公开(公告)号：US20190035091A1

公开(公告)日：2019-01-31

申请号：US15758859

申请日：2015-09-25

Applicant: QUALCOMM Incorporated

Inventor： Ning Bi ,  Fan Ling ,  Jingting Ding ,  Yu Sun

IPC: G06T7/246 ,  G06T9/00 ,  H04N7/18 ,  H04N5/247 ,  H04N5/232

Abstract: A system and method of video processing are disclosed. In a particular implementation, a device includes a frame buffer configured to receive a video frame sequence and to store the video frame sequence and a frame index for each frame of the video frame sequence. The device also includes a processor configured to compress a summary frame into an encoded file representative of the summary frame. The summary frame includes a first representation of an object at a first position in a first video frame associated with a first frame index of the video frame sequence. The summary frame further includes a second representation of an object at a second position in a second video frame associated with a second frame index associated with the video frame sequence. The device also includes a transmitter configured to output a notification signal associated with the summary frame.

公开(公告)号：US20180254065A1

公开(公告)日：2018-09-06

申请号：US15637042

申请日：2017-06-29

Applicant: QUALCOMM Incorporated

Inventor： Ying Chen ,  Ning Bi ,  Yang Zhou

IPC: G11B27/031 ,  G11B27/34 ,  G06T7/73

CPC classification number: G11B27/031 ,  G06K9/00718 ,  G06K9/342 ,  G06K9/38 ,  G06T7/248 ,  G06T7/254 ,  G06T7/74 ,  G06T2207/30196 ,  G11B27/34

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 a video frame. A first blob tracker and a second blob tracker are associated with the merged blob. A location and/or a size of the first blob tracker associated with the merged blob is adjusted. The merged blob is split into a first blob and a second blob based on a history of blob trackers associated with the merged blob. The first blob is associated with the adjusted first blob tracker and the second blob is associated with the second blob tracker. The first blob and the second blob are then output for object tracking for the current frame.

公开(公告)号：US20180157929A1

公开(公告)日：2018-06-07

申请号：US15370867

申请日：2016-12-06

Applicant: QUALCOMM Incorporated

Inventor： Yingyong Qi ,  Ning Bi

IPC: G06K9/46 ,  G06T7/00 ,  G06T1/20

CPC classification number: G06T7/0081 ,  G06T7/11 ,  G06T7/174 ,  G06T7/194 ,  G06T7/215 ,  G06T7/80 ,  G06T2207/10016 ,  G06T2207/20021

Abstract: A device includes a memory buffer and a processor. The memory buffer is configured to store background image-blocks corresponding to image-blocks of a plurality of image frames of a video stream. The processor is configured to partition a particular image frame of the video stream into multiple image-blocks. The processor is also configured to generate a predicted background image-block based on one or more of the background image-blocks. The processor is further configured to determine a background prediction error based on a comparison of the predicted background image-block and a corresponding image-block of the particular image frame. The processor is also configured, based on determining that the background prediction error is greater than a threshold, to extract from the image-block at least one of a background image-block corresponding to the image-block or a foreground image-block corresponding to the image-block.

公开(公告)号：US20180046877A1

公开(公告)日：2018-02-15

申请号：US15235999

申请日：2016-08-12

Applicant: QUALCOMM Incorporated

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

IPC: G06K9/46 ,  G06K9/00 ,  G06K9/38

CPC classification number: G06K9/4642 ,  G06K9/00711 ,  G06K9/38 ,  G06T7/11 ,  G06T7/136 ,  G06T7/194 ,  G06T7/254 ,  G06T2207/10016 ,  G06T2207/30232 ,  G06T2207/30242

Abstract: Techniques and systems are provided for processing video data. For example, techniques and systems are provided for determining blob size thresholds. Blob sizes of blobs generated for a video frame can be determined. A lower boundary of a category of blob sizes can then be determined that corresponds to a minimum blob size of the video frame. The lower boundary is determined from a plurality of possible blob sizes including the blob sizes of the blobs and one or more other possible blob sizes. One of the possible blob sizes is determined as the lower boundary when one or more lower boundary conditions are met by characteristics of the possible blob size. A blob size threshold for the video frame is assigned as the minimum blob size corresponding to the lower boundary.

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：US09852511B2

公开(公告)日：2017-12-26

申请号：US13951731

申请日：2013-07-26

Applicant: QUALCOMM Incorporated

Inventor： Dashan Gao ,  Xin Zhong ,  Yingyong Qi ,  Ning Bi

IPC: G06T7/20

CPC classification number: G06T7/20 ,  G06T2207/10016 ,  G06T2207/20021 ,  G06T2207/20104 ,  G06T2207/30241

Abstract: A method for detecting and tracking a target object is described. The method includes performing motion-based tracking for a current video frame by comparing a previous video frame and the current video frame. The method also includes selectively performing object detection in the current video frame based on a tracked parameter.

