公开(公告)号：US20180067572A1

公开(公告)日：2018-03-08

申请号：US15800531

申请日：2017-11-01

Applicant: Samsung Electronics Co., Ltd.

Inventor： Byung In YOO ,  Chang Kyu CHOI

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

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：US20240273884A1

公开(公告)日：2024-08-15

申请号：US18636615

申请日：2024-04-16

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sangil JUNG ,  Seungin PARK ,  Byung In YOO

IPC: G06V10/80 ,  G06V10/40 ,  G06V10/764 ,  G06V10/77 ,  G06V10/82

CPC classification number: G06V10/806 ,  G06V10/40 ,  G06V10/764 ,  G06V10/7715 ,  G06V10/82

Abstract: An object classification method and apparatus are disclosed. The object classification method includes receiving an input image, storing first feature data extracted by a first feature extraction layer of a neural network configured to extract features of the input image, receiving second feature data from a second feature extraction layer which is an upper layer of the first feature extraction layer, generating merged feature data by merging the first feature data and the second feature data, and classifying an object in the input image based on the merged feature data.

公开(公告)号：US20240169733A1

公开(公告)日：2024-05-23

申请号：US18514455

申请日：2023-11-20

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yi ZHOU ,  Seung-In PARK ,  Byung In YOO ,  Sangil JUNG ,  Hui ZHANG

IPC: G06V20/40 ,  G06V10/77 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G06V20/70

CPC classification number: G06V20/49 ,  G06V10/7715 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G06V20/41 ,  G06V20/46 ,  G06V20/70

Abstract: A processor-implemented method includes: obtaining a video feature of a video comprising a plurality of video frames; determining a target object representation of the video based on the video feature using a neural network; and generating a panorama segmentation result of the video based on the target object representation.

公开(公告)号：US20240144527A1

公开(公告)日：2024-05-02

申请号：US18311340

申请日：2023-05-03

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Changbeom PARK ,  Dongwook LEE ,  Byung In YOO

IPC: G06T7/73 ,  G06T7/62 ,  G06T7/66

CPC classification number: G06T7/74 ,  G06T7/62 ,  G06T7/66 ,  G06T2207/20081

Abstract: An object tracking apparatus is provided. The object tracking apparatus includes a processor configured to detect, from a first image frame, an amodal region including a first visible region in which a target object is visible and an occlusion region in which the target object is occluded, determine, based on the detected amodal region of the first image frame, that at least a partial region of a second image frame is a search region of the second image frame, the second image frame being temporally adjacent to the first image frame, and track the target object in the second image frame based on the determined search region.

公开(公告)号：US20230095716A1

公开(公告)日：2023-03-30

申请号：US17697160

申请日：2022-03-17

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sangil JUNG ,  Seungin PARK ,  Byung In YOO

IPC: G06V10/80 ,  G06V10/82 ,  G06V10/764 ,  G06V10/77 ,  G06V10/40

Abstract: An object classification method and apparatus are disclosed. The object classification method includes receiving an input image, storing first feature data extracted by a first feature extraction layer of a neural network configured to extract features of the input image, receiving second feature data from a second feature extraction layer which is an upper layer of the first feature extraction layer, generating merged feature data by merging the first feature data and the second feature data, and classifying an object in the input image based on the merged feature data.

公开(公告)号：US20220383514A1

公开(公告)日：2022-12-01

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: G06T7/246 ,  G06K9/20 ,  G06K9/62

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：US20220303455A1

公开(公告)日：2022-09-22

申请号：US17407463

申请日：2021-08-20

Applicant: SAMSUNG ELECTRONICS CO., LTD

Inventor： Seungin PARK ,  Jinwoo SON ,  Changyong SON ,  Byung In YOO ,  Sangil JUNG

IPC: H04N5/232 ,  G06T7/246

Abstract: An image sensor includes: a motion detection circuit configured to detect a motion in image frames; and a micro control unit (MCU) configured to adjust at least a portion of a target frame among the image frames based on whether the motion is detected, and detect whether a target object is present based on the adjusted portion of the target frame.

公开(公告)号：US20220180633A1

公开(公告)日：2022-06-09

申请号：US17537762

申请日：2021-11-30

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jingtao XU ,  Yiwei CHEN ,  Changbeom PARK ,  Hyunjeong LEE ,  Byung In YOO ,  Jaejoon HAN ,  Qiang WANG ,  Jiaqian YU

IPC: G06V20/40 ,  G06V10/22 ,  G06V10/44 ,  G06V10/74 ,  G06V10/75 ,  G06K9/62

Abstract: A target object detection method and apparatus are provided. The target object detection method and apparatus are applicable to fields such as artificial intelligence, object tracking, object detection, and image processing. An object is detected from a frame image of a video including a plurality of frame images based on a target template set including one or more target templates.

公开(公告)号：US20220130175A1

公开(公告)日：2022-04-28

申请号：US17570711

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: G06V40/40 ,  G06T7/00 ,  G06K9/62 ,  G06V10/20 ,  G06V10/25

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：US20210166045A1

公开(公告)日：2021-06-03

申请号：US16939757

申请日：2020-07-27

Applicant: Samsung Electronics Co., Ltd.

Inventor： Youngjun KWAK ,  Byung In YOO ,  Yong-Il LEE ,  Yunhao ZHANG ,  Huxing SUN

IPC: G06K9/00 ,  G06N3/08 ,  G06T7/521

Abstract: A method with liveness testing may include: acquiring an infrared (IR) image including an object, and a depth image including the object; generating a first preprocessed IR image by performing first edge enhancement preprocessing on the IR image; generating a preprocessed depth image by performing second edge enhancement preprocessing on the depth image; and determining whether the object is a genuine object based on the first preprocessed IR image and the preprocessed depth image.