-
公开(公告)号：US12079305B2
公开(公告)日：2024-09-03
申请号：US17459797
申请日：2021-08-27
Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE , Hanbat National University Industry-Academic Cooperation Foundation
Inventor： Hae-Chul Choi , Sang-Woon Kwak , Joung-Il Yun , Hee-Ji Han
CPC classification number: G06F18/213 , G06F18/22 , G06F18/23 , G06N3/04 , G06V10/758
Abstract: Disclosed herein are an apparatus for encoding and decoding a feature map and a method using the apparatus. The feature map encoding apparatus include a processor for acquiring feature map information corresponding to a feature map, reconstructing the feature map based on the feature map information, and generating an encoded feature map by converting each feature value corresponding to the reconstructed feature map from a real number into an integer, and a memory for storing the feature map information.
-
公开(公告)号：US20230222626A1
公开(公告)日：2023-07-13
申请号：US18095420
申请日：2023-01-10
Applicant: Electronics and Telecommunications Research Institute , HANBAT NATIONAL UNIVERSITY INDUSTRY-ACADEMIC COOPERATION FOUNDATION
Inventor： Soon-Heung JUNG , Sang Woon KWAK , Joung-Il Yun , Hae-Chul CHOI , Hee-Ji HAN
IPC: G06T3/40
CPC classification number: G06T3/4046 , G06T3/4007
Abstract: A neural network feature decoding method and apparatus according to the present disclosure receives a bitstream including an encoded feature, decodes a feature from a bitstream, and reconstructs features corresponding to a plurality of layers of a neural network based on a decoded feature.
-
Patent Agency Ranking
公开(公告)号：US12170785B2
公开(公告)日：2024-12-17
申请号：US17980135
申请日：2022-11-03
Inventor： Sang-Woon Kwak , Joung-Il Yun
IPC: H04N19/42 , H04N19/103 , H04N19/132
Abstract: Disclosed herein is a method for adaptive image preprocessing and reconstruction. The method includes preprocessing an input image, encoding and decoding the preprocessed image, and reconstructing the encoded and decoded image. Here, preprocessing the input image may be performed using a preprocessing kernel generated based on a control parameter indicating a weight for human vision and machine vision.
-
公开(公告)号：US10129051B2
公开(公告)日：2018-11-13
申请号：US15659453
申请日：2017-07-25
Inventor： Sang-Woon Kwak , Joung-Il Yun , Myung-Sun Baek , Hae-Chan Kwon , Young-Su Kim , Hyoung-Soo Lim , Nam-Ho Hur
Abstract: Disclosed herein are a method and apparatus for iterative interference cancellation and channel estimation in a system based on FTN communication including a pilot. Interference of a pilot symbol on a data symbol is estimated, and the estimated interference is eliminated from a sequence of data symbols. When demodulation and channel decoding are performed on the sequence of data symbols, interference between data symbols and interference of a data symbol on a pilot symbol are estimated. Such estimation is repeatedly performed, and as FTN interference is repeatedly estimated and eliminated, channel estimation performance is improved, and through the improved channel estimation performance, the reception performance of the entire system is improved.
-
公开(公告)号：US12069238B2
公开(公告)日：2024-08-20
申请号：US18084188
申请日：2022-12-19
Inventor： Joon-Soo Kim , Joung-Il Yun
IPC: H04N19/103 , G06T9/00 , G06V10/44 , G06V10/74 , G06V10/764 , G06V10/771 , H04N19/513
CPC classification number: H04N19/103 , G06T9/00 , G06V10/44 , G06V10/761 , G06V10/764 , G06V10/771 , H04N19/513
Abstract: Disclosed herein are an image compression method and apparatus for machine vision. The image compression method includes determining a prediction mode for frames of an input image, generating a prediction frame and a residual image using an input frame, generating a reconstructed frame by adding the prediction frame to the residual image, extracting respective features of the input frame and the reconstructed frame, correcting the reconstructed frame based on a difference value between the extracted features and a bit rate of the residual image, and encoding the corrected frame.
-
公开(公告)号：US11276142B2
公开(公告)日：2022-03-15
申请号：US15931410
申请日：2020-05-13
Inventor： Joung-Il Yun , Sang-Woon Kwak , Won-Sik Cheong , Gi-Mun Um
Abstract: Disclosed herein are an apparatus and method for synthesizing virtual viewpoint image. The apparatus for synthesizing virtual viewpoint images includes one or more processors, and an execution memory for storing at least one program that is executed by the one or more processors, wherein the at least one program is configured to receive multiple viewpoint images from cameras that capture images of multiple viewpoints, and back-project the multiple viewpoint images onto a world coordinate system in a three-dimensional (3D) space, generate warped images by performing triangular warping of projecting the multiple viewpoint images, back-projected onto the world coordinate system, onto a virtual viewpoint image coordinate system, and generate a finally synthesized virtual viewpoint image by blending the warped images.
-
7.发明授权公开(公告)号：US10142140B2
公开(公告)日：2018-11-27
申请号：US15421295
申请日：2017-01-31
Inventor： Joung-Il Yun , Sang-Woon Kwak , Myung-Sun Baek , Hae-Chan Kwon , Hyoung-Soo Lim , Nam-Ho Hur , Nam-Shik Kim , Bi-Woong Chung
IPC: H04L1/00 , H04L27/01 , H04L25/06 , H04L25/03 , H04B1/7107
Abstract: Disclosed herein are an apparatus and method for receiving a signal based on FTN. The apparatus for receiving a signal based on FTN includes an equalizer for creating a Log Likelihood Ratio (LLR) sequence by equalizing an FTN signal sequence sampled at an FTN signaling rate; a deinterleaver for deinterleaving the created LLR sequence; a decoder for decoding the LLR sequence by correcting errors in the deinterleaved LLR sequence; an interleaver for interleaving the decoded LLR sequence and providing the interleaved LLR sequence to the equalizer; and an FTN interference estimation unit for providing the FTN signal sequence, from which an FTN interference sequence is eliminated, to the equalizer, using the interleaved LLR sequence.
-
-
-
-
-
-
Search Results
7
records
(took 0.014 seconds)
