公开(公告)号：US20190188525A1

公开(公告)日：2019-06-20

申请号：US16155979

申请日：2018-10-10

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hee Min CHOI

IPC: G06K9/62 ,  G06K9/32 ,  G06T7/60 ,  G06N3/04

CPC classification number: G06K9/628 ,  G06K9/3233 ,  G06K9/6232 ,  G06K9/6261 ,  G06N3/04 ,  G06T7/60 ,  G06T2207/20084

Abstract: An image recognition method using a region-based convolutional neural network (R-CNN) includes generating a feature map from an input image, detecting one or more regions of interest (ROIs) in the feature map, classifying the ROIs into groups based on setting information, performing pooling on the ROIs classified into the groups independently for each of the groups, and performing a regression operation on a result of the pooling and applying an image classifier to a result of the regression operation.

公开(公告)号：US20190186945A1

公开(公告)日：2019-06-20

申请号：US16044819

申请日：2018-07-25

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hee Min CHOI ,  Jaewoo LEE

IPC: G01C21/36 ,  G06K9/00 ,  G05D1/00 ,  B60R1/00

Abstract: An autonomous vehicle and method of providing driving information of an autonomous vehicle, the method includes acquiring outside situation data via a sensor in the autonomous vehicle, generating, based on the acquired outside situation data, a local map comprising the autonomous vehicle, one or more external vehicles within a threshold distance from the autonomous vehicle, and a road on which the autonomous vehicle is travelling, and displaying the generated local map on a display of the autonomous vehicle.

公开(公告)号：US20250014145A1

公开(公告)日：2025-01-09

申请号：US18660939

申请日：2024-05-10

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hee Min CHOI ,  Hyo A KANG ,  Su Ji KIM

IPC: G06T3/4053 ,  G06V10/77 ,  G06V10/82

Abstract: A method of generating a model for image processing includes increasing, using a receptive field (RF) increasing module of at least one processor, a receptive field of an input image frame; generating, using a feature extraction (FE) module of the at least one processor, a feature map based on the input image frame with an increased receptive field; generating, using a super resolution (SR) module of the at least one processor, a target image having a target resolution, based on the feature map; and generating, using a model generation (MG) module of the at least one processor, a replacement model that replaces at least one of the RF increasing module, the FE module, and the SR module.

公开(公告)号：US20240187614A1

公开(公告)日：2024-06-06

申请号：US18350233

申请日：2023-07-11

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hyoa KANG ,  Hee Min CHOI

IPC: H04N19/184 ,  G06V10/764 ,  G06V10/82

CPC classification number: H04N19/184 ,  G06V10/764 ,  G06V10/82

Abstract: A processor-implemented method includes: initializing a neural network model with arbitrary values using a random seed; training the neural network model based on the arbitrary values; determining a number of coats and respective densities of the coats; learning respective scores of parameters of the neural network model based on the number of coats and the respective densities of the coats; determining mask information for determining the parameters of the neural network model to be comprised in each of the coats based on the scores; and generating a bitstream based on the number of coats, the respective densities of the coats, the mask information, and the random seed.

公开(公告)号：US20220237890A1

公开(公告)日：2022-07-28

申请号：US17550184

申请日：2021-12-14

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hee Min CHOI ,  Hyoa KANG

IPC: G06V10/762 ,  G06V20/58 ,  G06N3/04

Abstract: A processor-implemented method with neural network training includes: determining first backbone feature data corresponding to each input data by applying, to a first neural network model, two or more sets of the input data of the same scene, respectively; determining second backbone feature data corresponding to each input data by applying, to a second neural network model, the two or more sets of the input data, respectively; determining projection-based first embedded data and dropout-based first view data from the first backbone feature data; and determining projection-based second embedded data and dropout-based second view data from the second backbone feature data; and training either one or both of the first neural network model and the second neural network model based on a loss determined based on a combination of any two or more of the first embedded data, the first view data, the second embedded data, the second view data, and an embedded data clustering result.