公开(公告)号：US11645756B2

公开(公告)日：2023-05-09

申请号：US17095784

申请日：2020-11-12

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yueying Kao ,  Yang Liu ,  Hao Wang ,  Sunghoon Hong ,  Wooshik Kim ,  Chao Zhang ,  Lin Ma ,  Qiang Wang ,  Weiming Li

IPC: G06T7/149 ,  G06T7/11 ,  G06T15/00 ,  G06T7/168

CPC classification number: G06T7/149 ,  G06T7/11 ,  G06T7/168 ,  G06T15/00 ,  G06T2200/04 ,  G06T2200/08 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/20108 ,  G06T2215/08

Abstract: An image processing apparatus and method are provided. The image processing apparatus acquires a target image including a depth image of a scene, determines three-dimensional (3D) point cloud data corresponding to the depth image based on the depth image, and extracts an object included in the scene to acquire an object extraction result based on the 3D point cloud data.

公开(公告)号：US11436011B2

公开(公告)日：2022-09-06

申请号：US17172258

申请日：2021-02-10

Applicant: Samsung Electronics Co., Ltd.

Inventor： Bochao Dang ,  Hao Wang

IPC: G06F9/30 ,  G06F9/38

Abstract: A processor-implemented method includes: determining a first multiplication matrix and a second multiplication matrix, based on an input multiplicand matrix and an input multiplier matrix that are generated from an input signal; determining a matrix to be restored, based on the first multiplication matrix and the second multiplication matrix; determining a matrix restoration constraint value, based on the matrix to be restored; determining a multiplication result of the input multiplicand matrix and the input multiplier matrix, based on the matrix restoration constraint value and the matrix to be restored; and analyzing the input signal based on the multiplication result.

公开(公告)号：US11386637B2

公开(公告)日：2022-07-12

申请号：US16739325

申请日：2020-01-10

Applicant: Samsung Electronics Co., Ltd.

Inventor： Seungin Park ,  Lin Ma ,  Weiming Li ,  Yang Liu ,  Hao Wang ,  Hyong Euk Lee

IPC: G06V10/00 ,  G06V10/25 ,  G06K9/62 ,  G06N3/04 ,  G06V10/44

Abstract: An object detection method includes setting a first window region and a second window region larger than the first window region that correspond to partial regions of different sizes in an input image, downsampling the second window region to generate a resized second window region, detecting a first object candidate from the first window region and a second object candidate from the resized second window region, and detecting an object included in the input image based on one or both of the first object candidate and the second object candidate.

公开(公告)号：US11315354B2

公开(公告)日：2022-04-26

申请号：US16718404

申请日：2019-12-18

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hao Wang ,  Yang Liu ,  Hyong Euk Lee ,  Seungin Park ,  Qiang Wang ,  Yueying Kao ,  Weiming Li

IPC: G06V40/10 ,  G06N3/04 ,  G06K9/62 ,  G06V10/25 ,  G06V20/40 ,  G06V40/20

Abstract: A method and apparatus for controlling an augmented reality (AR) apparatus are provided. The method includes acquiring a video, detecting a human body from the acquired video, performing an action prediction with regard to the detected human body, and controlling the AR apparatus based on a result of the action prediction and a mapping relationship between human body actions and AR functions.

公开(公告)号：US10649904B2

公开(公告)日：2020-05-12

申请号：US15422442

申请日：2017-02-01

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hao Wang ,  Dilip Muthukrishnan ,  Brian C. Grayson

IPC: G06F12/0875 ,  G06F12/0888 ,  G06F12/0897

Abstract: According to one general aspect, an apparatus may include a load/store circuit and a region size detection circuit. The load/store circuit may be configured to issue a plurality of store instructions to store data in a memory system. The region size detection circuit may be configured to determine a cache from a plurality of caches to store a stream of store instructions based upon, at least in part, by tracking multiple cache-line address entries in the plurality of store instructions, wherein each address entry is updated at a different frequency.