知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

21 records (took 0.015 seconds)

    Advanced driver assist system and method of detecting object in the same
    1.
    发明授权
    Advanced driver assist system and method of detecting object in the same 有权

    公开(公告)号：US12190601B2

    公开(公告)日：2025-01-07

    申请号：US18443980

    申请日：2024-02-16

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Sangsoo Ko ,  Byeoungsu Kim ,  Kyoungyoung Kim ,  Sanghyuck Ha

    IPC: G06V20/56 ,  B60W50/00 ,  G06F18/214 ,  G06F18/241 ,  G06V10/22 ,  G06V10/25 ,  G06V10/77 ,  G06V20/64 ,  H04N13/111

    Abstract: ADAS includes a processing circuit and a memory which stores instructions executable by the processing circuit. The processing circuit executes the instructions to cause the ADAS to receive, from a vehicle that is in motion, a video sequence, generate a position image including at least one object included in the stereo image, generate a second position information associated with the at least one object based on reflected signals received from the vehicle, determine regions each including at least a portion of the at least one object as candidate bounding boxes based on the stereo image and the position image, and selectively adjusting class scores of respective ones of the candidate bounding boxes associated with the at least one object based on whether a respective first position information of the respective ones of the candidate bounding boxes matches the second position information.

    Computing device for training artificial neural network model, method of training the artificial neural network model, and memory system for storing the same
    2.
    发明授权
    Computing device for training artificial neural network model, method of training the artificial neural network model, and memory system for storing the same 有权

    公开(公告)号：US11556795B2

    公开(公告)日：2023-01-17

    申请号：US16786627

    申请日：2020-02-10

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Byeoungsu Kim ,  Sangsoo Ko ,  Kyoungyoung Kim ,  Jaegon Kim ,  Sanghyuck Ha

    IPC: G06N3/08 ,  G06K9/62

    Abstract: A computing device for training an artificial neural network model includes: a model analyzer configured to receive a first artificial neural network model and split the first artificial neural network model into a plurality of layers; a training logic configured to calculate first sensitivity data varying as the first artificial neural network model is pruned, calculate a target sensitivity corresponding to a target pruning rate based on the first sensitivity data, calculate second sensitivity data varying as each of the plurality of layers is pruned, and output, based on the second sensitivity data, an optimal pruning rate of each of the plurality of layers, the optimal pruning rate corresponding to the target pruning rate; and a model updater configured to prune the first artificial neural network model based on the optimal pruning rate to obtain a second artificial neural network model, and output the second artificial neural network model.

    Electronic device for performing object detection and operation method thereof
    5.
    发明授权
    Electronic device for performing object detection and operation method thereof 有权

    公开(公告)号：US11539871B2

    公开(公告)日：2022-12-27

    申请号：US17169648

    申请日：2021-02-08

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Sangsoo Ko ,  Kyoungyoung Kim ,  Byeoungsu Kim ,  Sanghyuck Ha

    IPC: H04N5/232 ,  H04N5/445 ,  H04N5/225 ,  B60R1/00

    Abstract: An electronic device includes: a first image sensor that outputs a first image produced by photographing a first viewing angle; a second image sensor that outputs a second image produced by photographing a second viewing angle that overlaps a portion of the first viewing angle; a third image sensor that outputs a third image produced by photographing a third viewing angle; and a processor that performs object detection on an object included in an image. The processor generates disparity information indicating a separation degree of a feature point of the first and second images, transforms the third image based on the disparity information, and performs object detection on the transformed third image.

    Neural network device, neural network system, and method of processing neural network model by using neural network system
    7.
    发明授权
    Neural network device, neural network system, and method of processing neural network model by using neural network system 有权

    公开(公告)号：US11900262B2

    公开(公告)日：2024-02-13

    申请号：US16738038

    申请日：2020-01-09

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Kyoungyoung Kim ,  Sangsoo Ko ,  Doyun Kim ,  Sanghyuck Ha

    IPC: G06N3/10

    CPC classification number: G06N3/10

    Abstract: A neural network system for processing a neural network model including an operation processing graph that includes a plurality of operations, includes an operation processor including an internal memory storing a first module input feature map. The operation processor is configured to obtain a first branch output feature map by performing a first operation among the plurality of operations, based on the stored first module input feature map, and obtain a second branch output feature map by performing a second operation among the plurality of operations after the first operation is performed, based on the stored first module input feature map. The internal memory maintains storage of the first module input feature map while the first operation is performed.

    SEMICONDUCTOR MEMORY DEVICE AND ELECTRONIC SYSTEM THE SAME
    8.
    发明申请
    SEMICONDUCTOR MEMORY DEVICE AND ELECTRONIC SYSTEM THE SAME 有权

    公开(公告)号：US20210019076A1

    公开(公告)日：2021-01-21

    申请号：US16790189

    申请日：2020-02-13

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Kyoungyoung Kim ,  Sangsoo Ko ,  Byeoungsu Kim ,  Jaegon Kim ,  Sanghyuck Ha

    IPC: G06F3/06 ,  G06N3/02

    Abstract: A semiconductor memory device is provided. The semiconductor memory device includes a memory core including a plurality of memory cells configured to store a plurality of data received from an external processor; and a statistical feature extractor disposed on a data path between the external processor and the memory core, the statistical feature extractor being configured to analyze statistical characteristics of the plurality of data, identify at least one statistical feature value associated with the statistical characteristics, store the at least one statistical feature value and transmit the at least one statistical feature value to the external processor.

    NEURAL NETWORK DEVICE, NEURAL NETWORK SYSTEM, AND METHOD OF PROCESSING NEURAL NETWORK MODEL BY USING NEURAL NETWORK SYSTEM
    9.
    发明申请
    NEURAL NETWORK DEVICE, NEURAL NETWORK SYSTEM, AND METHOD OF PROCESSING NEURAL NETWORK MODEL BY USING NEURAL NETWORK SYSTEM 审中-公开

    公开(公告)号：US20200234147A1

    公开(公告)日：2020-07-23

    申请号：US16738038

    申请日：2020-01-09

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Kyoungyoung Kim ,  Sangsoo Ko ,  Doyun Kim ,  Sanghyuck Ha

    IPC: G06N3/10

    Abstract: A neural network system for processing a neural network model including an operation processing graph that includes a plurality of operations, includes an operation processor including an internal memory storing a first module input feature map. The operation processor is configured to obtain a first branch output feature map by performing a first operation among the plurality of operations, based on the stored first module input feature map, and obtain a second branch output feature map by performing a second operation among the plurality of operations after the first operation is performed, based on the stored first module input feature map. The internal memory maintains storage of the first module input feature map while the first operation is performed.

Patent Agency Ranking