公开(公告)号：US11528494B2

公开(公告)日：2022-12-13

申请号：US17348131

申请日：2021-06-15

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Min-woo Park ,  Bo-ra Jin ,  In-kwon Choi

IPC: H04N19/44 ,  H04N19/105 ,  H04N19/117 ,  H04N19/132 ,  H04N19/159 ,  H04N19/172 ,  H04N19/136 ,  H04N19/176 ,  H04N19/593

Abstract: Provided is a method of decoding an image, the method including: determining at least one prediction unit included in a current frame that is one of at least one frame forming the image; determining a reference region to be referred to by a current prediction unit that is one of the at least one prediction unit; changing a sample value included in at least one of the current prediction unit and the reference region, based on an analyzing result of a sample value of the reference region; determining a sample value included in the current prediction unit, based on a result of changing the sample value; and decoding the image based on the determined sample value of the current prediction unit.

公开(公告)号：US11170201B2

公开(公告)日：2021-11-09

申请号：US16635024

申请日：2018-07-11

Applicant: Samsung Electronics Co., Ltd.

Inventor： In-kwon Choi ,  Gun-hee Lee ,  Hyun-joo Jung ,  Sung-jin Kim ,  Hyun-soo Choi

IPC: G06K9/00 ,  G06N20/00 ,  G06K9/62

Abstract: Provided are an artificial intelligence (AI) system that simulates functions of a human brain such as recognition and judgment by utilizing a machine learning algorithm such as deep learning, etc., and an application of the AI system. Provided are an AI system and a method of recognizing an object according to the application of the AI system, the method including: obtaining a plurality of pieces of sensor data about the object from a plurality of different types of sensors; converting at least some of the plurality of pieces of sensor data into two-dimensional (2D) sensor data; and recognizing the object by using a previously generated learning network model based on 2D image data obtained from an image sensor, which is one of the plurality of sensors, and the 2D sensor data.

公开(公告)号：US11095911B2

公开(公告)日：2021-08-17

申请号：US15998658

申请日：2017-02-15

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Min-woo Park ,  Bo-ra Jin ,  In-kwon Choi

IPC: H04N19/44 ,  H04N19/105 ,  H04N19/117 ,  H04N19/132 ,  H04N19/159 ,  H04N19/172 ,  H04N19/136 ,  H04N19/176 ,  H04N19/593

Abstract: Provided is a method of decoding an image, the method including: determining at least one prediction unit included in a current frame that is one of at least one frame forming the image; determining a reference region to be referred to by a current prediction unit that is one of the at least one prediction unit; changing a sample value included in at least one of the current prediction unit and the reference region, based on an analyzing result of a sample value of the reference region; determining a sample value included in the current prediction unit, based on a result of changing the sample value; and decoding the image based on the determined sample value of the current prediction unit.

公开(公告)号：US11956419B2

公开(公告)日：2024-04-09

申请号：US16939730

申请日：2020-07-27

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Ki-Ho Choi ,  Min-woo Park ,  Elena Alshina ,  Chan-yul Kim ,  In-kwon Choi

IPC: H04N19/105 ,  H04N19/119 ,  H04N19/122 ,  H04N19/129 ,  H04N19/13 ,  H04N19/176 ,  H04N19/44 ,  H04N19/46

CPC classification number: H04N19/105 ,  H04N19/122 ,  H04N19/129 ,  H04N19/13 ,  H04N19/176 ,  H04N19/44 ,  H04N19/119 ,  H04N19/46

Abstract: Provided is a method of decoding a video according to an embodiment, the method including determining at least one processing block for splitting the video; determining an order of determining at least one largest coding unit in the at least one processing block; determining at least one largest coding unit on the basis of the determined order; and decoding the determined at least one largest coding unit, wherein the order is one of a plurality of orders for determining a largest coding unit.

