公开(公告)号：US11838835B2

公开(公告)日：2023-12-05

申请号：US16530549

申请日：2019-08-02

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jangsu Lee ,  Byungdeok Kim ,  Youngmin Kim ,  Woosuk Kim

IPC: G06N20/00 ,  H04W4/38 ,  G06N20/20 ,  H04L67/00 ,  G06N5/043 ,  G06F18/214 ,  G06V10/774 ,  G06V10/94

CPC classification number: H04W4/38 ,  G06F18/214 ,  G06N5/043 ,  G06N20/20 ,  G06V10/774 ,  G06V10/95 ,  H04L67/34

Abstract: A distributed inference system includes an end device and a server. The end device generates status information and generates an inference result corresponding to target data based on a first machine learning model. The server creates a second machine learning model based on the status information and a training dataset including the inference result, calculates an accuracy of the inference result, and provides the second machine learning model to the end device based on the accuracy.

公开(公告)号：US11232323B2

公开(公告)日：2022-01-25

申请号：US17027733

申请日：2020-09-22

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Changhun Sung ,  Deokhwan Kim ,  Byungdeok Kim ,  Taeui Kim

IPC: G06K9/36 ,  G06K9/62 ,  G06T5/50 ,  G06T7/00 ,  G06T7/32

Abstract: Feature points included in input images are extracted and matching information indicating mapping relationships for feature points included in different input images is generated. A reference image is selected among the input images based on the matching information. Valid images are determined among the input images by excluding noise images from the input images based on the matching information. A two-dimensional bundle adjustment is performed to generate synchronized images by aligning the valid images to the reference image. A merged image is generated by merging the reference image and the synchronized images. Image merging performance is enhanced by selecting the reference image highly correlated with the other input images and estimating exact homography based on the reference image.

公开(公告)号：US11580617B2

公开(公告)日：2023-02-14

申请号：US17204434

申请日：2021-03-17

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Changhun Sung ,  Deokhwan Kim ,  Byungdeok Kim ,  Taeui Kim

IPC: G06V10/46 ,  G06T3/40 ,  G06V10/44

Abstract: Each input image from a plurality of input images is divided into a plurality of image tiles. A feature point map including a plurality of feature point tiles respectively corresponding to the plurality of image tiles is generated by extracting feature points included in each image tile of the plurality of image tiles. A descriptor map including a plurality of descriptor tiles respectively corresponding to the plurality of feature point tiles is generated by generating descriptors of feature points included in the feature point map. Mapping information containing matching relationships between feature points included in different input images of the plurality of input images is generated based on a plurality of descriptor maps respectively corresponding to the plurality of input images. Image merging performance may be enhanced by dividing the input image into the plurality of image tiles to increase distribution uniformity of the feature points.

公开(公告)号：US20220004799A1

公开(公告)日：2022-01-06

申请号：US17204434

申请日：2021-03-17

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： CHANGHUN SUNG ,  Deokhwan Kim ,  Byungdeok Kim ,  Taeui Kim

IPC: G06K9/46 ,  G06T3/40

Abstract: Each input image from a plurality of input images is divided into a plurality of image tiles. A feature point map including a plurality of feature point tiles respectively corresponding to the plurality of image tiles is generated by extracting feature points included in each image tile of the plurality of image tiles. A descriptor map including a plurality of descriptor tiles respectively corresponding to the plurality of feature point tiles is generated by generating descriptors of feature points included in the feature point map. Mapping information containing matching relationships between feature points included in different input images of the plurality of input images is generated based on a plurality of descriptor maps respectively corresponding to the plurality of input images. Image merging performance may be enhanced by dividing the input image into the plurality of image tiles to increase distribution uniformity of the feature points.

公开(公告)号：US20230267681A1

公开(公告)日：2023-08-24

申请号：US18153020

申请日：2023-01-11

Applicant: Samsung Electronics Co., Ltd.

Inventor： Changhun SUNG ,  Byungdeok Kim

IPC: G06T17/00 ,  G06T7/70 ,  G06T7/90 ,  G06T7/55 ,  G06T7/32 ,  G06T7/33 ,  G06T7/00

CPC classification number: G06T17/00 ,  G06T7/70 ,  G06T7/90 ,  G06T7/55 ,  G06T7/32 ,  G06T7/33 ,  G06T7/0002 ,  G06T2207/20072 ,  G06T2207/30168 ,  G06T2207/10028 ,  G06T2210/56

Abstract: Input images are obtained to include color data and depth data of a target. An image graph is generated based on the color data of the input images such that the image graph includes correlation values between the input images. A registration order is determined based on the image graph. Pose information of each input image is sequentially generated based on the registration order and the depth data of the input images. The input images are sequentially registered as registered images such that each registered image includes the pose information. A three-dimensional model of the target is reconstructed based on the registered images. The pose information may be generated and the elaborate three-dimensional model may be reconstructed by determining the registration order based on the color data and sequentially generating the pose information of the input images according to the registration order using the registered images.