中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

19 records (took 0.016 seconds)

    Method for encoding/decoding image and device thereof
    3.
    发明授权
    Method for encoding/decoding image and device thereof 有权

    公开(公告)号：US10742974B2

    公开(公告)日：2020-08-11

    申请号：US15781776

    申请日：2016-12-16

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Min-woo Park ,  Bo-ra Jin ,  Na-rae Choi ,  In-kwon Choi

    IPC: H04N19/176 ,  H04N19/11 ,  H04N19/44 ,  H04N19/159

    Abstract: Provided are a video decoding method including determining at least one first block for partitioning a current frame which is one of at least one frame included in a video, determining a first prediction mode indicating an intra-prediction method to be performed on a current first block which is one of the at least one first block based on first intra-prediction mode information obtained from a bitstream when intra-prediction is performed on the current first block, determining a plurality of second blocks included in the current first block, determining second prediction modes indicating intra-prediction methods to be performed on the plurality of second blocks based on at least one of the first prediction mode and second intra-prediction mode information obtained from the bitstream with respect to each of the plurality of second blocks, and decoding the video by performing intra-prediction based on the first prediction mode and the second prediction mode; and a video decoding apparatus capable of performing the video decoding method. Provided are also a video encoding method performed in a way opposite or similar to the video decoding method; and a video encoding apparatus capable of performing the video encoding method.

    Intra-prediction method for reducing intra-prediction errors and device for same
    7.
    发明授权
    Intra-prediction method for reducing intra-prediction errors and device for same 有权

    公开(公告)号：US11277615B2

    公开(公告)日：2022-03-15

    申请号：US16077830

    申请日：2017-02-16

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： In-kwon Choi ,  Min-woo Park

    IPC: H04N19/105 ,  H04N19/132 ,  H04N19/117 ,  H04N19/159 ,  H04N19/176

    Abstract: Provided is an image predicting method including: obtaining a plurality of adjacent samples located adjacent to a current block; determining an adjacent sample as a reference sample to be referred to by a current sample, the adjacent sample being from among the plurality of adjacent samples and being indicated by a direction of an intra mode of the current block; and adjusting a sample value of the reference sample according to a reference distance indicating a distance between the reference sample and the current sample, and determining a prediction value of the current sample based on the adjusted sample value of the reference sample.

    Method and apparatus for recognizing object
    8.
    发明授权
    Method and apparatus for recognizing object 有权

    公开(公告)号：US11216694B2

    公开(公告)日：2022-01-04

    申请号：US16633825

    申请日：2018-07-11

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Hyun-joo Jung ,  Gun-hee Lee ,  In-kwon Choi ,  Sung-jin Kim ,  Hyun-soo Choi

    IPC: G06K9/62 ,  G06K9/46 ,  G06N3/04 ,  G06N3/08

    Abstract: The present disclosure relates to an artificial intelligence (AI) system for simulating functions of a human brain such as cognition and decision-making by using machine learning algorithms such as deep learning, and applications thereof. In particular, the present disclosure provides a method of recognizing an object by using an AI system and its application, including: extracting pieces of first feature information respectively regarding a plurality of images, each image including an object; generating at least one piece of second feature information representing a correlation between the plurality of images by combining together the extracted pieces of first feature information respectively regarding the plurality of images; and recognizing, based on the at least one piece of second feature information, the object included in each of the plurality of images by using a pre-generated learning network model.

Patent Agency Ranking