公开(公告)号：US20170339392A1

公开(公告)日：2017-11-23

申请号：US15495730

申请日：2017-04-24

Applicant: QUALCOMM Incorporated

Inventor： Bijan Forutanpour ,  Ye-Kui Wang ,  Phi Hung Nguyen ,  Ning Bi

IPC: H04N13/00 ,  H04N5/232

CPC classification number: H04N13/161 ,  H04N5/23238 ,  H04N5/2628 ,  H04N19/597

Abstract: Provided are systems, methods, and computer-readable medium for including parameters that describe fisheye images in a 360-degree video with the 360-degree video. The 360-degree video can then be stored and/or transmitted as captured by the omnidirectional camera, without transforming the fisheye images into some other format. The parameters can later be used to map the fisheye images to an intermediate format, such as an equirectangular format. The intermediate format can be used to store, transmit, and/or display the 360-degree video. The parameters can alternatively or additionally be used to map the fisheye images directly to a format that can be displayed in a 360-degree video presentation, such as a spherical format.

公开(公告)号：US20170287107A1

公开(公告)日：2017-10-05

申请号：US15270650

申请日：2016-09-20

Applicant: QUALCOMM Incorporated

Inventor： Bijan Forutanpour ,  Phi Hung Le Nguyen ,  Ning Bi

IPC: G06T3/00 ,  G06T15/00 ,  G06T15/04 ,  G06T17/20 ,  G06T19/20

CPC classification number: G06T3/0062 ,  G06T3/0018 ,  G06T3/4038 ,  G06T15/005 ,  G06T15/04 ,  G06T17/205 ,  G06T19/20 ,  G06T2215/06

Abstract: Examples are described for overlaying circular images onto a three-dimensional mesh model to generated respective portions of image content for 360-degree viewable content, where each of the portions is a sub-capsule that is larger than half of the sphere. The portions are rendered and then blended based on overlapping portions of the image content from the 360-degree viewable content.

公开(公告)号：US20170200252A1

公开(公告)日：2017-07-13

申请号：US14993685

申请日：2016-01-12

Applicant: QUALCOMM Incorporated

Inventor： Phi Hung Nguyen ,  Ning Bi

IPC: G06T1/20 ,  G06F9/38 ,  G06F13/42 ,  G06T17/20 ,  G06T19/00 ,  G06T15/00 ,  G06F3/01 ,  G09G5/36 ,  G09G5/00 ,  G09G5/22 ,  G06F3/06 ,  G06T15/10

CPC classification number: G06T1/20 ,  G06F3/013 ,  G06F3/0619 ,  G06F3/0656 ,  G06F3/0673 ,  G06F9/3871 ,  G06F13/4239 ,  G06T15/005 ,  G06T15/10 ,  G06T17/20 ,  G06T19/006 ,  G09G5/006 ,  G09G5/227 ,  G09G5/363 ,  G09G5/393 ,  G09G5/395 ,  G09G2340/0407 ,  G09G2360/18

Abstract: An electronic device is described. The electronic device includes a memory. The electronic device also includes a very long instruction word (VLIW) circuit. The VLIW circuit includes an asynchronous memory controller. The asynchronous memory controller is configured to asynchronously access the memory to render different levels of detail. The electronic device may include a non-uniform frame buffer controller configured to dynamically access different subsets of a frame buffer. The different subsets may correspond to the different levels of detail.

公开(公告)号：US20170161569A1

公开(公告)日：2017-06-08

申请号：US14837606

申请日：2015-08-27

Applicant: QUALCOMM Incorporated

Inventor： Jianfeng Ren ,  Ruiduo Yang ,  Feng Guo ,  Shili Xu ,  Shuxue Quan ,  Ning Bi

IPC: G06K9/00 ,  G08G1/16 ,  G06K9/32

CPC classification number: G06K9/00798 ,  B60T7/22 ,  G06K9/00818 ,  G06K9/3233 ,  G06K9/325 ,  G08G1/16

Abstract: A system and method of object detection are disclosed. In a particular implementation, a method of processing an image includes receiving, at a processor, image data associated with an image of a scene. The scene includes a road region. The method further includes detecting the road region based on the image data and determining a subset of the image data. The subset excludes at least a portion of the image data corresponding to the road region. The method further includes performing an object detection operation on the subset of the image data to detect an object. The object detection operation performed on the subset of the image data is exclusive of the at least a portion of the image data corresponding to the road region.