公开(公告)号：US11741617B2

公开(公告)日：2023-08-29

申请号：US17528501

申请日：2021-11-17

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hyunjeong Lee ,  SeungWook Kim ,  Changbeom Park ,  Ju Hwan Song ,  Byung In Yoo

IPC: G06K9/00 ,  G06T7/246 ,  G06V10/22 ,  G06F18/213

CPC classification number: G06T7/248 ,  G06F18/213 ,  G06V10/22 ,  G06T2207/20084

Abstract: A processor-implemented method with object tracking includes: determining an initial template image based on an input bounding box and an input image; generating an initial feature map by extracting features from the initial template image; generating a transformed feature map by performing feature transformation adapted to objectness on the initial feature map; generating an objectness probability map and a bounding box map indicating bounding box information corresponding to each coordinate of the objectness probability map by performing objectness-based bounding box regression analysis on the transformed feature map; and determining a refined bounding box based on the objectness probability map and the bounding box map.

公开(公告)号：US09848244B2

公开(公告)日：2017-12-19

申请号：US15250080

申请日：2016-08-29

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Gyeong Ja Jang ,  Byung In Yoo ,  Yong Beom Lee ,  Young Chul Cho ,  Hyo Sun Hwang

IPC: H04N21/4728 ,  H04N21/442 ,  H04N21/858 ,  H04N21/81 ,  H04N21/41 ,  H04N21/4223 ,  H04N21/44 ,  H04N21/462 ,  H04N21/4722

CPC classification number: H04N21/4728 ,  H04N21/4126 ,  H04N21/4223 ,  H04N21/44008 ,  H04N21/44218 ,  H04N21/4622 ,  H04N21/4722 ,  H04N21/8133 ,  H04N21/858

Abstract: An interactive method includes displaying image content received through a television (TV) network, identifying an object of interest of a user among a plurality of regions or a plurality of objects included in the image content, and providing additional information corresponding to the object of interest.

公开(公告)号：US09836146B2

公开(公告)日：2017-12-05

申请号：US14476146

申请日：2014-09-03

Applicant: Samsung Electronics Co., Ltd.

Inventor： Byung In Yoo ,  Chang Kyu Choi

IPC: G06F3/048 ,  G06F3/041 ,  G06F3/0481 ,  G06F3/0488 ,  G06F3/0484

CPC classification number: G06F3/041 ,  G06F3/04815 ,  G06F3/04842 ,  G06F3/0488 ,  G06F3/04883 ,  G06F2203/04104 ,  G06F2203/04808

Abstract: A method of controlling a viewpoint of a user or a virtual object on a two-dimensional (2D) interactive display is provided. The method may convert a user input to at least 6 degrees of freedom (DOF) structured data according to a number of touch points, a movement direction thereof, and a rotation direction thereof. Any one of the virtual object and the viewpoint of the user may be determined as a manipulation target based on a location of the touch point.

公开(公告)号：US20140237495A1

公开(公告)日：2014-08-21

申请号：US14016573

申请日：2013-09-03

Applicant: Samsung Electronics Co., Ltd.

Inventor： Gyeong Ja JANG ,  Byung In Yoo ,  Yong Beom Lee ,  Young Chul Cho ,  Hyo Sun Hwang

IPC: H04N21/442 ,  H04N21/258 ,  H04N21/41

CPC classification number: H04N21/4728 ,  H04N21/4126 ,  H04N21/4223 ,  H04N21/44008 ,  H04N21/44218 ,  H04N21/4622 ,  H04N21/4722 ,  H04N21/8133 ,  H04N21/858

Abstract: An interactive method includes displaying image content received through a television (TV) network, identifying an object of interest of a user among a plurality of regions or a plurality of objects included in the image content, and providing additional information corresponding to the object of interest.

Abstract translation: 交互方法包括显示通过电视（TV）网络接收的图像内容，识别包含在图像内容中的多个区域或多个对象中的用户感兴趣对象，以及提供与感兴趣对象相对应的附加信息 。

公开(公告)号：US20130271449A1

公开(公告)日：2013-10-17

申请号：US13858336

申请日：2013-04-08

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Chang Kyo LEE ,  Byung In Yoo ,  Chang Kyu Choi ,  Jae Joon Han

IPC: G06T15/08

CPC classification number: G06T15/08 ,  G06T13/40

Abstract: A method of generating three-dimensional (3D) volumetric data may be performed by generating a multilayer image, generating volume information and a type of a visible part of an object, based on the generated multilayer image, and generating volume information and a type of an invisible part of the object, based on the generated multilayer image. The volume information and the type of each of the visible part and invisible part may be generated based on the generated multilayered image which may be include at least one of a ray-casting-based multilayer image, a chroma key screen-based multilayer image, and a primitive template-based multilayer image.

