中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

37 records (took 0.023 seconds)

    METHOD AND APPARATUS WITH ATTENTION-BASED OBJECT ANALYSIS
    11.
    发明公开
    METHOD AND APPARATUS WITH ATTENTION-BASED OBJECT ANALYSIS 审中-公开

    公开(公告)号：US20240153130A1

    公开(公告)日：2024-05-09

    申请号：US18342892

    申请日：2023-06-28

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Hyeongseok SON ,  Seungin PARK ,  Byung In YOO ,  Dongwook LEE ,  Solae LEE ,  Sangil JUNG

    IPC: G06T7/73 ,  G06T7/50 ,  G06V10/25 ,  G06V10/764 ,  G06V10/771

    CPC classification number: G06T7/73 ,  G06T7/50 ,  G06V10/25 ,  G06V10/764 ,  G06V10/771

    Abstract: An apparatus includes one or more processors configured to generate a plurality of feature maps having respective different resolutions based on an input image; and update, for each of the plurality of transformer layers, respective position estimation information comprising first position information of a respective bounding box corresponding to one object query and second position information of respective key points corresponding to the one object query, wherein each of the plurality of transformer layers includes a self-attention model configured to generate respective intermediate data by performing self-attention on respective content information on a feature of the input image; and a cross-attention model configured to generate respective output data by performing cross-attention on respective one or more feature maps among the plurality of feature maps and the respective generated intermediate data.

    METHOD AND APPARATUS WITH IMAGE AUGMENTATION
    13.
    发明申请
    METHOD AND APPARATUS WITH IMAGE AUGMENTATION 有权

    公开(公告)号：US20220276706A1

    公开(公告)日：2022-09-01

    申请号：US17749290

    申请日：2022-05-20

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Seungin PARK ,  Hyong Euk LEE

    IPC: G06F3/01 ,  G06K9/62 ,  G06T11/00 ,  G06T3/40 ,  G06V10/40 ,  G06V40/20

    Abstract: A method with image augmentation includes recognizing, based on a gaze of the user corresponding to the input image, any one or any combination of any two or more of an object of interest of a user, a situation of the object of interest, and a task of the user from partial regions of an input image determining relevant information indicating an intention of the user, based on any two or any other combination of the object of interest of the user, the situation of the object of interest, and the task of the user, and generating a visually augmented image by visually augmenting the input image based on the relevant information.

    METHOD AND APPARATUS WITH GRID-BASED PLANE ESTIMATION
    15.
    发明申请
    METHOD AND APPARATUS WITH GRID-BASED PLANE ESTIMATION 审中-公开

    公开(公告)号：US20190197772A1

    公开(公告)日：2019-06-27

    申请号：US15988383

    申请日：2018-05-24

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Jiyeon KIM ,  Seungin PARK ,  Minsu AHN

    IPC: G06T17/20 ,  G06T7/73 ,  G06K9/00 ,  G06T19/00 ,  G06T7/50

    CPC classification number: G06T17/20 ,  G06K9/00201 ,  G06K9/00624 ,  G06T7/50 ,  G06T7/73 ,  G06T19/006

    Abstract: A processor-implemented method of estimating a plane includes dividing a target image into a plurality of grid cells, estimating an initial plane based on reference feature points comprising a reference feature point selected from each of the plurality of grid cells, classifying each feature point of feature points extracted from the target image as being an inlier located on the same plane as the initial plane or an outlier located on a plane different from the initial plane, selecting boundary grid cells from the plurality of grid cells based on a distribution of the inliers and the outliers from among the feature points, and estimating an expanded plane associated with the initial plane based on the selected boundary grid cells for use in identifying boundaries of a planar surface presented in a scene corresponding to the target image.

    METHOD AND APPARATUS WITH MAP CONSTRUCTION
    16.
    发明申请
    METHOD AND APPARATUS WITH MAP CONSTRUCTION 有权

    公开(公告)号：US20250157206A1

    公开(公告)日：2025-05-15

    申请号：US18946809

    申请日：2024-11-13

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Yi ZHOU ,  Hui ZHANG ,  Byung In YOO ,  Seungin PARK ,  Sangil JUNG ,  Xiaoshuai HAO

    IPC: G06V10/80 ,  G06V10/764 ,  G06V10/77 ,  G06V10/774

    Abstract: A high-definition (HD) map-related map construction method, electronic device, and storage medium are provided. The method includes: extracting a bird's-eye view (BEV) feature map based on the data; determining map information through a hybrid decoder based on the BEV feature map and a hybrid query; and constructing an HD map corresponding to the data based on the map information, wherein the map includes a plurality of map elements each including an area formed by a plurality of coordinate points in the map, the map information comprises coordinate information and class information of the plurality of map elements, and the hybrid query includes a plurality of hybrid features each corresponding to one map element and including a point feature and an element feature. Optionally, the method may be executed using an artificial intelligence (AI) model.

    METHOD AND APPARATUS WITH OBJECT CLASSIFICATION
    18.
    发明申请
    METHOD AND APPARATUS WITH OBJECT CLASSIFICATION 有权

    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.

Patent Agency Ranking