of the input feature maps. The second set of layers may include a depthwise layer or a pointwise layer, or both.
-
公开(公告)号：US10687079B2
公开(公告)日：2020-06-16
申请号：US15125549
申请日：2014-03-13
Applicant: QUALCOMM Incorporated , Hongbin Liu , Ying Chen
Inventor： Hongbin Liu , Ying Chen
IPC: H04N19/597 , H04N19/11 , H04N19/176 , H04N19/119 , H04N19/70 , H04N19/96 , H04N19/593 , H04N19/159
Abstract: Techniques include constraining depth intra mode coding in a three-dimensional (3D) video coding process, such as 3D-High Efficiency Video Coding (3D-HEVC). In some examples, the techniques for constraining depth intra mode coding may prevent transform tree nodes from being split into sub-transform tree nodes when a depth prediction unit that corresponds to the transform tree node is predicted according to a depth modeling mode (DMM). In further examples, the techniques for constraining depth intra mode coding may prevent the DMM mode from being used when the maximum transform unit size that corresponds to a depth prediction unit is greater than the size of the depth prediction unit. The techniques for constraining depth intra mode coding may prevent characteristics of the DMM prediction modes used in 3D-HEVC and characteristics of the transform tree subdivision used in 3D-HEVC from interfering with each other.
-
公开(公告)号：US20200175334A1
公开(公告)日：2020-06-04
申请号：US16204242
申请日：2018-11-29
Applicant: QUALCOMM Incorporated
Inventor： Shuai Zhang , Ying Chen , Yang Zhou
IPC: G06K9/62
Abstract: Methods, systems, and devices for object localization and classification are described. A device may configure a first unit of a detection layer associated with a learning framework when a quantity of output feature channels of an input feature maps is less than or equal to a quantity of input feature channels of the input feature maps. The first set of layers may include a group convolution layer, a pointwise layer, a batch normalization layer, or a rectified linear layer, or a combination thereof. The device may also configure, a second unit of the detection layer associated with the learning framework, when a second quantity of output feature channels of the input feature maps is less than or equal to a second quantity of input feature channels of the input feature maps. The second set of layers may include a depthwise layer or a pointwise layer, or both.
-
Patent Agency Ranking
公开(公告)号：US20190205694A1
公开(公告)日：2019-07-04
申请号：US16224644
申请日：2018-12-18
Applicant: QUALCOMM Incorporated
CPC classification number: G06K9/6202 , G06K9/00248 , G06K9/00268 , G06K9/00281 , G06K9/00288 , G06K9/00926 , G06K9/42 , G06K9/46 , G06K9/527 , G06T7/50 , G06T2207/10016
Abstract: Techniques and systems are provided for determining features for one or more objects in one or more video frames. For example, an image of an object, such as a face, can be received, and features of the object in the image can be identified. A size of the object can be determined based on the image, for example based on inter-eye distance of a face. Based on the size, either a high-resolution set of features or a low-resolution set of features is selected to compare to the features of the object. The object can be identified by matching the features of the object to matching features from the selected set of features.
-
公开(公告)号：US10306265B2
公开(公告)日：2019-05-28
申请号：US15108764
申请日：2013-12-30
Applicant: QUALCOMM Incorporated
Inventor： Hongbin Liu , Ying Chen
IPC: H04N19/597 , H04N19/96 , H04N19/593 , H04N19/176 , H04N13/161 , H04N19/70
Abstract: In general, this disclosure describes techniques for simplifying SDC coding of large intra-prediction blocks, such as 64×64 blocks, in a 3D video coding process, such as 3D-HEVC. In some examples, the techniques may include processing 64×64 intra-prediction blocks as four 32×32 intra-prediction blocks in intra SDC. Processing large intra-prediction blocks as multiple, smaller intra-prediction blocks in intra SDC may reduce maximum buffer size requirements in the intra SDC process.
-
348.发明授权公开(公告)号：US10284842B2
公开(公告)日：2019-05-07
申请号：US14194159
申请日：2014-02-28
Applicant: QUALCOMM Incorporated
Inventor： Adarsh Krishnan Ramasubramonian , Ying Chen , Xiang Li , Ye-Kui Wang
IPC: H04N19/105 , H04N19/597 , H04N19/30 , H04N19/513 , H04N19/187 , H04N19/39 , H04N19/167 , H04N19/577
Abstract: A method of coding video data includes upsampling at least a portion of a reference layer picture to an upsampled picture having an upsampled picture size. The upsampled picture size has a horizontal upsampled picture size and a vertical upsampled picture size. At least one of the horizontal or vertical upsampled picture sizes may be different than a horizontal picture size or vertical picture size, respectively, of an enhancement layer picture. In addition, position information associated with the upsampled picture may be signaled. An inter-layer reference picture may be generated based on the upsampled picture and the position information.
-
公开(公告)号：US20180374233A1
公开(公告)日：2018-12-27
申请号：US15635059
申请日：2017-06-27
Applicant: QUALCOMM Incorporated
Inventor： Yang Zhou , Ying Chen , Yingyong Qi , Ning Bi
CPC classification number: G06T7/70 , G06K9/4604 , G06K9/6201 , G06T7/248 , G06T7/251 , G06T2207/10016 , G06T2207/20081 , G06T2207/30196 , G06T2207/30232 , G06T2207/30241
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：US10136119B2
公开(公告)日：2018-11-20
申请号：US14151586
申请日：2014-01-09
Applicant: QUALCOMM Incorporated
Inventor： Ying Chen , Ye-Kui Wang , Li Zhang
IPC: H04N13/00 , H04N13/161 , H04N19/597 , H04N19/176 , H04N19/70 , H04N19/58 , H04N19/577
Abstract: In an example, a method of decoding video data includes determining whether a reference index for a current block corresponds to an inter-view reference picture, and when the reference index for the current block corresponds to the inter-view reference picture, obtaining, from an encoded bitstream, data indicating a view synthesis prediction (VSP) mode of the current block, where the VSP mode for the reference index indicates whether the current block is predicted with view synthesis prediction from the inter-view reference picture.
-
-
-
-
-
-
-
-
-
Search Results
422
records
(took 0.03 seconds)