公开(公告)号：US11546624B2

公开(公告)日：2023-01-03

申请号：US17348223

申请日：2021-06-15

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Min-woo Park ,  Bo-ra Jin ,  In-kwon Choi

IPC: H04N19/44 ,  H04N19/105 ,  H04N19/117 ,  H04N19/132 ,  H04N19/159 ,  H04N19/172 ,  H04N19/136 ,  H04N19/176 ,  H04N19/593

Abstract: Provided is a method of decoding an image, the method including: determining at least one prediction unit included in a current frame that is one of at least one frame forming the image; determining a reference region to be referred to by a current prediction unit that is one of the at least one prediction unit; changing a sample value included in at least one of the current prediction unit and the reference region, based on an analyzing result of a sample value of the reference region; determining a sample value included in the current prediction unit, based on a result of changing the sample value; and decoding the image based on the determined sample value of the current prediction unit.

公开(公告)号：US11516491B2

公开(公告)日：2022-11-29

申请号：US17348351

申请日：2021-06-15

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Min-woo Park ,  Bo-ra Jin ,  In-kwon Choi

IPC: H04N19/44 ,  H04N19/105 ,  H04N19/117 ,  H04N19/132 ,  H04N19/159 ,  H04N19/172 ,  H04N19/136 ,  H04N19/176 ,  H04N19/593

Abstract: Provided is a method of decoding an image, the method including: determining at least one prediction unit included in a current frame that is one of at least one frame forming the image; determining a reference region to be referred to by a current prediction unit that is one of the at least one prediction unit; changing a sample value included in at least one of the current prediction unit and the reference region, based on an analyzing result of a sample value of the reference region; determining a sample value included in the current prediction unit, based on a result of changing the sample value; and decoding the image based on the determined sample value of the current prediction unit.

公开(公告)号：US20210314591A1

公开(公告)日：2021-10-07

申请号：US17348280

申请日：2021-06-15

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Min-woo PARK ,  Bo-ra Jin ,  In-kwon Choi

IPC: H04N19/44 ,  H04N19/105 ,  H04N19/117 ,  H04N19/132 ,  H04N19/159 ,  H04N19/172

Abstract: Provided is a method of decoding an image, the method including: determining at least one prediction unit included in a current frame that is one of at least one frame forming the image; determining a reference region to be referred to by a current prediction unit that is one of the at least one prediction unit; changing a sample value included in at least one of the current prediction unit and the reference region, based on an analyzing result of a sample value of the reference region; determining a sample value included in the current prediction unit, based on a result of changing the sample value; and decoding the image based on the determined sample value of the current prediction unit.

公开(公告)号：US10992933B2

公开(公告)日：2021-04-27

申请号：US15998649

申请日：2017-02-16

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： In-kwon Choi ,  Min-woo Park ,  Bo-ra Jin

IPC: H04N19/11 ,  H04N19/59 ,  H04N19/61 ,  H04N19/167 ,  H04N19/176 ,  H04N19/593 ,  H04N19/105

Abstract: Provided is a video decoding method including obtaining a bitstream including residual data about a residual block of a current block, determining a plurality of prediction directions with respect to the current block, determining a plurality of reference samples included in a neighboring region of the current block in a current image, by using the plurality of prediction directions that are determined, generating a prediction block of the current block by using the plurality of reference samples, obtaining a residual block of the current block based on the residual data about the residual block of the current block, and reconstructing the current block by using the prediction block of the current block and the residual block of the current block.

公开(公告)号：US10785476B2

公开(公告)日：2020-09-22

申请号：US15573216

申请日：2016-05-10

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Ki-ho Choi ,  Min-woo Park ,  Elena Alshina ,  Chan-yul Kim ,  In-kwon Choi

IPC: H04N19/105 ,  H04N19/176 ,  H04N19/122 ,  H04N19/13 ,  H04N19/129 ,  H04N19/44

Abstract: Provided is a method of decoding a video according to an embodiment, the method including determining at least one processing block for splitting the video; determining an order of determining at least one largest coding unit in the at least one processing block; determining at least one largest coding unit on the basis of the determined order; and decoding the determined at least one largest coding unit, wherein the order is one of a plurality of orders for determining a largest coding unit.