-
公开(公告)号:US11223815B2
公开(公告)日:2022-01-11
申请号:US16652601
申请日:2018-10-25
Applicant: Samsung Electronics Co., Ltd.
Inventor: Weiming Li , Wenbo Zhang , Hao Wang , Yang Liu , Zairan Wang
IPC: G06T15/20 , H04N13/246 , G06T7/593 , H04N13/128 , H04N13/243 , G06K9/00 , G06K9/62 , G06K9/72 , H04N13/00
Abstract: The method of the present invention for processing a video comprises: acquiring a first and a second omnidirectional videos having a stereoscopic parallax in a first direction which is a corresponding column direction when the first and the second omnidirectional videos are unfolded by longitude and latitude; and, determining one or two third omnidirectional videos according to the first and the second omnidirectional videos, the second and the third omnidirectional videos having a stereoscopic parallax in a second direction, wherein, if one third omnidirectional video is determined, the second and the third omnidirectional videos have a stereoscopic parallax in the second direction; if two third omnidirectional videos are determined, the two third omnidirectional videos have a stereoscopic parallax in the second direction; and, the second direction is a corresponding row direction when the first and the second omnidirectional videos are unfolded by longitude and latitude.
-
公开(公告)号:US10937189B2
公开(公告)日:2021-03-02
申请号:US16238785
申请日:2019-01-03
Applicant: Samsung Electronics Co., Ltd.
Inventor: Weiming Li , Zairan Wang , Dongdong Yu , Hao Wang , Minsu Ahn , Qiang Wang , Sunghoon Hong , Yang Liu , Yueying Kao
IPC: G06T7/73
Abstract: Disclosed are a pose estimation methods and apparatuses of displaying a virtual object using an estimated pose. The pose estimation method includes receiving an input image and estimating pose information of an object from the input image based on local information of the object.
-
公开(公告)号:US10885659B2
公开(公告)日:2021-01-05
申请号:US16161243
申请日:2018-10-16
Applicant: Samsung Electronics Co., Ltd.
Inventor: Weiming Li , Yueying Kao , Dongdong Yu , Hao Wang , Minsu Ahn , Qiang Wang , Sunghoon Hong , Yang Liu , Zairan Wang
Abstract: Disclosed is an object pose estimating method and apparatus. The pose estimating method includes acquiring a two-dimensional (2D) image corresponding to an object, extracting a global visual feature and a local geometric feature of the object in the 2D image, and estimating a three-dimensional (3D) pose of the object based on the global visual feature and the local geometric feature.
-
公开(公告)号:US10649900B2
公开(公告)日:2020-05-12
申请号:US15900789
申请日:2018-02-20
Applicant: Samsung Electronics Co., Ltd.
Inventor: Tarun Nakra , Hao Wang , Paul Kitchin
IPC: G06F12/00 , G06F12/0855 , G06F12/0884 , G06F12/0864 , G06F12/0897 , G06F12/0846
Abstract: According to one general aspect, an apparatus may include a first cache configured to store data. The apparatus may include a second cache configured to, in response to a fill request, supply the first cache with data, and an incoming fill signal. The apparatus may also include an execution circuit configured to, via a load request, retrieve data from the first cache. The first cache may be configured to: derive, from the incoming fill signal, address and timing information associated with the fill request, and based, at least partially, upon the address and timing information, schedule the load request to attempt to avoid a load-fill conflict.
-
公开(公告)号:US12175698B2
公开(公告)日:2024-12-24
申请号:US17545333
申请日:2021-12-08
Applicant: Samsung Electronics Co., Ltd.
Inventor: Weiming Li , Jiyeon Kim , Hyun Sung Chang , Qiang Wang , Sunghoon Hong , Yang Liu , Hao Wang , Yueying Kao
Abstract: A processor-implemented method with object pose estimation includes: determining an image feature corresponding to a point cloud of an input image; determining semantic segmentation information, instance mask information, and keypoint information of an object, based on the image feature; and estimating a pose of the object based on the semantic segmentation information, the instance mask information, and the keypoint information.