Abstract translation: 可以通过生成多层图像，基于生成的多层图像生成体信息和对象的可见部分的类型，并且生成体积信息和类型的多个图像，来生成三维（3D）体积数据的方法 基于生成的多层图像，对象的不可见部分。 可以基于所生成的多层图像来生成可见部分和不可见部分中的每一个的体积信息和类型，所述多层图像可以包括基于射线铸造的多层图像，基于色度键屏幕的多层图像， 和基于模板的原始多层图像。

公开(公告)号：US12148249B2

公开(公告)日：2024-11-19

申请号：US17570761

申请日：2022-01-07

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Solae Lee ,  Youngjun Kwak ,  Sungheon Park ,  Byung In Yoo ,  Yong-Il Lee ,  Hana Lee ,  Jiho Choi

IPC: G06V40/00 ,  G06F18/21 ,  G06F18/25 ,  G06T7/00 ,  G06V10/147 ,  G06V10/50 ,  G06V10/764 ,  G06V10/80 ,  G06V10/82 ,  G06V40/40

Abstract: A method and apparatus for detecting a liveness based on a phase difference are provided. The method includes generating a first phase image based on first visual information of a first phase, generating a second phase image based on second visual information of a second phase, generating a minimum map based on a disparity between the first phase image and the second phase image, and detecting a liveness based on the minimum map.

公开(公告)号：US11663728B2

公开(公告)日：2023-05-30

申请号：US17146752

申请日：2021-01-12

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jiaqian Yu ,  Jingtao Xu ,  Yiwei Chen ,  Byung In Yoo ,  Chang Kyu Choi ,  Hana Lee ,  Jaejoon Han ,  Qiang Wang

IPC: G06T7/50 ,  H01L27/146

CPC classification number: G06T7/50 ,  H01L27/14605 ,  G06T2207/10024

Abstract: A depth estimation method and apparatus are provided. The depth estimation method includes obtaining an image from an image sensor comprising upper pixels, each comprising N sub-pixels, obtaining N sub-images respectively corresponding to the N sub-pixels from the image, obtaining a viewpoint difference between the N sub-images using a first neural network, and obtaining a depth map of the image based on the viewpoint difference using a second neural network.

公开(公告)号：US11301704B2

公开(公告)日：2022-04-12

申请号：US16661394

申请日：2019-10-23

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Byung In Yoo

IPC: G06K9/00 ,  G06F16/535 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: A processor-implemented recognition method includes: receiving query input data; determining a domain to which the query input data belongs using a neural network-based classifier; and in response to the query input data belonging to a first domain, generating second query data of a second domain based on the query input data.

公开(公告)号：US11093734B2

公开(公告)日：2021-08-17

申请号：US16182861

申请日：2018-11-07

Applicant: Samsung Electronics Co., Ltd.

Inventor： Youngsung Kim ,  Youngjun Kwak ,  Byung In Yoo ,  Seohyung Lee

IPC: G06K9/00 ,  G06K9/62 ,  G10L15/02 ,  G10L15/06

Abstract: A method and apparatus with emotion recognition acquires a plurality of pieces of data corresponding a plurality of inputs for each modality and corresponding to a plurality of modalities; determines a dynamics representation vector corresponding to each of the plurality of modalities based on a plurality of features for each modality extracted from the plurality of pieces of data; determines a fused representation vector based on the plurality of dynamics representation vectors corresponding to the plurality of modalities; and recognizes an emotion of a user based on the fused representation vector.

公开(公告)号：US09697609B2

公开(公告)日：2017-07-04

申请号：US14289915

申请日：2014-05-29

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Won Jun Kim ,  Byung In Yoo ,  Chang Kyu Choi

IPC: G06K9/00 ,  G06T7/00 ,  G06T7/73

CPC classification number: G06T7/75 ,  G06K9/00342 ,  G06K9/00369 ,  G06T2207/10016 ,  G06T2207/10028 ,  G06T2207/30196

Abstract: A method and apparatus for estimating a pose that estimates a pose of a user using a depth image is provided, the method including, recognizing a pose of a user from a depth image, and tracking the pose of the user using a user model exclusively of one another to enhance precision of estimating the pose.