-
公开(公告)号:US11295532B2
公开(公告)日:2022-04-05
申请号:US16674139
申请日:2019-11-05
Applicant: Samsung Electronics Co., Ltd.
Inventor: Weiming Li , Hyong Euk Lee , Hao Wang , Seungin Park , Qiang Wang , Yang Liu , Yueying Kao
Abstract: Provided is a method and apparatus for aligning a three-dimensional (3D) model. The 3D model alignment method includes acquiring, by a processor, at least one two-dimensional (2D) image including an object, detecting, by the processor, a feature point of the object in the at least one 2D input image using a neural network, estimating, by the processor, a 3D pose of the object in the at least one 2D input image using the neural network, retrieving, by the processor, a target 3D model based on the estimated 3D pose, and aligning, by the processor, the target 3D model and the object based on the feature point.
-
公开(公告)号:US11188965B2
公开(公告)日:2021-11-30
申请号:US16161153
申请日:2018-10-16
Applicant: Samsung Electronics Co., Ltd.
Inventor: Weiming Li , Dongdong Yu , Yang Liu , Qiang Wang , Minsu Ahn , Sunghoon Hong , Yueying Kao , Zairan Wang , Hao Wang
IPC: G06Q30/06 , G06F16/583 , G06T7/11
Abstract: An apparatus for recommending a customer item identifies a purchase tendency of a customer based on an image, determines a recommended item for the customer by selecting a purchase tendency model corresponding to the purchase tendency, and provides information associated with the determined recommended item.
-
公开(公告)号:US12148182B2
公开(公告)日:2024-11-19
申请号:US17476920
申请日:2021-09-16
Applicant: Samsung Electronics Co., Ltd.
Inventor: Chao Zhang , Jiyeon Kim , Yang Liu , Yueying Kao , Hao Wang , Hyun Sung Chang , Qiang Wang , Sunghoon Hong , Weiming Li
Abstract: A method, an apparatus, an electronic device for estimating a pose of an object include determining a confidence of a depth image of an object based on a color image and the depth image of the object, estimating a pose of the object based on a three-dimensional (3D) keypoint in response to the depth image being reliable, and estimating the pose of the object based on a two-dimensional (2D) keypoint in response to the depth image being unreliable.
-
公开(公告)号:US20240219315A1
公开(公告)日:2024-07-04
申请号:US18493226
申请日:2023-10-24
Applicant: Samsung Electronics Co., Ltd.
Inventor: Jangwoon Sung , Lei Tian , Hao Wang , Jiabei Zhu , Myungjun Lee , Wookrae Kim , Seungbeom Park , Junho Shin , Hojun Lee
IPC: G01N21/95 , G01N21/88 , G01N21/956
CPC classification number: G01N21/9501 , G01N21/8806 , G01N21/956
Abstract: A substrate inspection apparatus includes a light irradiator including an objective lens and a plurality of optical fibers. The objective lens is configured to irradiate light to an illumination area on a semiconductor substrate having a plurality of circuit pattern layers, the plurality of optical fibers are adjacent a periphery of the objective lens and are configured to irradiate the light to a peripheral area adjacent the illumination area. A light generator is configured to generate the light. The light generator is configured to change an irradiation angle of the light to selectively irradiate the light to one or more of the objective lens and the plurality of optical fibers. A light analyzer is configured to obtain images of the circuit pattern layers from the light reflected from the illumination area and the peripheral area. The light analyzer is configured to model each of the circuit pattern layers of the semiconductor substrate to obtain image models and to measure an overlay between the circuit pattern layers through the images and the image models.
-
公开(公告)号:US11900610B2
公开(公告)日:2024-02-13
申请号:US18126042
申请日:2023-03-24
Applicant: Samsung Electronics Co., Ltd.
Inventor: Yueying Kao , Yang Liu , Hao Wang , Sunghoon Hong , Wooshik Kim , Chao Zhang , Lin Ma , Qiang Wang , Weiming Li
CPC classification number: G06T7/11 , G06T7/149 , G06T7/168 , G06T15/00 , G06V10/25 , G06V10/454 , G06V10/764 , G06V20/64 , 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.
-
-
-
-
-
-
-
-
-